Hi,
I've been profiling squid2.6S16, and reached a similar conclusion to Adrian's:
zeroing structures use about 2% of CPU usage, when squid as a hole is
using about 30%.
I did developed an optimization a little different than what Adrian
did: instead of leaving
large buffers untouched, I added an
On Sun, Sep 24, 2006, Guido Serassio wrote:
> Just a portability question:
> bzero() is deprecated and is not available on all platforms, memset()
> should be used instead.
I've fixed it in my local checkout. Could you give it a whirl (with the change
to memset() of course) and let me know if an
Hi Adrian,
At 09.20 24/09/2006, Adrian Chadd wrote:
Hiya,
Something thats been on the radar for a while but noone's actually done is
to modify the memory allocator to return non-zero'ed buffers where
appropriate.
I've written a patch which adds a couple of calls to the memory allocator
and m
Hiya,
Something thats been on the radar for a while but noone's actually done is
to modify the memory allocator to return non-zero'ed buffers where appropriate.
I've written a patch which adds a couple of calls to the memory allocator
and mempool allocator in squid-2.6 which doesn't zero the stri
