Managing NFS and KRPC Kernel Configurations in HP-UX 11i v2 (November 2013)

Note: The nfs_fine_grain_fs_lock tunable was first introduced

with patch PHNE_34550 and accepted only two values: 0

and 1. Beginning with patch PHNE_35118, the tunable is

modified to accept three values: 0, 1, and 2. If you set the

value to 2, verify that you have installed NFS patch

PHNE_36257 for a potential race condition fix

(SR:8606477797)

Restrictions on changing

The nfs_fine_grain_fs_lock tunable is dynamic. System reboot is not required to activate a change

made to this tunable. Changes made to the nfs_fine_grain_fs_lock tunable are applicable to all NFS

mounted filesystems.

Note: If there are no NFS mount points in the system, any

change made to the value of the tunable is effective

immediately. If there are NFS mount points in the system, a

system reboot is required for the change to be activated.

Modifying the value

Enable this tunable by setting the value of the tunable to 2. When the value is set to 2, alpha

semaphore contention is removed from all NFS client vnode operations

This tunable is not available in the next release of HP-UX. Starting with the HP-UX 11i v3 release the

alpha semaphore lock is not used by the NFS client.

2.1.6 nfs_new_lock_code

Description

The nfs_new_lock_code tunable controls the performance of asynchronous I/O against files that are

locked on NFS filesystems. By default, the client’s read-aheads and write-behinds are disabled when

an NFS client locks a file.

When nfs_new_lock_code is set to 1, NFS files that are completely locked (i.e. the entire contents of

the file are locked, as opposed to a partial file lock) can take advantage of asynchronous I/O. NFS

files with partial locks continue to use the original mechanism where asynchronous I/O is disabled.

Tested values

Default: 0 (Asynchronous I/O is disabled)

Min: 0

Max: 1 (Asynchronous I/O is enabled)

Restrictions on changing

The nfs_new_lock_code tunable is dynamic. System reboot is not required to activate a change made

to this tunable. Changes made to the nfs_new_lock_code tunable are applicable to all NFS mounted

filesystems.