This software and related documentation are provided under a license agreement containing restrictions on use and disclosure and are ...
Oracle® Solaris 11.1 Tunable Parameters Reference Manual Part No: E2902202 November 2012 Copyright © 2000, 2012, Oracle and/or its affiliates. All rights reserved. This software and related documentation are provided under a license agreement containing restrictions on use and disclosure and are protected by intellectual property laws. Except as expressly permitted in your license agreement or allowed by law, you may not use, copy, reproduce, translate, broadcast, modify, license, transmit, distribute, exhibit, perform, publish, or display any part, in any form, or by any means. Reverse engineering, disassembly, or decompilation of this software, unless required by law for interoperability, is prohibited. The information contained herein is subject to change without notice and is not warranted to be error-free. If you find any errors, please report them to us in writing. If this is software or related documentation that is delivered to the U.S. Government or anyone licensing it on behalf of the U.S. Government, the following notice is applicable: U.S. GOVERNMENT END USERS. Oracle programs, including any operating system, integrated software, any programs installed on the hardware, and/or documentation, delivered to U.S. Government end users are "commercial computer software" pursuant to the applicable Federal Acquisition Regulation and agency-specific supplemental regulations. As such, use, duplication, disclosure, modification, and adaptation of the programs, including any operating system, integrated software, any programs installed on the hardware, and/or documentation, shall be subject to license terms and license restrictions applicable to the programs. No other rights are granted to the U.S. Government. This software or hardware is developed for general use in a variety of information management applications. It is not developed or intended for use in any inherently dangerous applications, including applications that may create a risk of personal injury. If you use this software or hardware in dangerous applications, then you shall be responsible to take all appropriate fail-safe, backup, redundancy, and other measures to ensure its safe use. Oracle Corporation and its affiliates disclaim any liability for any damages caused by use of this software or hardware in dangerous applications. Oracle and Java are registered trademarks of Oracle and/or its affiliates. Other names may be trademarks of their respective owners. Intel and Intel Xeon are trademarks or registered trademarks of Intel Corporation. All SPARC trademarks are used under license and are trademarks or registered trademarks of SPARC International, Inc. AMD, Opteron, the AMD logo, and the AMD Opteron logo are trademarks or registered trademarks of Advanced Micro Devices. UNIX is a registered trademark of The Open Group. This software or hardware and documentation may provide access to or information on content, products, and services from third parties. Oracle Corporation and its affiliates are not responsible for and expressly disclaim all warranties of any kind with respect to third-party content, products, and services. Oracle Corporation and its affiliates will not be responsible for any loss, costs, or damages incurred due to your access to or use of third-party content, products, or services. Ce logiciel et la documentation qui l'accompagne sont protégés par les lois sur la propriété intellectuelle. Ils sont concédés sous licence et soumis à des restrictions d'utilisation et de divulgation. Sauf disposition de votre contrat de licence ou de la loi, vous ne pouvez pas copier, reproduire, traduire, diffuser, modifier, breveter, transmettre, distribuer, exposer, exécuter, publier ou afficher le logiciel, même partiellement, sous quelque forme et par quelque procédé que ce soit. Par ailleurs, il est interdit de procéder à toute ingénierie inverse du logiciel, de le désassembler ou de le décompiler, excepté à des fins d'interopérabilité avec des logiciels tiers ou tel que prescrit par la loi. Les informations fournies dans ce document sont susceptibles de modification sans préavis. Par ailleurs, Oracle Corporation ne garantit pas qu'elles soient exemptes d'erreurs et vous invite, le cas échéant, à lui en faire part par écrit. Si ce logiciel, ou la documentation qui l'accompagne, est concédé sous licence au Gouvernement des Etats-Unis, ou à toute entité qui délivre la licence de ce logiciel ou l'utilise pour le compte du Gouvernement des Etats-Unis, la notice suivante s'applique: U.S. GOVERNMENT END USERS. Oracle programs, including any operating system, integrated software, any programs installed on the hardware, and/or documentation, delivered to U.S. Government end users are "commercial computer software" pursuant to the applicable Federal Acquisition Regulation and agency-specific supplemental regulations. As such, use, duplication, disclosure, modification, and adaptation of the programs, including any operating system, integrated software, any programs installed on the hardware, and/or documentation, shall be subject to license terms and license restrictions applicable to the programs. No other rights are granted to the U.S. Government. Ce logiciel ou matériel a été développé pour un usage général dans le cadre d'applications de gestion des informations. Ce logiciel ou matériel n'est pas conçu ni n'est destiné à être utilisé dans des applications à risque, notamment dans des applications pouvant causer des dommages corporels. Si vous utilisez ce logiciel ou matériel dans le cadre d'applications dangereuses, il est de votre responsabilité de prendre toutes les mesures de secours, de sauvegarde, de redondance et autres mesures nécessaires à son utilisation dans des conditions optimales de sécurité. Oracle Corporation et ses affiliés déclinent toute responsabilité quant aux dommages causés par l'utilisation de ce logiciel ou matériel pour ce type d'applications. Oracle et Java sont des marques déposées d'Oracle Corporation et/ou de ses affiliés. Tout autre nom mentionné peut correspondre à des marques appartenant à d'autres propriétaires qu'Oracle. Intel et Intel Xeon sont des marques ou des marques déposées d'Intel Corporation. Toutes les marques SPARC sont utilisées sous licence et sont des marques ou des marques déposées de SPARC International, Inc. AMD, Opteron, le logo AMD et le logo AMD Opteron sont des marques ou des marques déposées d'Advanced Micro Devices. UNIX est une marque déposée d'The Open Group. Ce logiciel ou matériel et la documentation qui l'accompagne peuvent fournir des informations ou des liens donnant accès à des contenus, des produits et des services émanant de tiers. Oracle Corporation et ses affiliés déclinent toute responsabilité ou garantie expresse quant aux contenus, produits ou services émanant de tiers. En aucun cas, Oracle Corporation et ses affiliés ne sauraient être tenus pour responsables des pertes subies, des coûts occasionnés ou des dommages causés par l'accès à des contenus, produits ou services tiers, ou à leur utilisation. 121203@25097 Contents Preface ...................................................................................................................................................13 1 Overview of Oracle Solaris System Tuning ...................................................................................... 17 What's New in Oracle Solaris System Tuning? ................................................................................ 17 Tuning an Oracle Solaris System ....................................................................................................... 19 Tuning Format of Tunable Parameters Descriptions ..................................................................... 19 Tuning the Oracle Solaris Kernel ....................................................................................................... 21 /etc/system File .......................................................................................................................... 21 kmdb Command ............................................................................................................................ 22 mdb Command .............................................................................................................................. 22 Special Oracle Solaris tune and var Structures ................................................................................ 23 Viewing Oracle Solaris System Configuration Information .......................................................... 24 sysdef Command ....................................................................................................................... 24 kstat Utility ......................................................................................................................................... 24 2 Oracle Solaris Kernel Tunable Parameters ...................................................................................... 25 Where to Find Tunable Parameter Information ............................................................................. 25 General Kernel and Memory Parameters ......................................................................................... 26 physmem ......................................................................................................................................... 26 default_stksize ........................................................................................................................ 26 lwp_default_stksize ................................................................................................................ 27 logevent_max_q_sz .................................................................................................................... 28 segkpsize ..................................................................................................................................... 29 noexec_user_stack .................................................................................................................... 30 fsflush and Related Parameters ....................................................................................................... 30 fsflush ......................................................................................................................................... 30 tune_t_fsflushr ........................................................................................................................ 31 3 Contents 4 autoup ........................................................................................................................................... 32 dopageflush ................................................................................................................................. 33 doiflush ....................................................................................................................................... 33 Process-Sizing Parameters ................................................................................................................. 34 maxusers ....................................................................................................................................... 34 reserved_procs .......................................................................................................................... 35 pidmax ........................................................................................................................................... 36 max_nprocs ................................................................................................................................... 37 maxuprc ......................................................................................................................................... 37 ngroups_max ................................................................................................................................. 38 Paging-Related Parameters ................................................................................................................ 39 lotsfree ....................................................................................................................................... 40 desfree ......................................................................................................................................... 41 minfree ......................................................................................................................................... 42 throttlefree ............................................................................................................................... 43 pageout_reserve ........................................................................................................................ 44 pages_pp_maximum ...................................................................................................................... 45 tune_t_minarmem ........................................................................................................................ 45 fastscan ....................................................................................................................................... 46 slowscan ....................................................................................................................................... 47 min_percent_cpu ........................................................................................................................ 47 handspreadpages ........................................................................................................................ 48 pages_before_pager .................................................................................................................. 48 maxpgio ......................................................................................................................................... 49 Swapping-Related Parameters ........................................................................................................... 50 swapfs_reserve .......................................................................................................................... 50 swapfs_minfree .......................................................................................................................... 51 Kernel Memory Allocator ................................................................................................................... 52 kmem_flags ................................................................................................................................... 52 kmem_stackinfo .......................................................................................................................... 53 General Driver Parameters ................................................................................................................. 54 moddebug ....................................................................................................................................... 54 ddi_msix_alloc_limit .............................................................................................................. 55 Network Driver Parameters ............................................................................................................... 56 igb Parameters ............................................................................................................................. 56 ixgbe Parameters ......................................................................................................................... 57 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Contents General I/O Parameters ...................................................................................................................... 61 maxphys ......................................................................................................................................... 61 rlim_fd_max ................................................................................................................................. 61 rlim_fd_cur ................................................................................................................................. 62 General File System Parameters ........................................................................................................ 63 ncsize ........................................................................................................................................... 63 dnlc_dir_enable ........................................................................................................................ 64 dnlc_dir_min_size .................................................................................................................... 64 dnlc_dir_max_size .................................................................................................................... 65 dnlc_dircache_percent ............................................................................................................ 65 TMPFS Parameters ............................................................................................................................. 66 tmpfs:tmpfs_maxkmem ................................................................................................................ 66 tmpfs:tmpfs_minfree ................................................................................................................ 67 Pseudo Terminals ................................................................................................................................ 67 pt_cnt ........................................................................................................................................... 68 pt_pctofmem ................................................................................................................................. 69 pt_max_pty ................................................................................................................................... 69 STREAMS Parameters ........................................................................................................................ 70 nstrpush ....................................................................................................................................... 70 strmsgsz ....................................................................................................................................... 70 strctlsz ....................................................................................................................................... 71 System V Message Queues ................................................................................................................. 71 System V Semaphores ......................................................................................................................... 72 System V Shared Memory .................................................................................................................. 72 segspt_minfree .......................................................................................................................... 72 Scheduling ............................................................................................................................................ 73 disp_rechoose_interval .......................................................................................................... 73 Timers ................................................................................................................................................... 74 hires_tick ................................................................................................................................... 74 timer_max ..................................................................................................................................... 74 SPARC System Specific Parameters .................................................................................................. 75 tsb_alloc_hiwater_factor ..................................................................................................... 75 default_tsb_size ...................................................................................................................... 76 enable_tsb_rss_sizing ............................................................................................................ 77 tsb_rss_factor .......................................................................................................................... 77 Locality Group Parameters ................................................................................................................ 78 5 Contents 6 lpg_alloc_prefer ...................................................................................................................... 78 lgrp_mem_pset_aware ................................................................................................................ 79 3 Oracle Solaris ZFS Tunable Parameters ........................................................................................... 81 Where to Find Tunable Parameter Information ............................................................................. 81 Tuning ZFS Considerations ............................................................................................................... 82 ZFS ARC Parameters .......................................................................................................................... 82 zfs_arc_min ................................................................................................................................. 82 zfs_arc_max ................................................................................................................................. 83 ZFS File-Level Prefetch ....................................................................................................................... 83 zfs_prefetch_disable .............................................................................................................. 83 ZFS Device I/O Queue Depth ............................................................................................................ 84 zfs_vdev_max_pending .............................................................................................................. 84 ZFS and Cache Flushing ..................................................................................................................... 85 zfs_nocacheflush ...................................................................................................................... 86 ZFS Metadata Compression ............................................................................................................... 87 zfs_mdcomp_disable .................................................................................................................. 87 Tuning ZFS for Database Products ................................................................................................... 87 Tuning ZFS for an Oracle Database ........................................................................................... 88 Using ZFS with MySQL Considerations ................................................................................... 91 4 NFS Tunable Parameters ....................................................................................................................93 Where to Find Tunable Parameter Information ............................................................................. 93 Tuning the NFS Environment ........................................................................................................... 93 NFS Module Parameters ..................................................................................................................... 94 nfs:nfs3_pathconf_disable_cache ....................................................................................... 94 nfs:nfs4_pathconf_disable_cache ....................................................................................... 94 nfs:nfs_allow_preepoch_time ............................................................................................... 95 nfs:nfs_cots_timeo .................................................................................................................. 96 nfs:nfs3_cots_timeo ................................................................................................................ 96 nfs:nfs4_cots_timeo ................................................................................................................ 97 nfs:nfs_do_symlink_cache ..................................................................................................... 98 nfs:nfs3_do_symlink_cache ................................................................................................... 98 nfs:nfs4_do_symlink_cache ................................................................................................... 99 nfs:nfs_dynamic ........................................................................................................................ 99 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Contents nfs:nfs3_dynamic .................................................................................................................... 100 nfs:nfs_lookup_neg_cache ................................................................................................... 100 nfs:nfs3_lookup_neg_cache ................................................................................................. 101 nfs:nfs4_lookup_neg_cache ................................................................................................. 102 nfs:nfs_max_threads .............................................................................................................. 103 nfs:nfs3_max_threads ............................................................................................................ 104 nfs:nfs4_max_threads ............................................................................................................ 105 nfs:nfs_nra ............................................................................................................................... 105 nfs:nfs3_nra ............................................................................................................................. 106 nfs:nfs4_nra ............................................................................................................................. 107 nfs:nrnode ................................................................................................................................. 107 nfs:nfs_shrinkreaddir .......................................................................................................... 108 nfs:nfs3_shrinkreaddir ........................................................................................................ 109 nfs:nfs_write_error_interval ........................................................................................... 110 nfs:nfs_write_error_to_cons_only .................................................................................. 110 nfs:nfs_disable_rddir_cache ............................................................................................. 111 nfs:nfs3_bsize ........................................................................................................................ 112 nfs:nfs4_bsize ........................................................................................................................ 112 nfs:nfs_async_clusters ........................................................................................................ 113 nfs:nfs3_async_clusters ..................................................................................................... 114 nfs:nfs4_async_clusters ..................................................................................................... 115 nfs:nfs_async_timeout .......................................................................................................... 116 nfs:nacache ............................................................................................................................... 116 nfs:nfs3_jukebox_delay ........................................................................................................ 117 nfs:nfs3_max_transfer_size ............................................................................................... 118 nfs:nfs4_max_transfer_size ............................................................................................... 119 nfs:nfs3_max_transfer_size_clts ..................................................................................... 120 nfs:nfs3_max_transfer_size_cots ..................................................................................... 120 rpcmod Module Parameters .............................................................................................................. 121 rpcmod:clnt_max_conns .......................................................................................................... 121 rpcmod:clnt_idle_timeout ................................................................................................... 122 rpcmod:svc_idle_timeout ..................................................................................................... 122 rpcmod:svc_default_stksize ............................................................................................... 122 rpcmod:maxdupreqs .................................................................................................................. 123 rpcmod:cotsmaxdupreqs .......................................................................................................... 124 7 Contents 8 5 Internet Protocol Suite Tunable Parameters ................................................................................ 127 Where to Find Tunable Parameter Information ........................................................................... 127 Overview of Tuning IP Suite Parameters ....................................................................................... 127 IP Suite Parameter Validation .................................................................................................. 128 Internet Request for Comments (RFCs) ................................................................................. 128 IP Tunable Parameters ...................................................................................................................... 128 _icmp_err_interval and _icmp_err_burst ........................................................................ 128 _respond_to_echo_broadcast and _respond_to_echo_multicast (ipv4 or ipv6) ..129 _send_redirects (ipv4 or ipv6) .........................................................................................129 forwarding (ipv4 or ipv6) ...................................................................................................130 ttl ................................................................................................................................................ 130 hoplimit (ipv6) ....................................................................................................................... 130 _addrs_per_if ........................................................................................................................... 131 hostmodel (ipv4 or ipv6) .....................................................................................................131 ip_squeue_fanout .................................................................................................................... 132 IP Tunable Parameters With Additional Cautions ................................................................ 133 TCP Tunable Parameters ................................................................................................................. 134 _deferred_ack_interval ........................................................................................................ 134 _local_dack_interval ............................................................................................................ 135 _deferred_acks_max ................................................................................................................ 135 _local_dacks_max .................................................................................................................... 136 _wscale_always ........................................................................................................................ 136 _tstamp_always ........................................................................................................................ 137 send_buf ..................................................................................................................................... 137 recv_buf ..................................................................................................................................... 138 max_buf ....................................................................................................................................... 138 _cwnd_max ................................................................................................................................... 139 _slow_start_initial .............................................................................................................. 139 _local_slow_start_initial ................................................................................................. 140 _slow_start_after_idle ........................................................................................................ 140 sack .............................................................................................................................................. 140 _rev_src_routes ...................................................................................................................... 141 _time_wait_interval .............................................................................................................. 141 ecn ................................................................................................................................................ 142 _conn_req_max_q ...................................................................................................................... 143 _conn_req_max_q0 .................................................................................................................... 144 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Contents _conn_req_min ........................................................................................................................... 144 _rst_sent_rate_enabled ........................................................................................................ 145 _rst_sent_rate ........................................................................................................................ 145 TCP/IP Parameters Set in the /etc/system File .................................................................... 147 TCP Parameters With Additional Cautions ........................................................................... 148 UDP Tunable Parameters ................................................................................................................. 152 send_buf ..................................................................................................................................... 152 recv_buf ..................................................................................................................................... 152 max_buf ....................................................................................................................................... 153 smallest_anon_port ................................................................................................................ 153 largest_anon_port .................................................................................................................. 154 IPQoS Tunable Parameter ................................................................................................................ 154 _policy_mask ............................................................................................................................. 154 SCTP Tunable Parameters ............................................................................................................... 155 _max_init_retr ........................................................................................................................ 155 _pa_max_retr ............................................................................................................................. 155 _pp_max_retr ............................................................................................................................. 156 _cwnd_max ................................................................................................................................... 156 _ipv4_ttl ................................................................................................................................... 157 _heartbeat_interval .............................................................................................................. 157 _new_secret_interval ............................................................................................................ 158 _initial_mtu ............................................................................................................................. 158 _deferred_ack_interval ........................................................................................................ 