linux-kernel - Re: [Regression x2, 3.13-git] virtio block mq hang, iostat busted on virtio devices

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] [thread-next>] [day] [month] [year] [list]

Message-ID: <528B8EE6.7030005@kernel.dk>
Date:	Tue, 19 Nov 2013 09:16:38 -0700
From:	Jens Axboe <axboe@...nel.dk>
To:	Christoph Hellwig <hch@...radead.org>
CC:	Dave Chinner <david@...morbit.com>, linux-kernel@...r.kernel.org
Subject: Re: [Regression x2, 3.13-git] virtio block mq hang, iostat busted
 on virtio devices

On 11/19/2013 09:09 AM, Christoph Hellwig wrote:
> On Tue, Nov 19, 2013 at 09:05:09AM -0700, Jens Axboe wrote:
>> I have queued up the below.
> 
> I don't think that will work.  We only set QUEUE_FLAG_IO_STAT in
> blk_init_allocated_queue, which doesn't get called from
> blk_mq_init_queue.  That being said I really don't understand why we
> need to have the QUEUE_FLAG_IO_STAT flag at all.

Hmm good point, we need to init those flags there too. I'll get this
properly tested.

Back when the accounting was initially made optional, there was about a
1% reduction in overhead with it off. That's why the tunable is there.

-- 
Jens Axboe

--
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/