Varnish Lurker is getting slower / Ban lists keeps increasing
olivier.hanesse at gmail.com
Wed Aug 30 15:05:50 CEST 2017
Thanks for your reply. Now I understand better the definition of this
parameter (cache efficiency vs response time).
I've checked and I am really graphing the size of the ban list (using the
value "MAIN.bans" from varnishstat ). This value is the same that the
ban.list | wc -l" output.
I've just see that there is a "new" value in varnishstat
"MAIN.bans_lurker_obj_killed_cutoff". I will add this value to my
2017-08-30 14:37 GMT+02:00 Nils Goroll <slink at schokola.de>:
> Hi Olivier,
> I'm responding to the last two emails from you in one go
> On 30/08/17 08:47, Olivier Hanesse wrote:
> > What will happen when the ban list hits the size of bans defined in
> > value ?
> The ban lurker still works the list of bans as before, but when having
> the <ban_cutoff>th ban, we kill all objects hanging off these bans without
> testing the ban condition.
> This way, actively used objects (which get tested against the ban list at
> request time and will end up hanging off some ban near the top of the ban
> will not get killed, but rather only those which were least frequently
> (iow the long tail).
> On 30/08/17 11:44, Olivier Hanesse wrote:
> > Last night after your reply, I put a ban_cutoff value of 18500 according
> > the definition (50ms of latency, 370K/s ban.lurker.tested) (I've
> > varnish, "varnishadm param.show ban_cutoff" shows the right value)
> > This morning, nothing has changed : ban lists is increasing (well over
> > 18500).
> One obvious explanation would be that the lurker had not got to the cutoff
> But I wonder what exactly you are measuring here. In your first email you
> On 29/08/17 18:19, Olivier Hanesse wrote:
> > our ban list keeps increasing to reach 100K objects (and sometimes more).
> This makes me guess that maybe you'd be graphing the number of objects
> off the bans. Quick reminder:
> * the second column in the varnishadm ban.list output is the number of
> objects associated with this ban (objects, for which this ban has
> last been tested)
> * what the ban_cutoff parameter is limiting is the number of bans
> (that would be varnishadm ban.list | wc -l minus 2)
> So can you please double check that you are graphing the latter and not the
> former for ban.list?
> If you'd actually be graphing the former, then we don't have a problem as
> will just be the total number of objects in your cache.
> Thanks, Nils
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the varnish-misc