Re: Varnish 2.0.6 nuking all my objects?
I have seen this happen. I have a similar hardware setup, though I changed the multi-ssd raid into 3 separate cache file arguments. We had roughly 240GB storage space total, after about 2-3 weeks and sm_bfree reached ~20GB. lru_nuked started incrementing, sm_bfree climbed to ~60GB, but lru_nuking never stopped. On Wed, Feb 24, 2010 at 8:15 PM, Barry Abrahamson ba...@automattic.com wrote: Howdy, We are finally getting around to upgrading to the latest version of varnish and are running into quite a weird problem. Everything works fine for a bit (1+day) , then all of a sudden Varnish starts nuking all of the objects from the cache: About 4 hours ago there were 1 million objects in the cache, now there are just about 172k. This looks a bit weird to me: sms_nbytes 18446744073709548694 . SMS outstanding bytes Here are the options I am passing to varnishd: /usr/local/sbin/varnishd -a 0.0.0.0: -f /etc/varnish/varnish.vcl -P /var/run/varnishd.pid -T 0.0.0.0:47200 -t 600 -w 1,200,300 -p thread_pools 4 -p thread_pool_add_delay 2 -p lru_interval 60 -h classic,59 -p obj_workspace 4096 -s file,/varnish/cache,150G /varnish is 2 x 80GB Intel X-25M SSDs in a software RAID 0 array. OS is Debian Lenny 64-bit. There is plenty of space: /dev/md0 149G 52G 98G 35% /varnish Here is the output of varnishstat -1 uptime 134971 . Child uptime client_conn 12051037 89.29 Client connections accepted client_drop 0 0.00 Connection dropped, no sess client_req 12048672 89.27 Client requests received cache_hit 10161272 75.28 Cache hits cache_hitpass 133244 0.99 Cache hits for pass cache_miss 1750857 12.97 Cache misses backend_conn 1824594 13.52 Backend conn. success backend_unhealthy 0 0.00 Backend conn. not attempted backend_busy 0 0.00 Backend conn. too many backend_fail 3644 0.03 Backend conn. failures backend_reuse 0 0.00 Backend conn. reuses backend_toolate 0 0.00 Backend conn. was closed backend_recycle 0 0.00 Backend conn. recycles backend_unused 0 0.00 Backend conn. unused fetch_head 5309 0.04 Fetch head fetch_length 1816422 13.46 Fetch with Length fetch_chunked 0 0.00 Fetch chunked fetch_eof 0 0.00 Fetch EOF fetch_bad 0 0.00 Fetch had bad headers fetch_close 0 0.00 Fetch wanted close fetch_oldhttp 0 0.00 Fetch pre HTTP/1.1 closed fetch_zero 0 0.00 Fetch zero len fetch_failed 16 0.00 Fetch failed n_srcaddr 0 . N struct srcaddr n_srcaddr_act 0 . N active struct srcaddr n_sess_mem 578 . N struct sess_mem n_sess 414 . N struct sess n_object 172697 . N struct object n_objecthead 173170 . N struct objecthead n_smf 471310 . N struct smf n_smf_frag 62172 . N small free smf n_smf_large 67978 . N large free smf n_vbe_conn 18446744073709551611 . N struct vbe_conn n_bereq 315 . N struct bereq n_wrk 76 . N worker threads n_wrk_create 3039 0.02 N worker threads created n_wrk_failed 0 0.00 N worker threads not created n_wrk_max 0 0.00 N worker threads limited n_wrk_queue 0 0.00 N queued work requests n_wrk_overflow 25136 0.19 N overflowed work requests n_wrk_drop 0 0.00 N dropped work requests n_backend 4 . N backends n_expired 771687 . N expired objects n_lru_nuked 744693 . N LRU nuked objects n_lru_saved 0 . N LRU saved objects n_lru_moved 8675178 . N LRU moved objects n_deathrow 0 . N objects on deathrow losthdr 25 0.00 HTTP header overflows n_objsendfile 0 0.00 Objects sent with sendfile n_objwrite 11749415 87.05 Objects sent with write n_objoverflow 0 0.00 Objects overflowing workspace s_sess 12051007 89.29 Total Sessions s_req 12050184 89.28 Total Requests s_pipe 2661 0.02 Total pipe s_pass 134858 1.00 Total pass s_fetch 1821721
varnish-cache.org is moving
Hi. We'll be moving varnish-cache.org on monday march the first around 11:00 CET. The site will be unavailable for about 5 minutes while we move it. We'll be getting a newer trac version but other than that there should be no user-noticable changes. At some point we will also move the mailing lists away from projects.linpro.no and onto varnish-cache.org. More on this when we have a date. Please let me know if you experience any problems. -- Per Andreas Buer, CEO, Varnish Software AS Phone: +47 21 54 41 21 / Mobile: +47 958 39 117 / skype: per.buer ___ varnish-misc mailing list varnish-misc@projects.linpro.no http://projects.linpro.no/mailman/listinfo/varnish-misc
Re: Varnish 2.0.6 nuking all my objects?
