linux-kernel - Re: Scheduler regression: Too frequent timer interrupts(?)

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <alpine.DEB.1.10.0904171228380.7261@qirst.com>
Date:	Fri, 17 Apr 2009 12:33:48 -0400 (EDT)
From:	Christoph Lameter <cl@...ux.com>
To:	Peter Zijlstra <peterz@...radead.org>
cc:	Ingo Molnar <mingo@...e.hu>, linux-kernel@...r.kernel.org
Subject: Re: Scheduler regression: Too frequent timer interrupts(?)

On Fri, 17 Apr 2009, Peter Zijlstra wrote:

> As we've constituted, graph 1 is useless.

It certainly shows that the number of >1usec interrupts increases.

> I'm still not quite sure why you couldn't provide the data for the other
> graphs in email. They are not at all that much:

Could have but I thought I better focus on one.

> Graph 2: Noise Length
>
> Kernel          Test 1  Test 2  Test 3  Interruption(AVG)
> 2.6.22          2.55    2.61    1.92    2.36
> 2.6.23          1.33    1.38    1.34    1.35
> 2.6.24          1.97    1.86    1.87    1.90
> 2.6.25          2.09    2.29    2.09    2.16
> 2.6.26          1.49    1.22    1.22    1.31
> 2.6.27          1.67    1.28    1.18    1.38
> 2.6.28          1.27    1.21    1.14    1.21
> 2.6.29          1.44    1.33    1.54    1.44
> 2.6.30-rc2      2.06    1.49    1.24    1.60
>
> Is pretty useless too, since it only counts >1us events. Hence it will
> always be biased.

So what would be useful is to have all the differences in terms of
nanoseconds between measurements? I can just remove the cutoff and then
measure in tenth of usecs. That would be okay?

> You could for example run an NMI profiler at 10000 Hz and collect
> samples. Or use PMU hardware to collect numbers

The point is to have an test apps that can be used to measure OS noise
that may have a variety of causes.

Such a test app needs to be as simple as possible. The TSC loop should be
fine as far as I can tell. Histogram is already there. I can just remove
the 1usec cutoff to get you full details.

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