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?
Just to double check, what happens if you specify 100% UNcachable traffic.
Does the box survive longer?
Also, when does garbage collection start kicking in? Is your disk cache
already full at the beginning of the test?
Alex.
Received on Tue Jul 29 2003 - 13:15:57 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:12:06 MST