Re: High load average on disk I/O on 2.6.17-rc3



Erik Mouw wrote:
On Mon, May 08, 2006 at 04:55:48PM +0200, Arjan van de Ven wrote:

On Mon, 2006-05-08 at 07:24 -0700, Martin J. Bligh wrote:

It's pretty harmless though. The "load average" thing just means that the
extra pdflush threads are twiddling thumbs waiting on some disk I/O -
they'll later exit and clean themselves up. They won't be consuming
significant resources.

If they're waiting on disk I/O, they shouldn't be runnable, and thus
should not be counted as part of the load average, surely?

yes they are, since at least a decade. "load average" != "cpu
utilisation" by any means. It's "tasks waiting for a hardware resource
to become available". CPU is one such resource (runnable) but disk is
another. There are more ...


... except that any kernel < 2.6 didn't account tasks waiting for disk
IO. Load average has always been somewhat related to tasks contending
for CPU power. It's easy to say "shrug, it changed, live with it", but
at least give applications that want to be nice to the system a way to
figure out the real cpu load.

I had a patch to create a real, per-cpu load average. I guess I'll dig
it out again, since it was also extremely useful for diagnosing
scheduler issues.

Maybe I'm confused about what the loadavg figure in Linux was in 2.6,
I'll go read the code again. Not sure it's very useful to provide only
a combined figure of all waiting tasks without separated versions as
well, really.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/



Relevant Pages

  • Re: RAID Software Experiments
    ... Using bonnie++ to benchmark my configuration, ... Stewarts RAID-0 than on John-Paus Stewarts single disk. ... Above you were waiting for 7 minutes and 36.598 seconds. ... for your CPU is 7 minutes and 34.690 seconds. ...
    (comp.os.linux.hardware)
  • Re: RAID Software Experiments
    ... Using bonnie++ to benchmark my configuration, ... Stewarts RAID-0 than on John-Paus Stewarts single disk. ... Above you were waiting for 7 minutes and 36.598 seconds. ... for your CPU is 7 minutes and 34.690 seconds. ...
    (comp.os.linux.hardware)
  • Re: Delphi 7 and Pentium 4 issues
    ... application runs fine for the other 19-39 times and uses the 60% CPU. ... because it has to wait for the slow disk etc. ... Your app is still waiting, ... writing, since the time waiting blocked in the kernel is lost! ...
    (comp.lang.pascal.delphi.misc)
  • Re: Non-intel benchmarks on Conroe vs AMDs AM2 FX62
    ... Are you advocating waiting, for some future "shake-out" or price ... new and promising CPU? ... much better reason to wait than are future price reductions. ...
    (comp.sys.ibm.pc.hardware.chips)
  • RAID1 not save my system in case disk failure
    ... After dropping I/O operations on disk chained to ... Waiting Queue entries: ... Disconnected Queue entries: ... Please file a bug report against this driver. ...
    (Linux-Kernel)