* [Cluster-devel] cluster/group/man gfs_controld.8
@ 2007-12-07 17:03 teigland
0 siblings, 0 replies; 2+ messages in thread
From: teigland @ 2007-12-07 17:03 UTC (permalink / raw)
To: cluster-devel.redhat.com
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 <gfs_controld> 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.
+
+ <gfs_controld plock_rate_limit="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.
+
+ <gfs_controld plock_ownership="1"/>
+
+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).
+
+ <gfs_controld drop_resources_time="10000" drop_resources_count="10"
+ drop_resources_age="10000"/>
+
+
.SH OPTIONS
.TP
-\fB-l\fP <num>
-Limit the rate at which posix lock messages are sent to <num> 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 <num>
+Limit the rate at which posix lock messages are sent to <num> 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 <num>
+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 <ms>
+Ownership cache tuning, drop resources time (milliseconds). Default 10000.
+.TP
+\fB-c\fP <ms>
+Ownership cache tuning, drop resources count. Default 10.
+.TP
+\fB-a\fP <ms>
+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
^ permalink raw reply [flat|nested] 2+ messages in thread
* [Cluster-devel] cluster/group/man gfs_controld.8
@ 2007-12-07 17:05 teigland
0 siblings, 0 replies; 2+ messages in thread
From: teigland @ 2007-12-07 17:05 UTC (permalink / raw)
To: cluster-devel.redhat.com
CVSROOT: /cvs/cluster
Module name: cluster
Branch: RHEL5
Changes by: teigland at sourceware.org 2007-12-07 17:05:09
Modified files:
group/man : gfs_controld.8
Log message:
bz 359271
new plock ownership related stuff
Patches:
http://sourceware.org/cgi-bin/cvsweb.cgi/cluster/group/man/gfs_controld.8.diff?cvsroot=cluster&only_with_tag=RHEL5&r1=1.1.2.1&r2=1.1.2.2
--- cluster/group/man/gfs_controld.8 2007/08/22 14:15:22 1.1.2.1
+++ cluster/group/man/gfs_controld.8 2007/12/07 17:05:09 1.1.2.2
@@ -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 <gfs_controld> 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.
+
+ <gfs_controld plock_rate_limit="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.
+
+ <gfs_controld plock_ownership="1"/>
+
+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).
+
+ <gfs_controld drop_resources_time="10000" drop_resources_count="10"
+ drop_resources_age="10000"/>
+
+
.SH OPTIONS
.TP
-\fB-l\fP <num>
-Limit the rate at which posix lock messages are sent to <num> 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 <num>
+Limit the rate at which posix lock messages are sent to <num> 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 <num>
+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 <ms>
+Ownership cache tuning, drop resources time (milliseconds). Default 10000.
+.TP
+\fB-c\fP <ms>
+Ownership cache tuning, drop resources count. Default 10.
+.TP
+\fB-a\fP <ms>
+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
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2007-12-07 17:05 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-12-07 17:05 [Cluster-devel] cluster/group/man gfs_controld.8 teigland
-- strict thread matches above, loose matches on Subject: below --
2007-12-07 17:03 teigland
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.