xfs
[Top] [All Lists]

Re: easily reproducible filesystem crash on rebuilding array

To: xfs@xxxxxxxxxxx
Subject: Re: easily reproducible filesystem crash on rebuilding array
From: Emmanuel Florac <eflorac@xxxxxxxxxxxxxx>
Date: Tue, 13 Jan 2015 14:59:40 +0100
Delivered-to: xfs@xxxxxxxxxxx
In-reply-to: <20150113122108.2d3a5ccc@xxxxxxxxxxxxxxxxxxxx>
Organization: Intellique
References: <20141211123936.1f3d713d@xxxxxxxxxxxxxxxxxxxx> <20150113122108.2d3a5ccc@xxxxxxxxxxxxxxxxxxxx>
Le Tue, 13 Jan 2015 12:21:08 +0100
Emmanuel Florac <eflorac@xxxxxxxxxxxxxx> Ãcrivait:

> * XFS v4 on rebuilding adaptec RAID fails under heavy IO, with or
>   without LVM, with kernels 3.2.xx up to 3.17.7.
> 
> * Today I've run the same test with ext4 : no problem whatsoever. I'm
>   rechecking md5 of all files to get sure, but it looks OK so far
> after testing several terabytes. 
> 
> I don't understand how the RAID firmware could send back bad data
> (corrupted metadata AND data) to XFS but not to ext4...
> 

Beep, the md5 are wrong. So we see why we love XFS : when the RAID
controller spits nonsense, it barks and cries and dies noisily :)

ext4 didn't notice any problem, though the data is mangled. This is
bad...

-- 
------------------------------------------------------------------------
Emmanuel Florac     |   Direction technique
                    |   Intellique
                    |   <eflorac@xxxxxxxxxxxxxx>
                    |   +33 1 78 94 84 02
------------------------------------------------------------------------

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