159 _ignore_path_mtu .................................................................................................................... 159 _initial_ssthresh .................................................................................................................. 159 send_buf ..................................................................................................................................... 160 _xmit_lowat ............................................................................................................................... 160 recv_buf ..................................................................................................................................... 160 max_buf ....................................................................................................................................... 161 _rto_min ..................................................................................................................................... 161 _rto_max ..................................................................................................................................... 162 _rto_initial ............................................................................................................................. 162 _cookie_life ............................................................................................................................. 162 _max_in_streams ...................................................................................................................... 163 _initial_out_streams ............................................................................................................ 163 _shutack_wait_bound .............................................................................................................. 163 9 Contents 10 _maxburst ................................................................................................................................... 164 _addip_enabled ........................................................................................................................ 164 _prsctp_enabled ...................................................................................................................... 164 smallest_anon_port ................................................................................................................ 165 largest_anon_port .................................................................................................................. 165 Per-Route Metrics .............................................................................................................................. 166 6 System Facility Parameters ..............................................................................................................169 System Default Parameters .............................................................................................................. 170 autofs ......................................................................................................................................... 170 cron .............................................................................................................................................. 170 devfsadm ..................................................................................................................................... 170 dhcpagent ................................................................................................................................... 170 fs .................................................................................................................................................. 171 ftp ................................................................................................................................................ 171 inetinit ..................................................................................................................................... 171 init .............................................................................................................................................. 171 ipsec ........................................................................................................................................... 172 kbd ................................................................................................................................................ 172 keyserv ....................................................................................................................................... 172 login ........................................................................................................................................... 173 mpathd ......................................................................................................................................... 173 nfs ................................................................................................................................................ 173 nfslogd ....................................................................................................................................... 173 nss ................................................................................................................................................ 173 passwd ......................................................................................................................................... 173 su .................................................................................................................................................. 174 syslog ......................................................................................................................................... 174 tar ................................................................................................................................................ 174 telnetd ....................................................................................................................................... 174 utmpd ........................................................................................................................................... 174 A Tunable Parameters Change History .............................................................................................175 Kernel Parameters ............................................................................................................................. 175 General Kernel and Memory Parameters (Oracle Solaris 11 and 11.1) ............................... 175 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Contents Paging-Related Parameters (Oracle Solaris 11) ...................................................................... 176 Process-Sizing Tunables (Oracle Solaris 11.1) ....................................................................... 176 Swapping-Related Parameter (Oracle Solaris 11.1) ............................................................... 177 General File System Parameter (Oracle Solaris 11.1) ............................................................ 177 General Driver Parameter (Oracle Solaris 11) ........................................................................ 177 Network Driver Parameters (Oracle Solaris 11) ..................................................................... 177 TCP/IP Tunable Parameters (Oracle Solaris 11 and 11.1) ........................................................... 178 [tcp,sctp,udp]_smallest_anon_port and [tcp,sctp,udp]_largest_anon_port ..... 178 _local_slow_start_initial ................................................................................................. 178 IP Parameter Name Changes (Oracle Solaris 11) ................................................................... 178 TCP Parameter Name Changes (Oracle Solaris 11) ............................................................... 179 UDP Parameter Name Changes (Oracle Solaris 11) .............................................................. 181 SCTP Parameter Name Changes (Oracle Solaris 11) ............................................................. 181 Parameters That Are Obsolete or Have Been Removed (Oracle Solaris 11 and 11.1) ............... 182 NCA Parameters ........................................................................................................................ 183 consistent_coloring .............................................................................................................. 183 rstchown ..................................................................................................................................... 183 Obsolete TCP/IP Module Parameters (Oracle Solaris 11) .................................................... 184 B Revision History for This Manual .................................................................................................... 185 Current Version: Oracle Solaris 11.1 Release ................................................................................. 185 New or Changed Parameters in the Oracle Solaris Release .......................................................... 185 Index ................................................................................................................................................... 187 11 12 Preface The Oracle Solaris 11.1 Tunable Parameters Reference Manual provides reference information about Oracle Solaris OS kernel and network tunable parameters. This manual does not provide tunable parameter information about desktop systems or Java environments. This manual contains information for both SPARC based and x86 based systems. Note This Oracle Solaris release supports systems that use the SPARC and x86 families of processor architectures. The supported systems appear in the Oracle Solaris Hardware Compatibility List at http://www.oracle.com/webfolder/technetwork/hcl/index.html. This document cites any implementation differences between the platform types. Who Should Use This Book This book is intended for experienced Oracle Solaris system administrators who might need to change kernel tunable parameters in certain situations. For guidelines on changing Oracle Solaris tunable parameters, refer to "Tuning an Oracle Solaris System" on page 19. How This Book Is Organized The following table describes the chapters and appendixes in this book. Chapter Description Chapter 1, "Overview of Oracle Solaris An overview of tuning an Oracle Solaris system. Also provides a System Tuning" description of the format used in the book to describe the kernel tunables. Chapter 2, "Oracle Solaris Kernel Tunable Parameters" A description of Oracle Solaris kernel tunables such as kernel memory, file system, process size, and paging parameters. Chapter 3, "Oracle Solaris ZFS Tunable A description of Oracle Solaris ZFS tunable parameters. This chapter Parameters" also includes ZFS tuning information for database products. Chapter 4, "NFS Tunable Parameters" A description of NFS tunables such as caching symbolic links, dynamic retransmission, and RPC security parameters. 13 Preface Chapter Description Chapter 5, "Internet Protocol Suite Tunable Parameters" A description of TCP/IP tunables such as IP forwarding, source routing, and buffer-sizing parameters. Chapter 6, "System Facility Parameters" A description of parameters used to set default values of certain system facilities. Changes are made by modifying files in the /etc/default directory. Appendix A, "Tunable Parameters Change History" A history of parameters that have changed or are now obsolete. Appendix B, "Revision History for This A history of this manual's revisions including the current Oracle Manual" Solaris release. Other Resources for Oracle Solaris Tuning Information This table describes other resources for Oracle Solaris tuning information. Tuning Resource Online performance tuning information In-depth technical white papers For More Information http://www.solarisinternals.com/si/index.php http://www.oracle.com/ technetwork/server-storage/solaris/overview/ index.html Access to Oracle Support Oracle customers have access to electronic support through My Oracle Support. For information, visit http://www.oracle.com/pls/topic/lookup?ctx=acc&id=info or visit http://www.oracle.com/pls/topic/lookup?ctx=acc&id=trs if you are hearing impaired. Typographic Conventions The following table describes the typographic conventions that are used in this book. TABLE P1 Typographic Conventions Typeface AaBbCc123 Description Example The names of commands, files, and directories, Edit your .login file. and onscreen computer output Use ls -a to list all files. machine_name% you have mail. 14 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Preface TABLE P1 Typographic Conventions Typeface Description (Continued) AaBbCc123 What you type, contrasted with onscreen computer output aabbcc123 Placeholder: replace with a real name or value AaBbCc123 Book titles, new terms, and terms to be emphasized Example machine_name% su Password: The command to remove a file is rm filename. Read Chapter 6 in the User's Guide. A cache is a copy that is stored locally. Do not save the file. Note: Some emphasized items appear bold online. Shell Prompts in Command Examples The following table shows the default UNIX system prompt and superuser prompt for shells that are included in the Oracle Solaris OS. Note that the default system prompt that is displayed in command examples varies, depending on the Oracle Solaris release. TABLE P2 Shell Prompts Shell Prompt Bash shell, Korn shell, and Bourne shell $ Bash shell, Korn shell, and Bourne shell for superuser # C shell machine_name% C shell for superuser machine_name# 15 16 1C H A P T E R 1 Overview of Oracle Solaris System Tuning This section provides overview information about the format of the tuning information in this manual. This section also describes the different ways to tune an Oracle Solaris system. "What's New in Oracle Solaris System Tuning?" on page 17 "Tuning an Oracle Solaris System" on page 19 "Tuning Format of Tunable Parameters Descriptions" on page 19 "Tuning the Oracle Solaris Kernel" on page 21 "Special Oracle Solaris tune and var Structures" on page 23 "Viewing Oracle Solaris System Configuration Information" on page 24 "kstat Utility" on page 24 What's New in Oracle Solaris System Tuning? This section describes new or changed parameters in the Oracle Solaris 11.1 release. Oracle Solaris 11.1: Oracle Solaris ZFS tunable information is provided in Chapter 3, "Oracle Solaris ZFS Tunable Parameters." Oracle Solaris 11.1: The maxusers, max_nprocs, ngroups_max, pidmax, and segkpsize parameters have been revised. For more information, see Chapter 2, "Oracle Solaris Kernel Tunable Parameters." Oracle Solaris 11.1: The dnlc_dircache_percent parameter is new . For more information, see "dnlc_dircache_percent" on page 65. Oracle Solaris 11: The rstchown parameter that was previously set in the /etc/system file is obsolete. If you set this parameter in the /etc/system file, the following error message is displayed: sorry, variable 'rstchown' is not defined in the 'kernel' This parameter has been replaced by the ZFS rstchown file system property and a general file system mount option. For more information, see Oracle Solaris 11.1 Administration: ZFS File Systems and mount(1M). 17 What's New in Oracle Solaris System Tuning? Oracle Solaris 11: The following system configuration parameters that were previously configured by editing files in the /etc/default directory have changed to SMF services: autofs init kbd nfs For information about changing SMF service properties, see Chapter 6, "System Facility Parameters." Oracle Solaris 11: The ipadm command replaces the ndd command for setting network properties. TCP, IP, UDP, and SCTP properties are set as follows: ipadm set-prop -p parameter ip|ipv4|ipv6|tcp|udp|sctp In addition, most of the network tunable names have changed slightly to correlate better with the ipadm format. For more information, see "Overview of Tuning IP Suite Parameters" on page 127. Oracle Solaris 11: This release includes the disp_rechoose_interval parameter. For more information, see "disp_rechoose_interval" on page 73. Oracle Solaris 11: This release includes the ngroups_max parameter description. For more information, see "ngroups_max" on page 38. Oracle Solaris 11: This release includes the zfs_arc_min and zfs_arc_max parameter descriptions. For more information, see "zfs_arc_min" on page 82 and "zfs_arc_max" on page 83. Oracle Solaris 11: This release includes several igb and ixgbe network driver parameters. For more information, see "igb Parameters" on page 56 and "ixgbe Parameters" on page 57. Oracle Solaris 11: This release includes the ddi_msix_alloc_limit parameter that can be used to increase the number of MSI-X interrupts that a device instance can allocate. For more information, see "ddi_msix_alloc_limit" on page 55. Oracle Solaris 11: This release includes the kmem_stackinfo parameter, which can be enabled to monitor kernel thread stack usage. For more information, see "kmem_stackinfo" on page 53. Oracle Solaris 11: Memory locality group parameters are provided in this release. For more information about these parameters, see "Locality Group Parameters" on page 78. 18 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Tuning Format of Tunable Parameters Descriptions Tuning an Oracle Solaris System The Oracle Solaris OS is a multi-threaded, scalable UNIX operating system that runs on SPARC and x86 processors. It is self-adjusting to system load and demands minimal tuning. In some cases, however, tuning is necessary. This book provides details about the officially supported kernel tuning options available for the Oracle Solaris OS. The Solaris kernel is composed of a core portion, which is always loaded, and a number of loadable modules that are loaded as references are made to them. Many variables referred to in the kernel portion of this guide are in the core portion. However, a few variables are located in loadable modules. A key consideration in system tuning is that setting system parameters (or system variables) is often the least effective action that can be done to improve performance. Changing the behavior of the application is generally the most effective tuning aid available. Adding more physical memory and balancing disk I/O patterns are also useful. In a few rare cases, changing one of the variables described in this guide will have a substantial effect on system performance. Remember that one system's /etc/system settings might not be applicable, either wholly or in part, to another system's environment. Carefully consider the values in the file with respect to the environment in which they will be applied. Make sure that you understand the behavior of a system before attempting to apply changes to the system variables that are described here. We recommend that you start with an empty /etc/system file when moving to a new Oracle Solaris release. As a first step, add only those tunables that are required by in-house or third-party applications. After baseline testing has been established, evaluate system performance to determine if additional tunable settings are required. Caution The tunable parameters described in this book can and do change from Oracle Solaris release to Oracle Solaris release. Publication of these tunable parameters does not preclude changes to the tunable parameters and their descriptions without notice. Tuning Format of Tunable Parameters Descriptions The format for the description of each tunable parameter is as follows: Parameter Name Description Data Type Default Range Units Dynamic? Validation Chapter 1 · Overview of Oracle Solaris System Tuning 19 Tuning Format of Tunable Parameters Descriptions Implicit When to Change Zone Configuration Commitment Level Change History Parameter Name Is the exact name that is typed in the /etc/system file, or found in the /etc/default/facility file. Description Data Type Units Default Range Dynamic? Validation Implicit When to Change Most parameters names are of the form parameter where the parameter name does not contain a colon (:). These names refer to variables in the core portion of the kernel. If the name does contain a colon, the characters to the left of the colon reference the name of a loadable module. The name of the parameter within the module consists of the characters to the right of the colon. For example: module_name:variable Briefly describes what the parameter does or controls. Indicates the signed or unsigned short integer or long integer. A long integer is twice the width in bits as an integer. For example, an unsigned integer = 32 bits, an unsigned long integer = 64 bits. (Optional) Describes the unit type. What the system uses as the default value. Specifies the possible range allowed by system validation or the bounds of the data type. MAXINT A shorthand description for the maximum value of a signed integer (2,147,483,647) MAXUINT A shorthand description for the maximum value of an unsigned integer (4,294,967,295) Yes, if the parameter can be changed on a running system with the mdb or kmdb debugger. No, if the parameter is a boot time initialization only. Checks that the system applies to the value of the variable either as specified in the /etc/system file or the default value, as well as when the validation is applied. (Optional) Provides unstated constraints that might exist on the parameter, especially in relation to other parameters. Explains why someone might want to change this value. Includes error messages or return codes. 20 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Tuning the Oracle Solaris Kernel Zone Configuration Commitment Level Change History Identifies whether the parameter can be set in a exclusive-IP zone or must be set in the global zone. None of the parameters can be set in shared-IP zones. Identifies the stability of the interface. Many of the parameters in this manual are still evolving and are classified as unstable. For more information, see attributes(5). (Optional) Contains a link to the Change History appendix, if applicable. Tuning the Oracle Solaris Kernel The following table describes the different ways tunable parameters can be applied. Apply Tunable Parameters in These Ways Modify the /etc/system file Use the kernel debugger (kmdb) Use the modular debugger (mdb) Use the ipadm command to set TCP/IP parameters Modify the /etc/default files For More Information "/etc/system File" on page 21 "kmdb Command" on page 22 "mdb Command" on page 22 Chapter 5, "Internet Protocol Suite Tunable Parameters" Chapter 6, "System Facility Parameters" /etc/system File The /etc/system file provides a static mechanism for adjusting the values of kernel parameters. Values specified in this file are read at boot time and are applied. Any changes that are made to the file are not applied to the operating system until the system is rebooted. One pass is made to set all the values before the configuration parameters are calculated. Example-Setting a Parameter in /etc/system The following /etc/system entry sets the ZFS ARC maximum (zfs_arc_max) to 30 GB. set zfs:zfs_arc_max = 0x780000000 Chapter 1 · Overview of Oracle Solaris System Tuning 21 Tuning the Oracle Solaris Kernel Recovering From an Incorrect Value Make a copy of the /etc/system file before modifying it so that you can easily recover from incorrect value. For example: # cp /etc/system /etc/system.good If a value specified in the /etc/system file causes the system to become unbootable, you can recover with the following command: ok boot -a This command causes the system to ask for the name of various files used in the boot process. Press the Return key to accept the default values until the name of the /etc/system file is requested. When the Name of system file [/etc/system]: prompt is displayed, type the name of the good /etc/system file or /dev/null: Name of system file [/etc/system]: /etc/system.good If /dev/null is specified, this path causes the system to attempt to read from /dev/null for its configuration information. Because this file is empty, the system uses the default values. After the system is booted, the /etc/system file can be corrected. For more information on system recovery, see Oracle Solaris Administration: Common Tasks. kmdb Command kmdb is a interactive kernel debugger with the same general syntax as mdb. An advantage of interactive kernel debugger is that you can set breakpoints. When a breakpoint is reached, you can examine data or step through the execution of kernel code. kmdb can be loaded and unloaded on demand. You do not have to reboot the system to perform interactive kernel debugging, as was the case with kadb. For more information, see kmdb(1). mdb Command The modular debugger, mdb, is unique among Solaris debuggers because it is easily extensible. A programming API is available that allows compilation of modules to perform desired tasks within the context of the debugger. mdb also includes a number of desirable usability features, including command-line editing, command history, built-in output pager, syntax checking, and command pipelining. mdb is the recommended post-mortem debugger for the kernel. 22 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Special Oracle Solaris tune and var Structures For more information, see mdb(1). ExampleUsing mdb to Display Information Display a high-level view of a system's memory usage. For example: # mdb -k Loading modules: [ unix genunix specfs dtrace mac cpu.generic cpu_ms.AuthenticAMD.15 uppc pcplusmp scsi_vhci zfs mpt sd ip hook neti arp usba sockfs kssl qlc fctl stmf stmf_ sbd md lofs random idm fcp crypto cpc smbsrv nfs fcip sppp ufs logindmux ptm nsmb scu mpt_sas pmcs emlxs ] > ::memstat Page Summary Pages MB %Tot ------------ ---------------- ---------------- ---- Kernel 160876 628 16% ZFS File Data 303401 1185 30% Anon 25335 98 2% Exec and libs 1459 5 0% Page cache 5083 19 1% Free (cachelist) 6616 25 1% Free (freelist) 510870 1995 50% Total Physical > $q 1013640 3959 1013639 3959 For more information on using the modular debugger, see the Oracle Solaris Modular Debugger Guide. When using either kmdb or mdb debugger, the module name prefix is not required. After a module is loaded, its symbols form a common name space with the core kernel symbols and any other previously loaded module symbols. Special Oracle Solaris tune and var Structures Oracle Solaris tunable parameters come in a variety of forms. The tune structure defined in the/usr/include/sys/tuneable.h file is the runtime representation of tune_t_fsflushr, tune_t_minarmem, and tune_t_flkrec. After the kernel is initialized, all references to these variables are found in the appropriate field of the tune structure. The proper way to set parameters for this structure at boot time is to initialize the special parameter that corresponds to the desired field name. The system initialization process then loads these values into the tune structure. A second structure into which various tunable parameters are placed is the var structure named v. You can find the definition of a var structure in the /usr/include/sys/var.h file. The runtime representation of variables such as autoup and bufhwm is stored here. Do not change either the tune or v structure on a running system. Changing any field in these structures on a running system might cause the system to panic. Chapter 1 · Overview of Oracle Solaris System Tuning 23 Viewing Oracle Solaris System Configuration Information Viewing Oracle Solaris System Configuration Information Several tools are available to examine system configuration information. Some tools require superuser privilege. Other tools can be run by a non-privileged user. Every structure and data item can be examined with the kernel debugger by using mdb on a running system or by booting under kmdb. For more information, see mdb(1) or kadb(1M). sysdef Command The sysdef command provides the values of memory and process resource limits, and portions of the tune and v structures. For example, the sysdef "Tunable Parameters" section from a SPARC T3-4 system with 500 GB of memory is as follows: 2206203904 65546 99 65541 30 25 1 25 25 maximum memory allowed in buffer cache (bufhwm) maximum number of processes (v.v_proc) maximum global priority in sys class (MAXCLSYSPRI) maximum processes per user id (v.v_maxup) auto update time limit in seconds (NAUTOUP) page stealing low water mark (GPGSLO) fsflush run rate (FSFLUSHR) minimum resident memory for avoiding deadlock (MINARMEM) minimum swapable memory for avoiding deadlock (MINASMEM) For more information, see sysdef(1M). kstat Utility kstats are data structures maintained by various kernel subsystems and drivers. They provide a mechanism for exporting data from the kernel to user programs without requiring that the program read kernel memory or have superuser privilege. For more information, see kstat(1M) or kstat(3KSTAT). 24 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 2C H A P T E R 2 Oracle Solaris Kernel Tunable Parameters This chapter describes most of the Oracle Solaris kernel tunable parameters. "General Kernel and Memory Parameters" on page 26 "fsflush and Related Parameters" on page 30 "Process-Sizing Parameters" on page 34 "Paging-Related Parameters" on page 39 "Swapping-Related Parameters" on page 50 "Kernel Memory Allocator" on page 52 "General Driver Parameters" on page 54 "Network Driver Parameters" on page 56 "General I/O Parameters" on page 61 "General File System Parameters" on page 63 "TMPFS Parameters" on page 66 "Pseudo Terminals" on page 67 "STREAMS Parameters" on page 70 "System V Message Queues" on page 71 "System V Semaphores" on page 72 "System V Shared Memory" on page 72 "Scheduling" on page 73 "Timers" on page 74 "SPARC System Specific Parameters" on page 75 "Locality Group Parameters" on page 78 Where to Find Tunable Parameter Information Tunable Parameter Oracle Solaris ZFS tunables parameters NFS tunable parameters For Information Chapter 3, "Oracle Solaris ZFS Tunable Parameters" Chapter 4, "NFS Tunable Parameters" 25 General Kernel and Memory Parameters Tunable Parameter Internet Protocol Suite tunable parameters For Information Chapter 5, "Internet Protocol Suite Tunable Parameters" General Kernel and Memory Parameters This section describes general kernel parameters that are related to physical memory and stack configuration. The ZFS-related memory parameters have moved to Chapter 3, "Oracle Solaris ZFS Tunable Parameters." physmem Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Modifies the system's configuration of the number of physical pages of memory after the Oracle Solaris OS and firmware are accounted for. Unsigned long Number of usable pages of physical memory available on the system, not counting the memory where the core kernel and data are stored 1 to amount of physical memory on system Pages No None Whenever you want to test the effect of running the system with less physical memory. Because this parameter does not take into account the memory used by the core kernel and data, as well as various other data structures allocated early in the startup process, the value of physmem should be less than the actual number of pages that represent the smaller amount of memory. Unstable default_stksize Description Data Type Specifies the default stack size of all threads. No thread can be created with a stack size smaller than default_stksize. If default_stksize is set, it overrides lwp_default_stksize. See also "lwp_default_stksize" on page 27. Integer 26 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 General Kernel and Memory Parameters Default Range Units Dynamic? Validation When to Change Commitment Level 3 x PAGESIZE on SPARC systems 5 x PAGESIZE on x64 systems Minimum is the default values: 3 x PAGESIZE on SPARC systems 5 x PAGESIZE on x64 systems Maximum is 32 times the default value. Bytes in multiples of the value returned by the getpagesize parameter. For more information, see getpagesize(3C). Yes. Affects threads created after the variable is changed. Must be greater than or equal to 8192 and less than or equal to 262,144 (256 x 1024). Also must be a multiple of the system page size. If these conditions are not met, the following message is displayed: Illegal stack size, Using N The value of N is the default value of default_stksize. When the system panics because it has run out of stack space. The best solution for this problem is to determine why the system is running out of space and then make a correction. Increasing the default stack size means that almost every kernel thread will have a larger stack, resulting in increased kernel memory consumption for no good reason. Generally, that space will be unused. The increased consumption means other resources that are competing for the same pool of memory will have the amount of space available to them reduced, possibly decreasing the system's ability to perform work. Among the side effects is a reduction in the number of threads that the kernel can create. This solution should be treated as no more than an interim workaround until the root cause is remedied. Unstable lwp_default_stksize Description Data Type Specifies the default value of the stack size to be used when a kernel thread is created, and when the calling routine does not provide an explicit size to be used. Integer Chapter 2 · Oracle Solaris Kernel Tunable Parameters 27 General Kernel and Memory Parameters Default Range Units Dynamic? Validation When to Change Commitment Level 32,768 for SPARC platforms 20,480 for x64 platforms Minimum is the default values: 3 x PAGESIZE on SPARC systems 5 x PAGESIZE on x64 systems Maximum is 32 times the default value. Bytes in multiples of the value returned by the getpagesize parameter. For more information, see getpagesize(3C). Yes. Affects threads created after the variable is changed. Must be greater than or equal to 8192 and less than or equal to 262,144 (256 x 1024). Also must be a multiple of the system page size. If these conditions are not met, the following message is displayed: Illegal stack size, Using N The value of N is the default value of lwp_default_stksize. When the system panics because it has run out of stack space. The best solution for this problem is to determine why the system is running out of space and then make a correction. Increasing the default stack size means that almost every kernel thread will have a larger stack, resulting in increased kernel memory consumption for no good reason. Generally, that space will be unused. The increased consumption means other resources that are competing for the same pool of memory will have the amount of space available to them reduced, possibly decreasing the system's ability to perform work. Among the side effects is a reduction in the number of threads that the kernel can create. This solution should be treated as no more than an interim workaround until the root cause is remedied. Unstable logevent_max_q_sz Description Data Type Maximum number of system events allowed to be queued and waiting for delivery to the syseventd daemon. Once the size of the system event queue reaches this limit, no other system events are allowed on the queue. Integer 28 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 General Kernel and Memory Parameters Default Range Units Dynamic? Validation When to Change Commitment Level 5000 0 to MAXINT System events Yes The system event framework checks this value every time a system event is generated by ddi_log_sysevent and sysevent_post_event. For more information, see ddi_log_sysevent(9F) and sysevent_post_event(3SYSEVENT). When error log messages indicate that a system event failed to be logged, generated, or posted. Unstable segkpsize Description Data Type Default Range Units Dynamic? Validation When to Change Specifies the amount of kernel pageable memory available. This memory is used primarily for kernel thread stacks. Increasing this number allows either larger stacks for the same number of threads or more threads. Unsigned long 2 GB x the smaller result of nCPUs / 128 or the amount of physical memory / 256 GB 512 MB to 64 GB (SPARC) 200 MB to 8 GB (x86) Pages No Value is compared to minimum and maximum sizes. If smaller than the minimum or larger than the maximum, it is reset to 2 GB. A message to that effect is displayed. On SPARC systems, the segkpsize value cannot exceed twice the size of physical memory. On x86 systems, the value cannot exceed the size of physical memory. Required to support large numbers of processes on a system. The default size of 2 GB allows creation of 24-KB stacks for more than Chapter 2 · Oracle Solaris Kernel Tunable Parameters 29 fsflush and Related Parameters Commitment Level Change History 65,536 kernel threads. If more than this number is needed or the stack size needs to be increased, segkpsize can be increased, assuming sufficient physical memory exists. Unstable For information, see "segkpsize" on page 176. noexec_user_stack Description Enables the stack to be marked as nonexecutable, which helps make buffer-overflow attacks more difficult. Data Type Default Range Units Dynamic? Validation When to Change Commitment Level An Oracle Solaris system running a 64-bit kernel makes the stacks of all 64-bit applications nonexecutable by default. Setting this parameter is necessary to make 32-bit applications nonexecutable. Signed integer 0 (disabled) 0 (disabled) or 1 (enabled) Toggle (on/off) Yes. Does not affect currently running processes, only processes created after the value is set. None Should be enabled at all times unless applications are deliberately placing executable code on the stack without using mprotect to make the stack executable. For more information, see mprotect(2). Unstable fsflush and Related Parameters This section describes fsflush and related tunables. fsflush The system daemon, fsflush, runs periodically to do three main tasks: 1. On every invocation, fsflush flushes dirty file system pages over a certain age to disk. 30 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 fsflush and Related Parameters 2. On every invocation, fsflush examines a portion of memory and causes modified pages to be written to their backing store. Pages are written if they are modified and if they do not meet one of the following conditions: Pages are kernel page Pages are free Pages are locked Pages are associated with a swap device Pages are currently involved in an I/O operation The net effect is to flush pages from files that are mapped with mmap with write permission and that have actually been changed. Pages are flushed to backing store but left attached to the process using them. This will simplify page reclamation when the system runs low on memory by avoiding delay for writing the page to backing store before claiming it, if the page has not been modified since the flush. 