Strategies for splitting load across varnish instances? And avoiding single-point-of-failure?

Poul-Henning Kamp phk at
Mon Jan 18 21:50:05 CET 2010

In message <14B75F07-969A-43D1-8CC9-9605A2642C9C at>, Ken Brownfield wri

>> If you receive more than 100 requests/sec per Varnish instance and you 
>use a disk cache, you will die.  
>I was surprised by this, what appears to be grossly irresponsible 
>guidance, given how large the installed base is that does thousands per 
>second quite happily.

Just for the record:  I didn't comment onthat one, since I sort of
assumed that everybody could see that a blanket statement like that
could never be universally true.

Obviously, if your 100 requests are for DVD images, you have tough
row to hoe when it comes to designing a disk subsystem, but for
more reasonable loads, the above is patently wrong.

And yes, if your're worried about diskperformance SSD is the way
to go.


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.

More information about the varnish-misc mailing list