atom feed19 messages in ru.sysoev.nginxRe: varnish?
FromSent OnAttachments
Ilan BerknerMar 29, 2009 3:59 pm 
Kiril AngovMar 29, 2009 4:56 pm 
Cliff WellsMar 29, 2009 8:29 pm 
Chris ZimmermanMar 29, 2009 9:10 pm 
russlndrApr 12, 2009 8:17 pm 
CryptWizardApr 12, 2009 10:54 pm 
jeff emmingerApr 13, 2009 6:34 am 
russlndrApr 13, 2009 7:04 am 
Barry AbrahamsonApr 14, 2009 8:59 am 
Victor IggyApr 14, 2009 3:55 pm 
Barry AbrahamsonApr 14, 2009 7:12 pm 
Floren MunteanuApr 14, 2009 8:39 pm 
Victor IggyApr 15, 2009 10:43 am 
Barry AbrahamsonApr 15, 2009 12:14 pm 
zepolenApr 15, 2009 5:58 pm 
Phillip B OldhamApr 16, 2009 12:20 am 
Barry AbrahamsonApr 16, 2009 7:47 am 
Barry AbrahamsonApr 16, 2009 7:52 am 
zepolenApr 17, 2009 1:59 pm 
Subject:Re: varnish?
From:Barry Abrahamson (bar@automattic.com)
Date:Apr 16, 2009 7:52:24 am
List:ru.sysoev.nginx

On Apr 16, 2009, at 3:20 AM, Phillip B Oldham wrote:

Barry Abrahamson wrote:

Yes, except the vast majority images are generated dynamically, so they don't exist on a filesystem anywhere :)

Wouldn't it be faster to have the image generation script push the file to a memcached store on creation, and have nginx check this store before falling back to the generation script?

Maybe, but speed isn't the main issue here, the requests are served generally "fast enough" Its scaling a single box to serve a huge number of requests/sec.

BTW, I enabled http keep alives in nginx, and it seems to have reduced softirq by about 5% which is pretty good. I guess setting up and tearing down all of those TCP connections has a little bit of overhead. We have sacrificed a little bit of RAM to deal with the huge number of established connections (50k ish), but thats ok. I'm wondering if there are even more optimizations like this which could reduce sofirq even more.

-- Barry Abrahamson | Systems Wrangler | Automattic Blog: http://barry.wordpress.com