3. fsflush writes file system metadata to disk. This write is done every nth invocation, where n is computed from various configuration variables. See "tune_t_fsflushr" on page 31 and "autoup" on page 32 for details. The following features are configurable: Frequency of invocation (tune_t_fsflushr) Whether memory scanning is executed (dopageflush) Whether file system data flushing occurs (doiflush) The frequency with which file system data flushing occurs (autoup) For most systems, memory scanning and file system metadata synchronizing are the dominant activities for fsflush. Depending on system usage, memory scanning can be of little use or consume too much CPU time. tune_t_fsflushr Description Data Type Default Range Units Dynamic? Specifies the number of seconds between fsflush invocations Signed integer 1 1 to MAXINT Seconds No Chapter 2 · Oracle Solaris Kernel Tunable Parameters 31 fsflush and Related Parameters Validation When to Change Commitment Level If the value is less than or equal to zero, the value is reset to 1 and a warning message is displayed. This check is done only at boot time. See the autoup parameter. Unstable autoup Description Data Type Default Range Units Dynamic? Validation Implicit When to Change Along with tune_t_flushr, autoup controls the amount of memory examined for dirty pages in each invocation and frequency of file system synchronizing operations. The value of autoup is also used to control whether a buffer is written out from the free list. Buffers marked with the B_DELWRI flag (which identifies file content pages that have changed) are written out whenever the buffer has been on the list for longer than autoup seconds. Increasing the value of autoup keeps the buffers in memory for a longer time. Signed integer 30 1 to MAXINT Seconds No If autoup is less than or equal to zero, it is reset to 30 and a warning message is displayed. This check is done only at boot time. autoup should be an integer multiple of tune_t_fsflushr. At a minimum, autoup should be at least 6 times the value of tune_t_fsflushr. If not, excessive amounts of memory are scanned each time fsflush is invoked. The total system pages multiplied by tune_t_fsflushr should be greater than or equal to autoup to cause memory to be checked if dopageflush is non-zero. Here are several potential situations for changing autoup, tune_t_fsflushr, or both: Systems with large amounts of memory In this case, increasing autoup reduces the amount of memory scanned in each invocation of fsflush. 32 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 fsflush and Related Parameters Commitment Level Systems with minimal memory demand Increasing both autoup and tune_t_fsflushr reduces the number of scans made. autoup should be increased also to maintain the current ratio of autoup / tune_t_fsflushr. Systems with large numbers of transient files (for example, mail servers or software build machines) If large numbers of files are created and then deleted, fsflush might unnecessarily write data pages for those files to disk. Unstable dopageflush Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls whether memory is examined for modified pages during fsflush invocations. In each invocation of fsflush, the number of physical memory pages in the system is determined. This number might have changed because of a dynamic reconfiguration operation. Each invocation scans by using this algorithm: total number of pages x tune_t_fsflushr / autoup pages Signed integer 1 (enabled) 0 (disabled) or 1 (enabled) Toggle (on/off) Yes None If the system page scanner rarely runs, which is indicated by a value of 0 in the sr column of vmstat output. Unstable doiflush Description Controls whether file system metadata syncs will be executed during fsflush invocations. This synchronization is done every Nth invocation of fsflush where N= (autoup / tune_t_fsflushr). Because this algorithm is integer division, if tune_t_fsflushr is greater than autoup, a synchronization is done on every invocation of fsflush because the code checks to see if its iteration counter is greater Chapter 2 · Oracle Solaris Kernel Tunable Parameters 33 Process-Sizing Parameters Data Type Default Range Units Dynamic? Validation When to Change Commitment Level than or equal to N. Note that N is computed once on invocation of fsflush. Later changes to tune_t_fsflushr or autoup have no effect on the frequency of synchronization operations. Signed integer 1 (enabled) 0 (disabled) or 1 (enabled) Toggle (on/off) Yes None When files are frequently modified over a period of time and the load caused by the flushing perturbs system behavior. Files whose existence, and therefore consistency of state, does not matter if the system reboots are better kept in a TMPFS file system (for example, /tmp). Inode traffic can be reduced on systems by using the mount -noatime option. This option eliminates inode updates when the file is accessed. For a system engaged in realtime processing, you might want to disable this option and use explicit application file synchronizing to achieve consistency. Unstable Process-Sizing Parameters Several parameters (or variables) are used to control the number of processes that are available on the system and the number of processes that an individual user can create. The foundation parameter is maxusers. This parameter drives the values assigned to max_nprocs and maxuprc. maxusers Description Originally, maxusers defined the number of logged in users the system could support. When a kernel was generated, various tables were sized based on this setting. Current Oracle Solaris releases do much of its sizing based on the amount of memory on the system. Thus, much of the past use of maxusers has changed. A number of subsystems that are still derived from maxusers: 34 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Process-Sizing Parameters Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Change History The maximum number of processes on the system The number of quota structures held in the system The size of the directory name look-up cache (DNLC) Signed integer Lesser of the amount of memory in MB or 2048, and the greater of that value and nCPUs x 8 1 to the greater of 2048 or nCPUs x 8, based on the size of physical memory, if not set in the /etc/system file 1 to the greater of 4096 or the nCPUs x 8, if set in the /etc/system file Users No. After computation of dependent parameters is done, maxusers is never referenced again. If the value is greater than the maximum allowed, it is reset to the maximum. A message to that effect is displayed. When the default number of user processes derived by the system is too low. This situation is evident when the following message displays on the system console: out of processes You might also change this parameter when the default number of processes is too high, as in these situations: Database servers that have a lot of memory and relatively few running processes can save system memory when the default value of maxusers is reduced. If file servers have a lot of memory and few running processes, you might reduce this value. However, you should explicitly set the size of the DNLC. See "ncsize" on page 63. Unstable For information, see "maxusers" on page 176. reserved_procs Description Data Type Specifies the number of system process slots to be reserved in the process table for processes with a UID of root (0). For example, fsflush has a UID of root (0). Signed integer Chapter 2 · Oracle Solaris Kernel Tunable Parameters 35 Process-Sizing Parameters Default Range Units Dynamic? Validation Commitment Level When to Change 5 5 to MAXINT Processes No. Not used after the initial parameter computation. Any /etc/system setting is honored. Unstable Consider increasing to 10 + the normal number of UID 0 (root) processes on system. This setting provides some cushion should it be necessary to obtain a root shell when the system is otherwise unable to create user-level processes. pidmax Description Data Type Default Range Units Dynamic? Validation Implicit When to Change Commitment Level Change History Specifies the value of the largest possible process ID. pidmax sets the value for the maxpid variable. Once maxpid is set, pidmax is ignored. maxpid is used elsewhere in the kernel to determine the maximum process ID and for validation checking. Any attempts to set maxpid by adding an entry to the /etc/system file have no effect. Signed integer The larger of 30,000 or max_nprocs, but never more than 999,999 5 to 999,999 Processes No. Used only at boot time to set the value of pidmax. Yes. Value is compared to the value of reserved_procs and 999,999. If less than reserved_procs or greater than 999,999, the value is set to 999,999. max_nprocs range checking ensures that max_nprocs is always less than or equal to this value. Required to enable support for more than 30,000 processes on a system. See also "max_nprocs" on page 37. Unstable For information, see "pidmax" on page 176. 36 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Process-Sizing Parameters max_nprocs Description Specifies the maximum number of processes that can be created on a system. Includes system processes and user processes. Any value specified in /etc/system is used in the computation of maxuprc. Data Type Default This value is also used in determining the size of several other system data structures. Other data structures where this parameter plays a role are as follows: Determining the size of the directory name lookup cache (if ncsize is not specified) Verifying that the amount of memory used by configured system V semaphores does not exceed system limits Configuring Hardware Address Translation resources for x86 platforms Signed integer 10 + (16 x maxusers) if maxusers is set in the /etc/system file Range Dynamic? Validation When to Change Commitment Level Change History The larger of 30,000 or 10 + (128 x number of CPUs), if maxusers is not set in the /etc/system file 26 to value of maxpid No Yes. If the value exceeds maxpid, it is set to maxpid . Changing this parameter is one of the steps necessary to enable support for more than 30,000 processes on a system. Unstable For information, see "max_nprocs" on page 176. maxuprc Description Data Type Default Range Units Specifies the maximum number of processes that can be created on a system by any one user. Signed integer max_nprocs - reserved_procs 1 to max_nprocs - reserved_procs Processes Chapter 2 · Oracle Solaris Kernel Tunable Parameters 37 Process-Sizing Parameters Dynamic? Validation When to Change Commitment Level No Yes. This value is compared to max_nprocs - reserved_procs and set to the smaller of the two values. When you want to specify a hard limit for the number of processes a user can create that is less than the default value of however many processes the system can create. Attempting to exceed this limit generates the following warning messages on the console or in the messages file: out of per-user processes for uid N Unstable ngroups_max Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Change History Specifies the maximum number of supplemental groups per process. Signed integer 16 0 to 1024 Groups No Yes. If ngroups_max is set to an invalid value, it is automatically reset to the closest legal value. For example, if it is set to less than zero, it is reset to 0. If it is set to greater than 1024, it is reset to 1024. Review the following considerations if you are using NFS AUTH_SYS authentication and you want to increase the default ngroups_max value: 1. If ngroups_max is set to 16 or if the client's AUTH_SYS credential that is provided has 15 or fewer groups, the client's group information is used. 2. If ngroups_max is set to greater than 16 and the client's AUTH_SYS credential from the name server contains exactly 16 groups, the maximum allowed, the NFS server consults the name server and matches the client's UID to a user name. Then, the name server computes a list of groups to which the user belongs. Unstable For information, see "ngroups_max" on page 176. 38 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Paging-Related Parameters Paging-Related Parameters The Solaris OS uses a demand paged virtual memory system. As the system runs, pages are brought into memory as needed. When memory becomes occupied above a certain threshold and demand for memory continues, paging begins. Paging goes through several levels that are controlled by certain parameters. The general paging algorithm is as follows: A memory deficit is noticed. The page scanner thread runs and begins to walk through memory. A two-step algorithm is employed: 1. A page is marked as unused. 2. If still unused after a time interval, the page is viewed as a subject for reclaim. If the page has been modified, a request is made to the pageout thread to schedule the page for I/O. Also, the page scanner continues looking at memory. Pageout causes the page to be written to the page's backing store and placed on the free list. When the page scanner scans memory, no distinction is made as to the origin of the page. The page might have come from a data file, or it might represent a page from an executable's text, data, or stack. As memory pressure on the system increases, the algorithm becomes more aggressive in the pages it will consider as candidates for reclamation and in how frequently the paging algorithm runs. (For more information, see "fastscan" on page 46 and "slowscan" on page 47.) As available memory falls between the range lotsfree and minfree, the system linearly increases the amount of memory scanned in each invocation of the pageout thread from the value specified by slowscan to the value specified by fastscan. The system uses the desfree parameter to control a number of decisions about resource usage and behavior. The system initially constrains itself to use no more than 4 percent of one CPU for pageout operations. As memory pressure increases, the amount of CPU time consumed in support of pageout operations linearly increases until a maximum of 80 percent of one CPU is consumed. The algorithm looks through some amount of memory between slowscan and fastscan, then stops when one of the following occurs: Enough pages have been found to satisfy the memory shortfall. The planned number of pages have been looked at. Too much time has elapsed. If a memory shortfall is still present when pageout finishes its scan, another scan is scheduled for 1/4 second in the future. The configuration mechanism of the paging subsystem was changed. Instead of depending on a set of predefined values for fastscan, slowscan, and handspreadpages, the system determines the appropriate settings for these parameters at boot time. Setting any of these parameters in the /etc/system file can cause the system to use less than optimal values. Chapter 2 · Oracle Solaris Kernel Tunable Parameters 39 Paging-Related Parameters Caution Remove all tuning of the VM system from the /etc/system file. Run with the default settings and determine if it is necessary to adjust any of these parameters. Do not set either cachefree or priority_paging. Dynamic reconfiguration (DR) for CPU and memory is supported. A system in a DR operation that involves the addition or deletion of memory recalculates values for the relevant parameters, unless the parameter has been explicitly set in /etc/system. In that case, the value specified in /etc/system is used, unless a constraint on the value of the variable has been violated. In this case, the value is reset. lotsfree Description Data Type Default Range Units Dynamic? Validation Implicit When to Change Serves as the initial trigger for system paging to begin. When this threshold is crossed, the page scanner wakes up to begin looking for memory pages to reclaim. Unsigned long The greater of 1/64th of physical memory or 512 KB The minimum value is 512 KB or 1/64th of physical memory, whichever is greater, expressed as pages using the page size returned by getpagesize. For more information, seegetpagesize(3C). The maximum value is the number of physical memory pages. The maximum value should be no more than 30 percent of physical memory. The system does not enforce this range, other than that described in the Validation section. Pages Yes, but dynamic changes are lost if a memory-based DR operation occurs. If lotsfree is greater than the amount of physical memory, the value is reset to the default. The relationship of lotsfree being greater than desfree, which is greater than minfree, should be maintained at all times. When demand for pages is subject to sudden sharp spikes, the memory algorithm might be unable to keep up with demand. One workaround is to start reclaiming memory at an earlier time. This solution gives the paging system some additional margin. 40 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Paging-Related Parameters Commitment Level A rule of thumb is to set this parameter to 2 times what the system needs to allocate in a few seconds. This parameter is workload dependent. A DBMS server can probably work fine with the default settings. However, you might need to adjust this parameter for a system doing heavy file system I/O. For systems with relatively static workloads and large amounts of memory, lower this value. The minimum acceptable value is 512 KB, expressed as pages using the page size returned by getpagesize. Unstable desfree Description Data Type Default Range Units Dynamic? Validation Implicit Side Effects Specifies the preferred amount of memory to be free at all times on the system. Unsigned integer lotsfree / 2 The minimum value is 256 KB or 1/128th of physical memory, whichever is greater, expressed as pages using the page size returned by getpagesize. The maximum value is the number of physical memory pages. The maximum value should be no more than 15 percent of physical memory. The system does not enforce this range other than that described in the Validation section. Pages Yes, unless dynamic reconfiguration operations that add or delete memory occur. At that point, the value is reset to the value provided in the /etc/system file or calculated from the new physical memory value. If desfree is greater than lotsfree, desfree is set to lotsfree / 2. No message is displayed. The relationship of lotsfree being greater than desfree, which is greater than minfree, should be maintained at all times. Several side effects can arise from increasing the value of this parameter. When the new value nears or exceeds the amount of available memory on the system, the following can occur: Chapter 2 · Oracle Solaris Kernel Tunable Parameters 41 Paging-Related Parameters When to Change Commitment Level Asynchronous I/O requests are not processed, unless available memory exceeds desfree. Increasing the value of desfree can result in rejection of requests that otherwise would succeed. NFS asynchronous writes are executed as synchronous writes. The swapper is awakened earlier, and the behavior of the swapper is biased towards more aggressive actions. The system might not preload (prefault) as many executable pages as possible into the system. This side effect results in applications potentially running slower than they otherwise would. For systems with relatively static workloads and large amounts of memory, lower this value. The minimum acceptable value is 256 KB, expressed as pages using the page size returned by getpagesize. Unstable minfree Description Data Type Default Range Units Dynamic? Validation Specifies the minimum acceptable memory level. When memory drops below this number, the system biases allocations toward allocations necessary to successfully complete pageout operations or to swap processes completely out of memory. Either allocation denies or blocks other allocation requests. Unsigned integer desfree / 2 The minimum value is 128 KB or 1/256th of physical memory, whichever is greater, expressed as pages using the page size returned by getpagesize. The maximum value is the number of physical memory pages. The maximum value should be no more than 7.5 percent of physical memory. The system does not enforce this range other than that described in the Validation section. Pages Yes, unless dynamic reconfiguration operations that add or delete memory occur. At that point, the value is reset to the value provided in the /etc/system file or calculated from the new physical memory value. If minfree is greater than desfree, minfree is set to desfree / 2. No message is displayed. 42 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Paging-Related Parameters Implicit When to Change Commitment Level The relationship of lotsfree being greater than desfree, which is greater than minfree, should be maintained at all times. The default value is generally adequate. For systems with relatively static workloads and large amounts of memory, lower this value. The minimum acceptable value is 128 KB, expressed as pages using the page size returned by getpagesize. Unstable throttlefree Description Data Type Default Range Specifies the memory level at which blocking memory allocation requests are put to sleep, even if the memory is sufficient to satisfy the request. Unsigned integer minfree The minimum value is 128 KB or 1/256th of physical memory, whichever is greater, expressed as pages using the page size returned by getpagesize. Units Dynamic? Validation Implicit When to Change The maximum value is the number of physical memory pages. The maximum value should be no more than 4 percent of physical memory. The system does not enforce this range other than that described in the Validation section. Pages Yes, unless dynamic reconfiguration operations that add or delete memory occur. At that point, the value is reset to the value provided in the /etc/system file or calculated from the new physical memory value. If throttlefree is greater than desfree, throttlefree is set to minfree. No message is displayed. The relationship of lotsfree is greater than desfree, which is greater than minfree, should be maintained at all times. The default value is generally adequate. For systems with relatively static workloads and large amounts of memory, lower this value. The minimum acceptable value is 128 KB, expressed as pages using the page size returned by getpagesize. For more information, see getpagesize(3C). Chapter 2 · Oracle Solaris Kernel Tunable Parameters 43 Paging-Related Parameters Commitment Level Unstable pageout_reserve Description Data Type Default Range Specifies the number of pages reserved for the exclusive use of the pageout or scheduler threads. When available memory is less than this value, nonblocking allocations are denied for any processes other than pageout or the scheduler. Pageout needs to have a small pool of memory for its use so it can allocate the data structures necessary to do the I/O for writing a page to its backing store. Unsigned integer throttlefree / 2 The minimum value is 64 KB or 1/512th of physical memory, whichever is greater, expressed as pages using the page size returned by getpagesize(3C). Units Dynamic? Validation Implicit When to Change Commitment Level The maximum is the number of physical memory pages. The maximum value should be no more than 2 percent of physical memory. The system does not enforce this range, other than that described in the Validation section. Pages Yes, unless dynamic reconfiguration operations that add or delete memory occur. At that point, the value is reset to the value provided in the /etc/system file or calculated from the new physical memory value. If pageout_reserve is greater than throttlefree / 2, pageout_reserve is set to throttlefree / 2. No message is displayed. The relationship of lotsfree being greater than desfree, which is greater than minfree, should be maintained at all times. The default value is generally adequate. For systems with relatively static workloads and large amounts of memory, lower this value. The minimum acceptable value is 64 KB, expressed as pages using the page size returned by getpagesize. Unstable 44 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Paging-Related Parameters pages_pp_maximum Description Data Type Default Range Units Dynamic? Validation Defines the number of pages that must be unlocked. If a request to lock pages would force available memory below this value, that request is refused. Unsigned long The greater of (tune_t_minarmem + 100 and [4% of memory available at boot time + 4 MB]) Minimum value enforced by the system is tune_t_minarmem + 100. The system does not enforce a maximum value. Pages Yes, unless dynamic reconfiguration operations that add or delete memory occur. At that point, the value is reset to the value provided in the /etc/system file or was calculated from the new physical memory value. If the value specified in the /etc/system file or the calculated default is less than tune_t_minarmem + 100, the value is reset to tune_t_minarmem + 100. When to Change No message is displayed if the value from the /etc/system file is increased. Validation is done only at boot time and during dynamic reconfiguration operations that involve adding or deleting memory. When memory-locking requests fail or when attaching to a shared memory segment with the SHARE_MMU flag fails, yet the amount of memory available seems to be sufficient. Commitment Level Excessively large values can cause memory locking requests (mlock, mlockall, and memcntl) to fail unnecessarily. For more information, see mlock(3C), mlockall(3C), and memcntl(2). Unstable tune_t_minarmem Description Defines the minimum available resident (not swappable) memory to maintain necessary to avoid deadlock. Used to reserve a portion of memory for use by the core of the OS. Pages restricted in this way are not seen when the OS determines the maximum amount of memory available. Chapter 2 · Oracle Solaris Kernel Tunable Parameters 45 Paging-Related Parameters Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Signed integer 25 1 to physical memory Pages No None. Large values result in wasted physical memory. The default value is generally adequate. Consider increasing the default value if the system locks up and debugging information indicates that no memory was available. Unstable fastscan Description Data Type Default Range Units Dynamic? Validation Defines the maximum number of pages per second that the system looks at when memory pressure is highest. Signed integer The fastscan default value is set in one of the following ways: The fastscan value set in the /etc/system file is used. The maxfastscan value set in the /etc/system file is used. If neither fastscan nor maxfastscan is set in the /etc/system file, fastscan is set to 64 MB when the system is booted. Then, after the system is booted for a few minutes, the fastscan value is set to the number of pages that the scanner can scan in one second using 10% of a CPU. In all three cases, if the derived value is more than half the memory in the system, the fastscan value is capped at the value of half the memory in the system. 64 MB to half the system's physical memory Pages Yes, unless dynamic reconfiguration operations that add or delete memory occur. At that point, the value is reset to the value provided by /etc/system or calculated from the new physical memory value. The maximum value is the lesser of 64 MB and 1/2 of physical memory. 46 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Paging-Related Parameters When to Change Commitment Level When more aggressive scanning of memory is preferred during periods of memory shortfall, especially when the system is subject to periods of intense memory demand or when performing heavy file I/O. Unstable slowscan Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Defines the minimum number of pages per second that the system looks at when attempting to reclaim memory. Signed integer The smaller of 1/20th of physical memory in pages and 100. 1 to fastscan / 2 Pages Yes, unless dynamic reconfiguration operations that add or delete memory occur. At that point, the value is reset to the value provided in the /etc/system file or calculated from the new physical memory value. If slowscan is larger than fastscan / 2, slowscan is reset to fastscan / 2. No message is displayed. When more aggressive scanning of memory is preferred during periods of memory shortfall, especially when the system is subject to periods of intense memory demand. Unstable min_percent_cpu Description Data Type Default Range Units Dynamic? Defines the minimum percentage of CPU that pageout can consume. This parameter is used as the starting point for determining the maximum amount of time that can be consumed by the page scanner. Signed integer 4 1 to 80 Percentage Yes Chapter 2 · Oracle Solaris Kernel Tunable Parameters 47 Paging-Related Parameters Validation When to Change Commitment Level None Increasing this value on systems with multiple CPUs and lots of memory, which are subject to intense periods of memory demand, enables the pager to spend more time attempting to find memory. Unstable handspreadpages Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level The Oracle Solaris OS uses a two-handed clock algorithm to look for pages that are candidates for reclaiming when memory is low. The first hand of the clock walks through memory marking pages as unused. The second hand walks through memory some distance after the first hand, checking to see if the page is still marked as unused. If so, the page is subject to being reclaimed. The distance between the first hand and the second hand is handspreadpages. Unsigned long fastscan 1 to maximum number of physical memory pages on the system Pages Yes. This parameter requires that the kernel reset_hands parameter also be set to a non-zero value. Once the new value of handspreadpages has been recognized, reset_hands is set to zero. The value is set to the lesser of either the amount of physical memory and the handspreadpages value. When you want to increase the amount of time that pages are potentially resident before being reclaimed. Increasing this value increases the separation between the hands, and therefore, the amount of time before a page can be reclaimed. Unstable pages_before_pager Description Defines part of a system threshold that immediately frees pages after an I/O completes instead of storing the pages for possible reuse. The 48 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Paging-Related Parameters Data Type Default Range Units Dynamic? Validation When to Change Commitment Level threshold is lotsfree + pages_before_pager. The NFS environment also uses this threshold to curtail its asynchronous activities as memory pressure mounts. Signed integer 200 1 to amount of physical memory Pages No None You might change this parameter when the majority of I/O is done for pages that are truly read or written once and never referenced again. Setting this variable to a larger amount of memory keeps adding pages to the free list. You might also change this parameter when the system is subject to bursts of severe memory pressure. A larger value here helps maintain a larger cushion against the pressure. Unstable maxpgio Description Data Type Default Range Units Dynamic? Validation Defines the maximum number of page I/O requests that can be queued by the paging system. This number is divided by 4 to get the actual maximum number used by the paging system. This parameter is used to throttle the number of requests as well as to control process swapping. Signed integer 40 1 to a variable maximum that depends on the system architecture, but mainly by the I/O subsystem, such as the number of controllers, disks, and disk swap size I/0s No None Chapter 2 · Oracle Solaris Kernel Tunable Parameters 49 Swapping-Related Parameters Implicit When to Change Commitment Level The maximum number of I/O requests from the pager is limited by the size of a list of request buffers, which is currently sized at 256. Increase this parameter to page out memory faster. A larger value might help to recover faster from memory pressure if more than one swap device is configured or if the swap device is a striped device. Note that the existing I/O subsystem should be able to handle the additional I/O load. Also, increased swap I/O could degrade application I/O performance if the swap partition and application files are on the same disk. Unstable Swapping-Related Parameters Swapping in the Oracle Solaris OS is accomplished by the swapfs pseudo file system. The combination of space on swap devices and physical memory is treated as the pool of space available to support the system for maintaining backing store for anonymous memory. The system attempts to allocate space from disk devices first, and then uses physical memory as backing store. When swapfs is forced to use system memory for backing store, limits are enforced to ensure that the system does not deadlock because of excessive consumption by swapfs. swapfs_reserve Description Data Type Default Range Defines the amount of system memory that is reserved for use by system (UID = 0) processes. Unsigned long The smaller of 4 MB and 1/16th of physical memory The minimum value is 4 MB or 1/16th of physical memory, whichever is smaller, expressed as pages using the page size returned by getpagesize. Units Dynamic? The maximum value is the number of physical memory pages. The maximum value should be no more than 10 percent of physical memory. The system does not enforce this range, other than that described in the Validation section. Pages No 50 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Swapping-Related Parameters Validation When to Change Commitment Level None Generally not necessary. Only change when recommended by a software provider, or when system processes are terminating because of an inability to obtain swap space. A much better solution is to add physical memory or additional swap devices to the system. Unstable swapfs_minfree Description Data Type Default Range Units Dynamic? Validation When to Change Defines the desired amount of physical memory to be kept free for the rest of the system. Attempts to reserve memory for use as swap space by any process that causes the system's perception of available memory to fall below this value are rejected. Pages reserved in this manner can only be used for locked-down allocations by the kernel or by user-level processes. Unsigned long The larger of 2 MB and 12.5% of physical memory 1 to amount of physical memory Pages No None Consider reducing this parameter value when processes are failing because of an inability to obtain swap space, yet the system has memory available. For example, change this value to use no more than 6.25% of system memory, but do not reduce it below 5% of system memory. Commitment Level Change History On SPARC systems, the value should be at least 2 times the value of tsb_alloc_hiwater_factor. For more information, see "tsb_alloc_hiwater_factor" on page 75. Unstable For information, see "swapfs_minfree" on page 177. Chapter 2 · Oracle Solaris Kernel Tunable Parameters 51 Kernel Memory Allocator Kernel Memory Allocator The Oracle Solaris kernel memory allocator distributes chunks of memory for use by clients inside the kernel. The allocator creates a number of caches of varying size for use by its clients. Clients can also request the allocator to create a cache for use by that client (for example, to allocate structures of a particular size). Statistics about each cache that the allocator manages can be seen by using the kstat -c kmem_cache command. Occasionally, systems might panic because of memory corruption. The kernel memory allocator supports a debugging interface (a set of flags), that performs various integrity checks on the buffers. The kernel memory allocator also collects information on the allocators. The integrity checks provide the opportunity to detect errors closer to where they actually occurred. The collected information provides additional data for support people when they try to ascertain the reason for the panic. Use of the flags incurs additional overhead and memory usage during system operations. The flags should only be used when a memory corruption problem is suspected. kmem_flags Description The Oracle Solaris kernel memory allocator has various debugging and test options. Five supported flag settings are described here. Flag AUDIT TEST Setting 0x1 0x2 Description The allocator maintains a log that contains recent history of its activity. The number of items logged depends on whether CONTENTS is also set. The log is a fixed size. When space is exhausted, earlier records are reclaimed. The allocator writes a pattern into freed memory and checks that the pattern is unchanged when the buffer is next allocated. If some portion of the buffer is changed, then the memory was probably used by a client that had previously allocated and freed the buffer. If an overwrite is identified, the system panics. 