[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <166862457559.199729.5082175605885412089.b4-ty@kernel.dk>
Date: Wed, 16 Nov 2022 11:49:35 -0700
From: Jens Axboe <axboe@...nel.dk>
To: Gabriel Krisman Bertazi <krisman@...e.de>
Cc: mingo@...hat.com, linux-kernel@...r.kernel.org, jack@...e.cz,
chaitanyak@...dia.com, peterz@...radead.org,
liusong@...ux.alibaba.com, linux-block@...r.kernel.org
Subject: Re: [PATCH 0/3] sbitmap: Fix two issues in the per-bitmap wakeup counter code
On Tue, 15 Nov 2022 17:45:50 -0500, Gabriel Krisman Bertazi wrote:
> Jan reported two issues in the original thread.
>
> The first is that wake_index was not updated after returning from
> sbq_wake_ptr which meant we'd have to empty the wq before moving to the
> next one. Patch 1/3 in this series reorders the code to avoid this
> condition, increasing fairness of queue selection and preventing
> starvation. I sent this patch already on the other thread and Jan
> reviewed it, but since it is a small one, and a dependency for the
> other, I'm resending it a along this series.
>
> [...]
Applied, thanks!
[1/3] sbitmap: Advance the queue index before waking up a queue
commit: 976570b4ecd30d3ec6e1b0910da8e5edc591f2b6
[2/3] wait: Return number of exclusive waiters awaken
commit: ee7dc86b6d3e3b86c2c487f713eda657850de238
[3/3] sbitmap: Try each queue to wake up at least one waiter
commit: 26edb30dd1c0c9be11fa676b4f330ada7b794ba6
Best regards,
--
Jens Axboe
Powered by blists - more mailing lists