Need help: Varnish unexpectedly flushing cache weekly

[Joshua Levine]

I sent that reply explicit to crashes, crashes that actually appear addressed in your version, so I should also have asked, based on your references to a somewhat regular schedule, if you are using MALLOC or FILE, and also what you are allowing for NFILES… perhaps you are exceeding those resource allocations?

Cheers,
Joshua

On Aug 24, 2011, at 9:09 AM, Jordi Salvat wrote:

> Hi,
> 
> we restarted our Varnish instance on Sunday 7th around 19:00.
> 
> On Wednesday 10th 9:45 the child process restarted (causes unknown) -- loosing the existing cache.
> 
> ... the cache slowly grew again ....
> 
> On Wednesday 17th around 2:00, the cache was somehow flushed, loosing about 75% of its objects.
> 
> ... the cache slowly grew again ....
> 
> On Wednesday 24th at 2:00, the cache was flushed again, loosing about 85% of its objects.
> 
> On each of these occasions our cache hit rate went down from ~90% to under 50%. Needless to say this is highly undesirable.
> 
> What might be causing this behaviour? Any hints and directions helping research welcome.
> 
> Thanks.
> 
> More details:
> 
> Varnish version: 2.1.5 (Debian lenny package 2.1.5-1~lenny4)
> O.S.: Linux s229-161 2.6.38 #1 SMP Sat Mar 26 09:51:44 CET 2011 x86_64 GNU/Linux
> 
> MRTG daily graphs for cache size and objects in cache:
> 
> <varnish_cache-day.png>
> 
> <varnish_objects-day.png>
> 
> Note how the two graphs are slightly different: size goes down between 2:00 and 15:30, object count goes down suddenly at 15:30.
> 
> Main VCL file attached (long to read -- feel free to ask questions).
> 
> -- 
> Jordi Salvat i Alabart
> CTO & Project Manager
> Salir.com
> +34 676 49 86 00
> <salir.vcl>_______________________________________________
> varnish-misc mailing list
> varnish-misc at varnish-cache.org
> https://www.varnish-cache.org/lists/mailman/listinfo/varnish-misc