52 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Kernel Memory Allocator Flag REDZONE Setting 0x4 CONTENTS 0x8 LITE 0x100 Description The allocator provides extra memory at the end of the requested buffer and inserts a special pattern into that memory. When the buffer is freed, the pattern is checked to see if data was written past the end of the buffer. If an overwrite is identified, the kernel panics. The allocator logs up to 256 bytes of buffer contents when the buffer is freed. This flag requires that AUDIT also be set. The numeric value of these flags can be logically added together and set by the /etc/system file. Does minimal integrity checking when a buffer is allocated and freed. When enabled, the allocator checks that the redzone has not been written into, that a freed buffer is not being freed again, and that the buffer being freed is the size that was allocated. Do not combine this flag with any other flags. Data Type Default Range Dynamic? Validation When to Change Commitment Level Signed integer 0 (disabled) 0 (disabled) or 1 - 15 or 256 (0x100) Yes. Changes made during runtime only affect new kernel memory caches. After system initialization, the creation of new caches is rare. None When memory corruption is suspected Unstable kmem_stackinfo Description If the kmem_stackinfo variable is enabled in the /etc/system file at kernel thread creation time, the kernel thread stack is filled with a specific pattern instead of filled with zeros. During kernel thread execution, this kernel thread stack pattern is progressively overwritten. A simple count from the stack top until the pattern is not found gives a high watermark value, which is the maximum kernel stack space used by a kernel thread. This mechanism allows the following features: Chapter 2 · Oracle Solaris Kernel Tunable Parameters 53 General Driver Parameters Data Type Default Range Dynamic? Validation When to Change Zone Configuration Commitment Level Compute the percentage of kernel thread stack really used (a high watermark) for current kernel threads in the system When a kernel thread ends, the system logs the last kernel threads that have used the most of their kernel thread stacks before dying to a small circular memory buffer Unsigned integer 0 (disabled) 0 (disabled) or 1 (enabled) Yes None When you want to monitor kernel thread stack usage. Keep in mind that when kmem_stackinfo is enabled, the performance of creating and deleting kthreads is decreased. For more information, see the Chapter 5, "Built-In Commands," in Oracle Solaris Modular Debugger Guide. This parameter must be set in the global zone. Unstable General Driver Parameters moddebug Description When this parameter is enabled, messages about various steps in the module loading process are displayed. Data Type Signed integer Default 0 (messages off) Range Here are the most useful values: 0x80000000 Prints [un] loading... message. For every module loaded, messages such as the following appear on the console and in the /var/adm/messages file: Apr 20 17:18:04 neo genunix: [ID 943528 kern.notice] load 'sched/TS_DPTBL' id 15 loaded @ 0x7be1b2f8/0x19c8380 size 176/2096 Apr 20 17:18:04 neo genunix: [ID 131579 kern.notice] installing TS_DPTBL, module id 15. 54 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 General Driver Parameters 0x40000000 Prints detailed error messages. For every module loaded, messages such as the following appear on the console and in the /var/adm/messages file: Apr 20 18:30:00 neo unix: Errno = 2 Apr 20 18:30:00 neo unix: kobj_open: vn_open of /platform/sun4v/kernel/exec/sparcv9/intpexec fails Apr 20 18:30:00 neo unix: Errno = 2 Apr 20 18:30:00 neo unix: kobj_open: '/kernel/exec/sparcv9/intpexec' Apr 20 18:30:00 neo unix: vp = 60015777600 Apr 20 18:30:00 neo unix: kobj_close: 0x60015777600 Apr 20 18:30:00 neo unix: kobj_open: vn_open of /platform/SUNW,Sun-Fire-T200/kernel/exec/sparcv9 /intpexec fails, Apr 20 18:30:00 neo unix: Errno = 2 Apr 20 18:30:00 neo unix: kobj_open: vn_open of /platform/sun4v/kernel/exec/sparcv9/intpexec fails 0x20000000 - Prints even more detailed messages. This value doesn't print any additional information beyond what the 0x40000000 flag does during system boot. However, this value does print additional information about releasing the module when the module is unloaded. Dynamic? Validation When to Change Commitment Level These values can be added together to set the final value. Yes None When a module is either not loading as expected, or the system seems to hang while loading modules. Note that when 0x40000000 is set, system boot is slowed down considerably by the number of messages written to the console. Unstable ddi_msix_alloc_limit Description Data Type Default Range x86 only: This parameter controls the number of Extended Message Signaled Interrupts (MSI-X) that a device instance can allocate. Due to an existing system limitation, the default value is 2. You can increase the number of MSI-X interrupts that a device instance can allocate by increasing the value of this parameter. This parameter can be set either by editing the /etc/system file or by setting it with mdb before the device driver attach occurs. Signed integer 2 1 to 16 Chapter 2 · Oracle Solaris Kernel Tunable Parameters 55 Network Driver Parameters Dynamic? Validation When to Change Commitment Level Yes None To increase the number of MSI-X interrupts that a device instance can allocate. However, if you increase the number of MSI-X interrupts that a device instance can allocate, adequate interrupts might not be available to satisfy all allocation requests. If this happens, some devices might stop functioning or the system might fail to boot. Reduce the value or remove the parameter in this case. Unstable Network Driver Parameters igb Parameters mr_enable Description Data Type Default Range Dynamic? Validation When to Change Commitment Level This parameter enables or disables multiple receive and transmit queues that are used by the igb network driver. This parameter can be set by editing the /etc/driver/drv/igb.conf file before the igb driver attach occurs. Boolean 1 (disable multiple queues) 0 (enable multiple queues) or 1 (disable multiple queues) No None To enable or disable multiple receive and transmit queues that are used by the igb network driver. Unstable intr_force Description This parameter is used to force an interrupt type, such as MSI, MSI-X, or legacy, that is used by the igb network driver. This parameter can be set by editing the /etc/driver/drv/igb.conf file before the igb driver attach occurs. 56 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Network Driver Parameters Data Type Default Range Dynamic? Validation When to Change Commitment Level Unsigned integer 0 (do not force an interrupt type) 0 (do not force an interrupt type) 1 (force MSI-X interrupt type) 2 (force MSI interrupt type) 3 (force legacy interrupt type) No None To force an interrupt type that is used by the igb network driver. Unstable ixgbe Parameters tx_queue_number Description This parameter controls the number of transmit queues that are used by the ixgbe network driver. You can increase the number of transmit queues by increasing the value of this parameter. This parameter can be set by editing the /etc/driver/drv/ixgbe.conf file before the ixgbe driver attach occurs. Data Type Unsigned integer Default 8 Range 1 to 32 Dynamic? No Validation None When to Change To change the number of transmit queues that are used by the ixgbe network driver. Commitment Level Unstable rx_queue_number Description This parameter controls the number of receive queues that are used by the ixgbe network driver. You can increase the number of receive Chapter 2 · Oracle Solaris Kernel Tunable Parameters 57 Network Driver Parameters Data Type Default Range Dynamic? Validation When to Change Commitment Level queues by increasing the value of this parameter. This parameter can be set by editing the /etc/driver/drv/ixgbe.conf file before the ixgbe driver attach occurs. Unsigned integer 8 1 to 64 No None To change the number of receive queues that are used by the ixgbe network driver. Unstable intr_throttling Description Data Type Default Range Dynamic? Validation When to Change Commitment Level This parameter controls the interrupt throttling rate of the ixgbe network driver. You can increase the rate of interrupt by decreasing the value of this parameter. This parameter can be set by editing the /etc/driver/drv/ixgbe.conf file before the ixgbe driver attach occurs. Unsigned integer 200 0 to 65535 No None To change the interrupt throttling rate that is used by the ixgbe network driver. Unstable rx_limit_per_intr Description This parameter controls the maximum number of receive queue buffer descriptors per interrupt that are used by the ixgbe network driver. You can increase the number of receive queue buffer descriptors by increasing the value of this parameter. This parameter can be set by editing the /etc/driver/drv/ixgbe.conf file before the ixgbe driver attach occurs. 58 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Network Driver Parameters Data Type Default Range Dynamic? Validation When to Change Commitment Level Unsigned integer 256 16 to 4096 No None To change the number of receive queue buffer descriptors that are handled per interrupt by the ixgbe network driver. Unstable tx_ring_size Description Data Type Default Range Dynamic? Validation When to Change Commitment Level This parameter controls the transmit queue size that is used by the ixgbe network driver. You can increase the transmit queue size by increasing the value of this parameter. This parameter can be set by editing the /etc/driver/drv/ixgbe.conf file before the ixgbe driver attach occurs. Unsigned integer 1024 64 to 4096 No None To change the transmit queue size that is used by the ixgbe network driver. Unstable rx_ring_size Description Data Type Default Range This parameter controls the receive queue size that is used by the ixgbe network driver. You can increase the receive queue size by increasing the value of this parameter. This parameter can be set by editing the /etc/driver/drv/ixgbe.conf file before the ixgbe driver attach occurs. Unsigned integer 1024 64 to 4096 Chapter 2 · Oracle Solaris Kernel Tunable Parameters 59 Network Driver Parameters Dynamic? Validation When to Change Commitment Level No None To change the receive queue size that is used by the ixgbe network driver. Unstable tx_copy_threshold Description This parameter controls the transmit buffer copy threshold that is used by the ixgbe network driver. You can increase the transmit buffer copy threshold by increasing the value of this parameter. This parameter can be set by editing the /etc/driver/drv/ixgbe.conf file before the ixgbe driver attach occurs. Data Type Unsigned integer Default 512 Range 0 to 9126 Dynamic? No Validation None When to Change To change the transmit buffer copy threshold that is used by the ixgbe network driver. Commitment Level Unstable rx_copy_threshold Description This parameter controls the receive buffer copy threshold that is used by the ixgbe network driver. You can increase the receive buffer copy threshold by increasing the value of this parameter. This parameter can be set by editing the /etc/driver/drv/ixgbe.conf file before the ixgbe driver attach occurs. Data Type Unsigned integer Default 128 Range 0 to 9126 Dynamic? No Validation None When to Change To change the receive buffer copy threshold that is used by the ixgbe network driver. 60 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Commitment Level Unstable General I/O Parameters General I/O Parameters maxphys Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Defines the maximum size of physical I/O requests. If a driver encounters a request larger than this size, the driver breaks the request into maxphys sized chunks. File systems can and do impose their own limit. Signed integer 131,072 (sun4u or sun4v) or 57,344 (x86). The sd driver uses the value of 1,048,576 if the drive supports wide transfers. The ssd driver uses 1,048,576 by default. Machine-specific page size to MAXINT Bytes Yes, but many file systems load this value into a per-mount point data structure when the file system is mounted. A number of drivers load the value at the time a device is attached to a driver-specific data structure. None When doing I/O to and from raw devices in large chunks. Note that a DBMS doing OLTP operations issues large numbers of small I/Os. Changing maxphys does not result in any performance improvement in that case. Unstable rlim_fd_max Description Data Type Default Range Specifies the "hard" limit on file descriptors that a single process might have open. Overriding this limit requires superuser privilege. Signed integer 65,536 1 to MAXINT Chapter 2 · Oracle Solaris Kernel Tunable Parameters 61 General I/O Parameters Units Dynamic? Validation When to Change Commitment Level File descriptors No None When the maximum number of open files for a process is not enough. Other limitations in system facilities can mean that a larger number of file descriptors is not as useful as it might be. For example: A 32-bit program using standard I/O is limited to 256 file descriptors. A 64-bit program using standard I/O can use up to 2 billion descriptors. Specifically, standard I/O refers to the stdio(3C) functions in libc(3LIB). select is by default limited to 1024 descriptors per fd_set. For more information, see select(3C). A 32-bit application code can be recompiled with a larger fd_set size (less than or equal to 65,536). A 64-bit application uses an fd_set size of 65,536, which cannot be changed. An alternative to changing this on a system wide basis is to use the plimit(1) command. If a parent process has its limits changed by plimit, all children inherit the increased limit. This alternative is useful for daemons such as inetd. Unstable rlim_fd_cur Description Data Type Default Range Units Dynamic? Validation Defines the "soft" limit on file descriptors that a single process can have open. A process might adjust its file descriptor limit to any value up to the "hard" limit defined by rlim_fd_max by using the setrlimit() call or by issuing the limit command in whatever shell it is running. You do not require superuser privilege to adjust the limit to any value less than or equal to the hard limit. Signed integer 256 1 to MAXINT File descriptors No Compared to rlim_fd_max. If rlim_fd_cur is greater than rlim_fd_max, rlim_fd_cur is reset to rlim_fd_max. 62 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 General File System Parameters When to Change Commitment Level When the default number of open files for a process is not enough. Increasing this value means only that it might not be necessary for a program to use setrlimit to increase the maximum number of file descriptors available to it. Unstable General File System Parameters ncsize Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Defines the number of entries in the directory name look-up cache (DNLC). This parameter is used by UFS, NFS, and ZFS to cache elements of path names that have been resolved. The DNLC also caches negative look-up information, which means it caches a name not found in the cache. Signed integer (4 x (v.v_proc + maxusers) + 320) + (4 x (v.v_proc + maxusers) + 320 / 100 0 to MAXINT DNLC entries No None. Larger values cause the time it takes to unmount a file system to increase as the cache must be flushed of entries for that file system during the unmount process. You can use the kstat -n dnlcstats command to determine when entries have been removed from the DNLC because it was too small. The sum of the pick_heuristic and the pick_last parameters represents otherwise valid entries that were reclaimed because the cache was too small. Excessive values of ncsize have an immediate impact on the system because the system allocates a set of data structures for the DNLC based on the value of ncsize. By default, a system allocates 64-byte structures for ncsize. The value has a further effect on UFS and NFS, unless ufs_ninode and nfs:nrnode are explicitly set. Unstable Chapter 2 · Oracle Solaris Kernel Tunable Parameters 63 General File System Parameters dnlc_dir_enable Description Enables large directory caching Note This parameter has no effect on NFS or ZFS file systems. Data Type Default Range Dynamic? Validation When to Change Commitment Level Unsigned integer 1 (enabled) 0 (disabled) or 1 (enabled) Yes, but do not change this tunable dynamically. You can enable this parameter if it was originally disabled. Or, you can disable this parameter if it was originally enabled. However, enabling, disabling, and then enabling this parameter might lead to stale directory caches. No Directory caching has no known problems. However, if problems occur, then set dnlc_dir_enable to 0 to disable caching. Unstable dnlc_dir_min_size Description Specifies the minimum number of entries cached for one directory. Note This parameter has no effect on NFS or ZFS file systems. Data Type Default Range Units Dynamic? Validation When to Change Unsigned integer 40 0 to MAXUINT (no maximum) Entries Yes, this parameter can be changed at any time. None If performance problems occur with caching small directories, then increase dnlc_dir_min_size. Note that individual file systems might have their own range limits for caching directories. 64 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Commitment Level Unstable General File System Parameters dnlc_dir_max_size Description Specifies the maximum number of entries cached for one directory. Note This parameter has no effect on NFS or ZFS file systems. Data Type Default Range Dynamic? Validation When to Change Commitment Level Unsigned integer MAXUINT (no maximum) 0 to MAXUINT Yes, this parameter can be changed at any time. None If performance problems occur with large directories, then decrease dnlc_dir_max_size. Unstable dnlc_dircache_percent Description Data Type Default Range Units Dynamic? Validation When to Change Calculates the maximum percentage of physical memory that the DNLC directory cache can consume. Integer 100 0 to 100 Percentage No At boot time, the value range is checked and default value is enforced. When the system experiences a memory shortage and high kernel memory consumption, consider lowering this value. If performance issues are seen with the default value, consider increasing the value. Chapter 2 · Oracle Solaris Kernel Tunable Parameters 65 TMPFS Parameters Note The DNLC is used by UFS and ZFS file systems and NFS clients. Setting this tunable might be considered for better performance when there are memory shortages and high kernel memory consumption or when a memory is needed by the ARC or other kernel caches. Commitment Level Change History Unstable For information, see "dnlc_dircache_percent" on page 177. TMPFS Parameters tmpfs:tmpfs_maxkmem Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Defines the maximum amount of kernel memory that TMPFS can use for its data structures (tmpnodes and directory entries). Unsigned long One page or 4 percent of physical memory, whichever is greater. Number of bytes in one page (8192 for sun4u or sun4v systems, 4096 for all other systems) to 25 percent of the available kernel memory at the time TMPFS was first used. Bytes Yes None Increase if the following message is displayed on the console or written in the messages file: tmp_memalloc: tmpfs over memory limit The current amount of memory used by TMPFS for its data structures is held in the tmp_kmemspace field. This field can be examined with a kernel debugger. Unstable 66 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Pseudo Terminals tmpfs:tmpfs_minfree Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Defines the minimum amount of swap space that TMPFS leaves for the rest of the system. Signed long 512 0 to maximum swap space size Pages Yes None To maintain a reasonable amount of swap space on systems with large amounts of TMPFS usage, you can increase this number. The limit has been reached when the console or messages file displays the following message: fs-name: File system full, swap space limit exceeded Unstable Pseudo Terminals Pseudo terminals, ptys, are used for two purposes in Oracle Solaris software: Supporting remote logins by using the telnet, rlogin, or rsh commands Providing the interface through which the X Window system creates command interpreter windows The default number of pseudo-terminals is sufficient for a desktop workstation. So, tuning focuses on the number of ptys available for remote logins. The default number of ptys is now based on the amount of memory on the system. This default should be changed only to restrict or increase the number of users who can log in to the system. Three related variables are used in the configuration process: pt_cnt Default maximum number of ptys. pt_pctofmem Percentage of kernel memory that can be dedicated to pty support structures. A value of zero means that no remote users can log in to the system. pt_max_pty Hard maximum for number of ptys. Chapter 2 · Oracle Solaris Kernel Tunable Parameters 67 Pseudo Terminals pt_cnt has a default value of zero, which tells the system to limit logins based on the amount of memory specified in pct_pctofmem, unless pt_max_pty is set. If pt_cnt is non-zero, ptys are allocated until this limit is reached. When that threshold is crossed, the system looks at pt_max_pty. If pt_max_pty has a non-zero value, it is compared to pt_cnt. The pty allocation is allowed if pt_cnt is less than pt_max_pty. If pt_max_pty is zero, pt_cnt is compared to the number of ptys supported based on pt_pctofmem. If pt_cnt is less than this value, the pty allocation is allowed. Note that the limit based on pt_pctofmem only comes into play if both pt_cnt and ptms_ptymax have default values of zero. To put a hard limit on ptys that is different than the maximum derived from pt_pctofmem, set pt_cnt and ptms_ptymax in /etc/system to the preferred number of ptys. The setting of ptms_pctofmem is not relevant in this case. To dedicate a different percentage of system memory to pty support and let the operating system manage the explicit limits, do the following: Do not set pt_cnt or ptms_ptymax in /etc/system. Set pt_pctofmem in /etc/system to the preferred percentage. For example, set pt_pctofmem=10 for a 10 percent setting. Note that the memory is not actually allocated until it is used in support of a pty. Once memory is allocated, it remains allocated. pt_cnt Description Data Type Default Range Units Dynamic? Validation The number of available /dev/pts entries is dynamic up to a limit determined by the amount of physical memory available on the system. pt_cnt is one of three variables that determines the minimum number of logins that the system can accommodate. The default maximum number of /dev/pts devices the system can support is determined at boot time by computing the number of pty structures that can fit in a percentage of system memory (see pt_pctofmem). If pt_cnt is zero, the system allocates up to that maximum. If pt_cnt is non-zero, the system allocates to the greater of pt_cnt and the default maximum. Unsigned integer 0 0 to maxpid Logins/windows No None 68 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Pseudo Terminals When to Change Commitment Level When you want to explicitly control the number of users who can remotely log in to the system. Unstable pt_pctofmem Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Specifies the maximum percentage of physical memory that can be consumed by data structures to support /dev/pts entries. A system consumes 176 bytes per /dev/pts entry. Unsigned integer 5 0 to 100 Percentage No None When you want to either restrict or increase the number of users who can log in to the system. A value of zero means that no remote users can log in to the system. Unstable pt_max_pty Description Data Type Default Range Units Dynamic? Validation Implicit Defines the maximum number of ptys the system offers Unsigned integer 0 (Uses system-defined maximum) 0 to MAXUINT Logins/windows Yes None Should be greater than or equal to pt_cnt. Value is not checked until the number of ptys allocated exceeds the value of pt_cnt. Chapter 2 · Oracle Solaris Kernel Tunable Parameters 69 STREAMS Parameters When to Change Commitment Level When you want to place an absolute ceiling on the number of logins supported, even if the system could handle more based on its current configuration values. Unstable STREAMS Parameters nstrpush Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Specifies the number of modules that can be inserted into (pushed onto) a STREAM. Signed integer 9 9 to 16 Modules Yes None At the direction of your software vendor. No messages are displayed when a STREAM exceeds its permitted push count. A value of EINVAL is returned to the program that attempted the push. Unstable strmsgsz Description Data Type Default Range Units Specifies the maximum number of bytes that a single system call can pass to a STREAM to be placed in the data part of a message. Any write exceeding this size is broken into multiple messages. For more information, see write(2). Signed integer 65,536 0 to 262,144 Bytes 70 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 System V Message Queues Dynamic? Validation When to Change Commitment Level Yes None When putmsg calls return ERANGE. For more information, see putmsg(2). Unstable strctlsz Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Specifies the maximum number of bytes that a single system call can pass to a STREAM to be placed in the control part of a message Signed integer 1024 0 to MAXINT Bytes Yes None At the direction of your software vendor. putmsg(2) calls return ERANGE if they attempt to exceed this limit. Unstable System V Message Queues System V message queues provide a message-passing interface that enables the exchange of messages by queues created in the kernel. Interfaces are provided in the Oracle Solaris environment to enqueue and dequeue messages. Messages can have a type associated with them. Enqueueing places messages at the end of a queue. Dequeuing removes the first message of a specific type from the queue or the first message if no type is specified. For detailed information on tuning these system resources, see Chapter 6, "Resource Controls (Overview)," in Oracle Solaris Administration: Oracle Solaris Zones, Oracle Solaris 10 Zones, and Resource Management. Chapter 2 · Oracle Solaris Kernel Tunable Parameters 71 System V Semaphores System V Semaphores System V semaphores provide counting semaphores in the Oracle Solaris OS. A semaphore is a counter used to provide access to a shared data object for multiple processes. In addition to the standard set and release operations for semaphores, System V semaphores can have values that are incremented and decremented as needed (for example, to represent the number of resources available). System V semaphores also provide the ability to do operations on a group of semaphores simultaneously as well as to have the system undo the last operation by a process if the process dies. System V Shared Memory System V shared memory allows the creation of a segment by a process. Cooperating processes can attach to the memory segment (subject to access permissions on the segment) and gain access to the data contained in the segment. This capability is implemented as a loadable module. Entries in the /etc/system file must contain the shmsys: prefix. A special kind of shared memory known as intimate shared memory (ISM) is used by DBMS vendors to maximize performance. When a shared memory segment is made into an ISM segment, the memory for the segment is locked. This feature enables a faster I/O path to be followed and improves memory usage. A number of kernel resources describing the segment are then shared between all processes that attach to the segment in ISM mode. segspt_minfree Description Data Type Default Range Units Dynamic? Validation When to Change Identifies pages of system memory that cannot be allocated for ISM shared memory. Unsigned long 5 percent of available system memory when the first ISM segment is created 0 to 50 percent of physical memory Pages Yes None. Values that are too small can cause the system to hang or performance to severely degrade when memory is consumed with ISM segments. On database servers with large amounts of physical memory using ISM, the value of this parameter can be decreased. If ISM segments are not 72 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Scheduling Commitment Level used, this parameter has no effect. A maximum value of 128 MB (0x4000) is almost certainly sufficient on large memory machines. Unstable Scheduling disp_rechoose_interval Description Similar to the previous rechoose_interval parameter, this parameter specifies the amount of time before a process is deemed to have lost all affinity for the last CPU it ran on. However, this parameter is set in more granular time increments. This parameter should be used instead of the deprecated rechoose_interval parameter, but the rechoose_interval parameter is still accepted if it is set in the /etc/system file. After this interval expires, any CPU is considered a candidate for scheduling a thread. This parameter does not apply to threads in the real-time class, but applies to threads in all other scheduling classes. Data Type Use mdb if you want to change the value of this parameter by using the following steps: 1. Convert nanoseconds to unscaled time. For example, to convert a 5000000 nanosecond based value to unscaled time, use the following syntax: # mdb -kw . . . > 0t5000000::time -u 0xb6a444 2. Set disp_rechoose_interval to the unscaled time value. For example, provide the value that was returned in preceding step. > disp_rechoose_interval /Z 0xb6a444 disp_rechoose_interval: 0x447d998 = 0xb6a444 3. Verify that disp_rechoose_interval has been set to the right value. For example: > disp_rechoose_interval::print 0xb6a444 Signed integer Chapter 2 · Oracle Solaris Kernel Tunable Parameters 73 Timers Default Range Dynamic? Validation When to Change Commitment Level Change History 3 0 to MAXINT Yes None When caches are large, or when the system is running a critical process or a set of processes that seem to suffer from excessive cache misses not caused by data access patterns. Consider using the processor set capabilities or processor binding before changing this parameter. For more information, see psrset(1M) or pbind(1M). Unstable For information, see "disp_rechoose_interval" on page 176. Timers hires_tick Description Data Type Default Range Dynamic? Validation When to Change Commitment Level When set, this parameter causes the Oracle Solaris OS to use a system clock rate of 1000 instead of the default value of 100. Signed integer 0 0 (disabled) or 1 (enabled) No. Causes new system timing variable to be set at boot time. Not referenced after boot. None When you want timeouts with a resolution of less than 10 milliseconds, and greater than or equal to 1 millisecond. Unstable timer_max Description Specifies the number of POSIX timers available. 74 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 SPARC System Specific Parameters Data Type Default Range Dynamic? Validation When to Change Commitment Level Signed integer 1000 0 to MAXINT No. Increasing the value can cause a system crash. None When the default number of timers offered by the system is inadequate. Applications receive an EAGAIN error when executing timer_create system calls. Unstable SPARC System Specific Parameters The following parameters apply to sun4v and SPARC M-Series sun4u platforms. tsb_alloc_hiwater_factor Description Initializes tsb_alloc_hiwater to impose an upper limit on the amount of physical memory that can be allocated for translation storage buffers (TSBs) as follows: tsb_alloc_hiwater = physical memory (bytes) / tsb_alloc_hiwater_factor When the memory that is allocated to TSBs is equal to the value of tsb_alloc_hiwater, the TSB memory allocation algorithm attempts to reclaim TSB memory as pages are unmapped. Data Type Default Range Exercise caution when using this factor to increase the value of tsb_alloc_hiwater. To prevent system hangs, the resulting high water value must be considerably lower than the value of swapfs_minfree and segspt_minfree. Integer 32 1 to MAXINIT Chapter 2 · Oracle Solaris Kernel Tunable Parameters 75 SPARC System Specific Parameters Dynamic? Validation When to Change Commitment Level Note that a factor of 1 makes all physical memory available for allocation to TSBs, which could cause the system to hang. A factor that is too high will not leave memory available for allocation to TSBs, decreasing system performance. Yes None Change the value of this parameter if the system has many processes that attach to very large shared memory segments. Under most circumstances, tuning of this variable is not necessary. Unstable default_tsb_size Description Data Type Default Range Selects size of the initial translation storage buffers (TSBs) allocated to all processes. Integer Default is 0 (8 KB), which corresponds to 512 entries Possible values are: Dynamic? Validation Value 0 1 3 4 5 6 7 Yes None Description 8 KB 16 KB 32 KB 128 KB 256 KB 512 KB 1 Mbyte 76 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 SPARC System Specific Parameters When to Change Commitment Level Generally, you do not need to change this value. However, doing so might provide some advantages if the majority of processes on the system have a larger than average working set, or if resident set size (RSS) sizing is disabled. Unstable enable_tsb_rss_sizing Description Data Type Default Range Enables a resident set size (RSS) based TSB sizing heuristic. Boolean 1 (TSBs can be resized) 0 (TSBs remain at tsb_default_size) or 1 (TSBs can be resized) Dynamic? Validation When to Change Commitment Level If set to 0, then tsb_rss_factor is ignored. Yes Yes Can be set to 0 to prevent growth of the TSBs. Under most circumstances, this parameter should be left at the default setting. Unstable tsb_rss_factor Description Data Type Default Range Dynamic? Validation Controls the RSS to TSB span ratio of the RSS sizing heuristic. This factor divided by 512 yields the percentage of the TSB span which must be resident in memory before the TSB is considered as a candidate for resizing. Integer 384, resulting in a value of 75%. Thus, when the TSB is 3/4 full, its size will be increased. Note that some virtual addresses typically map to the same slot in the TSB. Therefore, conflicts can occur before the TSB is at 100% full. 0 to 512 Yes None Chapter 2 · Oracle Solaris Kernel Tunable Parameters 77 Locality Group Parameters When to Change Commitment Level If the system is experiencing an excessive number of traps due to TSB misses, for example, due to virtual address conflicts in the TSB, you might consider decreasing this value toward 0. For example, changing tsb_rss_factor to 256 (effectively, 50%) instead of 384 (effectively, 75%) might help eliminate virtual address conflicts in the TSB in some cases, but will use more kernel memory, particularly on a heavily loaded system. TSB activity can be monitored with the trapstat -T command. Unstable Locality Group Parameters This section provides generic memory tunables, which apply to any SPARC or x86 system that uses a Non-Uniform Memory Architecture (NUMA). lpg_alloc_prefer Description Controls a heuristic for allocation of large memory pages when the requested page size is not immediately available in the local memory group, but could be satisfied from a remote memory group. Data Type Default Range By default, the Oracle Solaris OS allocates a remote large page if local free memory is fragmented, but remote free memory is not. Setting this parameter to 1 indicates that additional effort should be spent attempting to allocate larger memory pages locally, potentially moving smaller pages around to coalesce larger pages in the local memory group. Boolean 0 (Prefer remote allocation if local free memory is fragmented and remote free memory is not) 0 (Prefer remote allocation if local free memory is fragmented and remote free memory is not) Dynamic? Validation 1 (Prefer local allocation whenever possible, even if local free memory is fragmented and remote free memory is not) No None 78 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Locality Group Parameters When to Change Commitment Level This parameter might be set to 1 if long-running programs on the system tend to allocate memory that is accessed by a single program, or if memory that is accessed by a group of programs is known to be running in the same locality group (lgroup). In these circumstances, the extra cost of page coalesce operations can be amortized over the long run of the programs. This parameter might be left at the default value (0) if multiple programs tend to share memory across different locality groups, or if pages tend to be used for short periods of time. In these circumstances, quick allocation of the requested size tends to be more important than allocation in a particular location. TLB miss activity might be observed by using the trapstat -T command. Uncommitted lgrp_mem_pset_aware Description If a process is running within a user processor set, this variable determines whether randomly placed memory for the process is selected from among all the lgroups in the system or only from those lgroups that are spanned by the processors in the processor set. Data Type Default Range Dynamic? Validation When to Change For more information about creating processor sets, see psrset(1M). Boolean 0, the Oracle Solaris OS selects memory from all the lgroups in the system 0, the Oracle Solaris OS selects memory from all the lgroups in the system (default) 1, try selecting memory only from those lgroups that are spanned by the processors in the processor set. If the first attempt fails, memory can be allocated in any lgroup. No None Setting this value to a value of one (1) might lead to more reproducible performance when processor sets are used to isolate applications from one another. Chapter 2 · Oracle Solaris Kernel Tunable Parameters 79 Locality Group Parameters Commitment Level Uncommitted 80 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 3C H A P T E R 3 Oracle Solaris ZFS Tunable Parameters This chapter describes ZFS tunable parameters that might need consideration, depending on your system and application requirements. In addition, tunable recommendations for using ZFS with database products are provided. "Tuning ZFS Considerations" on page 82 "ZFS ARC Parameters" on page 82 "ZFS File-Level Prefetch" on page 83 "ZFS Device I/O Queue Depth" on page 84 "ZFS and Cache Flushing" on page 85 "ZFS Metadata Compression" on page 87 "Tuning ZFS for Database Products" on page 87 Where to Find Tunable Parameter Information Tunable Parameter Oracle Solaris kernel tunable parameters NFS tunable parameters Internet Protocol Suite tunable parameters For Information Chapter 2, "Oracle Solaris Kernel Tunable Parameters" Chapter 4, "NFS Tunable Parameters" Chapter 5, "Internet Protocol Suite Tunable Parameters" 81 Tuning ZFS Considerations Tuning ZFS Considerations Review the following considerations before tuning ZFS: Default values are generally the best value. If a better value exists, it should be the default. While alternative values might help a given workload, it could quite possibly degrade some other aspects of performance. Occasionally, catastrophically so. The ZFS best practices should be followed before ZFS tuning is applied. These practices are a set of recommendations that have been shown to work in different environments and are expected to keep working in the foreseeable future. So, before turning to tuning, make sure you've read and understood the best practices. For more information, see Chapter 12, "Recommended Oracle Solaris ZFS Practices," in Oracle Solaris 11.1 Administration: ZFS File Systems. Unless noted otherwise, the tunable parameters are global and impact ZFS behavior across the system. ZFS ARC Parameters This section describes parameters related to ZFS ARC behavior. zfs_arc_min Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Change History Determines the minimum size of the ZFS Adaptive Replacement Cache (ARC). See also "zfs_arc_max" on page 83. Unsigned Integer (64-bit) 64 MB 64 MB to zfs_arc_max Bytes No Yes, the range is validated. When a system's workload demand for memory fluctuates, the ZFS ARC caches data at a period of weak demand and then shrinks at a period of strong demand. However, ZFS does not shrink below the value of zfs_arc_min. Generally, you do not need to change the default value. Unstable For information, see "zfs_arc_min" on page 175. 