Jump to content United States-English
HP.com Home Products and Services Support and Drivers Solutions How to Buy
» Contact HP
More options
HP.com home
VERITAS File System 3.5 (HP OnlineJFS/JFS 3.5) Administrator's Guide: HP-UX 11i v2 > Chapter 2 VxFS Performance: Creating, Mounting, and Tuning File Systems

Kernel Tunables

» 

Technical documentation

Complete book in PDF
» Feedback
Content starts here

 » Table of Contents

 » Glossary

This section describes the kernel tunable parameters in VxFS. All kernel tunables can be set or changed using the sam or kctune commands (see the sam(1M) and kctune(1M) manual pages).

Internal Inode Table Size

VxFS caches inodes in an inode table. The kernel tunable vx_ninode determines the number of entries in the inode table.

vx_ninode is a static tunable that is initialized when VxFS is loaded, so any changes to vx_ninode cannot take effect until the next system reboot.By default, the initial value of vx_ninode is zero; the file system later computes a value based on the system memory size. The following example shows how to change the value of vx_ninode to 1,000,000: # kctune -s vx_ninode=1000000

VxFS Buffer Cache High Water Mark

VxFS maintains its own buffer cache in the kernel for frequently accessed file system metadata. This cache is different from the HP-UX kernel buffer cache that caches file data. The size of the VxFS buffer cache,, that is, the maximum amount of memory that can be used to cache VxFS metadata, is determined by the vxfs_bc_bufhwm tunable parameter.

By default, the initial value of vxfs_bc_bufhwm is zero ; the file system later computes a value based on the system memory size. The value of vxfs_bc_bufhwm is specified in kilobytes. The minimum acceptable value is 6144 kilobytes. The following example sets the VxFS buffer cache high water mark to 300,000 kilobytes. # kctune -s vxfs_bc_bufhwm=300000.

Typically, the default value computed by VxFS based on the amount of system memory ensures good system performance across a wide range of applications. For application loads that cause frequent file system metadata changes on the system (for example, a high rate of file creation or deletion, or accessing large directories), changing the value of vxfs_bc_bufhwm may improve performance.

You can use the vxfsstat command to monitor buffer cache statistics and inode cache usage (see the vxfsstat(1M) manual page).

Number of Links to a File

In VxFS, the number of possible links to a file can be configured by the vx_maxlink tunable. vx_maxlink is a static tunable that is initialized when VxFS is loaded, so any changes to vx_maxlink cannot take effect until the next system reboot. The default value of vx_maxlink is 32767, the maximum value is 65534. The following example sets the maximum number of links to a file to 40,000: # kctune -s vx_maxlink=40000

VxFS Inode Free Time Lag

In VxFS, an inode is put on a freelist if it is not being used. The memory space for this unused inode can be freed it it stays on the freelist for a specified amount of time. The vxfs_ifree_timelag tunable specifies the minimum amount of time an unused inode spends on a freelist before its memory space is freed.vxfs_ifree_timelag is a dynamic tunable. Any changes to vxfs_ifree_timelag take affect immediately. The default value of vxfs_ifree_timelag is 0. By setting vxfs_ifree_timelag to 0, the inode free timelag is autotuned to 1800 seconds. Specifying negative one (-1) stops the freeing of inode space; no further inode allocations are freed until the value is changed back to a value other than negative one.The following example changes the value of vxfs_ifree_timelag to 2400 seconds: # kctune -s vxfs_ifree_timelag=2400

NOTE: The default value vxfs_ifree_timelag typically provides optimal VxFS performance. Be careful when adjusting the tunable because incorrect tuning can adversely affect system performance.

VxVM Maximum I/O Size

When using VxFS with the VERITAS Volume Manager (VxVM), VxVM by default breaks up I/O requests larger than 256K. When using striping, to optimize performance, the file system issues I/O requests that are up to a full stripe in size. If the stripe size is larger than 256K, those requests are broken up.

See the VERITAS Volume Manager Administrator’s Guide for more information on avoiding I/O breakup by setting the maximum I/O tunable parameter.

Printable version
Privacy statement Using this site means you accept its terms Feedback to webmaster
© 2003 Hewlett-Packard Development Company, L.P.