[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <CACycT3t-UzaLOFSTmYyKniHYPK8jH9SevgB+1xrnCTc_4JKXQw@mail.gmail.com>
Date: Tue, 21 Dec 2021 11:39:22 +0800
From: Yongji Xie <xieyongji@...edance.com>
To: Bart Van Assche <bvanassche@....org>
Cc: Josef Bacik <josef@...icpanda.com>, Jens Axboe <axboe@...nel.dk>,
linux-block@...r.kernel.org, nbd@...er.debian.org,
linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] nbd: Don't use workqueue to handle recv work
On Tue, Dec 21, 2021 at 1:10 AM Bart Van Assche <bvanassche@....org> wrote:
>
> On 12/20/21 04:22, Xie Yongji wrote:
> > The rescuer thread might take over the works queued on
> > the workqueue when the worker thread creation timed out.
> > If this happens, we have no chance to create multiple
> > recv threads which causes I/O hung on this nbd device.
> >
> > To fix it, this tries to create kthreads directly to
> > handle the recv work instead of using workqueue.
>
> Why a kthread instead of only removing the WQ_MEM_RECLAIM flag from the
I think we can not simply remove the WQ_MEM_RECLAIM flag because the
recv work is in the memory reclaim path.
> alloc_workqueue() call? This should have been explained in the patch
> description. Additionally, a Fixes: tag is missing.
>
OK, will do it in v2.
Thanks,
Yongji
Powered by blists - more mailing lists