82 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 ZFS File-Level Prefetch zfs_arc_max Description Data Type Default Determines the maximum size of the ZFS Adaptive Replacement Cache (ARC). See also "zfs_arc_min" on page 82. Unsigned Integer (64-bit) 75% of memory on systems with less than 4 GB of memory Range Units Dynamic? Validation When to Change Commitment Level Change History physmem minus 1 GB on systems with greater than 4 GB of memory 64 MB to physmem Bytes No Yes, the range is validated. If a future memory requirement is significantly large and well defined, you might consider reducing the value of this parameter to cap the ARC so that it does not compete with the memory requirement. For example, if you know that a future workload requires 20% of memory, it makes sense to cap the ARC such that it does not consume more than the remaining 80% of memory. Unstable For information, see "zfs_arc_max " on page 175. ZFS File-Level Prefetch zfs_prefetch_disable Description This parameter determines a file-level prefetching mechanism called zfetch. This mechanism looks at the patterns of reads to files and anticipates on some reads, thereby reducing application wait times. The current behavior suffers from two drawbacks: Sequential read patterns made of small reads very often hit in the cache. In this case, the current behavior consumes a significant amount of CPU time trying to find the next I/O to issue, whereas performance is governed more by the CPU availability. The zfetch code has been observed to limit scalability of some loads. CPU profiling can be done by using the lockstat -I command or er_kernel as described here: Chapter 3 · Oracle Solaris ZFS Tunable Parameters 83 ZFS Device I/O Queue Depth Data Type Default Range Dynamic? Validation When to Change Commitment Level http://developers.sun.com/ prodtech/cc/articles/perftools.html You can disable prefetching by setting zfs_prefetch_disable in the /etc/system file. Device-level prefetching is disabled when zfs_vdev_cache_size is disabled. This means that tuning vdev cache shift is no longer necessary if zfs_vdev_cache_size is disabled. Boolean 0 (enabled) 0 (enabled) or 1 (disabled) Yes No If the results of er_kernel show significant time in zfetch_* functions, or if lock profiling with lockstat shows contention around zfetch locks, then disabling file level prefetching should be considered. Unstable ZFS Device I/O Queue Depth zfs_vdev_max_pending Description Data Type Default Range Dynamic? Validation When to Change This parameter controls the maximum number of concurrent I/Os pending to each device. Integer 10 0 to MAXINT Yes No In a storage array where LUNs are made of a large number of disk drives, the ZFS queue can become a limiting factor on read IOPS. This behavior is one of the underlying reasoning for the best practice of presenting as many LUNS as there are backing spindles to the ZFS storage pool. That is, if you create LUNS from a 10 disk-wide array level 84 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 ZFS and Cache Flushing Commitment Level raid-group, then using 5 to 10 LUNs to build a storage pool allows ZFS to manage enough of an I/O queue without the need to set this specific tunable. However, when no separate intent log is in use and the pool is made of JBOD disks, using a small zfs_vdev_max_pending value, such as 10, can improve the synchronous write latency as those are competing for the disk resource. Using separate intent log devices can alleviate the need to tune this parameter for loads that are synchronously write intensive since those synchronous writes are not competing with a deep queue of non-synchronous writes. Tuning this parameter is not expected to be effective for NVRAM-based storage arrays in the case where volumes are made of small number of spindles. However, when ZFS is presented with a volume made of a large (greater than 10) number of spindles, then this parameter can limit the read throughput obtained on the volume. The reason is that with a maximum of 10 or 35 queued I/Os per LUN, this can translate into less than 1 I/O per storage spindle, which is not enough for individual disks to deliver their IOPS. This issue would appear in iostat actv queue output approaching the value of zfs_vdev_max_pending. Device drivers may also limit the number of outstanding I/Os per LUN. If you are using LUNs on storage arrays that can handle large numbers of concurrent IOPS, then the device driver constraints can limit concurrency. Consult the configuration for the drivers your system uses. For example, the limit for the QLogic ISP2200, ISP2300, and SP212 family FCl HBA (qlc) driver is described as the execution-throttle parameter in /kernel/drv/qlc.conf. Unstable ZFS and Cache Flushing ZFS is designed to work with storage devices that manage a disk-level cache. ZFS commonly asks the storage device to ensure that data is safely placed on stable storage by requesting a cache flush. For JBOD storage, this works as designed and without problems. For many NVRAM-based storage arrays, a performance problem might occur if the array takes the cache flush request and actually does something with it, rather than ignoring it. Some storage arrays flush their large caches despite the fact that the NVRAM protection makes those caches as good as stable storage. Chapter 3 · Oracle Solaris ZFS Tunable Parameters 85 ZFS and Cache Flushing ZFS issues infrequent flushes (every 5 second or so) after the uberblock updates. The flushing infrequency is fairly inconsequential so no tuning is warranted here. ZFS also issues a flush every time an application requests a synchronous write (O_DSYNC, fsync, NFS commit, and so on). The completion of this type of flush is waited upon by the application and impacts performance. Greatly so, in fact. From a performance standpoint, this neutralizes the benefits of having an NVRAM-based storage. zfs_nocacheflush Description This parameter controls ZFS write cache flushes for the entire system. Oracle's Sun hardware should not require tuning this parameter. If you need to tune cache flushing, considering tuning it per hardware device. See the general instructions below. Contact your storage vendor for instructions on how to tell the storage devices to ignore the cache flushes sent by ZFS. Data Type Boolean Default 0 Range 0 (enabled) or 1 (disabled) Dynamic? Yes Validation No When to Change Cache flush tuning was recently shown to help some SSD performance when used as log devices. This tuning syntax can be included in sd.conf but there must be only a single sd-config-list entry per vendor/product. For example: sd-config-list = "ATA TX43E10100GB0LSI","throttle-max:32, disksort:false, cache-nonvolatile:true"; As a last resort, when all LUNs exposed to ZFS come from NVRAM-protected storage array and procedures ensure that no unprotected LUNs will be added in the future, ZFS can be tuned to not issue the flush requests by setting zfs_nocacheflush. If some LUNs exposed to ZFS are not protected by NVRAM, then this tuning can lead to data loss, application level corruption, or even pool corruption. In some NVRAM-protected storage arrays, the cache flush command is a no-op, so tuning in this situation makes no performance difference. Commitment Level Unstable 86 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 ZFS Metadata Compression Tuning ZFS for Database Products zfs_mdcomp_disable Description Data Type Default Range Dynamic? Validation When to Change This parameter controls compression of ZFS metadata (indirect blocks only). ZFS data block compression is controlled by the ZFS compression property that can be set per file system. Boolean 0 0 (enabled) or 1 (disabled) Yes No In general, metadata compression should be enabled. For metadata intensive loads, this default is expected to gain some amount of space (a few percentages) at the expense of a little extra CPU computation. However, a bigger motivation exists to have metadata compression on. For directories that grow to millions of objects then shrink to just a few, metadata compression saves large amounts of space (greater than 10 times). Commitment Level I/O on flash storage devices is aligned along 4 KB boundaries. If metadata compression is enabled, the I/O on flash storage devices might become unaligned. You might consider disabling metadata compression to resolve the I/O alignment problem if you are using flash devices for primary storage. Using separate log devices on flash devices are not effected by the alignment problem. Unstable Tuning ZFS for Database Products Review the following considerations when using ZFS with a database product. If the database uses a fixed disk block or record size for I/O, set the ZFS recordsize property to match it. You can do this on a per-file system basis, even though multiple file systems might share a single pool. With ZFS's copy-on-write design, tuning down the recordsize is a way to improve OLTP performance at the expense of batch reporting queries. Chapter 3 · Oracle Solaris ZFS Tunable Parameters 87 Tuning ZFS for Database Products ZFS checksums every block stored on disk. This alleviates the need for the database layer to checksum data an additional time. If checksums are computed by ZFS instead of at the database layer, any discrepancy can be caught and fixed before the data is returned to the application. UFS direct I/O is used to overcome some of the design deficiencies of UFS and to eliminate double buffering of data. In ZFS, the UFS design deficiencies do not exist and ZFS uses the primarycache and secondarycache properties to manage buffering data in the ARC. Note that using the secondarycache (L2ARC) property to improve random reads also requires the primarycache property to be enabled. Keep pool space under 80% utilization to maintain pool performance. Tuning ZFS for an Oracle Database ZFS is recommended for any Oracle database version in single instance mode. ZFS can be used with an Oracle RAC database when it is available as a NFS-shared file system. Review the following recommendations below for tuning ZFS for an Oracle database: Verify that you are running the latest Solaris release Start with the latest Solaris 10 or Solaris 11 release, with the Solaris 10 9/10 release as a minimum starting point. Create LUNs for your ZFS storage pools, if needed Use your storage array tools to create LUNs that will be presented to the ZFS storage pool. Or, consider using whole disks for your mirrored ZFS storage pools. For more information, see Chapter 3, "Managing Oracle Solaris ZFS Storage Pools," in Oracle Solaris 11.1 Administration: ZFS File Systems. Create a storage pool for data files for tables, index, undo and temp data Consider creating a mirrored storage pool to provide a higher level of data redundancy. For example: # zpool status dbpool pool: dbpool state: ONLINE scan: none requested config: NAME dbpool mirror-0 c0t5000C500335F95E3d0 c0t5000C500335F907Fd0 mirror-1 c0t5000C500335BD117d0 c0t5000C500335DC60Fd0 STATE ONLINE ONLINE ONLINE ONLINE ONLINE ONLINE ONLINE READ WRITE CKSUM 000 000 000 000 000 000 000 88 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Tuning ZFS for Database Products errors: No known data errors For databases with high redo log activity, such as a typical OLTP database with many commits, use a separate LUN for a separate log device. Create a storage pool for the archivelog If available, a system's internal disk can handle this type of load. The archivelog file system can also be a file system in the dbpool. # zpool create archivepool c0t5000C500335E106Bd0 Create the ZFS file systems and set the specific file system properties by using the following guidelines. Create separate file systems for redo, archive, undo, and temp database components using the default record size of 128 KB. The general rule is to set the file system recordsize = db_block_size for the file systems that contains Oracle data files. For table data and index components, create a file system with an 8 KB record size. Also consider providing metadata caching hints for your database file systems by using the primarycache property. For more information about ZFS file system properties, see "Introducing ZFS Properties" in Oracle Solaris 11.1 Administration: ZFS File Systems. Create file systems for the table data files and index data files with an 8 KB recordsize. Use the default value for primarycache. # zfs create -o recordsize=8k -o mountpoint=/my_db_path/index dbpool/index # zfs set logbias=throughput dbpool/index # zfs get primarycache,recordsize,logbias dbpool/index NAME PROPERTY VALUE SOURCE dbpool/index primarycache all default dbpool/index recordsize 8K local dbpool/index logbias throughput local Create file systems for temporary and undo table spaces, using the default recordsize and primarycache values. # zfs create -o mountpoint=/my_db_path/temp dbpool/temp # zfs set logbias=throughput dbpool/temp # zfs create -o mountpoint=/my_db_path/undo dbpool/undo # zfs set logbias=throughput dbpool/undo Create a storage pool for redo logs with a separate log device. For databases with high redo log activity, such as a typical OLTP database with many commits, use a separate log device LUN. Partition the disk into two slices, a small slice, s0, in the 64 to 150 MB range, for the separate log device. The s1 slice contains the remaining disk space for the redo log. # zpool create redopool c0t50015179594B6F11d0s1 log c0t50015179594B6F11d0s0 # zpool status redopool pool: redopool state: ONLINE scan: none requested config: Chapter 3 · Oracle Solaris ZFS Tunable Parameters 89 Tuning ZFS for Database Products NAME redopool c0t50015179594B6F11d0s1 logs c0t50015179594B6F11d0s0 STATE ONLINE ONLINE ONLINE READ WRITE CKSUM 000 000 000 errors: No known data errors Create a file system for redo logs in the redo pool. Use default file system values for recordsize and primarycache. # zfs create -o mountpoint=/my_db_path/redo redopool/redo # zfs set logbias=latency redopool/redo Create a file system for archivelog files in the archive pool, enabling compression, use the default value for recordsize and set primarycache to metadata. # zfs create -o compression=on -o primarycache=metadata -o mountpoint= /my_db_admin_path/archive archivepool/archive # zfs get primarycache,recordsize,compressratio,compression,available, used,quota archivepool/archive NAME PROPERTY VALUE SOURCE archivepool/archive primarycache metadata local archivepool/archive recordsize 128K default archivepool/archive compressratio 1.32x - archivepool/archive compression on local archivepool/archive available 40.0G - archivepool/archive used 10.0G - archivepool/archive quota 50G local Consider tuning storage array I/O queues (for systems with HDS or EMC storage arrays) ZFS aggregates read and write I/O and manages the priority of I/O before sending it to the driver level, which handles the device. The zfs_vdev_max_pending parameter defines the maximum number of I/Os that ZFS sends to any storage pool device. In a legacy storage environment, the ssd_max_throttle and sd_max_throttle parameters define the maximum number of concurrent I/Os that the driver can send to the storage. By setting the zfs_vdev_max_pending default value equal to the value of the [s]sd_max_throttle parameter, we prevent ZFS from queuing I/O to yet another unnecessary SD layer. If you have ssd:ssd_max_throttle or sd:sd_max_throttle in the /etc/system file in your existing environment, then set zfs:zfs_vdev_max_pending at the same value. For example, if the storage array administrator asked for the following setting: set ssd:ssd_max_throttle=20 Then, also set this parameter as follows: set ssd:ssd_max_throttle=20 set zfs:zfs_vdev_max_pending=20 Setting this parameter allows ZFS to control each LUN queue. This means that the total number of pending I/Os in the storage can grow as follows: 90 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Tuning ZFS for Database Products number of LUNs * ZFS_VDEV_MAX_PENDING Allocate sufficient memory and swap resources You can reduce ZFS memory consumption by tuning the zfs_arc_max parameter to a low value, but we still recommend provisioning enough memory to cache metadata for the actively used portion of the database, which is estimated at 1.5% with an 8 KB ZFS record size and proportionately less or more with larger or smaller records. The file system that hold index files is the one that has the largest benefit from file system caching because it is the last one to invalidate in case of lack of memory. The zfs_arc_max parameter is in bytes and accepts decimal or hexadecimal values. The following example sets this parameter to 2 GB: set zfs:zfs_arc_max=2147483648 or set zfs:zfs_arc_max=0x80000000 To prevent applications from failing due to lack of memory, you must configure some amount of swap space. The amount of swap equivalent to all of system memory is always enough for this purpose. This swap space is not expected to be used, but is needed as a reservation area. For information about increasing swap space, see "Managing Your ZFS Swap and Dump Devices" in Oracle Solaris 11.1 Administration: ZFS File Systems. Additional Oracle database configuration recommendations Configuring Your Oracle Database on ZFS File Systems in the following white paper: http://www.oracle.com/ technetwork/server-storage/solaris/config-solaris-zfs-wp-167894.pdf Dynamic SGA Tuning of Oracle Database on Oracle Solaris with DISM white paper: http://www.oracle.com/ technetwork/articles/systems-hardware-architecture/ using-dynamic-intimate-memory-sparc-168402.pdf Oracle 11g Installation Guides Oracle Database Quick Installation Guide 11g Release 2 (11.2) for Oracle Solaris on SPARC (64-Bit) http://docs.oracle.com/cd/E11882_01/install.112/e24349/toc.htm Oracle Database Quick Installation Guide 11g Release 2 (11.2) for Oracle Solaris on x86-64 (64-Bit) http://docs.oracle.com/cd/E11882_01/install.112/e24351/toc.htm Using ZFS with MySQL Considerations Review the following considerations when using ZFS with MySQL. ZFS recordsize Chapter 3 · Oracle Solaris ZFS Tunable Parameters 91 Tuning ZFS for Database Products Match the ZFS recordsize property to the storage engine block size for better OLTP performance. InnoDB With a known application memory footprint, such as for a database application, you might cap the ARC size so that the application will not need to reclaim its necessary memory from the ZFS cache. Create a separate pool for the logs. Set a different path for data and log in the my.cnf file. Set the ZFS recordsize property to 16K for the InnoDB data files, and use the default recordsize value for InnoDB logs, prior to creating data files. 92 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 4C H A P T E R 4 NFS Tunable Parameters This section describes the NFS tunable parameters. "Tuning the NFS Environment" on page 93 "NFS Module Parameters" on page 94 "rpcmod Module Parameters" on page 121 Where to Find Tunable Parameter Information Tunable Parameter Oracle Solaris kernel tunable parameters Oracle Solaris ZFS tunable parameters Internet Protocol Suite tunable parameters For Information Chapter 2, "Oracle Solaris Kernel Tunable Parameters" Chapter 3, "Oracle Solaris ZFS Tunable Parameters" Chapter 5, "Internet Protocol Suite Tunable Parameters" Tuning the NFS Environment You can define NFS parameters in the /etc/system file, which is read during the boot process. Each parameter includes the name of its associated kernel module. For more information, see "Tuning an Oracle Solaris System" on page 19. Caution The names of the parameters, the modules that they reside in, and the default values can change between releases. Check the documentation for the version of the active SunOS release before making changes or applying values from previous releases. 93 NFS Module Parameters NFS Module Parameters This section describes parameters related to the NFS kernel module. nfs:nfs3_pathconf_disable_cache Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls the caching of pathconf information for NFS Version 3 mounted file systems. Integer (32-bit) 0 (caching enabled) 0 (caching enabled) or 1 (caching disabled) Boolean values Yes None The pathconf information is cached on a per file basis. However, if the server can change the information for a specific file dynamically, use this parameter to disable caching. There is no mechanism for the client to validate its cache entry. Unstable nfs:nfs4_pathconf_disable_cache Description Data Type Default Range Units Dynamic? Validation When to Change Controls the caching of pathconf information for NFS Version 4 mounted file systems. Integer (32-bit) 0 (caching enabled) 0 (caching enabled) or 1 (caching disabled) Boolean values Yes None The pathconf information is cached on a per file basis. However, if the server can change the information for a specific file dynamically, use this parameter to disable caching. There is no mechanism for the client to validate its cache entry. 94 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Commitment Level Unstable NFS Module Parameters nfs:nfs_allow_preepoch_time Description Controls whether files with incorrect or negative time stamps should be made visible on the client. Historically, neither the NFS client nor the NFS server would do any range checking on the file times being returned. The over-the-wire timestamp values are unsigned and 32-bits long. So, all values have been legal. The timestamp values on the 64-bit Solaris kernel are signed and 64-bits long. It is impossible to determine whether a time field represents a full 32-bit time or a negative time, that is, a time prior to January 1, 1970. Data Type Default Range Units Dynamic? Validation When to Change Commitment Level It is impossible to determine whether to sign extend a time value when converting from 32 bits to 64 bits. The time value should be sign extended if the time value is truly a negative number. However, the time value should not be sign extended if it does truly represent a full 32-bit time value. This problem is resolved by simply disallowing full 32-bit time values. Integer (32-bit) 0 (32-bit time stamps disabled) 0 (32-bit time stamps disabled) or 1 (32-bit time stamps enabled) Boolean values Yes None Even during normal operation, it is possible for the timestamp values on some files to be set very far in the future or very far in the past. If access to these files is preferred using NFS mounted file systems, set this parameter to 1 to allow the timestamp values to be passed through unchecked. Unstable Chapter 4 · NFS Tunable Parameters 95 NFS Module Parameters nfs:nfs_cots_timeo Description Data Type Default Range Units Dynamic? Validation When to Change Controls the default RPC timeout for NFS version 2 mounted file systems using connection-oriented transports such as TCP for the transport protocol. Signed integer (32-bit) 600 (60 seconds) 0 to 231 - 1 10th of seconds Yes, but the RPC timeout for a file system is set when the file system is mounted. To affect a particular file system, unmount and mount the file system after changing this parameter. None TCP does a good job ensuring requests and responses are delivered appropriately. However, if the round-trip times are very large in a particularly slow network, the NFS version 2 client might time out prematurely. Commitment Level Increase this parameter to prevent the client from timing out incorrectly. The range of values is very large, so increasing this value too much might result in situations where a retransmission is not detected for long periods of time. Unstable nfs:nfs3_cots_timeo Description Data Type Default Range Units Dynamic? Controls the default RPC timeout for NFS version 3 mounted file systems using connection-oriented transports such as TCP for the transport protocol. Signed integer (32-bit) 600 (60 seconds) 0 to 231 - 1 10th of seconds Yes, but the RPC timeout for a file system is set when the file system is mounted. To affect a particular file system, unmount and mount the file system after changing this parameter. 96 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters Validation When to Change Commitment Level None TCP does a good job ensuring requests and responses are delivered appropriately. However, if the round-trip times are very large in a particularly slow network, the NFS version 3 client might time out prematurely. Increase this parameter to prevent the client from timing out incorrectly. The range of values is very large, so increasing this value too much might result in situations where a retransmission is not detected for long periods of time. Unstable nfs:nfs4_cots_timeo Description Controls the default RPC timeout for NFS version 4 mounted file systems using connection-oriented transports such as TCP for the transport protocol. Data Type Default Range Units Dynamic? Validation When to Change The NFS Version 4 protocol specification disallows retransmission over the same TCP connection. Thus, this parameter primarily controls how quickly the client responds to certain events, such as detecting a forced unmount operation or detecting how quickly the server fails over to a new server. Signed integer (32-bit) 600 (60 seconds) 0 to 231 - 1 10th of seconds Yes, but this parameter is set when the file system is mounted. To affect a particular file system, unmount and mount the file system after changing this parameter. None TCP does a good job ensuring requests and responses are delivered appropriately. However, if the round-trip times are very large in a particularly slow network, the NFS version 4 client might time out prematurely. Chapter 4 · NFS Tunable Parameters 97 NFS Module Parameters Commitment Level Increase this parameter to prevent the client from timing out incorrectly. The range of values is very large, so increasing this value too much might result in situations where a retransmission is not detected for long periods of time. Unstable nfs:nfs_do_symlink_cache Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls whether the contents of symbolic link files are cached for NFS version 2 mounted file systems. Integer (32bit) 1 (caching enabled) 0 (caching disabled) or 1 (caching enabled) Boolean values Yes None If a server changes the contents of a symbolic link file without updating the modification timestamp on the file or if the granularity of the timestamp is too large, then changes to the contents of the symbolic link file might not be visible on the client for extended periods. In this case, use this parameter to disable the caching of symbolic link contents. Doing so makes the changes immediately visible to applications running on the client. Unstable nfs:nfs3_do_symlink_cache Description Data Type Default Range Units Dynamic? Controls whether the contents of symbolic link files are cached for NFS version 3 mounted file systems. Integer (32-bit) 1 (caching enabled) 0 (caching disabled) or 1 (caching enabled) Boolean values Yes 98 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters Validation When to Change Commitment Level None If a server changes the contents of a symbolic link file without updating the modification timestamp on the file or if the granularity of the timestamp is too large, then changes to the contents of the symbolic link file might not be visible on the client for extended periods. In this case, use this parameter to disable the caching of symbolic link contents. Doing so makes the changes immediately visible to applications running on the client. Unstable nfs:nfs4_do_symlink_cache Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls whether the contents of symbolic link files are cached for NFS version 4 mounted file systems. Integer (32-bit) 1 (caching enabled) 0 (caching disabled) or 1 (caching enabled) Boolean values Yes None If a server changes the contents of a symbolic link file without updating the modification timestamp on the file or if the granularity of the timestamp is too large, then changes to the contents of the symbolic link file might not be visible on the client for extended periods. In this case, use this parameter to disable the caching of symbolic link contents. Doing so makes the changes immediately visible to applications running on the client. Unstable nfs:nfs_dynamic Description Controls whether a feature known as dynamic retransmission is enabled for NFS version 2 mounted file systems using connectionless transports such as UDP. This feature attempts to reduce retransmissions by monitoring server response times and then adjusting RPC timeouts and read- and write- transfer sizes. Chapter 4 · NFS Tunable Parameters 99 NFS Module Parameters Data Type Default Range Dynamic? Validation When to Change Commitment Level Integer (32-bit) 1 (enabled) 0 (disabled) or 1 (enabled) Yes, but this parameter is set per file system at mount time. To affect a particular file system, unmount and mount the file system after changing this parameter. None Do not change this parameter. Unstable nfs:nfs3_dynamic Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls whether a feature known as dynamic retransmission is enabled for NFS version 3 mounted file systems using connectionless transports such as UDP. This feature attempts to reduce retransmissions by monitoring server response times and then adjusting RPC timeouts and read- and write- transfer sizes. Integer (32-bit) 0 (disabled) 0 (disabled) or 1 (enabled) Boolean values Yes, but this parameter is set per file system at mount time. To affect a particular file system, unmount and mount the file system after changing this parameter. None Do not change this parameter. Unstable nfs:nfs_lookup_neg_cache Description Controls whether a negative name cache is used for NFS version 2 mounted file systems. This negative name cache records file names that 100 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters Data Type Default Range Units Dynamic? Validation When to Change Commitment Level were looked up, but not found. The cache is used to avoid over-the-network look-up requests made for file names that are already known to not exist. Integer (32-bit) 1 (enabled) 0 (disabled) or 1 (enabled) Boolean values Yes None For the cache to perform correctly, negative entries must be strictly verified before they are used. This consistency mechanism is relaxed slightly for read-only mounted file systems. It is assumed that the file system on the server is not changing or is changing very slowly, and that it is okay for such changes to propagate slowly to the client. The consistency mechanism becomes the normal attribute cache mechanism in this case. If file systems are mounted read-only on the client, but are expected to change on the server and these changes need to be seen immediately by the client, use this parameter to disable the negative cache. If you disable the nfs:nfs_disable_rddir_cache parameter, you should probably also disable this parameter. For more information, see "nfs:nfs_disable_rddir_cache" on page 111. Unstable nfs:nfs3_lookup_neg_cache Description Data Type Default Range Units Controls whether a negative name cache is used for NFS version 3 read-only mounted file systems. This negative name cache records file names that were looked up, but were not found. The cache is used to avoid over-the-network look-up requests made for file names that are already known to not exist. Integer (32-bit) 1 (enabled) 0 (disabled) or 1 (enabled) Boolean values Chapter 4 · NFS Tunable Parameters 101 NFS Module Parameters Dynamic? Validation When to Change Commitment Level Yes None For the cache to perform correctly, negative entries must be strictly verified before they are used. This consistency mechanism is relaxed slightly for read-only mounted file systems. It is assumed that the file system on the server is not changing or is changing very slowly, and that it is okay for such changes to propagate slowly to the client. The consistency mechanism becomes the normal attribute cache mechanism in this case. Negative cache entries are used only for read-only mounted file system. By assuming that the file system on the server is not changing or is changing very slowly, it is okay for such changes to propagate slowly to the client. The consistency mechanism becomes the normal attribute cache mechanism in this case. If file systems are mounted read-only on the client, but are expected to change on the server and these changes need to be seen immediately by the client, use this parameter to disable the negative cache. If you disable the nfs:nfs_disable_rddir_cache parameter, you should probably also disable this parameter. For more information, see "nfs:nfs_disable_rddir_cache" on page 111. Unstable nfs:nfs4_lookup_neg_cache Description Data Type Default Range Units Dynamic? Validation Controls whether a negative name cache is used for NFS version 4 mounted file systems. This negative name cache records file names that were looked up, but were not found. The cache is used to avoid over-the-network look-up requests made for file names that are already known to not exist. Integer (32-bit) 1 (enabled) 0 (disabled) or 1 (enabled) Boolean values Yes None 102 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters When to Change Commitment Level For the cache to perform correctly, negative entries must be strictly verified before they are used. This consistency mechanism is relaxed slightly for read-only mounted file systems. It is assumed that the file system on the server is not changing or is changing very slowly, and that it is okay for such changes to propagate slowly to the client. The consistency mechanism becomes the normal attribute cache mechanism in this case. If file systems are mounted read-only on the client, but are expected to change on the server and these changes need to be seen immediately by the client, use this parameter to disable the negative cache. If you disable the nfs:nfs_disable_rddir_cache parameter, you should probably also disable this parameter. For more information, see "nfs:nfs_disable_rddir_cache" on page 111. Unstable nfs:nfs_max_threads Description Controls the number of kernel threads that perform asynchronous I/O for the NFS version 2 client. Because NFS is based on RPC and RPC is inherently synchronous, separate execution contexts are required to perform NFS operations that are asynchronous from the calling thread. Data Type Default Range Units Dynamic? Validation When to Change The operations that can be executed asynchronously are read for read-ahead, readdir for readdir read-ahead, write for putpage and pageio operations, commit, and inactive for cleanup operations that the client performs when it stops using a file. Unsigned short 8 0 to 215 - 1 Threads Yes, but this parameter is set per file system at mount time. To affect a particular file system, unmount and mount the file system after changing this parameter. None To increase or reduce the number of simultaneous I/O operations that are outstanding at any given time. For example, for a very low bandwidth network, you might want to decrease this value so that the Chapter 4 · NFS Tunable Parameters 103 NFS Module Parameters Commitment Level NFS client does not overload the network. Alternately, if the network is very high bandwidth, and the client and server have sufficient resources, you might want to increase this value. Doing so can more effectively utilize the available network bandwidth, and the client and server resources. Unstable nfs:nfs3_max_threads Description Controls the number of kernel threads that perform asynchronous I/O for the NFS version 3 client. Because NFS is based on RPC and RPC is inherently synchronous, separate execution contexts are required to perform NFS operations that are asynchronous from the calling thread. Data Type Default Range Units Dynamic? Validation When to Change Commitment Level The operations that can be executed asynchronously are read for read-ahead, readdir for readdir read-ahead, write for putpage and pageio requests, and commit. Unsigned short 8 0 to 215 - 1 Threads Yes, but this parameter is set