On Feb 25, 2010, at 12:47 PM, David Birdsong wrote: On Thu, Feb 25, 2010 at 8:41 AM, Barry Abrahamson ba...@automattic.com wrote: On Feb 25, 2010, at 2:26 AM, David Birdsong wrote: I have seen this happen. I have a similar hardware setup, though I changed the multi-ssd raid into 3 separate cache file arguments. Did you try RAID and switch to the separate cache files because performance was better? seemingly so. for some reason enabling block_dump showed that kswapd was always writing to those devices despite their not being any swap space on them. i searched around fruitlessly to try to understand the overhead of software raid to explain this, but once i discovered varnish could take on multiple cache files, i saw no reason for the software raid and just abandoned it. Interesting - I will try it out! Thanks for the info. We had roughly 240GB storage space total, after about 2-3 weeks and sm_bfree reached ~20GB. lru_nuked started incrementing, sm_bfree climbed to ~60GB, but lru_nuking never stopped. How did you fix it? i haven't yet. i'm changing up how i cache content, such that lru_nuking can be better tolerated. In my case, Varnish took a cache of 1 million objects, purged 920k of them. When there were 80k objects left the child restarted, thus dumping the remaining 80k :) -- Barry Abrahamson | Systems Wrangler | Automattic Blog: http://barry.wordpress.com ___ varnish-misc mailing list varnish-misc@projects.linpro.no http://projects.linpro.no/mailman/listinfo/varnish-misc
RE: Varnish and language cookie
Hello,
I am having hard time to to cache a multilingual web site. Vanish listen on
port 80 and proxy the request to a multilingual django cms what I would like
to do is to cache the pages per language and serve them from the
cache. Unfortunately so far I have not been able to get this working and
varnish keep on fetching th pages from the cms.
I am going to add below all the information I think useful do not hesitate
to let me know if you need more info ?
Here it is my configuration :
sub vcl_recv {
# clean out requests sent via curls -X mode and LWP
# http://varnish.projects.linpro.no/wiki/VCLExampleNormalizingReqUrl
if (req.url ~ ^http://;) {
set req.url = regsub(req.url, http://[^/]*;, );
}
# Set the backend based on the subdomain name
if (req.http.host == static.gwadeloop.com) {
set req.backend = static;
}
if (req.http.host == dev.gwadeloop.com) {
set req.backend = django;
# Add a trailing slash if missing
if ((req.url ~ [^\]$) (! (req.url ~ ^/media/))) {
set req.url = req.url /;
}
}
if (req.http.Cookie) {
# removes all cookies named __utm? (utma, utmb...) -- Google
Analytics
set req.http.Cookie = regsuball(req.http.Cookie, (^|; )
*__utm.=[^;]+;? *, \1);
if (req.http.Cookie == ) {
remove req.http.Cookie;
}
}
if (req.http.Cookie ~ django_language=) {
set req.http.X-Varnish-Language =
regsub(req.http.Cookie, django_language=([a-z]{2}), \1);
}
}
-
sub vcl_hash {
set req.hash += req.url;
if (req.http.host) {
set req.hash += req.http.host;
} else {
set req.hash += server.ip;
}
set req.hash += req.http.X-Varnish-Language;
return (hash);
}
-
here it is the information outputed by varnishlog when I try to access the
same page twice:
http://dpaste.com/163624/
I would be glad if someone could point me what I am doing wrong here.
Regards,
--yml
___
varnish-misc mailing list
varnish-misc@projects.linpro.no
http://projects.linpro.no/mailman/listinfo/varnish-misc
