10 hour live-test
Anders Berg
andersb at vgnett.no
Sun Jul 23 12:16:14 CEST 2006
On Jul 23, 2006, at 10:08, Poul-Henning Kamp wrote:
>
> Varnish has run overnight at Alteon weight=1.
>
> Here is a snapshot of relevant stats at 10 hours:
>
> 10:00:00
> Hitrate ratio: 10 100 1000
> Hitrate avg: 0.9604 0.9763 0.9313
>
> 99678 4.00 2.77 Client connections accepted
> 787265 36.96 21.87 Client requests received
> 748108 35.96 20.78 Cache hits
> 35 0.00 0.00 Cache hits for pass
> 36981 1.00 1.03 Cache misses
> 39180 1.00 1.09 Backend connections initiated
> 18215 0.00 0.51 N struct object
> 17226 0.00 0.48 N struct objecthead
> 19971 2.00 0.55 N struct smf
> 20218 0.00 0.56 N expired objects
> 36 0.00 0.00 HTTP header overflows
> I need to look into these
>
> 99499 4.00 2.76 Total Sessions
> 787263 35.96 21.87 Total Requests
> 53 0.00 0.00 Total pipe
> 2196 0.00 0.06 Total pass
> 36894 0.00 1.02 Total fetch
> 17262774889 8164.48 479521.52 Total header bytes
> 3709537800 208307.57 103042.72 Total body bytes
>
> I find it interesting that we have sent almost five times as many
> headerbytes as bodybytes. I wonder if somebody did a HEAD on the
> entire site overnight.
That was alot of head's :) Though it could be that we get browsers to
only send IMS's, like they really should when the content is not new.
I guess a quick look in the logfiles will show what has happend.
Anders Berg
> Process RSS size was 439MB
>
> --
> 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.
> _______________________________________________
> varnish-dev mailing list
> varnish-dev at projects.linpro.no
> http://projects.linpro.no/mailman/listinfo/varnish-dev
>
More information about the varnish-dev
mailing list