Re: [squid-users] Filedescriptors

-----BEGIN PGP SIGNED MESSAGE-----

Morning all,
    Yeh, its me again. And as I had suspected the file desc problem
    was due to my own stupidity:

2002/09/11 09:14:50| With 32768 file descriptors available

    A remake of squid and I was sorted (thanks Colin).

    I actually do have no doubt it will go faster than 350reqs/per
sec.
    I think you underestimate it perhaps, although I'm cautious with
    my words as I'm sure you know it much better than I do; but you
    dont feel thats its mearly limited because of hardware?
                    As I've faith in FreeBSD (smile).

    How fast is it generally assumed squid will go with a massive
    amount of hardware - if it was to be used as an enterprise
    solution as such.

    Some stuff on my tests:

[CUT]
[... all +/- 150 per sec ...]
001.62| i-wait 14081 151.38 1511 50.92 0 241
001.70| i-wait 14841 151.93 1521 52.50 0 281
001.79| i-wait 15648 161.15 1649 49.57 0 254
001.87| i-wait 16315 133.13 2103 50.07 0 324
001.95| i-wait 16736 84.02 3149 49.64 0 636
002.04| i-wait 17197 92.18 4900 48.37 0 937
002.12| i-wait 17615 83.59 6456 55.50 0 1284
002.20| i-wait 17988 74.60 8375 49.06 0 1665
[CUT]

    Thats a small sample when it was set to do 150 per sec on the
    datacomm-1.pg testfile distributed with polygraph.
    After that it starts to slow down, as the disk gets more load.
    I should point out however, that I'm running with straight ufs,
and
    the drives are NOT mounted async. Its clearly the drives that are
    limiting me. I get the exact same results with 200 hits, and 250.
    (time wise - when it slows down)...

    At 75 it goes fine. up to 125 its fine really. as soon as I go
higher
    it dies out after about a while.

    Another test:

[CUT]
000.45| i-dflt 5300 241.79 4 0.00 0 1
000.53| i-dflt 6521 244.16 4 0.00 0 1
000.62| i-dflt 7735 242.73 4 0.00 0 1
000.70| i-dflt 8202 93.37 10 0.00 0 1
000.78| i-dflt 9276 214.77 4 0.00 0 1
000.87| i-dflt 10305 205.77 4 0.00 0 1
000.90| Xaction.cc:74: error: 1/1 (c19) unsupported HTTP status code
1031732110.157136# obj:
http://192.168.0.18:9090/w071db10b.54f61802:00000004/t01/_000006be
flags: basic,GET, xact: 071db10b.54f61802:00005410
HTTP/1.0 500 Internal Server Error
[CUT]

    Now this is something interesting. its using simple.pg; and
    automatically going to 240 odd requests. but then it dies
    with a ton of those messages above. And it happens at
    the same stage the whole time.

    Is that squid simply falling over due to low hardware spec's?
    It doesnt seem to happen on the other tests.

    I'm not sure if this is something that should be discussed on the
list.
    But I'd be keen to talk privately with you (Joe), or anyone else
    interested in helping me better the performance (on a low end
unit).

    Otherwise, thanks for the help so far everyone.
    If I make any startling discoveries I'll be sure to say.

Dave Raven.

- ----- Original Message -----
From: "Joe Cooper" <joe@swelltech.com>
To: "Dave Raven" <dave@reason.za.org>
Cc: <squid-users@squid-cache.org>
Sent: Wednesday, September 11, 2002 5:36 AM
Subject: Re: [squid-users] Filedescriptors

[...]

-----BEGIN PGP SIGNATURE-----
Version: PGPfreeware 7.0.3 for non-commercial use <http://www.pgp.com>

iQEVAwUBPX7+X7TAuMekS5e2AQEsLQf/R2AD6R/7TJZQTX30TzLAilZJ8KcrFX04
U7hXdVBwHGOvQ6kkdZk+YLFhv3Zk1dLYcFo9Y0YUWrFEkt9NWCoFr+W9+MzzHHWz
K1C81aB/yxSDWVKzGP4cbEeI1QDnQvZI+tiAyVN/wUQ1f1HmCoYALPx4w2Ptld/l
VQEL5YyIGc8TXkgp5+AnmUE5dWPAzO1YgHLXGDE24h7SJLyCz3irsUH4cmJTVmL7
O9F8//oezR/C9gf6MDW6PFYxTOiabPHedF72vL+knE7CGzElOCRnyznJU/HschdJ
SsM/aAq7zeTHKOyTydWvPlr/RnqVG6UZX/ak8K5j42rS8HXCUhCSFw==
=WZGw
-----END PGP SIGNATURE-----
Received on Wed Sep 11 2002 - 02:28:33 MDT