[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <569B5DE3.1010908@dev.mellanox.co.il>
Date: Sun, 17 Jan 2016 11:24:51 +0200
From: Sagi Grimberg <sagig@....mellanox.co.il>
To: Parav Pandit <pandit.parav@...il.com>,
Christoph Hellwig <hch@....de>
Cc: linux-rdma@...r.kernel.org,
Bart Van Assche <bart.vanassche@...disk.com>, axboe@...com,
linux-scsi@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 07/13] IB: add a proper completion queue abstraction
> Hi Christoph, Sagi,
>
> On Tue, Dec 8, 2015 at 2:21 AM, Christoph Hellwig <hch@....de> wrote:
>
>> +static void ib_cq_poll_work(struct work_struct *work)
>> +{
>> + struct ib_cq *cq = container_of(work, struct ib_cq, work);
>> + int completed;
>> +
>> + completed = __ib_process_cq(cq, IB_POLL_BUDGET_WORKQUEUE);
>> + if (completed >= IB_POLL_BUDGET_WORKQUEUE ||
>> + ib_req_notify_cq(cq, IB_POLL_FLAGS) > 0)
>> + queue_work(ib_comp_wq, &cq->work);
>> +}
>
> In above code, Let says completion is added in a time window where
> ib_process_cq is completed (CQ is diarmed in hw at that point) and
> ib_req_notify_cq is yet to be called.
> Provider vendor driver say mlx4 or mlx5 as specific case always
> returns ib_req_notify_cq = 0.
> Will it result into a missed notification? (so queue_work is not done).
If we have not drained the CQ (consumed budget or more) the second
condition (ib_req_notify_cq) will not be invoked. We are only rearming
the CQ when we drained it completely. So I don't see how we can end up
with missed notifications.
Powered by blists - more mailing lists