Bad VM behaivor [2.2.2]

Stephan =?ISO-8859-1?Q?Engstr=F6m (sem@devedge.net)
Fri, 05 Mar 1999 18:54:35 +0100

We have had some problem with a webserver that is under very high load.
When
I try to investigate this problem further on another machine it is quite
clear
that it is some sort of bad VM behaivor. I made a test app that forks
256 times and then tries to connect to apache on the same machine, and
apache stops and must be restarted.

Trying to run anything results in a "couldn't allocate memory" error.
Top
report follows:

------------
6:46pm up 8 days, 3:55, 9 users, load average: 1.91, 1.02, 1.05
295 processes: 270 sleeping, 18 running, 7 zombie, 0 stopped
CPU states: 10.6% user, 17.3% system, 0.0% nice, 74.4% idle
Mem: 128012K av, 123944K used, 4068K free, 129932K shrd, 21248K buff
Swap: 130748K av, 656K used, 130092K free 22540K
cached
-------------

Under 2.0.36 this works OK.
The machine is a PII 350, RedHat 5.2 + few updates, kernel 2.2.2.
The machine is stable all the time.

Am I the only person bitten by this one?

Regards

Stephan Engström

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/