linux-kernel - Re: [PATCH V5 00/30] loop: Issue O_DIRECT aio using bio

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] [day] [month] [year] [list]

Message-ID: <x49622pb3fg.fsf@segfault.boston.devel.redhat.com>
Date:	Tue, 22 Jan 2013 11:14:27 -0500
From:	Jeff Moyer <jmoyer@...hat.com>
To:	Dave Kleikamp <dave.kleikamp@...cle.com>
Cc:	linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
	Zach Brown <zab@...bo.net>,
	"Maxim V. Patlasov" <mpatlasov@...allels.com>
Subject: Re: [PATCH V5 00/30] loop: Issue O_DIRECT aio using bio_vec

Dave Kleikamp <dave.kleikamp@...cle.com> writes:

> On 01/18/2013 03:48 PM, Jeff Moyer wrote:
>> Dave Kleikamp <dave.kleikamp@...cle.com> writes:
>> 
>>> On 01/18/2013 11:56 AM, Jeff Moyer wrote:
>>>> Jeff Moyer <jmoyer@...hat.com> writes:
>>>>
>>>>> ./check -g aio
>>>>>
>>>>> and here is the summary:
>>>>>
>>>>> Ran: 112 113 198 207 208 209 210 211 212 239 240
>>>>> Failures: 112 198 207 239 240
>>>>> Failed 5 of 11 tests
>>>>>
>>>>> To be fair, I have not yet run this on a kernel without your changes.
>>>>
>>>> I re-ran the same test against a vanilla 3.8.0-rc4 kernel and it passed:
>>>>
>>>> Ran: 112 113 198 207 208 209 210 211 212 239 240
>>>> Passed all 11 tests
>>>>
>>>> I'll start digging into the failures.
>>>
>>> Thanks, I'll take a look at it too.
>> 
>> Note that the failures occur on regular block devices, too;  this isn't
>> restricted to loop.  The fix I mentioned in reply to patch 17 actually
>> fixes all of the failures reported in the aio group.  I'm going to do
>> some more thorough testing over the weekend.
>
> Thanks much. I'll definitely add this to my testing.

After fixing up that thinko, a full run of xfstests on an xfs file
system backed by a loop device (which itself is a file on an xfs file
system) shows no regressions.

Cheers,
Jeff
--
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/