Alex Rousskov wrote:
>
> On Tue, 6 Jun 2000, Hamid Reza Shahriari wrote:
>
> > Hi all,
> > I want to test my proxy server with Polygraph 2.2.9, like as bake-off #2.
> > First I have two linux machine for polyclt and polysrv. With Poly 1.3.2 and
> > best-effort no-proxy test, I got 150 req/sec.
>
> 150/sec on a best-effort no-proxy is quite low, I think. However, I do
> not remember much about ancient 1.3.2 version. Recent versions should do
> at least 300/sec on any reasonable, properly configured, hardware.
>
I upgraded client/server machines and could get 300/sec (noproxy) with
Poly-1.3.9. Since I didn't need, I didn't test higher rate.
> > I setup IP aliases client/server machines and changed polymix-2.pg:
> >
> > max RR=300 req/sec ==> servers=570, robots=750
> > addr[] srv_ips = ['10.100.129-131.1-190:8080' ];
> > addr[] rbt_ips = ['10.100.1-3.1-250' ];
> >
> > But in no-proxy test throughput is very low (20-30 req/sec), why?
>
> Two things I would check first are:
>
> - how many robots and servers were actually started
> (see binary log with lr or console log)
>
> - delayed ACK settings
> (delayed ACKs should be disabled;
> I do not know how to do that on Linux; FreeBSD instructions
> are on the "Tips" Polygraph Web page)
>
I was impatient and didn't wait for end of test! I saw reply rate in
warmup phase console output! warmup load_factor_beg was 0.1 so It was
30/sec!
I disabled delayed acks in linux using patches reachable from:
http://www.icase.edu/coral/LinuxTCP.html
I could get 300/sec with Poly-2.2.9 no-proxy test.
But I got some errors by polyclt:
002.06| i-warm 2914 47.91 2477 0.00 0 400
002.06| Connection.cc:172: error: 1/1 (104) Connection reset by peer
002.06| Connection.cc:172: error: 2/2 (104) Connection reset by peer
002.06| Connection.cc:172: error: 3/3 (104) Connection reset by peer
002.06| Connection.cc:172: error: 7/7 (104) Connection reset by peer
002.06| Connection.cc:197: error: 1/8 (11) Resource temporarily
unavailable
or
006.65| i-inc1 11784 42.00 2503 0.00 0 364
006.70| Connection.cc:172: error: 63/80 (104) Connection reset by peer
006.71| Connection.cc:172: error: 1/95 (32) Broken pipe
006.73| i-inc1 12091 72.91 2519 0.00 59 396
006.75| Connection.cc:172: error: 2/139 (32) Broken pipe
006.78| Connection.cc:197: error: 31/141 (11) Resource temporarily
unavailable
006.81| Connection.cc:172: error: 127/162 (104) Connection reset by peer
I have 128M RAM in both client/server, Max fds is 1024. Is this
efficient?
Thanks,
--Hamid
This archive was generated by hypermail 2b29 : Tue Jul 10 2001 - 12:00:13 MDT