Re: Houston, I think we have a problem

From: Jan Harkes (jaharkes@cs.cmu.edu)
Date: Mon Apr 28 2003 - 01:15:08 EST


On Sun, Apr 27, 2003 at 12:52:49PM +0200, Mike Galbraith wrote:
> <SQUEAK! SQUEAK! SQUEAK!>
<description>

Hehe, at first I thought you were describing the excessive flamewars
where someone of 'low priority' downs a semaphore (flameworthy topic)
which then 'starves' useful discussions for several days. One good thing
is that is looks like fewer core developers seem to get sucked up in
these nowadays. (perhaps they have switched to some lockless RCU scheme?)

In any case, I have seen minute long stalls with 100% cpu usage about 3
or 4 times. I believe it started around the time the interactive
scheduler changes went in. One time it looked like the xserver, the
windowmanager and an inactive xterm were having a foodfight (when the
stall cleared a top showed 50%/25%/25% cpu usage for those processes).

Interestingly this was right after a reboot, so most of the 1GB of
memory was not used.

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



This archive was generated by hypermail 2b29 : Wed Apr 30 2003 - 22:00:28 EST