From: Jeff Garzik <jgarzik@pobox.com>
To: Rusty Russell <rusty@rustcorp.com.au>
Cc: torvalds@osdl.org, akpm@osdl.org, mingo@redhat.com,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH 1/2] kthread_create
Date: Wed, 31 Dec 2003 01:34:39 -0500 [thread overview]
Message-ID: <3FF26DFF.3040909@pobox.com> (raw)
In-Reply-To: <20031231053032.255202C08B@lists.samba.org>
Rusty Russell wrote:
> For #2, if you really can't wait for keventd, perhaps your own
> workqueue is in order?
Way too wasteful, and doing so is working around a fundamental failing
of workqueues: keventd gives no guarantee that your scheduled work will
be executed this week, this month, or this year :)
keventd is used by two competing classes of users: those who want
low-latency, quick execution in task context (Tux-ish), and those who
just want to run something in task context, where they might sleep
(perhaps for a long time).
So it would be nice to have thread pool semantics occasionally found in
userspace: if thread pool is full when new work is queued,
_temporarily_ increase the pool size (or create a one-shot kthread).
Sure you have kthread creation overhead, but at least you have a
reasonable guarantee that your work won't wait 5-30 seconds or more
before being performed.
Jeff
next prev parent reply other threads:[~2003-12-31 6:35 UTC|newest]
Thread overview: 47+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-12-31 3:31 [PATCH 1/2] kthread_create Rusty Russell
2003-12-31 4:33 ` Jeff Garzik
2003-12-31 5:28 ` Rusty Russell
2003-12-31 6:34 ` Jeff Garzik [this message]
2003-12-31 8:47 ` Benjamin Herrenschmidt
2004-01-01 23:51 ` Rusty Russell
2003-12-31 4:49 ` Andrew Morton
2003-12-31 5:18 ` Rusty Russell
2003-12-31 5:06 ` Davide Libenzi
2003-12-31 5:34 ` Rusty Russell
2003-12-31 5:56 ` Davide Libenzi
2003-12-31 6:27 ` Rusty Russell
2004-01-01 3:45 ` Davide Libenzi
2004-01-02 7:09 ` Rusty Russell
2004-01-02 16:58 ` Davide Libenzi
2004-01-03 3:05 ` Rusty Russell
2004-01-03 3:43 ` Davide Libenzi
2004-01-03 11:47 ` Rusty Russell
2004-01-04 4:23 ` Davide Libenzi
2004-03-29 15:42 ` Davide Libenzi
2004-01-03 19:00 ` Davide Libenzi
2004-01-03 23:53 ` Davide Libenzi
2004-01-04 2:34 ` Rusty Russell
2004-01-04 4:42 ` Davide Libenzi
2004-01-04 4:55 ` Davide Libenzi
2004-01-04 9:35 ` Rusty Russell
2004-01-04 23:03 ` Davide Libenzi
2004-01-05 4:09 ` Rusty Russell
2004-01-05 5:06 ` Davide Libenzi
2004-01-05 6:38 ` Rusty Russell
2004-01-05 6:52 ` Davide Libenzi
2004-01-07 7:00 ` Rusty Russell
2004-01-07 7:25 ` Davide Libenzi
2004-01-08 0:33 ` Rusty Russell
2004-03-29 15:42 ` Davide Libenzi
2004-03-29 15:42 ` Davide Libenzi
2004-03-29 15:41 ` Davide Libenzi
2004-03-29 15:42 ` Rusty Russell
2004-03-29 15:40 ` Davide Libenzi
2004-03-29 15:41 ` Rusty Russell
2004-03-29 15:39 ` Davide Libenzi
2004-03-29 15:39 ` Rusty Russell
2004-03-29 15:38 ` Davide Libenzi
2003-12-31 6:31 ` Srivatsa Vaddagiri
2003-12-31 7:12 ` Davide Libenzi
2003-12-31 23:25 ` Rusty Russell
-- strict thread matches above, loose matches on Subject: below --
2003-12-31 18:02 Albert Cahalan
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=3FF26DFF.3040909@pobox.com \
--to=jgarzik@pobox.com \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=rusty@rustcorp.com.au \
--cc=torvalds@osdl.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.