On 6/10/13 4:43 AM, Stefan Ring wrote:
> On Sun, Jun 9, 2013 at 12:46 PM, Stan Hoeppner <stan@xxxxxxxxxxxxxxxxx> wrote:
>> In a recent linux-raid list thread here:
>> seriously flawed arguments against the reliability of XFS, and even the
>> performance of XFS, are made. The OP even quotes Dave's LCA
>> presentation as a performance reason to avoid XFS. The party really
>> gets started at paragraph 7.
>> I made a brief effort to debunk his claims and explained that he can't
>> have O_PONIES, that he should use fsync or O_DIRECT, etc for data
>> safety. To non experts/advanced filesystem users, his long winded
>> argument may be persuasive. Obviously none of you experts has time to
>> debunk every such post, but this one may be worth a read at least,
>> especially given the weight Google gives to vger lists.
> The really unfortunate thing about this is that the bug which would
> prevent transaction flushing from happening got imported and shipped
> for a rather long time in RHEL. It's one thing to get a file zeroed
> that's a few seconds old, but having the same happen to files which
> haven't been touched in hours, even before issuing manual sync, is
> certainly not very reassuring.
Bugs and regressions are always unfortunate, and this one was no exception.
It was pretty obscure, but we (mostly Dave) worked with our customers
to identify & resolve it within days of the bug report.
As far as I know, the bug existed only for a crash, not a reboot.
> As a very satisfied user of XFS on CentOS 6, I have been nervous
> enough about that to go through the trouble of rebooting our main
> server for a kernel upgrade a few weeks ago. Thanks to RedHat's
> deceptive tactics regarding kernel patches, I have also not been able
deceptive - adj. - Giving an appearance or impression different from the true
which sounds pretty damning. Perhaps more accurate is:
obfuscated - adj. - Rendered obscure, unclear, or unintelligible ;)
> to pin-point the exact range of kernel versions affected by this in a
> reasonable amount of time and hence have not found out (thankfully not
> the hard way) if it was even necessary.
It was introduced in 6.2 and resolved in 6.4, as well as 6.2
and 6.3 z-stream kernels. Those are the sorts of things Red Hat support
can help customers identify more quickly & clearly.
> xfs mailing list