varnish suddenly restarting / flushing itself after several hours? can ping response time be configure?

[Frank van Lingen]

I downloaded and compiled the latest version 2.0.6
I started varnish with just 40 threads: -p thread_pool_max=40

I then start it with:

varnishd -a :80 -s malloc,40M -p thread_pool_min=5 -p
thread_pool_max=40 -T localhost:6082 -f /etc/varnish/default.vcl

Using malloc makes things worse and I have more restarts so I switched
back to file:

varnishd -a :80 -p thread_pool_min=5 -p thread_pool_max=40 -T
localhost:6082 -f /etc/varnish/default.vcl -s
file,/var/cache/varnish.cache,40M

Everything works fine (the restart is graceful), but it is still
restarting (see below). I installed it on a non virtualized box and
have no problems with it. I suspect that it might have something to do
with the resources allocated to the VM.

Is there a way to configure the number of times it pings before restart?

Jan 12 06:15:20 server1 varnishd[1573]: Child (3576) said Ready
Jan 12 08:45:47 server1 varnishd[1573]: Child (3576) not responding to
ping, killing it.
Jan 12 08:45:47 server1 varnishd[1573]: Child (3576) not responding to
ping, killing it.
Jan 12 08:45:47 server1 varnishd[1573]: Child (3576) died signal=3
Jan 12 08:45:47 server1 varnishd[1573]: child (7996) Started
Jan 12 08:45:47 server1 varnishd[1573]: Child (7996) said Closed fds:
4 5 9 10 12 13
Jan 12 08:45:47 server1 varnishd[1573]: Child (7996) said Child starts
Jan 12 08:45:47 server1 varnishd[1573]: Child (7996) said managed to
mmap 41943040 bytes of 41943040
Jan 12 08:45:47 server1 varnishd[1573]: Child (7996) said Ready




On Mon, Jan 11, 2010 at 12:38 PM, Frank van Lingen <frank at vanlingen.name> wrote:
> From the varnish documentation I see that the threadpool max has a
> default of 1000 as I am doing some test on a (smal) VPS I reduced this
> number to 40 just to see if this might cause the problem.
>
> Frank.
>
>
> On Mon, Jan 11, 2010 at 12:22 PM, Frank van Lingen <frank at vanlingen.name> wrote:
>> Below the last messages. These are two restarts within the hour, but
>> most of the times it seems to run for several hours 4-8 without
>> problems.  I could not find any panic messages. I found some messages
>> in the varnish mailing list regarding this but the only ones I found
>> where 'died signal=6'
>>
>> JJan 10 18:17:22 server1 varnishd[14016]: Child (23771) not responding
>> to ping, killing it.
>> Jan 10 18:17:23 server1 varnishd[14016]: Child (23771) not responding
>> to ping, killing it.
>> Jan 10 18:17:23 server1 varnishd[14016]: Child (23771) died signal=3
>> Jan 10 18:17:23 server1 varnishd[14016]: child (25855) Started
>> Jan 10 18:17:23 server1 varnishd[14016]: Child (25855) said Closed
>> fds: 4 5 9 10 12 13
>> Jan 10 18:17:23 server1 varnishd[14016]: Child (25855) said Child starts
>> Jan 10 18:17:23 server1 varnishd[14016]: Child (25855) said managed to
>> mmap 41943040 bytes of 41943040
>> Jan 10 18:17:23 server1 varnishd[14016]: Child (25855) said Ready
>> Jan 10 18:49:43 server1 varnishd[14016]: Child (25855) not responding
>> to ping, killing it.
>> Jan 10 18:49:44 server1 varnishd[14016]: Child (25855) not responding
>> to ping, killing it.
>> Jan 10 18:49:44 server1 varnishd[14016]: Child (25855) died signal=3
>> Jan 10 18:49:44 server1 varnishd[14016]: child (5186) Started
>> Jan 10 18:49:44 server1 varnishd[14016]: Child (5186) said Closed fds:
>> 4 5 9 10 12 13
>> Jan 10 18:49:44 server1 varnishd[14016]: Child (5186) said Child starts
>> Jan 10 18:49:44 server1 varnishd[14016]: Child (5186) said managed to
>> mmap 41943040 bytes of 41943040
>> Jan 10 18:49:44 server1 varnishd[14016]: Child (5186) said Ready
>> Jan 10 20:13:43 server1 varnishd[14016]: Child (5186) not responding
>> to ping, killing it.
>> Jan 10 20:13:44 server1 varnishd[14016]: Child (5186) not responding
>> to ping, killing it.
>> Jan 10 20:13:44 server1 varnishd[14016]: Child (5186) died signal=3
>> Jan 10 20:13:44 server1 varnishd[14016]: child (13400) Started
>> Jan 10 20:13:44 server1 varnishd[14016]: Child (13400) said Closed
>> fds: 4 5 9 10 12 13
>> Jan 10 20:13:44 server1 varnishd[14016]: Child (13400) said Child starts
>> Jan 10 20:13:44 server1 varnishd[14016]: Child (13400) said managed to
>> mmap 41943040 bytes of 41943040
>> Jan 10 20:13:44 server1 varnishd[14016]: Child (13400) said Ready
>>
>> Jan 10 18:49:44 server1 varnishd[14016]: child (5186) Started
>>
>> --------------------------------------------
>> Frank van Lingen
>> email : frank at vanlingen.name
>> VOIP (skype) : fvlingen
>> IM (yahoo,hotmail) : fvlingen
>> IM (AIM) : frank at vanlingen.name
>> URL : http://vanlingen.name
>> LinkedIn : fvlingen
>> -------------------------------------------
>>
>>
>>
>> On Mon, Jan 11, 2010 at 9:49 AM, Poul-Henning Kamp <phk at phk.freebsd.dk> wrote:
>>> In message <458a97201001090528g12f87amfdd974e85f00f288 at mail.gmail.com>, Frank v
>>> an Lingen writes:
>>>
>>>>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.
>>>
>>> Check your syslog for panic messages from varnish, this should not
>>> happen in regular use.
>>>
>>> --
>>> Poul-Henning Kamp       | UNIX since Zilog Zeus 3.20
>>> phk at FreeBSD.ORG         | TCP/IP since RFC 956
>>> FreeBSD committer       | BSD since 4.3-tahoe
>>> Never attribute to malice what can adequately be explained by incompetence.
>>>
>>
>