per file system at mount time. To affect a particular file system, unmount and mount the file system after changing this parameter. None To increase or reduce the number of simultaneous I/O operations that are outstanding at any given time. For example, for a very low bandwidth network, you might want to decrease this value so that the NFS client does not overload the network. Alternately, if the network is very high bandwidth, and the client and server have sufficient resources, you might want to increase this value. Doing so can more effectively utilize the available network bandwidth, and the client and server resources. Unstable 104 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters nfs:nfs4_max_threads Description Controls the number of kernel threads that perform asynchronous I/O for the NFS version 4 client. Because NFS is based on RPC and RPC is inherently synchronous, separate execution contexts are required to perform NFS operations that are asynchronous from the calling thread. Data Type Default Range Units Dynamic? Validation When to Change Commitment Level The operations that can be executed asynchronously are read for read-ahead, write-behind, directory read-ahead, and cleanup operations that the client performs when it stops using a file. Unsigned short 8 0 to 215 - 1 Threads Yes, but this parameter is set per file system at mount time. To affect a particular file system, unmount and mount the file system after changing this parameter. None To increase or reduce the number of simultaneous I/O operations that are outstanding at any given time. For example, for a very low bandwidth network, you might want to decrease this value so that the NFS client does not overload the network. Alternately, if the network is very high bandwidth, and the client and server have sufficient resources, you might want to increase this value. Doing so can more effectively utilize the available network bandwidth, and the client and server resources. Unstable nfs:nfs_nra Description Data Type Default Controls the number of read-ahead operations that are queued by the NFS version 2 client when sequential access to a file is discovered. These read-ahead operations increase concurrency and read throughput. Each read-ahead request is generally for one logical block of file data. Integer (32-bit) 4 Chapter 4 · NFS Tunable Parameters 105 NFS Module Parameters Range Units Dynamic? Validation When to Change Commitment Level 0 to 231 - 1 Logical blocks. Yes None To increase or reduce the number of read-ahead requests that are outstanding for a specific file at any given time. For example, for a very low bandwidth network or on a low memory client, you might want to decrease this value so that the NFS client does not overload the network or the system memory. Alternately, if the network is very high bandwidth, and the client and server have sufficient resources, you might want to increase this value. Doing so can more effectively utilize the available network bandwidth, and the client and server resources. Unstable nfs:nfs3_nra Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls the number of read-ahead operations that are queued by the NFS version 3 client when sequential access to a file is discovered. These read-ahead operations increase concurrency and read throughput. Each read-ahead request is generally for one logical block of file data. Integer (32-bit) 4 0 to 231 - 1 Logical blocks. (See "nfs:nfs3_bsize" on page 112.) Yes None To increase or reduce the number of read-ahead requests that are outstanding for a specific file at any given time. For example, for a very low bandwidth network or on a low memory client, you might want to decrease this value so that the NFS client does not overload the network or the system memory. Alternately, if the network is very high bandwidth and the client and server have sufficient resources, you might want to increase this value. Doing so can more effectively utilize the available network bandwidth, and the client and server resources. Unstable 106 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters nfs:nfs4_nra Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls the number of read-ahead operations that are queued by the NFS version 4 client when sequential access to a file is discovered. These read-ahead operations increase concurrency and read throughput. Each read-ahead request is generally for one logical block of file data. Integer (32-bit) 4 0 to 231 - 1 Logical blocks. (See "nfs:nfs4_bsize" on page 112.) Yes None To increase or reduce the number of read-ahead requests that are outstanding for a specific file at any given time. For example, for a very low bandwidth network or on a low memory client, you might want to decrease this value so that the NFS client does not overload the network or the system memory. Alternately, if the network is very high bandwidth, and the client and server have sufficient resources, you might want to increase this value. Doing so can more effectively utilize the available network bandwidth, and the client and server resources. Unstable nfs:nrnode Description Data Type Controls the size of the rnode cache on the NFS client. The rnode, used by both NFS version 2, 3, and 4 clients, is the central data structure that describes a file on the NFS client. The rnode contains the file handle that identifies the file on the server. The rnode also contains pointers to various caches used by the NFS client to avoid network calls to the server. Each rnode has a one-to-one association with a vnode. The vnode caches file data. The NFS client attempts to maintain a minimum number of rnodes to attempt to avoid destroying cached data and metadata. When an rnode is reused or freed, the cached data and metadata must be destroyed. Integer (32-bit) Chapter 4 · NFS Tunable Parameters 107 NFS Module Parameters Default Range Units Dynamic? Validation When to Change Commitment Level The default setting of this parameter is 0, which means that the value of nrnode should be set to the value of the ncsize parameter. Actually, any non positive value of nrnode results in nrnode being set to the value of ncsize. 1 to 231 - 1 rnodes No. This value can only be changed by adding or changing the parameter in the /etc/system file, and then rebooting the system. The system enforces a maximum value such that the rnode cache can only consume 25 percent of available memory. Because rnodes are created and destroyed dynamically, the system tends to settle upon a nrnode-size cache, automatically adjusting the size of the cache as memory pressure on the system increases or as more files are simultaneously accessed. However, in certain situations, you could set the value of nrnode if the mix of files being accessed can be predicted in advance. For example, if the NFS client is accessing a few very large files, you could set the value of nrnode to a small number so that system memory can cache file data instead of rnodes. Alternately, if the client is accessing many small files, you could increase the value of nrnode to optimize for storing file metadata to reduce the number of network calls for metadata. Although it is not recommended, the rnode cache can be effectively disabled by setting the value of nrnode to 1. This value instructs the client to only cache 1 rnode, which means that it is reused frequently. Unstable nfs:nfs_shrinkreaddir Description Some older NFS servers might incorrectly handle NFS version 2 READDIR requests for more than 1024 bytes of directory information. This problem is due to a bug in the server implementation. However, this parameter contains a workaround in the NFS version 2 client. When this parameter is enabled, the client does not generate a READDIR request for larger than 1024 bytes of directory information. If this parameter is disabled, then the over-the-wire size is set to the lesser of either the size passed in by using the getdents system call or by using NFS_MAXDATA, which is 8192 bytes. For more information, see getdents(2). 108 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Integer (32-bit) 0 (disabled) 0 (disabled) or 1 (enabled) Boolean values Yes None Examine the value of this parameter if an older NFS version 2 only server is used and interoperability problems occur when the server tries to read directories. Enabling this parameter might cause a slight decrease in performance for applications that read directories. Unstable nfs:nfs3_shrinkreaddir Description Some older NFS servers might incorrectly handle NFS version 3 READDIR requests for more than 1024 bytes of directory information. This problem is due to a bug in the server implementation. However, this parameter contains a workaround in the NFS version 3 client. Data Type Default Range Units Dynamic? Validation When to Change When this parameter is enabled, the client does not generate a READDIR request for larger than 1024 bytes of directory information. If this parameter is disabled, then the over-the-wire size is set to the minimum of either the size passed in by using the getdents system call or by using MAXBSIZE, which is 8192 bytes. For more information, see getdents(2). Integer (32-bit) 0 (disabled) 0 (disabled) or 1 (enabled) Boolean values Yes None Examine the value of this parameter if an older NFS version 3 only server is used and interoperability problems occur when the server tries to read directories. Enabling this parameter might cause a slight decrease in performance for applications that read directories. Chapter 4 · NFS Tunable Parameters 109 NFS Module Parameters Commitment Level Unstable nfs:nfs_write_error_interval Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls the time duration in between logging ENOSPC and EDQUOT write errors received by the NFS client. This parameter affects NFS version 2, 3, and 4 clients. Long integer (64-bit) 5 seconds 0 to 263 - 1 Seconds Yes None Increase or decrease the value of this parameter in response to the volume of messages being logged by the client. Typically, you might want to increase the value of this parameter to decrease the number of out of space messages being printed when a full file system on a server is being actively used. Unstable nfs:nfs_write_error_to_cons_only Description Data Type Default Range Units Dynamic? Validation When to Change Controls whether NFS write errors are logged to the system console and syslog or to the system console only. This parameter affects messages for NFS version 2, 3, and 4 clients. Integer (32-bit) 0 (system console and syslog) 0 (system console and syslog) or 1 (system console) Boolean values Yes None Examine the value of this parameter to avoid filling up the file system containing the messages logged by the syslogd daemon. When this 110 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters Commitment Level parameter is enabled, messages are printed on the system console only and are not copied to the syslog messages file. Unstable nfs:nfs_disable_rddir_cache Description Data Type Default Range Units Dynamic? Validation When to Change Controls the use of a cache to hold responses from READDIR and READDIRPLUS requests. This cache avoids over-the-wire calls to the server to retrieve directory information. Integer (32-bit) 0 (caching enabled) 0 (caching enabled) or 1 (caching disabled) Boolean values Yes None Examine the value of this parameter if interoperability problems develop due to a server that does not update the modification time on a directory when a file or directory is created in it or removed from it. The symptoms are that new names do not appear in directory listings after they have been added to the directory or that old names do not disappear after they have been removed from the directory. This parameter controls the caching for NFS version 2, 3, and 4 mounted file systems. This parameter applies to all NFS mounted file systems, so caching cannot be disabled or enabled on a per file system basis. Commitment Level If you disable this parameter, you should also disable the following parameters to prevent bad entries in the DNLC negative cache: "nfs:nfs_lookup_neg_cache" on page 100 "nfs:nfs3_lookup_neg_cache" on page 101 "nfs:nfs4_lookup_neg_cache" on page 102 Unstable Chapter 4 · NFS Tunable Parameters 111 NFS Module Parameters nfs:nfs3_bsize Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls the logical block size used by the NFS version 3 client. This block size represents the amount of data that the client attempts to read from or write to the server when it needs to do an I/O. Unsigned integer (32-bit) 32,768 (32 KB) 0 to 231 - 1 Bytes Yes, but the block size for a file system is set when the file system is mounted. To affect a particular file system, unmount and mount the file system after changing this parameter. None. Setting this parameter too low or too high might cause the system to malfunction. Do not set this parameter to anything less than PAGESIZE for the specific platform. Do not set this parameter too high because it might cause the system to hang while waiting for memory allocations to be granted. Examine the value of this parameter when attempting to change the maximum data transfer size. Change this parameter in conjunction with the nfs:nfs3_max_transfer_size parameter. If larger transfers are preferred, increase both parameters. If smaller transfers are preferred, then just reducing this parameter should suffice. Unstable nfs:nfs4_bsize Description Data Type Default Range Units Dynamic? Controls the logical block size used by the NFS version 4 client. This block size represents the amount of data that the client attempts to read from or write to the server when it needs to do an I/O. Unsigned integer (32-bit) 32,768 (32 KB) 0 to 231 - 1 Bytes Yes, but the block size for a file system is set when the file system is mounted. To affect a particular file system, unmount and mount the file system after changing this parameter. 112 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters Validation When to Change Commitment Level None. Setting this parameter too low or too high might cause the system to malfunction. Do not set this parameter to anything less than PAGESIZE for the specific platform. Do not set this parameter too high because it might cause the system to hang while waiting for memory allocations to be granted. Examine the value of this parameter when attempting to change the maximum data transfer size. Change this parameter in conjunction with the nfs:nfs4_max_transfer_size parameter. If larger transfers are preferred, increase both parameters. If smaller transfers are preferred, then just reducing this parameter should suffice. Unstable nfs:nfs_async_clusters Description Controls the mix of asynchronous requests that are generated by the NFS version 2 client. The four types of asynchronous requests are read-ahead, putpage, pageio, and readdir-ahead. The client attempts to round-robin between these different request types to attempt to be fair and not starve one request type in favor of another. However, the functionality in some NFS version 2 servers such as write gathering depends upon certain behaviors of existing NFS Version 2 clients. In particular, this functionality depends upon the client sending out multiple WRITE requests at about the same time. If one request is taken out of the queue at a time, the client would be defeating this server functionality designed to enhance performance for the client. Data Type Default Range Units Dynamic? Thus, use this parameter to control the number of requests of each request type that are sent out before changing types. Unsigned integer (32-bit) 1 0 to 231 - 1 Asynchronous requests Yes, but the cluster setting for a file system is set when the file system is mounted. To affect a particular file system, unmount and mount the file system after changing this parameter. Chapter 4 · NFS Tunable Parameters 113 NFS Module Parameters Validation When to Change Commitment Level None. However, setting the value of this parameter to 0 causes all of the queued requests of a particular request type to be processed before moving on to the next type. This effectively disables the fairness portion of the algorithm. To increase the number of each type of asynchronous request that is generated before switching to the next type. Doing so might help with server functionality that depends upon clusters of requests coming from the client. Unstable nfs:nfs3_async_clusters Description Controls the mix of asynchronous requests that are generated by the NFS version 3 client. The five types of asynchronous requests are read-ahead, putpage, pageio, readdir-ahead, and commit. The client attempts to round-robin between these different request types to attempt to be fair and not starve one request type in favor of another. However, the functionality in some NFS version 3 servers such as write gathering depends upon certain behaviors of existing NFS version 3 clients. In particular, this functionality depends upon the client sending out multiple WRITE requests at about the same time. If one request is taken out of the queue at a time, the client would be defeating this server functionality designed to enhance performance for the client. Data Type Default Range Units Dynamic? Validation Thus, use this parameter to control the number of requests of each request type that are sent out before changing types. Unsigned integer (32-bit) 1 0 to 231 - 1 Asynchronous requests Yes, but the cluster setting for a file system is set when the file system is mounted. To affect a particular file system, unmount and mount the file system after changing this parameter. None. However, setting the value of this parameter to 0 causes all of the queued requests of a particular request type to be processed before moving on to the next type. This value effectively disables the fairness portion of the algorithm. 114 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters When to Change Commitment Level To increase the number of each type of asynchronous operation that is generated before switching to the next type. Doing so might help with server functionality that depends upon clusters of operations coming from the client. Unstable nfs:nfs4_async_clusters Description Controls the mix of asynchronous requests that are generated by the NFS version 4 client. The six types of asynchronous requests are read-ahead, putpage, pageio, readdir-ahead, commit, and inactive. The client attempts to round-robin between these different request types to attempt to be fair and not starve one request type in favor of another. However, the functionality in some NFS version 4 servers such as write gathering depends upon certain behaviors of existing NFS version 4 clients. In particular, this functionality depends upon the client sending out multiple WRITE requests at about the same time. If one request is taken out of the queue at a time, the client would be defeating this server functionality designed to enhance performance for the client. Data Type Default Range Units Dynamic? Validation When to Change Thus, use this parameter to control the number of requests of each request type that are sent out before changing types. Unsigned integer (32-bit) 1 0 to 231 - 1 Asynchronous requests Yes, but the cluster setting for a file system is set when the file system is mounted. To affect a particular file system, unmount and mount the file system after changing this parameter. None. However, setting the value of this parameter to 0 causes all of the queued requests of a particular request type to be processed before moving on to the next type. This effectively disables the fairness portion of the algorithm. To increase the number of each type of asynchronous request that is generated before switching to the next type. Doing so might help with server functionality that depends upon clusters of requests coming from the client. Chapter 4 · NFS Tunable Parameters 115 NFS Module Parameters Commitment Level Unstable nfs:nfs_async_timeout Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls the duration of time that threads, which execute asynchronous I/O requests, sleep with nothing to do before exiting. When there are no more requests to execute, each thread goes to sleep. If no new requests come in before this timer expires, the thread wakes up and exits. If a request does arrive, a thread is woken up to execute requests until there are none again. Then, the thread goes back to sleep waiting for another request to arrive, or for the timer to expire. Integer (32-bit) 6000 (1 minute expressed as 60 sec * 100Hz) 0 to 231 - 1 Hz. (Typically, the clock runs at 100Hz.) Yes None. However, setting this parameter to a non positive value causes these threads exit as soon as there are no requests in the queue for them to process. If the behavior of applications in the system is known precisely and the rate of asynchronous I/O requests can be predicted, it might be possible to tune this parameter to optimize performance slightly in either of the following ways: By making the threads expire more quickly, thus freeing up kernel resources more quickly By making the threads expire more slowly, thus avoiding thread create and destroy overhead Unstable nfs:nacache Description Tunes the number of hash queues that access the file access cache on the NFS client. The file access cache stores file access rights that users have with respect to files that they are trying to access. The cache itself is dynamically allocated. However, the hash queues used to index into the cache are statically allocated. The algorithm assumes that there is one access cache entry per active file and four of these access cache 116 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters Data Type Default Range Units Dynamic? Validation When to Change Commitment Level entries per hash bucket. Thus, by default, the value of this parameter is set to the value of the nrnode parameter. Integer (32-bit) The default setting of this parameter is 0. This value means that the value of nacache should be set to the value of the nrnode parameter. 1 to 231 - 1 Access cache entries No. This value can only be changed by adding or changing the parameter in the /etc/system file, and then rebooting system. None. However, setting this parameter to a negative value will probably cause the system to try to allocate a very large set of hash queues. While trying to do so, the system is likely to hang. Examine the value of this parameter if the basic assumption of one access cache entry per file would be violated. This violation could occur for systems in a timesharing mode where multiple users are accessing the same file at about the same time. In this case, it might be helpful to increase the expected size of the access cache so that the hashed access to the cache stays efficient. Unstable nfs:nfs3_jukebox_delay Description Data Type Default Range Units Dynamic? Validation Controls the duration of time that the NFS version 3 client waits to transmit a new request after receiving the NFS3ERR_JUKEBOX error from a previous request. The NFS3ERR_JUKEBOX error is generally returned from the server when the file is temporarily unavailable for some reason. This error is generally associated with hierarchical storage, and CD or tape jukeboxes. Long integer (64-bit) 1000 (10 seconds expressed as 10 sec * 100Hz) 0 to 263 - 1 on 64-bit platforms Hz. (Typically, the clock runs at 100Hz.) Yes None Chapter 4 · NFS Tunable Parameters 117 NFS Module Parameters When to Change Commitment Level Examine the value of this parameter and perhaps adjust it to match the behaviors exhibited by the server. Increase this value if the delays in making the file available are long in order to reduce network overhead due to repeated retransmissions. Decrease this value to reduce the delay in discovering that the file has become available. Unstable nfs:nfs3_max_transfer_size Description Data Type Default Range Units Dynamic? Validation Controls the maximum size of the data portion of an NFS version 3 READ, WRITE, READDIR, or READDIRPLUS request. This parameter controls both the maximum size of the request that the server returns as well as the maximum size of the request that the client generates. Integer (32-bit) 1,048,576 (1 Mbyte) 0 to 231 - 1 Bytes Yes, but this parameter is set per file system at mount time. To affect a particular file system, unmount and mount the file system after changing this parameter. None. However, setting the maximum transfer size on the server to 0 is likely to cause clients to malfunction or just decide not to attempt to talk to the server. When to Change There is also a limit on the maximum transfer size when using NFS over the UDP transport. UDP has a hard limit of 64 KB per datagram. This 64 KB must include the RPC header as well as other NFS information, in addition to the data portion of the request. Setting the limit too high might result in errors from UDP and communication problems between the client and the server. To tune the size of data transmitted over the network. In general, the nfs:nfs3_bsize parameter should also be updated to reflect changes in this parameter. For example, when you attempt to increase the transfer size beyond 32 KB, update nfs:nfs3_bsize to reflect the increased value. Otherwise, no change in the over-the-wire request size is observed. For more information, see "nfs:nfs3_bsize" on page 112. 118 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 NFS Module Parameters Commitment Level If you want to use a smaller transfer size than the default transfer size, use the mount command's -wsize or -rsize option on a per-file system basis. Unstable nfs:nfs4_max_transfer_size Description Data Type Default Range Units Dynamic? Validation Controls the maximum size of the data portion of an NFS version 4 READ, WRITE, READDIR, or READDIRPLUS request. This parameter controls both the maximum size of the request that the server returns as well as the maximum size of the request that the client generates. Integer (32-bit) 32, 768 (32 KB) 0 to 231 - 1 Bytes Yes, but this parameter is set per file system at mount time. To affect a particular file system, unmount and mount the file system after changing this parameter. None. However, setting the maximum transfer size on the server to 0 is likely to cause clients to malfunction or just decide not to attempt to talk to the server. When to Change There is also a limit on the maximum transfer size when using NFS over the UDP transport. For more information on the maximum for UDP, see "nfs:nfs3_max_transfer_size" on page 118. To tune the size of data transmitted over the network. In general, the nfs:nfs4_bsize parameter should also be updated to reflect changes in this parameter. For example, when you attempt to increase the transfer size beyond 32 KB, update nfs:nfs4_bsize to reflect the increased value. Otherwise, no change in the over-the-wire request size is observed. For more information, see "nfs:nfs4_bsize" on page 112. Commitment Level If you want to use a smaller transfer size than the default transfer size, use the mount command's -wsize or -rsize option on a per-file system basis. Unstable Chapter 4 · NFS Tunable Parameters 119 NFS Module Parameters nfs:nfs3_max_transfer_size_clts Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls the maximum size of the data portion of an NFS version 3 READ, WRITE, READDIR, or READDIRPLUS request over UDP. This parameter controls both the maximum size of the request that the server returns as well as the maximum size of the request that the client generates. Integer (32-bit) 32, 768 (32 KB) 0 to 231 - 1 Bytes Yes, but this parameter is set per file system at mount time. To affect a particular file system, unmount and mount the file system after changing this parameter. None. However, setting the maximum transfer size on the server to 0 is likely to cause clients to malfunction or just decide not to attempt to talk to the server. Do not change this parameter. Unstable nfs:nfs3_max_transfer_size_cots Description Data Type Default Range Units Dynamic? Controls the maximum size of the data portion of an NFS version 3 READ, WRITE, READDIR, or READDIRPLUS request over TCP. This parameter controls both the maximum size of the request that the server returns as well as the maximum size of the request that the client generates. Integer (32-bit) 1,048,576 bytes 0 to 231 - 1 Bytes Yes, but this parameter is set per file system at mount time. To affect a particular file system, unmount and mount the file system after changing this parameter. 120 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 rpcmod Module Parameters Validation When to Change Commitment Level None. However, setting the maximum transfer size on the server to 0 is likely to cause clients to malfunction or just decide not to attempt to talk to the server. Do not change this parameter unless transfer sizes larger than 1 Mbyte are preferred. Unstable rpcmod Module Parameters This section describes NFS parameters for the rpcmod module. rpcmod:clnt_max_conns Description Data Type Default Range Units Dynamic? Validation When to Change Controls the number of TCP connections that the NFS client uses when communicating with each NFS server. The kernel RPC is constructed so that it can multiplex RPCs over a single connection. However, multiple connections can be used, if preferred. Integer (32-bit) 1 1 to 231 - 1 Connections Yes None In general, one connection is sufficient to achieve full network bandwidth. However, if TCP cannot utilize the bandwidth offered by the network in a single stream, then multiple connections might increase the throughput between the client and the server. Commitment Level Increasing the number of connections doesn't come without consequences. Increasing the number of connections also increases kernel resource usage needed to keep track of each connection. Unstable Chapter 4 · NFS Tunable Parameters 121 rpcmod Module Parameters rpcmod:clnt_idle_timeout Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls the duration of time on the client that a connection between the client and server is allowed to remain idle before being closed. Long integer (64-bit) 300,000 milliseconds (5 minutes) 0 to 263 - 1 Milliseconds Yes None Use this parameter to change the time that idle connections are allowed to exist on the client before being closed. You might might want to close connections at a faster rate to avoid consuming system resources. Unstable rpcmod:svc_idle_timeout Description Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Controls the duration of time on the server that a connection between the client and server is allowed to remain idle before being closed. Long integer (64-bit) 360,000 milliseconds (6 minutes) 0 to 263 - 1 Milliseconds Yes None Use this parameter to change the time that idle connections are allowed to exist on the server before being closed. You might want to close connections at a faster rate to avoid consuming system resources. Unstable rpcmod:svc_default_stksize Description Sets the size of the kernel stack for kernel RPC service threads. 122 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 rpcmod Module Parameters Data Type Default Range Units Dynamic? Validation When to Change Commitment Level Integer (32-bit) The default value is 0. This value means that the stack size is set to the system default. 0 to 231 - 1 Bytes Yes, for all new threads that are allocated. The stack size is set when the thread is created. Therefore, changes to this parameter do not affect existing threads but are applied to all new threads that are allocated. None Very deep call depths can cause the stack to overflow and cause red zone faults. The combination of a fairly deep call depth for the transport, coupled with a deep call depth for the local file system, can cause NFS service threads to overflow their stacks. Set this parameter to a multiple of the hardware pagesize on the platform. Unstable rpcmod:maxdupreqs Description Data Type Default Range Units Dynamic? Controls the size of the duplicate request cache that detects RPC- level retransmissions on connectionless transports. This cache is indexed by the client network address and the RPC procedure number, program number, version number, and transaction ID. This cache avoids processing retransmitted requests that might not be idempotent. Integer (32-bit) 8192 1 to 231 - 1 Requests The cache is dynamically sized, but the hash queues that provide fast access to the cache are statically sized. Making the cache very large might result in long search times to find entries in the cache. Validation Do not set the value of this parameter to 0. This value prevents the NFS server from handling non idempotent requests. None Chapter 4 · NFS Tunable Parameters 123 rpcmod Module Parameters When to Change Commitment Level Examine the value of this parameter if false failures are encountered by NFS clients. For example, if an attempt to create a directory fails, but the directory is actually created, perhaps that retransmitted MKDIR request was not detected by the server. The size of the cache should match the load on the server. The cache records non idempotent requests and so only needs to track a portion of the total requests. The cache does need to hold the information long enough to be able to detect a retransmission by the client. Typically, the client timeout for connectionless transports is relatively short, starting around 1 second and increasing to about 20 seconds. Unstable rpcmod:cotsmaxdupreqs Description Data Type Default Range Units Dynamic? Validation Controls the size of the duplicate request cache that detects RPC- level retransmissions on connection-oriented transports. This cache is indexed by the client network address and the RPC procedure number, program number, version number, and transaction ID. This cache avoids processing retransmitted requests that might not be idempotent. Integer (32bit) 8192 1 to 231 - 1 Requests Yes The cache is dynamically sized, but the hash queues that provide fast access to the cache are statically sized. Making the cache very large might result in long search times to find entries in the cache. When to Change Do not set the value of this parameter to 0. It prevents the NFS server from handling non-idempotent requests. Examine the value of this parameter if false failures are encountered by NFS clients. For example, if an attempt to create a directory fails, but the directory is actually created, it is possible that a retransmitted MKDIR request was not detected by the server. The size of the cache should match the load on the server. The cache records non-idempotent requests and so only needs to track a portion 124 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 rpcmod Module Parameters Commitment Level of the total requests. It does need to hold the information long enough to be able to detect a retransmission on the part of the client. Typically, the client timeout for connection oriented transports is very long, about 1 minute. Thus, entries need to stay in the cache for fairly long times. Unstable Chapter 4 · NFS Tunable Parameters 125 126 5C H A P T E R 5 Internet Protocol Suite Tunable Parameters This chapter describes various Internet Protocol suite properties. "IP Tunable Parameters" on page 128 "TCP Tunable Parameters" on page 134 "UDP Tunable Parameters" on page 152 "IPQoS Tunable Parameter" on page 154 "SCTP Tunable Parameters" on page 155 "Per-Route Metrics" on page 166 Where to Find Tunable Parameter Information Tunable Parameter Oracle Solaris kernel tunable parameters Oracle Solaris ZFS tunable parameters NFS tunable parameters For Information Chapter 2, "Oracle Solaris Kernel Tunable Parameters" Chapter 3, "Oracle Solaris ZFS Tunable Parameters" Chapter 4, "NFS Tunable Parameters" Overview of Tuning IP Suite Parameters You can set all of the tuning parameters described in this chapter by using the ipadm command except for the following parameters: "ipcl_conn_hash_size" on page 147 "ip_squeue_worker_wait" on page 147 "ip_squeue_fanout" on page 132 These parameters can only be set in the /etc/system file. 127 IP Tunable Parameters Use the following syntax to set TCP/IP parameters by using the ipadm command: # ipadm set-prop -p parameter ip|ipv4|ipv6|tcp|udp|sctp For example: # ipadm set-prop -p extra_priv_ports=1047 tcp # ipadm show-prop -p extra_priv_ports tcp PROTO PROPERTY PERM CURRENT PERSISTENT tcp extra_priv_ports rw 1047 1047 For more information, see ipadm(1M). DEFAULT 2049,4045 POSSIBLE 1-65535 Use the following syntax to set TCP/IP parameters by using the ndd command: # ndd -set driver parameter value For more information, see ndd(1M). IP Suite Parameter Validation All parameters described in this section are checked to verify that they fall in the parameter range. The parameter's range is provided with the description for each parameter. Internet Request for Comments (RFCs) Internet protocol and standard specifications are described in RFC documents. You can review RFCs from the following site: https://www.ietf.org/rfc.html At this site, you can browse RFC topics by entering an RFC number or an internet-draft file name in the IETF Repository Retrieval search field. IP Tunable Parameters _icmp_err_interval and _icmp_err_burst Description Controls the rate of IP in generating ICMP error messages. IP generates only up to _icmp_err_burst IP error messages in any _icmp_err_interval. The _icmp_err_interval parameter protects IP from denial of service attacks. Setting this parameter to 0 disables rate limiting. It does not disable the generation of error messages. 128 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 IP Tunable Parameters Default Range Dynamic? When to Change Commitment Level Change History 100 milliseconds for _icmp_err_interval 10 error messages for _icmp_err_burst 0 99,999 milliseconds for _icmp_err_interval 1 99,999 error messages for _icmp_err_burst Yes If you need a higher error message generation rate for diagnostic purposes. Unstable For information, see "IP Parameter Name Changes (Oracle Solaris 11)" on page 178. _respond_to_echo_broadcast and _respond_to_echo_multicast (ipv4 or ipv6) Description Default Range Dynamic? When to Change Commitment Level Change History Controls whether IP responds to a broadcast ICMPv4 echo request or a IPv6 multicast ICMPv6 echo request. 