On 08/03/2016 10:27 AM, Amos Jeffries wrote:
On 3/08/2016 9:45 p.m., Marcus Kool wrote:
On 08/03/2016 12:30 AM, Amos Jeffries wrote:
If thats not fast enough, you may also wish to patch in a larger value
for HTTP_REQBUF_SZ in src/defines.h to 64KB with a matching incease to
read_ahead_gap in squid.conf. That has had some mixed results though,
faster traffic, but also some assertions being hit.
I remember the thread about increasing the request buffer to 64K and it
looked so promising.
Is there any evidence of setting HTTP_REQBUF_SZ to 16K is stable in 3.5.x?
It has not had much testing other than Nathan's use, so I'm a bit
hesitant to call it stable. But just raising the 4KB limit a bit to 64K
or less should not have much effect negative effect other than extra RAM
per transaction for buffering (bumped x8 from 256KB per client
connection to 2MB).
I am about to configure an array of squid servers to process 50 gbit of traffic
and the performance increase that Nathan originally reported is significant...
So if I understand it correctly, raising it to 16K in 3.5.20
will most likely have no issues. I will give it a try.
Thanks
Marcus
We got a bit ambitious and made the main buffers dynamic and effectively
unlimited for Squid-4. But that hit an issue, so has been pulled out
while Nathan figures out how to avoid it.
Amos
_______________________________________________
squid-users mailing list
squid-users@lists.squid-cache.org
http://lists.squid-cache.org/listinfo/squid-users
_______________________________________________
squid-users mailing list
squid-users@lists.squid-cache.org
http://lists.squid-cache.org/listinfo/squid-users
