xfs
[Top] [All Lists]

Re: Corruption of root fs during git bisect of drm system hang

To: Stan Hoeppner <stan@xxxxxxxxxxxxxxxxx>
Subject: Re: Corruption of root fs during git bisect of drm system hang
From: Markus Trippelsdorf <markus@xxxxxxxxxxxxxxx>
Date: Thu, 11 Jul 2013 05:47:18 +0200
Cc: xfs@xxxxxxxxxxx
Delivered-to: xfs@xxxxxxxxxxx
Dkim-signature: v=1; a=rsa-sha256; c=simple; d=mail.ud10.udmedia.de; h= date:from:to:cc:subject:message-id:references:mime-version :content-type:in-reply-to; s=beta; bh=cVqqkN+QX3uPFJH7FQaAVPEJmr 97aVtrsXtABO6MSLw=; b=nrrK+z8NZB0odxcBc+CkoB0CW/gKuh7mOtIjTms0VV AWDY8Nz/q7M3b2t3QsOEsMOVTJWzmnZoPo9wh0Oc9uKYhfuSD5P0chKWn9YTChM7 WatsxvPhlUY245pnl7ZizNgcVbiUSbbrGzAwatNvitnueWWXfRwJU74Y8jyfPpu7 k=
In-reply-to: <51DDFE44.9000606@xxxxxxxxxxxxxxxxx>
References: <20130710090634.GA356@x4> <51DDFE44.9000606@xxxxxxxxxxxxxxxxx>
On 2013.07.10 at 19:37 -0500, Stan Hoeppner wrote:
> On 7/10/2013 4:06 AM, Markus Trippelsdorf wrote:
> > While bisecting a system hang, caused by the drm gpu subsystem, my root fs 
> > got
> > corrupted:
> ...
> > My root fs lives on a small SSD:
> > 
> > /dev/root on / type xfs (rw,relatime,attr2,inode64,logbsize=256k,noquota)
> > /dev/root      xfs        30G   15G   16G  50% /
> 
> Does your SSD honor barriers and cache flushes?

Yes, I hope so:

  Enabled Supported:
     ...
     *    Mandatory FLUSH_CACHE
     *    FLUSH_CACHE_EXT

But please note that the system hang mentioned above turned out to be a
locking problem. So the SSD had plenty of time to process any out-
standing commands before reboot.

-- 
Markus

<Prev in Thread] Current Thread [Next in Thread>