1 (enabled) 0 (disabled) or 1 (enabled) Yes If you do not want this behavior for security reasons, disable it. Unstable For information, see "IP Parameter Name Changes (Oracle Solaris 11)" on page 178. _send_redirects (ipv4 or ipv6) Description Default Range Dynamic? When to Change Controls whether IPv4 or IPv6 sends out ICMPv4 or ICMPv6 redirect messages. 1 (enabled) 0 (disabled) or 1 (enabled) Yes If you do not want this behavior for security reasons, disable it. Chapter 5 · Internet Protocol Suite Tunable Parameters 129 IP Tunable Parameters Commitment Level Change History Unstable For information, see "IP Parameter Name Changes (Oracle Solaris 11)" on page 178. forwarding (ipv4 or ipv6) Description Default Range Dynamic? When to Change Commitment Level Change History Controls whether IPv4 or IPv6 forwards packets with source IPv4 routing options or IPv6 routing headers. 0 (disabled or off) 0 (disabled or off) or 1 (enabled or on) Yes Keep this parameter disabled to prevent denial of service attacks. Unstable For information, see "IP Parameter Name Changes (Oracle Solaris 11)" on page 178. ttl Description Default Range Dynamic? When to Change Commitment Level Change History Controls the time to live (TTL) value in the IPv4 header for the outbound IPv4 packets on an IP association. 255 1 to 255 Yes Generally, you do not need to change this value. Unstable For information, see "IP Parameter Name Changes (Oracle Solaris 11)" on page 178. hoplimit (ipv6) Description Default Sets the value of the hop limit in the IPv6 header for the outbound IPv6 packets on an IP association. 255 130 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 IP Tunable Parameters Range Dynamic? When to Change Commitment Level Change History 0 to 255 Yes Generally, you do not need to change this value. Unstable For information, see "IP Parameter Name Changes (Oracle Solaris 11)" on page 178. _addrs_per_if Description Default Range Dynamic? When to Change Commitment Level Change History Defines the maximum number of logical IP interfaces associated with a real interface. 256 1 to 8,192 Yes Do not change the value. If more logical interfaces are required, you might consider increasing the value. However, recognize that this change might have a negative impact on IP's performance. Unstable For information, see "IP Parameter Name Changes (Oracle Solaris 11)" on page 178. hostmodel (ipv4 or ipv6) Description Default Range Controls send and receive behavior for IPv4 or IPv6 packets on a multi-homed system. This property can have the following values: weak, strong, and src-priority. The default value is weak. weak weak, strong, or src-priority weak Outgoing packets - The source address of the packet going out need not match the address configured on the outgoing interface. Chapter 5 · Internet Protocol Suite Tunable Parameters 131 IP Tunable Parameters Dynamic? When to Change Commitment Level Change History Incoming packets - The destination address of the incoming packet need not match the address configured on the incoming interface. strong Outgoing packets - The source address of the packet going out must match the address configured on the outgoing interface. Incoming packets - The destination address of the incoming packet must match the address configured on the incoming interface. src-priority Outgoing packets - If multiple routes for the IP destination in the packet are available, the system prefers routes where the IP source address in the packet is configured on the outgoing interface. If no such route is available, the system falls back to selecting the best route, as with the weak ES case. Incoming packets - The destination address of the incoming packet must be configured on any one of the host's interface. Yes If a machine has interfaces that cross strict networking domains (for example, a firewall or a VPN node), set this parameter to strong. Unstable For information, see "IP Parameter Name Changes (Oracle Solaris 11)" on page 178. ip_squeue_fanout Description Determines the mode of associating TCP/IP connections with squeues. Default Range Dynamic? A value of 0 associates a new TCP/IP connection with the CPU that creates the connection. A value of 1 associates the connection with multiple squeues that belong to different CPUs. 1 0 or 1 Yes 132 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 IP Tunable Parameters When to Change Zone Configuration Commitment Level Consider setting this parameter to 1 to spread the load across all CPUs in certain situations. For example, when the number of CPUs exceed the number of NICs, and one CPU is not capable of handling the network load of a single NIC, change this parameter to 1. This property can only be set in the /etc/system file. This parameter can only be set in the global zone. Unstable IP Tunable Parameters With Additional Cautions Changing the following parameters is not recommended. _pathmtu_interval Description Specifies the interval in milliseconds when IP flushes the path maximum transfer unit (PMTU) discovery information, and tries to rediscover PMTU. Default Range Dynamic? When to Change Commitment Level Change History Refer to RFC 1191 on PMTU discovery. 1200 milliseconds (20 minutes) 2-999999999 Yes Do not change this value. Unstable For information, see "IP Parameter Name Changes (Oracle Solaris 11)" on page 178. _icmp_return_data_bytes (ipv4 or ipv6) Description When IPv4 or IPv6 sends an ICMPv4 or ICMPv6 error message, it includes the IP header of the packet that caused the error message. This parameter controls how many extra bytes of the packet beyond the IPv4 or IPv6 header are included in the ICMPv4 or ICMPv6 error message. Default 64 for IPv4 1280 for IPv6 Chapter 5 · Internet Protocol Suite Tunable Parameters 133 TCP Tunable Parameters Range Dynamic? When to Change Commitment Level Change History 8-6,636 for IPv4 8-1,280 for IPv6 Yes Do not change the value. Including more information in an ICMP error message might help in diagnosing network problems. If this feature is needed, increase the value. Unstable For information, see "IP Parameter Name Changes (Oracle Solaris 11)" on page 178. TCP Tunable Parameters _deferred_ack_interval Description Specifies the time-out value for the TCP-delayed acknowledgment (ACK) timer for hosts that are not directly connected. Default Range Dynamic? When to Change Refer to RFC 1122, 4.2.3.2. 100 milliseconds 1 millisecond to 1 minute Yes Do not increase this value to more than 500 milliseconds. Commitment Level Change History Increase the value under the following circumstances: Slow network links (less than 57.6 Kbps) with greater than 512 bytes maximum segment size (MSS) The interval for receiving more than one TCP segment is short Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. 134 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 TCP Tunable Parameters _local_dack_interval Description Specifies the time-out value for TCP-delayed acknowledgment (ACK) timer for hosts that are directly connected. Default Range Dynamic? When to Change Refer to RFC 1122, 4.2.3.2. 50 milliseconds 10 milliseconds to 500 milliseconds Yes Do not increase this value to more than 500 milliseconds. Commitment Level Change History Increase the value under the following circumstances: Slow network links (less than 57.6 Kbps) with greater than 512 bytes maximum segment size (MSS) The interval for receiving more than one TCP segment is short Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _deferred_acks_max Description Default Range Dynamic? When to Change Commitment Level Specifies the maximum number of TCP segments received from remote destinations (not directly connected) before an acknowledgment (ACK) is generated. TCP segments are measured in units of maximum segment size (MSS) for individual connections. If set to 0 or 1, no ACKs are delayed, assuming all segments are 1 MSS long. The actual number is dynamically calculated for each connection. The value is the default maximum. 2 0 to 16 Yes Do not change the value. In some circumstances, when the network traffic becomes very bursty because of the delayed ACK effect, decrease the value. Do not decrease this value below 2. Unstable Chapter 5 · Internet Protocol Suite Tunable Parameters 135 TCP Tunable Parameters Change History For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _local_dacks_max Description Default Range Dynamic? When to Change Commitment Level Change History Specifies the maximum number of TCP segments received from directly connected destinations before an acknowledgment (ACK) is generated. TCP segments are measured in units of maximum segment size (MSS) for individual connections. If set to 0 or 1, it means no ACKs are delayed, assuming all segments are 1 MSS long. The actual number is dynamically calculated for each connection. The value is the default maximum. 8 0 to 16 Yes Do not change the value. In some circumstances, when the network traffic becomes very bursty because of the delayed ACK effect, decrease the value. Do not decrease this value below 2. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _wscale_always Description When this parameter is enabled, which is the default setting, TCP always sends a SYN segment with the window scale option, even if the window scale option value is 0. Note that if TCP receives a SYN segment with the window scale option, even if the parameter is disabled, TCP responds with a SYN segment with the window scale option. In addition, the option value is set according to the receive window size. Default Range Dynamic? Refer to RFC 1323 for the window scale option. 1 (enabled) 0 (disabled) or 1 (enabled) Yes 136 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 TCP Tunable Parameters When to Change Commitment Level Change History If there is an interoperability problem with an old TCP stack that does not support the window scale option, disable this parameter. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _tstamp_always Description Default Range Dynamic? When to Change If set to 1, TCP always sends a SYN segment with the timestamp option. Note that if TCP receives a SYN segment with the timestamp option, TCP responds with a SYN segment with the timestamp option even if the parameter is set to 0. 0 (disabled) 0 (disabled) or 1 (enabled) Yes If getting an accurate measurement of round-trip time (RTT) and TCP sequence number wraparound is a problem, enable this parameter. Commitment Level Change History Refer to RFC 1323 for more reasons to enable this option. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. send_buf Description Default Range Dynamic? When to Change Commitment Level Defines the default send window size in bytes. Refer to "Per-Route Metrics" on page 166 for a discussion of setting a different value on a per-route basis. See also "max_buf" on page 138. 49,152 4,096 to the current value of "max_buf" on page 138 Yes An application can use setsockopt(3XNET) SO_SNDBUF to change the individual connection's send buffer. Unstable Chapter 5 · Internet Protocol Suite Tunable Parameters 137 TCP Tunable Parameters Change History For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. recv_buf Description Default Range Dynamic? When to Change Commitment Level Change History Defines the default receive window size in bytes. Refer to "Per-Route Metrics" on page 166 for a discussion of setting a different value on a per-route basis. See also "max_buf" on page 138 and "_recv_hiwat_minmss" on page 151. 128,000 2,048 to the current value of "max_buf" on page 138 Yes An application can use setsockopt(3XNET) SO_RCVBUF to change the individual connection's receive buffer. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. max_buf Description Default Range Dynamic? When to Change Commitment Level Change History Defines the maximum send and receive buffer size in bytes. This parameter controls how large the send and receive buffers are set to by an application that uses setsockopt(3XNET). 1,048,576 128,000 to 1,073,741,824 Yes If TCP connections are being made in a high-speed network environment, increase the value to match the network link speed. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. 138 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 TCP Tunable Parameters _cwnd_max Description Defines the maximum value of the TCP congestion window (cwnd) in bytes. Default Range Dynamic? When to Change Commitment Level Change History For more information on the TCP congestion window, refer to RFC 1122 and RFC 2581. 1,048,576 128 to 1,073,741,824 Yes Even if an application uses setsockopt(3XNET) to change the window size to a value higher than _cwnd_max, the actual window used can never grow beyond _cwnd_max. Thus, _max_buf should be greater than _cwnd_max. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _slow_start_initial Description Defines the maximum initial congestion window (cwnd) size in the maximum segment size (MSS) of a TCP connection. Default Range Dynamic? When to Change Refer to RFC 2414 on how the initial congestion window size is calculated. 10 1 to 10 Yes Do not change the value. Commitment Level Change History If the initial cwnd size causes network congestion under special circumstances, decrease the value. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. Chapter 5 · Internet Protocol Suite Tunable Parameters 139 TCP Tunable Parameters _local_slow_start_initial Description Default Range Dynamic? When to Change Commitment Level Change History Defines the initial congestion window (cwnd) size in the maximum segment size (MSS) of a TCP connection between directly connected hosts. 10 1 to 16,384 Yes Consider increasing this parameter value if applications would benefit from a larger initial window. Unstable For information, see "_local_slow_start_initial" on page 178. _slow_start_after_idle Description The congestion window size in the maximum segment size (MSS) of a TCP connection after it has been idled (no segment received) for a period of one retransmission timeout (RTO). Default Range Dynamic? When to Change Commitment Level Change History Refer to RFC 2414 on how the initial congestion window size is calculated. 4 1 to 16,384 Yes For more information, see "_slow_start_initial" on page 139. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. sack Description If set to 2, TCP always sends a SYN segment with the selective acknowledgment (SACK) permitted option. If TCP receives a SYN segment with a SACK-permitted option and this parameter is set to 1, TCP responds with a SACK-permitted option. If the parameter is set to 140 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 TCP Tunable Parameters Default Range Dynamic? When to Change Commitment Level Change History 0, TCP does not send a SACK-permitted option, regardless of whether the incoming segment contains the SACK permitted option. Refer to RFC 2018 for information on the SACK option. 2 (active enabled) 0 (disabled), 1 (passive enabled), or 2 (active enabled) Yes SACK processing can improve TCP retransmission performance so it should be actively enabled. Sometimes, the other side can be confused with the SACK option actively enabled. If this confusion occurs, set the value to 1 so that SACK processing is enabled only when incoming connections allow SACK processing. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _rev_src_routes Description Default Range Dynamic? When to Change Commitment Level Change History If set to 0, TCP does not reverse the IP source routing option for incoming connections for security reasons. If set to 1, TCP does the normal reverse source routing. 0 (disabled) 0 (disabled) or 1 (enabled) Yes If IP source routing is needed for diagnostic purposes, enable it. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _time_wait_interval Description Specifies the time in milliseconds that a TCP connection stays in TIME-WAIT state. For more information, refer to RFC 1122, 4.2.2.13. Chapter 5 · Internet Protocol Suite Tunable Parameters 141 TCP Tunable Parameters Default Range Dynamic? When to Change Commitment Level Change History 60,000 (60 seconds) 1 second to 10 minutes Yes Do not set the value lower than 60 seconds. For information on changing this parameter, refer to RFC 1122, 4.2.2.13. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. ecn Description Default Range Dynamic? When to Change Controls Explicit Congestion Notification (ECN) support. If this parameter is set to 0, TCP does not negotiate with a peer that supports the ECN mechanism. If this parameter is set to 1 when initiating a connection, TCP does not tell a peer that it supports ECN mechanism. However, TCP tells a peer that it supports ECN mechanism when accepting a new incoming connection request if the peer indicates that it supports ECN mechanism in the SYN segment. If this parameter is set to 2, in addition to negotiating with a peer on the ECN mechanism when accepting connections, TCP indicates in the outgoing SYN segment that it supports the ECN mechanism when TCP makes active outgoing connections. Refer to RFC 3168 for information on ECN. 1 (passive enabled) 0 (disabled), 1 (passive enabled), or 2 (active enabled) Yes ECN can help TCP better handle congestion control. However, there are existing TCP implementations, firewalls, NATs, and other network devices that are confused by this mechanism. These devices do not comply to the IETF standard. 142 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 TCP Tunable Parameters Commitment Level Change History Because of these devices, the default value of this parameter is set to 1. In rare cases, passive enabling can still cause problems. Set the parameter to 0 only if absolutely necessary. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _conn_req_max_q Description Default Range Dynamic? When to Change Specifies the default maximum number of pending TCP connections for a TCP listener waiting to be accepted by accept(3SOCKET). See also "_conn_req_max_q0" on page 144. 128 1 to 4,294,967,295 Yes For applications such as web servers that might receive several connection requests, the default value might be increased to match the incoming rate. Do not increase the parameter to a very large value. The pending TCP connections can consume excessive memory. Also, if an application cannot handle that many connection requests fast enough because the number of pending TCP connections is too large, new incoming requests might be denied. Commitment Level Change History Note that increasing _conn_req_max_q does not mean that applications can have that many pending TCP connections. Applications can use listen(3SOCKET) to change the maximum number of pending TCP connections for each socket. This parameter is the maximum an application can use listen() to set the number to. Thus, even if this parameter is set to a very large value, the actual maximum number for a socket might be much less than _conn_req_max_q, depending on the value used in listen(). Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. Chapter 5 · Internet Protocol Suite Tunable Parameters 143 TCP Tunable Parameters _conn_req_max_q0 Description Specifies the default maximum number of incomplete (three-way handshake not yet finished) pending TCP connections for a TCP listener. Default Range Dynamic? When to Change For more information on TCP three-way handshake, refer to RFC 793. See also "_conn_req_max_q" on page 143. 1,024 0 to 4,294,967,295 Yes For applications such as web servers that might receive excessive connection requests, you can increase the default value to match the incoming rate. The following explains the relationship between _conn_req_max_q0 and the maximum number of pending connections for each socket. Commitment Level Change History When a connection request is received, TCP first checks if the number of pending TCP connections (three-way handshake is done) waiting to be accepted exceeds the maximum (N) for the listener. If the connections are excessive, the request is denied. If the number of connections is allowable, then TCP checks if the number of incomplete pending TCP connections exceeds the sum of N and _conn_req_max_q0. If it does not, the request is accepted. Otherwise, the oldest incomplete pending TCP request is dropped. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _conn_req_min Description Default Range Dynamic? Specifies the default minimum value for the maximum number of pending TCP connection requests for a listener waiting to be accepted. This is the lowest maximum value of listen(3SOCKET) that an application can use. 1 1 to 1,024 Yes 144 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 TCP Tunable Parameters When to Change Commitment Level Change History This parameter can be a solution for applications that use listen(3SOCKET) to set the maximum number of pending TCP connections to a value too low. Increase the value to match the incoming connection request rate. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _rst_sent_rate_enabled Description Default Range Dynamic? When to Change Commitment Level Change History If this parameter is set to 1, the maximum rate of sending a RST segment is controlled by the ipmadm parameter, _rst_sent_rate. If this parameter is set to 0, no rate control when sending a RST segment is available. 1 (enabled) 0 (disabled) or 1 (enabled) Yes This tunable helps defend against denial of service attacks on TCP by limiting the rate by which a RST segment is sent out. The only time this rate control should be disabled is when strict conformance to RFC 793 is required. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _rst_sent_rate Description Default Range Dynamic? When to Change Sets the maximum number of RST segments that TCP can send out per second. 40 0 to 4,294,967,295 Yes In a TCP environment, there might be a legitimate reason to generate more RSTs than the default value allows. In this case, increase the default value of this parameter. Chapter 5 · Internet Protocol Suite Tunable Parameters 145 TCP Tunable Parameters Commitment Level Change History Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. smallest_anon_port Description This parameter controls the smallest port number TCP can select as an ephemeral port. An application can use an ephemeral port when it creates a connection with a specified protocol and it does not specify a port number. Ephemeral ports are not associated with a specific application. When the connection is closed, the port number can be reused by a different application. Unit Port number Default 32,768 Range 1,024 to 65,535 Dynamic? Yes When to Change When a larger ephemeral port range is required. Commitment Level Unstable Change History For information, see "[tcp,sctp,udp]_smallest_anon_port and [tcp,sctp,udp]_largest_anon_port" on page 178. largest_anon_port Description This parameter controls the largest port number TCP can select as an ephemeral port. An application can use an ephemeral port when it creates a connection with a specified protocol and it does not specify a port number. Ephemeral ports are not associated with a specific application. When the connection is closed, the port number can be reused by a different application. Unit Port number Default 65,535 Range 32,768 to 65,535 Dynamic? Yes When to Change When a larger ephemeral port range is required. Commitment Level Unstable 146 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Change History TCP Tunable Parameters For information, see "[tcp,sctp,udp]_smallest_anon_port and [tcp,sctp,udp]_largest_anon_port" on page 178. TCP/IP Parameters Set in the /etc/system File The following parameters can be set only in the /etc/system file. After the file is modified, reboot the system. For example, the following entry sets the ipcl_conn_hash_size parameter: set ip:ipcl_conn_hash_size=value ipcl_conn_hash_size Description Controls the size of the connection hash table used by IP. The default value of 0 means that the system automatically sizes an appropriate value for this parameter at boot time, depending on the available memory. Data Type Unsigned integer Default 0 Range 0 to 82,500 Dynamic? No. The parameter can only be changed at boot time. When to Change If the system consistently has tens of thousands of TCP connections, the value can be increased accordingly. Increasing the hash table size means that more memory is wired down, thereby reducing available memory to user applications. Commitment Level Unstable ip_squeue_worker_wait Description Governs the maximum delay in waking up a worker thread to process TCP/IP packets that are enqueued on an squeue. An squeue is a serialization queue that is used by the TCP/IP kernel code to process TCP/IP packets. Default 10 milliseconds Range 0 50 milliseconds Dynamic? Yes Chapter 5 · Internet Protocol Suite Tunable Parameters 147 TCP Tunable Parameters When to Change Zone Configuration Commitment Level Consider tuning this parameter if latency is an issue, and network traffic is light. For example, if the machine serves mostly interactive network traffic. The default value usually works best on a network file server, a web server, or any server that has substantial network traffic. This parameter can only be set in the global zone. Unstable TCP Parameters With Additional Cautions Changing the following parameters is not recommended. _keepalive_interval Description This ipadm parameter sets a probe interval that is first sent out after a TCP connection is idle on a system-wide basis. Solaris supports the TCP keep-alive mechanism as described in RFC 1122. This mechanism is enabled by setting the SO_KEEPALIVE socket option on a TCP socket. If SO_KEEPALIVE is enabled for a socket, the first keep-alive probe is sent out after a TCP connection is idle for two hours, the default value of the tcp_keepalive_interval parameter. If the peer does not respond to the probe after eight minutes, the TCP connection is aborted. For more information, refer to "_rexmit_interval_initial" on page 149. Default Range Units Dynamic? When to Change You can also use the TCP_KEEPALIVE_THRESHOLD socket option on individual applications to override the default interval so that each application can have its own interval on each socket. The option value is an unsigned integer in milliseconds. See also tcp(7P). 2 hours 10 seconds to 10 days Unsigned integer (milliseconds) Yes Do not change the value. Lowering it may cause unnecessary network traffic and might also increase the chance of premature termination of the connection because of a transient network problem. 148 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 TCP Tunable Parameters Commitment Level Change History Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _ip_abort_interval Description Specifies the default total retransmission timeout value for a TCP connection. For a given TCP connection, if TCP has been retransmitting for _ip_abort_interval period of time and it has not received any acknowledgment from the other endpoint during this period, TCP closes this connection. Default Range Dynamic? When to Change Commitment Level Change History For TCP retransmission timeout (RTO) calculation, refer to RFC 1122, 4.2.3. See also "_rexmit_interval_max" on page 150. 5 minutes 500 milliseconds to 1193 hours Yes Do not change this value. See "_rexmit_interval_max" on page 150 for exceptions. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _rexmit_interval_initial Description Specifies the default initial retransmission timeout (RTO) value for a TCP connection. Refer to "Per-Route Metrics" on page 166 for a discussion of setting a different value on a per-route basis. Default 1000 milliseconds Range 1 millisecond to 20000 milliseconds Dynamic? Yes When to Change Do not change this value. Lowering the value can result in unnecessary retransmissions. Commitment Level Unstable Change History For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. Chapter 5 · Internet Protocol Suite Tunable Parameters 149 TCP Tunable Parameters _rexmit_interval_max Description Defines the default maximum retransmission timeout value (RTO). The calculated RTO for all TCP connections cannot exceed this value. See also "_ip_abort_interval" on page 149. Default 6000 milliseconds Range 1 millisecond to 7200000 milliseconds Dynamic? Yes When to Change Do not change the value in a normal network environment. Commitment Level Change History If, in some special circumstances, the round-trip time (RTT) for a connection is about 10 seconds, you can increase this value. If you change this value, you should also change the _ip_abort_interval parameter. Change the value of _ip_abort_interval to at least four times the value of _rexmit_interval_max. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _rexmit_interval_min Description Specifies the default minimum retransmission time out (RTO) value. The calculated RTO for all TCP connections cannot be lower than this value. See also "_rexmit_interval_max" on page 150. Default 200 milliseconds Range 1 millisecond to 7200000 milliseconds Dynamic? Yes When to Change Do not change the value in a normal network environment. Commitment Level Change History TCP's RTO calculation should cope with most RTT fluctuations. If, in some very special circumstances, the round-trip time (RTT) for a connection is about 10 seconds, increase this value. If you change this value, you should change the _rexmit_interval_max parameter. Change the value of _rexmit_interval_max to at least eight times the value of _rexmit_interval_min. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. 150 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 TCP Tunable Parameters _rexmit_interval_extra Description Specifies a constant added to the calculated retransmission time out value (RTO). Default 0 milliseconds Range 0 to 7200000 milliseconds Dynamic? Yes When to Change Do not change the value. Commitment Level Change History When the RTO calculation fails to obtain a good value for a connection, you can change this value to avoid unnecessary retransmissions. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _tstamp_if_wscale Description If this parameter is set to 1, and the window scale option is enabled for a connection, TCP also enables the timestamp option for that connection. Default 1 (enabled) Range 0 (disabled) or 1 (enabled) Dynamic? Yes When to Change Do not change this value. In general, when TCP is used in high-speed network, protection against sequence number wraparound is essential. Thus, you need the timestamp option. Commitment Level Unstable Change History For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. _recv_hiwat_minmss Description Controls the default minimum receive window size. The minimum is _recv_hiwat_minmss times the size of maximum segment size (MSS) of a connection. Default 8 Range 1 to 65,536 Chapter 5 · Internet Protocol Suite Tunable Parameters 151 UDP Tunable Parameters Dynamic? When to Change Commitment Level Change History Yes Do not change the value. If changing it is necessary, do not change the value lower than 4. Unstable For information, see "TCP Parameter Name Changes (Oracle Solaris 11)" on page 179. UDP Tunable Parameters send_buf Description Default Range Dynamic? When to Change Commitment Level Change History Defines the default send buffer size for a UDP socket. For more information, see "max_buf" on page 153. 57,344 bytes 1,024 to the current value of "max_buf" on page 153 Yes Note that an application can use setsockopt(3XNET) SO_SNDBUF to change the size for an individual socket. In general, you do not need to change the default value. Unstable For information, see "UDP Parameter Name Changes (Oracle Solaris 11)" on page 181. recv_buf Description Default Range Dynamic? When to Change Defines the default receive buffer size for a UDP socket. For more information, see "max_buf" on page 153. 57,344 bytes 128 to the current value of "max_buf" on page 153 Yes Note that an application can use setsockopt(3XNET) SO_RCVBUF to change the size for an individual socket. In general, you do not need to change the default value. 152 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 UDP Tunable Parameters Commitment Level Change History Unstable For information, see "UDP Parameter Name Changes (Oracle Solaris 11)" on page 181. max_buf Description Default Range Dynamic? When to Change Commitment Level Change History Defines the maximum send and receive buffer size for a UDP socket. It controls how large the send and receive buffers are set to by an application that uses getsockopt(3SOCKET). 2,097,152 65,536 to 1,073,741,824 Yes Increase the value of this parameter to match the network link speed if associations are being made in a high-speed network environment. Unstable For information, see "UDP Parameter Name Changes (Oracle Solaris 11)" on page 181. smallest_anon_port Description Unit Default Range Dynamic? When to Change Commitment Level Change History This parameter controls the smallest port number UDP can select as an ephemeral port. An application can use an ephemeral port when it creates a connection with a specified protocol and it does not specify a port number. Ephemeral ports are not associated with a specific application. When the connection is closed, the port number can be reused by a different application. Port number 32,768 1,024 to 65,535 Yes When a larger ephemeral port range is required. Unstable For information, see "[tcp,sctp,udp]_smallest_anon_port and [tcp,sctp,udp]_largest_anon_port" on page 178. Chapter 5 · Internet Protocol Suite Tunable Parameters 153 IPQoS Tunable Parameter largest_anon_port Description Unit Default Range Dynamic? When to Change Commitment Level Change History This parameter controls the largest port number UDP can select as an ephemeral port. An application can use an ephemeral port when it creates a connection with a specified protocol and it does not specify a port number. Ephemeral ports are not associated with a specific application. When the connection is closed, the port number can be reused by a different application. Port number 65,535 32,768 to 65,535 Yes When a larger ephemeral port range is required. Unstable For information, see "[tcp,sctp,udp]_smallest_anon_port and [tcp,sctp,udp]_largest_anon_port" on page 178. IPQoS Tunable Parameter _policy_mask Description Enables or disables IPQoS processing in any of the following callout positions: forward outbound, forward inbound, local outbound, and local inbound. This parameter is a bitmask as follows: Not Not Used Used X X Not Used X Forward Forward Not Used Outbound Inbound X 0 0 Local Local Outbound Inbound 0 0 Default A 1 in any of the position masks or disables IPQoS processing in that particular callout position. For example, a value of 0x01 disables IPQoS processing for all the local inbound packets. The default value is 0, meaning that IPQoS processing is enabled in all the callout positions. 154 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 SCTP Tunable Parameters Range Dynamic? When to Change Commitment Level 0 (0x00) to 15 (0x0F). A value of 15 indicates that IPQoS processing is disabled in all the callout positions. Yes If you want to enable or disable IPQoS processing in any of the callout positions. Unstable SCTP Tunable Parameters _max_init_retr Description Default Range Dynamic? When to Change Commitment Level Change History Controls the maximum number of attempts an SCTP endpoint should make at resending an INIT chunk. The SCTP endpoint can use the SCTP initiation structure to override this value. 8 0 to 128 Yes The number of INIT retransmissions depend on "_pa_max_retr" on page 155. Ideally, _max_init_retr should be less than or equal to _pa_max_retr. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _pa_max_retr Description Default Range Dynamic? When to Change Controls the maximum number of retransmissions (over all paths) for an SCTP association. The SCTP association is aborted when this number is exceeded. 10 1 to 128 Yes The maximum number of retransmissions over all paths depend on the number of paths and the maximum number of retransmission over Chapter 5 · Internet Protocol Suite Tunable Parameters 155 SCTP Tunable Parameters Commitment Level Change History each path. Ideally, sctp_pa_max_retr should be set to the sum of "_pp_max_retr" on page 156 over all available paths. For example, if there are 3 paths to the destination and the maximum number of retransmissions over each of the 3 paths is 5, then _pa_max_retr should be set to less than or equal to 15. (See the Note in Section 8.2, RFC 2960.) Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _pp_max_retr Description Default Range Dynamic? When to Change Commitment Level Change History Controls the maximum number of retransmissions over a specific path. When this number is exceeded for a path, the path (destination) is considered unreachable. 5 1 to 128 Yes Do not change this value to less than 5. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _cwnd_max Description Default Range Dynamic? When to Change Commitment Level Controls the maximum value of the congestion window for an SCTP association. 1,048,576 128 to 1,073,741,824 Yes Even if an application uses setsockopt(3XNET) to change the window size to a value higher than _cwnd_max, the actual window used can never grow beyond _cwnd_max. Thus, "max_buf" on page 161 should be greater than _cwnd_max. Unstable 156 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Change History SCTP Tunable Parameters For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _ipv4_ttl Description Default Range Dynamic? When to Change Commitment Level Change History Controls the time to live (TTL) value in the IP version 4 header for the outbound IPv4 packets on an SCTP association. 64 1 to 255 Yes Generally, you do not need to change this value. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _ipv6_hoplimit Description Default Range Dynamic? When to Change Commitment Level Change History Sets the value of the hop limit in the IPv6 header for the outbound IPv6 packets on an SCTP association. 