From mboxrd@z Thu Jan 1 00:00:00 1970 From: teigland@sourceware.org Date: 7 Dec 2007 17:03:30 -0000 Subject: [Cluster-devel] cluster/group/man gfs_controld.8 Message-ID: <20071207170330.25863.qmail@sourceware.org> List-Id: To: cluster-devel.redhat.com MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit CVSROOT: /cvs/cluster Module name: cluster Changes by: teigland at sourceware.org 2007-12-07 17:03:30 Modified files: group/man : gfs_controld.8 Log message: new plock ownership related stuff Patches: http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/group/man/gfs_controld.8.diff?cvsroot=cluster&r1=1.1&r2=1.2 --- cluster/group/man/gfs_controld.8 2007/08/16 20:07:53 1.1 +++ cluster/group/man/gfs_controld.8 2007/12/07 17:03:29 1.2 @@ -33,12 +33,58 @@ gfs_controld manages cluster-wide posix locks for gfs and passes results back to gfs in the kernel. +.SH CONFIGURATION FILE + +Optional cluster.conf settings are placed in the section. + +.SS Posix locks + +Heavy use of plocks can result in high network load. The rate at which +plocks are processed are limited by the +.I plock_rate_limit +setting, which limits the maximum plock performance, and limits potentially +excessive network load. This value is the maximum number of plock operations +a single node will process every second. To achieve maximum posix locking +performance, the rate limiting should be disabled by setting it to 0. The +default value is 100. + + + +To optimize performance for repeated locking of the same locks by +processes on a single node, +.I plock_ownership +can be set to 1. The default is 0. If this is enabled, gfs_controld +cannot interoperate with older versions that did not support this option. + + + +Three options can be used to tune the behavior of the plock_ownership +optimization. All three relate to the caching of lock ownership state. +Specifically, they define how agressively cached ownership state is dropped. +More caching of ownership state can result in better performance, at the +expense of more memory usage. + +.I drop_resources_time +is the frequency of drop attempts in milliseconds. Default 10000 (10 sec). + +.I drop_resources_count +is the maximum number of items to drop from the cache each time. Default 10. + +.I drop_resources_age +is the time in milliseconds a cached item should be unused before being +considered for dropping. Default 10000 (10 sec). + + + + .SH OPTIONS .TP -\fB-l\fP -Limit the rate at which posix lock messages are sent to messages per -second. 0 disables the limit and results in the maximum performance of -posix locks. Default is 100. +\fB-D\fP +Run the daemon in the foreground and print debug statements to stdout. +.TP +\fB-P\fP +Enable posix lock debugging messages. .TP \fB-w\fP Disable the "withdraw" feature. @@ -46,17 +92,29 @@ \fB-p\fP Disable posix lock handling. .TP -\fB-D\fP -Run the daemon in the foreground and print debug statements to stdout. +\fB-l\fP +Limit the rate at which posix lock messages are sent to messages per +second. 0 disables the limit and results in the maximum performance of +posix locks. Default 100. .TP -\fB-P\fP -Enable posix lock debugging messages. +\fB-o\fP +Enable (1) or disable (0) plock ownership optimization. Default 0. All +nodes must run with the same value. .TP -\fB-V\fP -Print the version information and exit. +\fB-t\fP +Ownership cache tuning, drop resources time (milliseconds). Default 10000. +.TP +\fB-c\fP +Ownership cache tuning, drop resources count. Default 10. +.TP +\fB-a\fP +Ownership cache tuning, drop resources age (milliseconds). Default 10000. .TP \fB-h\fP Print out a help message describing available options, then exit. +.TP +\fB-V\fP +Print the version information and exit. .SH DEBUGGING The gfs_controld daemon keeps a circular buffer of debug messages that can