[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <hk4gfwg7cua6rbcly7qzpqah7bfxbzgndgwasmsqqzsim5uxzu@ofpo4e6koms2>
Date: Mon, 30 Sep 2024 14:50:16 +0200
From: Michal Koutný <mkoutny@...e.com>
To: Chen Ridong <chenridong@...weicloud.com>
Cc: tj@...nel.org, lizefan.x@...edance.com, hannes@...xchg.org,
longman@...hat.com, chenridong@...wei.com, cgroups@...r.kernel.org,
linux-kernel@...r.kernel.org
Subject: Re: [PATCH v5 2/3] workqueue: doc: Add a note saturating the
system_wq is not permitted
Hi.
On Fri, Sep 27, 2024 at 04:08:26PM GMT, Chen Ridong <chenridong@...weicloud.com> wrote:
> How about:
> Note: If something may generate works frequently, it may saturate the
> system_wq and potentially lead to deadlock. It should utilize its own
> dedicated workqueue rather than system wq.
It doesn't depend only on generating frequency (in Tetsuo's example with
slow works, the "high" would only be 256/s) and accurate information is
likely only empirical, thus I'd refine it further:
> Note: If something may generate more than @max_active outstanding
> work items (do stress test your producers), it may saturate a system
> wq and potentially lead to deadlock. It should utilize its own
> dedicated workqueue rather than the system wq.
(besides @max_active reference, I also changed generic system_wq to
system wq as the surrounding text seems to refer to any of the
system_*wq)
Michal
Download attachment "signature.asc" of type "application/pgp-signature" (229 bytes)
Powered by blists - more mailing lists