| 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
| ||
|
Date: Wed, 25 Oct 2006 16:24:38 +0100 From: Paulo Marques <pmarques@...popie.com> To: Michael <michael.sallaway@...il.com> CC: ray-gmail@...rabbit.org, linux-kernel@...r.kernel.org Subject: Re: PROBLEM: Oops when doing disk heavy disk I/O Michael wrote: >> From: Ray Lee [mailto:madrabbit@...il.com] >> Try swapping out the RAM (or getting it down to 1Gig). Try a really >> old kernel, such as debian's 2.6.8 package. > > [...] > Although, having said that, I'm curious... It is working because there's > only 1 gig of RAM in there, or because it's only a single stick (ie. not > dual-channel)? It works fine with both sticks, individually, just not both > together... I wonder what the cause of it actually is... Another thing that I would try is to tweak the /proc/sys/vm/dirty_ratio and /proc/sys/vm/dirty_background_ratio settings. pdflush appears in your trace and with twice the RAM there is twice the dirty data to write out. Maybe choosing half the ratio in both settings with 2Gb of RAM would produce the same amount of dirty data as using just 1Gb of RAM with the original settings. This is still a bug, though. This test would just give more debug information. -- Paulo "grasping at straws" Marques - www.grupopie.com "The face of a child can say it all, especially the mouth part of the face." - 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/
Powered by blists - more mailing lists