[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <e12067aa-9465-4c3f-a67e-e8e8dee14c8b@gmail.com>
Date: Tue, 5 Nov 2024 19:28:48 +0200
From: Tariq Toukan <ttoukan.linux@...il.com>
To: Paolo Abeni <pabeni@...hat.com>,
Caleb Sander Mateos <csander@...estorage.com>,
Saeed Mahameed <saeedm@...dia.com>, Leon Romanovsky <leon@...nel.org>,
Tariq Toukan <tariqt@...dia.com>, Andrew Lunn <andrew+netdev@...n.ch>,
"David S. Miller" <davem@...emloft.net>, Eric Dumazet <edumazet@...gle.com>,
Jakub Kicinski <kuba@...nel.org>
Cc: Parav Pandit <parav@...dia.com>, netdev@...r.kernel.org,
linux-rdma@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH net-next v3] mlx5/core: Schedule EQ comp tasklet only if
necessary
On 05/11/2024 14:21, Paolo Abeni wrote:
> On 10/31/24 17:34, Caleb Sander Mateos wrote:
>> Currently, the mlx5_eq_comp_int() interrupt handler schedules a tasklet
>> to call mlx5_cq_tasklet_cb() if it processes any completions. For CQs
>> whose completions don't need to be processed in tasklet context, this
>> adds unnecessary overhead. In a heavy TCP workload, we see 4% of CPU
>> time spent on the tasklet_trylock() in tasklet_action_common(), with a
>> smaller amount spent on the atomic operations in tasklet_schedule(),
>> tasklet_clear_sched(), and locking the spinlock in mlx5_cq_tasklet_cb().
>> TCP completions are handled by mlx5e_completion_event(), which schedules
>> NAPI to poll the queue, so they don't need tasklet processing.
>>
>> Schedule the tasklet in mlx5_add_cq_to_tasklet() instead to avoid this
>> overhead. mlx5_add_cq_to_tasklet() is responsible for enqueuing the CQs
>> to be processed in tasklet context, so it can schedule the tasklet. CQs
>> that need tasklet processing have their interrupt comp handler set to
>> mlx5_add_cq_to_tasklet(), so they will schedule the tasklet. CQs that
>> don't need tasklet processing won't schedule the tasklet. To avoid
>> scheduling the tasklet multiple times during the same interrupt, only
>> schedule the tasklet in mlx5_add_cq_to_tasklet() if the tasklet work
>> queue was empty before the new CQ was pushed to it.
>>
>> The additional branch in mlx5_add_cq_to_tasklet(), called for each EQE,
>> may add a small cost for the userspace Infiniband CQs whose completions
>> are processed in tasklet context. But this seems worth it to avoid the
>> tasklet overhead for CQs that don't need it.
>>
>> Note that the mlx4 driver works the same way: it schedules the tasklet
>> in mlx4_add_cq_to_tasklet() and only if the work queue was empty before.
>>
>> Signed-off-by: Caleb Sander Mateos <csander@...estorage.com>
>> Reviewed-by: Parav Pandit <parav@...dia.com>
>
> @Saeed, @Leon, @Tariq: I assume you will apply this one and include in
> the next mlx5 PR. please correct me if I'm wrong.
>
Hi Paolo,
I am doing the mlx5 core/en maintainer work right now. I work
differently to Saeed, as I do not have a kernel.org branch of my own
(nor use Saeed's ofcourse),
Please consider applying this one and any others once I acknowledge/review.
Acked-by: Tariq Toukan <tariqt@...dia.com>
Regards,
Tariq
Powered by blists - more mailing lists