Re: Squid 2.x performance curioisities

Alex Rousskov wrote:
>
> On Mon, 26 Apr 1999, Dancer wrote:
>
> > So, at 120/sec the test runs along for nearly an hour. Around the time
> > we are getting to say 300MB in the disk _buffers_ (the stuff that linux
> > allocates unused memory to, to avoid confusion at this juncture), the
> > capacity of the box to handle proxy requests suddenly dips below
> > 120/sec, and the number of in-use connections in polyclt begins to rise
> > sharply. Within two minutes, the test run aborts.
>
> At 120req/sec, polymix#1 will pull about 2GB of unique cachable objects
> through Squid:
> 3600sec * 120req/sec * 0.80%cachable * 0.45%miss * 13KB ~= 2GB.
> Thus, I would expect disk buffers to become full much sooner than one hour.
> Why does it take so long?

Good question. Something that's been nagging at me is that the number of
blocks involved seems much lower than I am expecting. Hrm.

> Just to double check, what happens if you specify 100% UNcachable traffic.
> Does the box survive longer?

I can find out. I'll queue that up as the next test.

> Also, when does garbage collection start kicking in? Is your disk cache
> already full at the beginning of the test?

It was empty at the start of the tests. I've been letting it fill, but
it's not hit 10% yet, so no...no garbage collection at all.

D
Received on Tue Jul 29 2003 - 13:15:57 MDT