Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Jens Axboe <axboe@kernel.dk>
To:     Christoph Hellwig <hch@infradead.org>,
        Ross Lagerwall <ross.lagerwall@citrix.com>
Cc:     linux-block@vger.kernel.org, linux-kernel@vger.kernel.org
In-Reply-To: <20230714101106.3635611-1-ross.lagerwall@citrix.com>
References: <20230714101106.3635611-1-ross.lagerwall@citrix.com>
Subject: Re: [PATCH v2] blk-mq: Fix stall due to recursive flush plug
Message-Id: <168936388618.743920.17372805107217904539.b4-ty@kernel.dk>
Date:   Fri, 14 Jul 2023 13:44:46 -0600
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 7bit
Precedence: bulk


On Fri, 14 Jul 2023 11:11:06 +0100, Ross Lagerwall wrote:
> We have seen rare IO stalls as follows:
> 
> * blk_mq_plug_issue_direct() is entered with an mq_list containing two
> requests.
> * For the first request, it sets last == false and enters the driver's
> queue_rq callback.
> * The driver queue_rq callback indirectly calls schedule() which calls
> blk_flush_plug(). This may happen if the driver has the
> BLK_MQ_F_BLOCKING flag set and is allowed to sleep in ->queue_rq.
> * blk_flush_plug() handles the remaining request in the mq_list. mq_list
> is now empty.
> * The original call to queue_rq resumes (with last == false).
> * The loop in blk_mq_plug_issue_direct() terminates because there are no
> remaining requests in mq_list.
> 
> [...]

Applied, thanks!

[1/1] blk-mq: Fix stall due to recursive flush plug
      commit: 70904263512a74a3b8941dd9e6e515ca6fc57821

Best regards,
-- 
Jens Axboe