[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAHk-=whmN7cxAgmhDBqiE=c67Q2pp2+SqCknNcj3K+QNKivaSg@mail.gmail.com>
Date: Mon, 15 May 2023 08:56:39 -0700
From: Linus Torvalds <torvalds@...ux-foundation.org>
To: Jens Axboe <axboe@...nel.dk>
Cc: Christian Brauner <brauner@...nel.org>,
Thorsten Leemhuis <linux@...mhuis.info>,
Mike Christie <michael.christie@...cle.com>,
nicolas.dichtel@...nd.com,
Linux kernel regressions list <regressions@...ts.linux.dev>,
hch@...radead.org, stefanha@...hat.com, jasowang@...hat.com,
mst@...hat.com, sgarzare@...hat.com,
virtualization@...ts.linux-foundation.org, ebiederm@...ssion.com,
konrad.wilk@...cle.com, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v11 8/8] vhost: use vhost_tasks for worker threads
On Mon, May 15, 2023 at 8:52 AM Jens Axboe <axboe@...nel.dk> wrote:
>
> Only potential downside is that it does make file references more
> expensive for other syscalls, since you now have a shared file table.
> But probably not something to worry about here?
Would the vhost user worker user processes ever be otherwise single-threaded?
I'd *assume* that a vhost user is already doing its own threads. But
maybe that's a completely bogus assumption. I don't actually use any
of this, so...
Because you are obviously 100% right that if you're otherwise
single-threaded, then a CLONE_FILES kernel helper thread will cause
the extra cost for file descriptor lookup/free due to all the race
prevention.
Linus
Powered by blists - more mailing lists