60 0 to 255 Yes Generally, you do not need to change this value. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _heartbeat_interval Description Computes the interval between HEARTBEAT chunks to an idle destination, that is allowed to heartbeat. Default An SCTP endpoint periodically sends an HEARTBEAT chunk to monitor the reachability of the idle destinations transport addresses of its peer. 30 seconds Chapter 5 · Internet Protocol Suite Tunable Parameters 157 SCTP Tunable Parameters Range Dynamic? When to Change Commitment Level Change History 0 to 86,400 seconds Yes Refer to RFC 2960, section 8.3. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _new_secret_interval Description Default Range Dynamic? When to Change Commitment Level Change History Determines when a new secret needs to be generated. The generated secret is used to compute the MAC for a cookie. 2 minutes 0 to 1,440 minutes Yes Refer to RFC 2960, section 5.1.3. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _initial_mtu Description Default Range Dynamic? When to Change Commitment Level Change History Determines the initial maximum send size for an SCTP packet including the length of the IP header. 1500 bytes 68 to 65,535 Yes Increase this parameter if the underlying link supports frame sizes that are greater than 1500 bytes. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. 158 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 SCTP Tunable Parameters _deferred_ack_interval Description Default Range Dynamic? When to Change Commitment Level Change History Sets the time-out value for SCTP delayed acknowledgment (ACK) timer in milliseconds. 100 milliseconds 1 to 60,000 milliseconds Yes Refer to RFC 2960, section 6.2. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _ignore_path_mtu Description Default Range Dynamic? When to Change Commitment Level Change History Enables or disables path MTU discovery. 0 (disabled) 0 (disabled) or 1 (enabled) Yes Enable this parameter if you want to ignore MTU changes along the path. However, doing so might result in IP fragmentation if the path MTU decreases. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _initial_ssthresh Description Default Range Dynamic? When to Change Commitment Level Sets the initial slow start threshold for a destination address of the peer. 1,048,576 1,024 to 4,294,967,295 Yes Refer to RFC 2960, section 7.2.1. Unstable Chapter 5 · Internet Protocol Suite Tunable Parameters 159 SCTP Tunable Parameters Change History For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. send_buf Description Default Range Dynamic? When to Change Commitment Level Change History Defines the default send buffer size in bytes. See also "max_buf" on page 161. 102,400 8,192 to the current value of "max_buf" on page 161 Yes An application can use setsockopt(3XNET) SO_SNDBUF to change the individual connection's send buffer. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _xmit_lowat Description Default Range Dynamic? When to Change Commitment Level Change History Controls the lower limit on the send window size. 8,192 8,192 to 1,073,741,824 Yes Generally, you do not need to change this value. This parameter sets the minimum size required in the send buffer for the socket to be marked writable. If required, consider changing this parameter in accordance with "send_buf" on page 160. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. recv_buf Description Defines the default receive buffer size in bytes. See also "max_buf" on page 161. 160 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 SCTP Tunable Parameters Default Range Dynamic? When to Change Commitment Level Change History 102,400 8,192 to the current value of "max_buf" on page 161 Yes An application can use setsockopt(3XNET) SO_RCVBUF to change the individual connection's receive buffer. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. max_buf Description Default Range Dynamic? When to Change Commitment Level Change History Controls the maximum send and receive buffer size in bytes. It controls how large the send and receive buffers are set to by an application that uses getsockopt(3SOCKET). 1,048,576 102,400 to 1,073,741,824 Yes Increase the value of this parameter to match the network link speed if associations are being made in a high-speed network environment. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _rto_min Description Default Range Dynamic? When to Change Commitment Level Change History Sets the lower bound for the retransmission timeout (RTO) in milliseconds for all the destination addresses of the peer. 1,000 500 to 60,000 Yes Refer to RFC 2960, section 6.3.1. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. Chapter 5 · Internet Protocol Suite Tunable Parameters 161 SCTP Tunable Parameters _rto_max Description Default Range Dynamic? When to Change Commitment Level Change History Controls the upper bound for the retransmission timeout (RTO) in milliseconds for all the destination addresses of the peer. 60,000 1,000 to 60,000,000 Yes Refer to RFC 2960, section 6.3.1. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _rto_initial Description Default Range Dynamic? When to Change Commitment Level Change History Controls the initial retransmission timeout (RTO) in milliseconds for all the destination addresses of the peer. 3,000 1,000 to 60,000,000 Yes Refer to RFC 2960, section 6.3.1. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _cookie_life Description Default Range Dynamic? When to Change Commitment Level Sets the lifespan of a cookie in milliseconds. 60,000 10 to 60,000,000 Yes Generally, you do not need to change this value. This parameter might be changed in accordance with "_rto_max" on page 162. Unstable 162 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Change History SCTP Tunable Parameters For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _max_in_streams Description Default Range Dynamic? When to Change Commitment Level Change History Controls the maximum number of inbound streams permitted for an SCTP association. 32 1 to 65,535 Yes Refer to RFC 2960, section 5.1.1. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _initial_out_streams Description Default Range Dynamic? When to Change Commitment Level Change History Controls the maximum number of outbound streams permitted for an SCTP association. 32 1 to 65,535 Yes Refer to RFC 2960, section 5.1.1. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _shutack_wait_bound Description Default Range Dynamic? Controls the maximum time, in milliseconds, to wait for a SHUTDOWN ACK after having sent a SHUTDOWN chunk. 60,000 0 to 300,000 Yes Chapter 5 · Internet Protocol Suite Tunable Parameters 163 SCTP Tunable Parameters When to Change Commitment Level Change History Generally, you do not need to change this value. This parameter might be changed in accordance with "_rto_max" on page 162. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _maxburst Description Default Range Dynamic? When to Change Commitment Level Change History Sets the limit on the number of segments to be sent in a burst. 4 2 to 8 Yes You do not need to change this parameter. You might change it for testing purposes. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _addip_enabled Description Default Range Dynamic? When to Change Commitment Level Change History Enables or disables SCTP dynamic address reconfiguration. 0 (disabled) 0 (disabled) or 1 (enabled) Yes The parameter can be enabled if dynamic address reconfiguration is needed. Due to security implications, enable this parameter only for testing purposes. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. _prsctp_enabled Description Enables or disables the partial reliability extension (RFC 3758) to SCTP. 164 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 SCTP Tunable Parameters Default Range Dynamic? When to Change Commitment Level Change History 1 (enabled) 0 (disabled) or 1 (enabled) Yes Disable this parameter if partial reliability is not supported in your SCTP environment. Unstable For information, see "SCTP Parameter Name Changes (Oracle Solaris 11)" on page 181. smallest_anon_port Description Unit Default Range Dynamic? When to Change Commitment Level Change History This parameter controls the smallest port number SCTP can select as an ephemeral port. An application can use an ephemeral port when it creates a connection with a specified protocol and it does not specify a port number. Ephemeral ports are not associated with a specific application. When the connection is closed, the port number can be reused by a different application. Port number 32,768 1,024 to 65,535 Yes When a larger ephemeral port range is required. Unstable For information, see "[tcp,sctp,udp]_smallest_anon_port and [tcp,sctp,udp]_largest_anon_port" on page 178. largest_anon_port Description Unit This parameter controls the largest port number SCTP can select as an ephemeral port. An application can use an ephemeral port when it creates a connection with a specified protocol and it does not specify a port number. Ephemeral ports are not associated with a specific application. When the connection is closed, the port number can be reused by a different application. Port number Chapter 5 · Internet Protocol Suite Tunable Parameters 165 Per-Route Metrics Default Range Dynamic? When to Change Commitment Level Change History 65,535 32,768 to 65,535 Yes When a larger ephemeral port range is required. Unstable For information, see "[tcp,sctp,udp]_smallest_anon_port and [tcp,sctp,udp]_largest_anon_port" on page 178. Per-Route Metrics You can use per-route metrics to associate some properties with IPv4 and IPv6 routing table entries. For example, a system has two different network interfaces, a fast Ethernet interface and a gigabit Ethernet interface. The system default recv_maxbuf is 128,000 bytes. This default is sufficient for the fast Ethernet interface, but may not be sufficient for the gigabit Ethernet interface. Instead of increasing the system's default for recv_maxbuf, you can associate a different default TCP receive window size to the gigabit Ethernet interface routing entry. By making this association, all TCP connections going through the route will have the increased receive window size. For example, the following is in the routing table (netstat -rn), assuming IPv4: 192.123.123.0 192.123.124.0 default 192.123.123.4 192.123.124.4 192.123.123.1 In this example, do the following: U 1 4 hme0 U 1 4 ge0 UG 1 8 # route change -net 192.123.124.0 -recvpipe x Then, all connections going to the 192.123.124.0 network, which is on the ge0 link, use the receive buffer size x, instead of the default 128,000 receive window size. If the destination is in the a.b.c.d network, and no specific routing entry exists for that network, you can add a prefix route to that network and change the metric. For example: # route add -net a.b.c.d 192.123.123.1 -netmask w.x.y.z # route change -net a.b.c.d -recvpipe y 166 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Per-Route Metrics Note that the prefix route's gateway is the default router. Then, all connections going to that network use the receive buffer size y. If you have more than one interface, use the -ifp argument to specify which interface to use. This way, you can control which interface to use for specific destinations. To verify the metric, use the route(1M) get command. Chapter 5 · Internet Protocol Suite Tunable Parameters 167 168 6C H A P T E R 6 System Facility Parameters This chapter describes most of the parameters default values for various system facilities. "autofs" on page 170 "cron" on page 170 "devfsadm" on page 170 "dhcpagent" on page 170 "fs" on page 171 "ftp" on page 171 "inetinit" on page 171 "init" on page 171 "ipsec" on page 172 "kbd" on page 172 "keyserv" on page 172 "login" on page 173 "mpathd" on page 173 "nfs" on page 173 "nfslogd" on page 173 "nss" on page 173 "passwd" on page 173 "su" on page 174 "syslog" on page 174 "tar" on page 174 "telnetd" on page 174 "utmpd" on page 174 169 System Default Parameters System Default Parameters The functioning of various system facilities is governed by a set of values that are read by each facility on startup. The values for each facility might be stored in a file for the facility located in the /etc/default directory, or in properties of a service instance in the Service Management Facility (SMF) configuration repository. For more information on SMF services and properties, see "Managing SMF Services" in Managing Services and Faults in Oracle Solaris 11.1. For information about setting power management properties, see Chapter 5, "Managing the System Console, Terminal Devices, and Power Services (Tasks)," in Managing System Information, Processes, and Performance in Oracle Solaris 11.1. autofs You can display or configure SMF autofs properties by using the sharectl command. For example: # sharectl get autofs timeout=600 automount_verbose=false automountd_verbose=false nobrowse=false trace=0 environment= # sharectl set -p timeout=200 autofs For details, see sharectl(1M). cron This facility enables you to disable or enable cron logging. devfsadm This file is not currently used. dhcpagent Client usage of DHCP is provided by the dhcpagent daemon. When ipadm is used to create a DHCP address object, or when ipadm identifies an interface that has been configured to receive its network configuration from DHCP, dhcpagent is started to manage an address on that interface. 170 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 System Default Parameters For more information, see the /etc/default/dhcpagent information in the FILES section of dhcpagent(1M). fs File system administrative commands have a generic and file system-specific portion. If the file system type is not explicitly specified with the -F option, a default is applied. The value is specified in this file. For more information, see the Description section of default_fs(4). ftp This facility enables you to set the ls command behavior to the RFC 959 NLST command. The default ls behavior is the same as in the previous Solaris release. For details, see ftp(4). inetinit This facility enables you to configure TCP sequence numbers and to enable or disable support for 6to4 relay routers. init System initialization properties are now part of the following SMF service: svc:/system/environment:init You can display and configure system initialization properties, such as TZ and LANG, by using similar syntax: # svccfg -s svc:/system/environment:init svc:/system/environment:init> setprop Usage: setprop pg/name = [type:] value setprop pg/name = [type:] ([value...]) Set the pg/name property of the currently selected entity. Values may be enclosed in double-quotes. Value lists may span multiple lines. svc:/system/environment:init> listprop umask application umask/value_authorization astring umask/umask astring upgrade application upgrade/skip_init_upgrade boolean solaris.smf.value.environment 022 false Chapter 6 · System Facility Parameters 171 System Default Parameters upgrade/value_authorization environment environment/LANG . . . astring application astring solaris.smf.value.environment C For more information, see the FILES section of init(1M). ipsec This facility enables you to configure parameters, such as IKE daemon debugging information and the ikeadm privilege level. kbd Keyboard configuration properties are now part of the following SMF service: svc:/system/keymap:default You display and configure keyboard properties by using similar syntax: # svccfg -s svc:/system/keymap:default svc:/system/keymap:default> setprop Usage: setprop pg/name = [type:] value setprop pg/name = [type:] ([value...]) Set the pg/name property of the currently selected entity. Values may be enclosed in double-quotes. Value lists may span multiple lines. svc:/system/keymap:default> listprop general framework general/complete astring general/enabled boolean keymap system keymap/console_beeper_freq integer keymap/kbd_beeper_freq integer keymap/keyboard_abort astring keymap/keyclick boolean . . . false 900 2000 enable false For more information, see kbd(1). keyserv For details, see the /etc/default/keyserv information in the FILES section of keyserv(1M). 172 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 System Default Parameters login For details, see the /etc/default/login information in the FILES section of login(1). mpathd This facility enables you to set in.mpathd configuration parameters. For details, see in.mpathd(1M). nfs You can display or configure SMF NFS properties by using the sharectl command. For example: # sharectl get nfs servers=1024 lockd_listen_backlog=32 lockd_servers=1024 lockd_retransmit_timeout=5 grace_period=90 server_versmin=2 server_versmax=4 client_versmin=2 client_versmax=4 server_delegation=on nfsmapid_domain= # sharectl set -p grace_period=60 nfs For details, see nfs(4). nfslogd For details, see the Description section of nfslogd(1M). nss This facility enables you to configure initgroups(3C) lookup parameters. For details, see nss(4). passwd For details, see the /etc/default/passwd information in the FILES section of passwd(1). Chapter 6 · System Facility Parameters 173 System Default Parameters su For details, see the /etc/default/su information in the FILES section of su(1M). syslog For details, see the /etc/default/syslogd information in the FILES section of syslogd(1M). tar For a description of the -f function modifier, see tar(1). If the TAPE environment variable is not present and the value of one of the arguments is a number and -f is not specified, the number matching the archiveN string is looked up in the /etc/default/tar file. The value of the archiveN string is used as the output device with the blocking and size specifications from the file. For example: % tar -c 2 /tmp/* This command writes the output to the device specified as archive2 in the /etc/default/tar file. telnetd This file identifies the default BANNER that is displayed upon a telnet connection. utmpd The utmpd daemon monitors /var/adm/utmpx (and /var/adm/utmp in earlier Solaris versions) to ensure that utmp entries inserted by non-root processes by pututxline(3C) are cleaned up on process termination. Two entries in /etc/default/utmpd are supported: SCAN_PERIOD The number of seconds that utmpd sleeps between checks of /proc to see if monitored processes are still alive. The default is 300. MAX_FDS The maximum number of processes that utmpd attempts to monitor. The default value is 4096 and should never need to be changed. 174 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 AA P P E N D I X A Tunable Parameters Change History This chapter describes the change history of specific tunable parameters. If a parameter is in this section, it has changed from a previous release. Parameters whose functionality has been removed are listed also. "Kernel Parameters" on page 175 "TCP/IP Tunable Parameters (Oracle Solaris 11 and 11.1)" on page 178 "Parameters That Are Obsolete or Have Been Removed (Oracle Solaris 11 and 11.1)" on page 182 Kernel Parameters General Kernel and Memory Parameters (Oracle Solaris 11 and 11.1) zfs_arc_min This parameter description is newly documented in the Oracle Solaris 11 release. For more information, see "zfs_arc_min" on page 82. In Oracle Solaris 11.1, the zfs_arc_min parameter information has moved to Chapter 3, "Oracle Solaris ZFS Tunable Parameters." zfs_arc_max This parameter description is newly documented in the Oracle Solaris 11 release. For more information, see "zfs_arc_max" on page 83. In Oracle Solaris 11.1, the zfs_arc_max parameter information has moved to Chapter 3, "Oracle Solaris ZFS Tunable Parameters." 175 Kernel Parameters disp_rechoose_interval This parameter is new in the Oracle Solaris 11 release. For more information, see "disp_rechoose_interval" on page 73. Paging-Related Parameters (Oracle Solaris 11) fastscan The default value of fastscan was clarified. For more information, see "fastscan" on page 46. Process-Sizing Tunables (Oracle Solaris 11.1) ngroups_max This parameter is newly documented in the Oracle Solaris 11 release. In the Oracle Solaris 11.1 release, the When to Change description was revised to include interaction information for AUTH_SYS authentication when this parameter is set to greater than 16. For more information, see "ngroups_max" on page 38. max_nprocs The default value of this parameter was updated in the Oracle Solaris 11.1 release. For more information, see "max_nprocs" on page 37. maxusers The default value of this parameter was updated in the Oracle Solaris 11.1 release. For more information, see "maxusers" on page 34. pidmax The default value of this parameter was updated in the Oracle Solaris 11.1 release. For more information, see "pidmax" on page 36. segkpsize The default value of this parameter was updated in the Oracle Solaris 11.1 release. For more information, see "segkpsize" on page 29. 176 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Kernel Parameters Swapping-Related Parameter (Oracle Solaris 11.1) swapfs_minfree The When to Change section of this parameter information was updated in the Oracle Solaris 11.1 release. For more information, see "swapfs_minfree" on page 51. General File System Parameter (Oracle Solaris 11.1) dnlc_dircache_percent This parameter is new in the Oracle Solaris 11.1 release. For more information, see "dnlc_dircache_percent" on page 65. General Driver Parameter (Oracle Solaris 11) ddi_msix_alloc_limit This parameter is newly documented in the Oracle Solaris 11 release. For more information, see "ddi_msix_alloc_limit" on page 55. Network Driver Parameters (Oracle Solaris 11) igb Parameters The igb network driver parameters are provided in the Oracle Solaris 11 release. For more information, see "igb Parameters" on page 56. ixgbe Parameters The ixgbe network driver parameters are provided in the Oracle Solaris 11 release. For more information, see "ixgbe Parameters" on page 57. Appendix A · Tunable Parameters Change History 177 TCP/IP Tunable Parameters (Oracle Solaris 11 and 11.1) TCP/IP Tunable Parameters (Oracle Solaris 11 and 11.1) [tcp,sctp,udp]_smallest_anon_port and [tcp,sctp,udp]_largest_anon_port These parameters are newly documented in the Oracle Solaris 11 release. "smallest_anon_port" on page 165 "largest_anon_port" on page 165 "smallest_anon_port" on page 146 "largest_anon_port" on page 146 "smallest_anon_port" on page 153 "largest_anon_port" on page 154 _local_slow_start_initial This parameter is newly documented in the Oracle Solaris 11.1 release. For more information, see "_local_slow_start_initial" on page 140. IP Parameter Name Changes (Oracle Solaris 11) The following IP parameters have been renamed to IP properties. You can set an IP property by using syntax similar to the following: # ipadm set-prop -p _icmp_err_interval=100 ip You can display IP property information by using syntax similar to the following: # ipadm show-prop -p _icmp_err_interval ip PROTO PROPERTY PERM CURRENT ip _icmp_err_interval rw 100 PERSISTENT DEFAULT 100 100 POSSIBLE 0-99999 TABLE A1 IP Parameter Name Changes Previous IP Parameter Name ip_addrs_per_if ip_forwarding ip6_forwarding ip_forward_src_routed IP Property Name _addrs_per_if forwarding (IPv4) forwarding (IPv6) _forward_src_routed (IPv4) 178 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 TCP/IP Tunable Parameters (Oracle Solaris 11 and 11.1) TABLE A1 IP Parameter Name Changes Previous IP Parameter Name ip6_forward_src_routed ip_icmp_err_interval ip_icmp_err_burst ip_icmp_return_data_bytes ip6_icmp_return_data_bytes ip_ire_pathmtu_interval ip_respond_to_echo_broadcast ip6_respond_to_echo_broadcast ip_respond_to_echo_multicast ip6_respond_to_echo_multicast ip_send_redirects ip6_send_redirects ip_strict_dst_multihoming (Continued) IP Property Name _forward_src_routed (IPv6) _icmp_err_interval _icmp_err_burst _icmp_return_data_bytes (IPv4) _icmp_return_data_bytes (IPv6) _pathmtu_interval _respond_to_echo_broadcast (IPv4) _respond_to_echo_broadcast (IPv6) _respond_to_echo_multicast (IPv4) _respond_to_echo_multicast (IPv6) _send_redirects (IPv4) _send_redirects (IPv6) hostmodel TCP Parameter Name Changes (Oracle Solaris 11) The following TCP parameters have been renamed to TCP properties. You can set a TCP property by using syntax similar to the following: # ipadm set-prop -p _deferred_ack_interval=100 tcp You can display TCP property information by using syntax similar to the following: # ipadm show-prop -p _deferred_ack_interval tcp PROTO PROPERTY PERM CURRENT PERSISTENT DEFAULT tcp _deferred_ack_interval rw 100 -- 100 TABLE A2 TCP Parameter Name Changes Previous TCP Parameter Name tcp_deferred_ack_interval tcp_local_dack_interval tcp_deferred_acks_max tcp_local_dacks_max TCP Property Name _deferred_ack_interval _local_dack_interval _deferred_acks_max _local_dacks_max POSSIBLE 1-60000 Appendix A · Tunable Parameters Change History 179 TCP/IP Tunable Parameters (Oracle Solaris 11 and 11.1) TABLE A2 TCP Parameter Name Changes Previous TCP Parameter Name tcp_wscale_always tcp_tstamp_always tcp_xmit_hiwat tcp_recv_hiwat tcp_max_buf tcp_cwnd_max tcp_slow_start_initial tcp_slow_start_after_idle tcp_sack_permitted tcp_rev_src_routes tcp_time_wait_interval tcp_ecn_permitted tcp_conn_req_max_q tcp_conn_req_max_q0 tcp_conn_req_min tcp_rst_sent_rate_enabled tcp_rst_sent_rate tcp_keepalive_interval tcp_ip_abort_interval tcp_rexmit_interval_initial tcp_rexmit_interval_max tcp_rexmit_interval_min tcp_rexmit_interval_extra tcp_tstamp_if_wscale tcp_recv_hiwat_minmss (Continued) TCP Property Name _wscale_always _tstamp_always send_buf recv_buf max_buf _cwnd_max _slow_start_initial _slow_start_after_idle sack _rev_src_routes _time_wait_interval ecn _conn_req_max_q _conn_req_max_q0 _conn_req_min _rst_sent_rate_enabled _rst_sent_rate _keepalive_interval _ip_abort_interval _rexmit_interval_initial _rexmit_interval_max _rexmit_interval_min _rexmit_interval_extra _tstamp_if_wscale _recv_hiwat_minmss 180 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 TCP/IP Tunable Parameters (Oracle Solaris 11 and 11.1) UDP Parameter Name Changes (Oracle Solaris 11) The following UDP parameters have been renamed to UDP properties. You can set a UDP property by using syntax similar to the following: # ipadm set-prop -p send_buf=57344 udp You can display UDP property information by using syntax similar to the following: # ipadm show-prop -p send_buf udp PROTO PROPERTY PERM CURRENT udp send_buf rw 57344 TABLE A3 UDP Parameter Name Changes Previous UDP Parameter Name udp_max_buf udp_xmit_hiwat udp_recv_hiwat PERSISTENT DEFAULT 57344 57344 UDP Property Name max_buf send_buf recv_buf POSSIBLE 1024-2097152 SCTP Parameter Name Changes (Oracle Solaris 11) The following SCTP parameters have been renamed to SCTP properties. You can set an SCTP property by using syntax similar to the following: # ipadm set-prop -p _max_init_retr=8 sctp You can display SCTP property information by using syntax similar to the following: # ipadm show-prop -p _max_init_retr sctp PROTO PROPERTY PERM CURRENT sctp _max_init_retr rw 8 PERSISTENT DEFAULT 8 8 POSSIBLE 0-128 TABLE A4 SCTP Parameter Name Changes Previous SCTP Parameter Name sctp_max_init_retr sctp_pa_max_retr sctp_pp_max_retr sctp_cwnd_max sctp_ipv4_ttl SCTP Property Name _max_init_retr _pa_max_retr _pp_max_retr _cwnd_max _ipv4_ttl Appendix A · Tunable Parameters Change History 181 Parameters That Are Obsolete or Have Been Removed (Oracle Solaris 11 and 11.1) TABLE A4 SCTP Parameter Name Changes Previous SCTP Parameter Name sctp_heartbeat_interval sctp_new_secret_interval sctp_initial_mtu sctp_deferred_ack_interval sctp_ignore_path_mtu sctp_initial_ssthresh sctp_ipv6_hoplimit sctp_xmit_lowat sctp_xmit_hiwat sctp_recv_hiwat sctp_max_buf sctp_rto_min sctp_rto_max sctp_rto_initial sctp_cookie_life sctp_max_in_streams sctp_initial_out_streams sctp_shutack_wait_bound sctp_maxburst sctp_addip_enabled sctp_prsctp_enabled (Continued) SCTP Property Name _heartbeat_interval _new_secret_interval _initial_mtu _deferred_ack_interval _ignore_path_mtu _initial_ssthresh _ipv6_hoplimit _xmit_lowat send_buf recv_buf max_buf _rto_min _rto_max _rto_initial _cookie_life _max_in_streams _initial_out_streams _shutack_wait_bound _maxburst _addip_enabled _prsctp_enabled Parameters That Are Obsolete or Have Been Removed (Oracle Solaris 11 and 11.1) The following section describes parameters that are obsolete or have been removed from more recent Oracle Solaris releases. 182 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Parameters That Are Obsolete or Have Been Removed (Oracle Solaris 11 and 11.1) NCA Parameters The network cache accelerator (NCA) parameter information is obsolete and has been removed. consistent_coloring This parameter is obsolete starting in the Oracle Solaris 11.1 release. rstchown This parameter is obsolete starting in the Oracle Solaris 11 release. Description Indicates whether the POSIX semantics for the chown system call are in effect. POSIX semantics are as follows: A process cannot change the owner of a file, unless it is running with UID 0. A process cannot change the group ownership of a file to a group in which it is not currently a member, unless it is running as UID 0. Data Type Default Range Units Dynamic? Validation When to Change Commitment Level For more information, see chown(2). Signed integer 1, indicating that POSIX semantics are used 0 = POSIX semantics not in force or 1 = POSIX semantics used Toggle (on/off) Yes None When POSIX semantics are not wanted. Note that turning off POSIX semantics opens the potential for various security holes. Doing so also opens the possibility of a user changing ownership of a file to another user and being unable to retrieve the file without intervention from the user or the system administrator. Obsolete Appendix A · Tunable Parameters Change History 183 Parameters That Are Obsolete or Have Been Removed (Oracle Solaris 11 and 11.1) Obsolete TCP/IP Module Parameters (Oracle Solaris 11) ip_multidata_outbound This parameter is obsolete in the Oracle Solaris 11 release. tcp_mdt_max_pbufs This parameter is obsolete in the Oracle Solaris 11 release. 184 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 BA P P E N D I X B Revision History for This Manual This section describes the revision history for this manual. "Current Version: Oracle Solaris 11.1 Release" on page 185 "New or Changed Parameters in the Oracle Solaris Release" on page 185 Current Version: Oracle Solaris 11.1 Release The current version of this manual applies to the Oracle Solaris 11.1 release. New or Changed Parameters in the Oracle Solaris Release The following sections describe new, changed, or obsolete kernel tunables. Oracle Solaris 11.1: Oracle Solaris ZFS tunable information is provided in Chapter 3, "Oracle Solaris ZFS Tunable Parameters." Oracle Solaris 11.1: The maxusers, max_nprocs, ngroups_max, pidmax, and segkpsize parameters have been revised in the Oracle Solaris 11.1 release. For more information, see Chapter 2, "Oracle Solaris Kernel Tunable Parameters." Oracle Solaris 11.1: The dnlc_dircache_percent parameter is new in the Oracle Solaris 11.1 release. For more information, see "dnlc_dircache_percent" on page 65. Oracle Solaris 11: The rstchown parameter is obsolete. For more information, see "What's New in Oracle Solaris System Tuning?" on page 17. Oracle Solaris 11: The ipadm command replaces the ndd command for setting TCP, IP, UDP, and SCTP properties. In addition, the names of the network parameters have changed to better correlate to the ipadm format. For more information, see "Overview of Tuning IP Suite Parameters" on page 127. Oracle Solaris 11: This release includes the disp_rechoose_interval parameter. For more information, see "disp_rechoose_interval" on page 73. 185 New or Changed Parameters in the Oracle Solaris Release Oracle Solaris 11: This release includes the ngroups_max parameter description. For more information, see "ngroups_max" on page 38. Oracle Solaris 11: This release includes the zfs_arc_min and zfs_arc_max parameter descriptions. For more information, see "zfs_arc_min" on page 82 and "zfs_arc_max" on page 83. Oracle Solaris 11 : This release includes several igb and ixgbe network driver parameters. For more information, see "igb Parameters" on page 56 and "ixgbe Parameters" on page 57. Oracle Solaris 11: This release includes the ddi_msix_alloc_limit parameter that can be used to increase the number of MSI-X interrupts that a device instance can allocate. For more information, see "ddi_msix_alloc_limit" on page 55. Oracle Solaris 11: This release includes the kmem_stackinfo parameter, which can be enabled to monitor kernel thread stack usage. For more information, see "kmem_stackinfo" on page 53. Oracle Solaris 11: Memory locality group parameters are provided in this release. For more information about these parameters, see "Locality Group Parameters" on page 78. Oracle Solaris 11: Parameter information was updated to include sun4v systems. For more information, see the following references: "maxphys" on page 61 "tmpfs:tmpfs_maxkmem" on page 66 "SPARC System Specific Parameters" on page 75 186 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 Index A _addip_enabled, 164 _addrs_per_if, 131 autofs, 170 autoup, 32 C _conn_req_max_q, 143 _conn_req_max_q0, 144 _conn_req_min, 144 _cookie_life, 162 cron, 170 _cwnd_max, 139, 156 D ddi_msix_alloc_limit parameter, 55 default_stksize, 26 default_tsb_size, 76 _deferred_ack_interval, 134, 159 _deferred_acks_max, 135 desfree, 41 dhcpagent, 170 disp_rechoose_interval, 73, 176 dnlc_dir_enable, 64 dnlc_dir_max_size, 65 dnlc_dir_min_size, 64 dnlc_dircache_percent, 65 doiflush, 33 dopageflush, 33 E ecn, 142 enable_tsb_rss_sizing, 77 F fastscan, 46 forwarding, 130 fs, 171 fsflush, 30 ftp, 171 H handspreadpages, 48 _heartbeat_interval, 157 hires_tick, 74 hoplimit (ipv6), 130 hostmodel, 131 I _icmp_err_burst, 128 _icmp_err_interval, 128 _icmp_return_data_bytes, 133 _ignore_path_mtu, 159 187 Index inetinit, 171 init, 172 _initial_mtu, 158 _initial_out_streams, 163 _initial_ssthresh, 159 intr_force, 56 intr_throttling, 58 _ip_abort_interval, 149 ip_squeue_fanout, 132 ip_squeue_worker_wait, 147 ipcl_conn_hash_size, 147 ipsec, 172 _ipv4_ttl, 157 _ipv6_hoplimit, 157 K kbd, 172 _keepalive_interval, 148 keyserv, 172 kmem_flags, 52 kmem_stackinfo, 53 L largest_anon_port, 146, 154, 165 lgrp_mem_pset_aware, 79 _local_dack_interval, 135 _local_dacks_max, 136 _local_slow_start_initial, 140 logevent_max_q_sz, 28 login, 173 lotsfree, 40 lpg_alloc_prefer, 78 lwp_default_stksize, 27 M max_buf (SCTP), 161 max_buf (TCP), 138 max_buf (UDP), 153 _max_in_streams, 163 _max_init_retr, 155 max_nprocs, 37, 176 maxpgio, 49 maxphys, 61 maxpid, 36 maxuprc, 37 maxusers, 34, 176 min_percent_cpu, 47 minfree, 42 moddebug, 54 mpathd, 173 mr_enable, 56 N ncsize, 63 ndd, 128 _new_secret_interval, 158 nfs_max_threads, 103 nfs:nacache, 116 nfs:nfs_allow_preepoch_time, 95 nfs:nfs_async_clusters, 113 nfs:nfs_async_timeout, 116 nfs:nfs_cots_timeo, 96 nfs:nfs_disable_rddir_cache, 111 nfs:nfs_do_symlink_cache, 98 nfs:nfs_dynamic, 99 nfs:nfs_lookup_neg_cache, 100 nfs:nfs_nra, 105 nfs:nfs_shrinkreaddir, 108 nfs:nfs_write_error_interval, 110 nfs:nfs_write_error_to_cons_only, 110 nfs:nfs3_async_clusters, 114 nfs:nfs3_bsize, 112 nfs:nfs3_cots_timeo, 96 nfs:nfs3_do_symlink_cache, 98 nfs:nfs3_dynamic, 100 nfs:nfs3_jukebox_delay, 117 nfs:nfs3_lookup_neg_cache, 101 nfs:nfs3_max_threads, 104 nfs:nfs3_max_transfer_size, 118 nfs:nfs3_max_transfer_size_clts, 120 nfs:nfs3_max_transfer_size_cots, 120 nfs:nfs3_nra, 106 188 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012 nfs:nfs3_pathconf_disable_cache, 94 nfs:nfs3_shrinkreaddir, 109 nfs:nfs4_async_clusters, 115 nfs:nfs4_bsize, 112 nfs:nfs4_cots_timeo, 97 nfs:nfs4_do_symlink_cache, 99 nfs:nfs4_lookup_neg_cache, 102 nfs:nfs4_max_threads, 105 nfs:nfs4_max_transfer_size, 119 nfs:nfs4_nra, 107 nfs:nfs4_pathconf_disable_cache, 94 nfs:nrnode, 107 nfslogd, 173 ngroups_max, 38 noexec_user_stack, 30 nss, 173 nstrpush, 70 O Oracle database tuning, ZFS file systems, 88 P pageout_reserve, 44 pages_before_pager, 48 pages_pp_maximum, 45 passwd, 173 _pathmtu_interval, 133 physmem, 26 pidmax, 36, 176 _policy_mask, 154 _pp_max_retr, 156 primarycache, ZFS file system property, 88 _prsctp_enabled, 164 pt_cnt, 68 pt_max_pty, 69 pt_pctofmem, 69 R recordsize, ZFS file system property, 87 Index recv_buf (SCTP), 160 recv_buf (TCP), 138 recv_buf (UDP), 152 _recv_hiwat_minmss, 151 reserved_procs, 35 _respond_to_echo_broadcast, 129 _respond_to_echo_multicast, 129 _rev_src_routes, 141 _rexmit_interval_extra, 151 _rexmit_interval_initial, 149 _rexmit_interval_max, 150 _rexmit_interval_min, 150 rlim_fd_cur, 62 rlim_fd_max, 61 rpcmod:clnt_idle_timeout, 122 rpcmod:clnt_max_conns, 121 rpcmod:cotsmaxdupreqs, 124 rpcmod:maxdupreqs, 123 rpcmod:svc_default_stksize, 122 rpcmod:svc_idle_timeout, 122 _rst_sent_rate, 145 _rst_sent_rate_enabled, 145 rstchown, 183 _rto_max, 162 _rto_min, 161 rx_copy_threshold, 60 rx_limit_per_intr, 58 rx_queue_number, 58 rx_ring_size, 59 S sack, 140 sctp_maxburst, 164 secondarycache, ZFS file system property, 88 segkpsize, 176 segspt_minfree, 72 send_buf (SCTP), 160 send_buf (TCP), 137 send_buf (UDP), 152 _send_redirects, 129 _shutack_wait_bound, 163 _slow_start_after_idle, 140 _slow_start_initial, 139 189 Index slowscan, 47 smallest_anon_port, 146, 153, 165 strmsgsz, 70, 71 su, 174 swapfs_minfree, 51, 177 swapfs_reserve, 50 syslog, 174 T tar, 174 throttlefree, 43 _time_wait_interval, 141 timer_max, 74 tmpfs_maxkmem, 66 tmpfs_minfree, 67 tsb_alloc_hiwater, 75 tsb_rss_factor, 77 _tstamp_always, 137 _tstamp_if_wscale, 151 ttl (ipv4), 130 tune_t_fsflushr, 31 tune_t_minarmem, 45 tx_copy_threshold, 60 tx_queue_number, 57 tx_ring_size, 59 U utmpd, 174 W _wscale_always, 136 X _xmit_lowat, 160 Z zfs_arc_max, 83, 175 zfs_arc_min, 82, 175 ZFS file system property primarycache, 88 recordsize, 87 secondarycache, 88 ZFS file systems, tuning for an Oracle database, 88 zfs_mdcomp_disable, 87 zfs_nocacheflush, 86 zfs_prefetch_disable, 84 190 Oracle Solaris 11.1 Tunable Parameters Reference Manual · November 2012Acrobat Distiller Server 6.0.1 (Sparc Solaris, Built: 2003-11-03)