Swapping & High Load

[Sean Allen]

We have a varnish 3 server that was performing fine that we just increased
malloc size to as we started pulling a lot more data through it.

Malloc is 6 gigs.
We gave the entire machine 7.5 gigs

And we started using a couple gigs of swap being used which lead to load
average rapidly climbing.

Does Varnish need additional memory beyond what is allocated via malloc?
For all our other services that are running on this version of cent/os, 1.5
gigs for OS has been fine.

Specific version of varnish is:

(varnish-3.0.3 revision 9e6a70f)

sysconfig/varnish is:

# -*- mode: conf-unix -*-
#
# Configuration file for varnish
#
# This file is managed by puppet.
# Local changes will be reverted.
#
# /etc/init.d/varnish expects the variable $DAEMON_OPTS to be set from this
# shell script fragment.
#

# Maximum number of open files (for ulimit -n)
NFILES=131072

# Locked shared memory (for ulimit -l)
# Default log size is 82MB + header
MEMLOCK=82000

# Maximum size of corefile (for ulimit -c). Default in Fedora is 0
# DAEMON_COREFILE_LIMIT="unlimited"

# Listen on port 6081, administration on localhost:6082, and forward to
# one content server selected by the vcl file, based on the request.  Use a
# fixed-size cache file.
#
# Without "ban_lurker_sleep," nothing banned from the cache ever gets
evicted.
#
DAEMON_OPTS="-a :6081 \
             -T :6082 \
             -f /etc/varnish/default.vcl \
             -u varnish -g varnish \
             -p thread_pool_min=500 \
             -p thread_pool_max=5000 \
             -s malloc,6G \
             -p thread_pools=2 \
             -p thread_pool_add_delay=1 \
             -p ban_lurker_sleep=60s"

If varnish/default.vcl is needed, please let me know.

Running on a vmware vm with 2 cores.


-- 

Ce n'est pas une signature
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://www.varnish-cache.org/lists/pipermail/varnish-misc/attachments/20130319/db3f245d/attachment.html>