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