varnish suddenly restarting / flushing itself after several hours?

David Birdsong david.birdsong at gmail.com
Sun Jan 10 05:00:33 CET 2010


The parent will restart the child if it becomes unresponsive to pings. This
can happen for multiple reasons.  Do you have historical metrics for the
server that you can examine to see if load goes up or idle cpu goes down or
if memory is consumed?

(Sorry for the top post, friggin mobile device)

On Jan 9, 2010 5:34 AM, "Frank van Lingen" <frank at vanlingen.name> wrote:

Hello,

After setting up varnish and starting it I looked at the statistics
using varnsihstat. The timer in the left uppper corner seems to be the
uptime since it last started or was flushed. When I loaded some pages,
I can see the cache is working

But I notice that once every so often the cache seems to either flush
itself or restart. During this 2-3 seconds that this happens I can not
load any pages.

Is there a default 'cash flush' value that makes this (for me
undesirable) behavior happen?

I added the example described in
http://varnish.projects.linpro.no/wiki/VCLExampleLongerCaching to my
vcl file, but if the cash flushes itself a couple of times per day
then it defeats the purpose.

I am using varnish-2.0.5-1.el5 on centos5 and use the default.vcl file
with the above longer caching example added to it and ignore swf and
pdf files. I start varnish with 40 MB of cache and test this with a
few html pages and jpgs (less then 15 MB in size). During tests
normally not more than 50% of the cache is used.

Besides this issue varnish seems to work almost right out of the box.

Frank.
_______________________________________________
varnish-misc mailing list
varnish-misc at projects.linpro.no
http://projects.linpro.no/mailman/listinfo/varnish-misc
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://www.varnish-cache.org/lists/pipermail/varnish-misc/attachments/20100109/2e8b0f57/attachment-0001.html>


More information about the varnish-misc mailing list