linux-kernel - Re: large intermittent latency spike 2.6.28 (and 2.6.27.10), bisect commit ca7e716c7833aeaeb8fedd6d004c5f5d5e14d325 -> Revert "sched_clock: prevent scd->clock from moving backwards"

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <495BF1BD.1070408@jaysonking.com>
Date:	Wed, 31 Dec 2008 16:27:09 -0600
From:	Jayson King <dev@...sonking.com>
To:	arjan@...ux.intel.com
CC:	linux-kernel@...r.kernel.org, mingo@...e.hu,
	torvalds@...ux-foundation.org, a.p.zijlstra@...llo.nl,
	shaggy@...ux.vnet.ibm.com, rjw@...k.pl, fabio.comolli@...il.com
Subject: Re: large intermittent latency spike 2.6.28 (and 2.6.27.10), bisect
 commit ca7e716c7833aeaeb8fedd6d004c5f5d5e14d325 -> Revert "sched_clock: prevent
 scd->clock from moving backwards"

Arjan van de Ven wrote:
 > Jayson King <dev@...sonking.com> wrote:
 >> Please disregard this. ...
 >
 > can you run latencytop to see if it can pinpoint a cause of latency?

Like I said in my other reply I was running the wrong kernel when I 
wrote that (oops)... So now I am still sure it is ca7e716.

Ingo's patch makes the same change that reverting ca7e716 does here:

-	max_clock = scd->tick_gtod + TICK_NSEC;
+	max_clock = wrap_max(scd->clock, scd->tick_gtod + TICK_NSEC);


And with that change (I'm using Ingo's patch now) I can't trigger the 
hang anymore. And before, I could reliably trigger it in a short time.

Jayson

--
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/