best version for server?
We're not sure if it is something we've done or just increased usage, but bkbits.net is getting hammered lately. We see load averages in ~15-20 range pretty regularly. It's got some nasty characteristics from the point of view of server/VM system, tons of data and not really any good working sets. I'm running 2.4.5 on it and that clearly has to go. I am going to try the rmap kernel but I'm open to other suggestions.
Signature · 2 lines
--- Larry McVoy lm at bitmover.com http://www.bitmover.com/lm
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
Larry McVoy wrote:
| We're not sure if it is something we've done or just increased usage, but | bkbits.net is getting hammered lately. We see load averages in ~15-20 | range pretty regularly. It's got some nasty characteristics from the | point of view of server/VM system, tons of data and not really any good | working sets. I'm running 2.4.5 on it and that clearly has to go. I am | going to try the rmap kernel but I'm open to other suggestions.
I've been running 2.4.17 + O(1) patch for a while on a pretty heavily loaded server (dual CPU) and it works like a charm.
I've put 2.4.19+O(1) on the test machine, it seems to behave OK.
2.4.1[7,9] have Andrea's VM BTW.
I think I still have the sources of the 2.4.17 O(1) patch... somewhere, if you want to try, just email me.
Cheers,
- --
F. CAMI
- ---------------------------------------------------------- ~ "To disable the Internet to save EMI and Disney is the moral equivalent of burning down the library of Alexandria to ensure the livelihood of monastic scribes."
~ - John Ippolito (Guggenheim)
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.0.7 (GNU/Linux)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org
iD8DBQE9oahCuBGY13rZQM8RAsjiAJ9GVYb9V/xj28noF/GmjIpVv13IbwCfQU4t V8GUthptR6y3lUVKNONLtPY=
=Wy/K
-----END PGP SIGNATURE-----
Quoted 5 lines · Larry McVoy
We're not sure if it is something we've done or just increased usage, but bkbits.net is getting hammered lately. We see load averages in ~15-20 range pretty regularly. It's got some nasty characteristics from the point of view of server/VM system, tons of data and not really any good working sets.
There are a few things that could help here:
1) Andrew Morton's io scheduler patch (read-latency2), which is in the -rmap kernel
2) reducing the number of outstanding IO commands in the 3ware controller/driver, so akpm's io scheduler gets a chance to do its work
3) better readahead, if possible...
regards,
Rik
Signature · 5 lines
Bravely reimplemented by the knights who say "NIH". http://www.surriel.com/ http://distro.conectiva.com/ Spamtraps of the month: [email protected] [email protected]
Quoted 6 lines · Larry McVoy
We're not sure if it is something we've done or just increased usage, but bkbits.net is getting hammered lately. We see load averages in ~15-20 range pretty regularly. It's got some nasty characteristics from the point of view of server/VM system, tons of data and not really any good working sets. I'm running 2.4.5 on it and that clearly has to go. I am going to try the rmap kernel but I'm open to other suggestions.
I think your being slashdotted..
Gerhard
--
Gerhard Mack
<>< As a computer I find your faith in technology amusing.