From: Ingo Molnar <mingo@elte.hu>
To: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Andrew Morton <akpm@osdl.org>, linux-kernel@vger.kernel.org
Subject: Re: [patch] sched: fix scheduling latencies for !PREEMPT kernels
Date: Wed, 15 Sep 2004 08:19:22 +0200 [thread overview]
Message-ID: <20040915061922.GA11683@elte.hu> (raw)
In-Reply-To: <414776CE.5030302@yahoo.com.au>
* Nick Piggin <nickpiggin@yahoo.com.au> wrote:
> No, but I mean putting them right down into fastpaths like the vmscan
> one, for example.
it is a very simple no-parameters call to a function that reads a
likely-cached word and returns. The cost is in the 2-3 cycles range - a
_single_ cachemiss can be 10-100 times more expensive, and cachemisses
happen very frequently in every iteration of the VM _scanning_ path
since it (naturally and inevitably) deals with lots of sparsely
scattered data structures that havent been referenced for quite some
time.
The function (cond_resched()) triggers scheduling only very rarely, you
should not be worried about that aspect either.
> And if I remember correctly, you resorted to putting them into
> might_sleep as well (but I haven't read the code for a while, maybe
> you're now getting decent results without doing that).
i'm not arguing that now at all, that preemption model clearly has to be
an optional thing - at least initially.
Ingo
next prev parent reply other threads:[~2004-09-15 6:18 UTC|newest]
Thread overview: 76+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-09-14 9:15 [patch] preempt-cleanup.patch, 2.6.9-rc2 Ingo Molnar
2004-09-14 9:34 ` [printk] make console_conditional_schedule() __sched and use cond_resched() William Lee Irwin III
2004-09-14 9:38 ` [patch] preempt-lock-need-resched.patch, 2.6.9-rc2 Ingo Molnar
2004-09-14 9:51 ` [patch] sched: add cond_resched_softirq() Ingo Molnar
2004-09-14 9:57 ` [patch] sched: fix latency in random driver Ingo Molnar
2004-09-14 10:06 ` [patch] sched, ext3: fix scheduling latencies in ext3 Ingo Molnar
2004-09-14 10:13 ` [patch] sched, vfs: fix scheduling latencies in invalidate_inodes() Ingo Molnar
2004-09-14 10:19 ` [patch] sched, vfs: fix scheduling latencies in prune_dcache() and select_parent() Ingo Molnar
2004-09-14 10:25 ` [patch] sched, net: fix scheduling latencies in netstat Ingo Molnar
2004-09-14 10:44 ` [patch] sched, net: fix scheduling latencies in __release_sock Ingo Molnar
2004-09-14 10:50 ` [patch] sched, mm: fix scheduling latencies in copy_page_range() Ingo Molnar
2004-09-14 10:56 ` [patch] sched, mm: fix scheduling latencies in unmap_vmas() Ingo Molnar
2004-09-14 10:59 ` [patch] sched, mm: fix scheduling latencies in get_user_pages() Ingo Molnar
2004-09-14 11:02 ` [patch] sched, mm: fix scheduling latencies in filemap_sync() Ingo Molnar
2004-09-14 11:06 ` [patch] sched, tty: fix scheduling latencies in tty_io.c Ingo Molnar
2004-09-14 10:53 ` Alan Cox
2004-09-14 12:00 ` Ingo Molnar
2004-09-14 11:18 ` Alan Cox
2004-09-14 12:27 ` Ingo Molnar
2004-09-14 12:11 ` Alan Cox
2004-09-14 11:08 ` [patch] sched, pty: fix scheduling latencies in pty.c Ingo Molnar
2004-09-14 11:12 ` [patch] might_sleep() additions to fs-writeback.c Ingo Molnar
2004-09-14 11:25 ` [patch] fix keventd execution dependency Ingo Molnar
2004-09-15 22:18 ` Rusty Russell
2004-09-14 11:28 ` [patch] sched: fix scheduling latencies in mttr.c Ingo Molnar
2004-09-14 11:32 ` [patch] sched: fix scheduling latencies in vgacon.c Ingo Molnar
2004-09-14 11:35 ` [patch] sched: fix scheduling latencies in NTFS mount Ingo Molnar
2004-09-14 13:31 ` Anton Altaparmakov
2004-09-14 11:42 ` [patch] sched: fix scheduling latencies for !PREEMPT kernels Ingo Molnar
2004-09-14 12:55 ` Nick Piggin
2004-09-14 13:22 ` Ingo Molnar
2004-09-14 13:33 ` Nick Piggin
2004-09-14 14:09 ` Andrea Arcangeli
2004-09-14 14:28 ` Nick Piggin
2004-09-14 15:03 ` Andrea Arcangeli
2004-09-14 18:05 ` Robert Love
2004-09-14 18:52 ` William Lee Irwin III
2004-09-14 19:02 ` Robert Love
2004-09-14 19:21 ` William Lee Irwin III
2004-09-14 19:19 ` Alan Cox
2004-09-15 0:22 ` Lee Revell
2004-09-15 1:46 ` William Lee Irwin III
2004-09-15 2:00 ` Lee Revell
2004-09-15 2:36 ` William Lee Irwin III
2004-09-15 2:59 ` Lee Revell
2004-09-15 13:36 ` Hans Reiser
2004-09-15 20:40 ` William Lee Irwin III
2004-09-15 1:18 ` William Lee Irwin III
2004-09-14 19:26 ` Robert Love
2004-09-14 21:06 ` William Lee Irwin III
2004-09-14 19:25 ` Andrea Arcangeli
2004-09-14 19:29 ` Robert Love
2004-09-14 19:34 ` William Lee Irwin III
2004-09-15 1:02 ` Lee Revell
2004-09-15 1:39 ` William Lee Irwin III
2004-09-15 2:11 ` Lee Revell
2004-09-15 11:17 ` Ingo Molnar
2004-09-15 9:56 ` Ingo Molnar
2004-09-15 9:57 ` William Lee Irwin III
2004-09-15 10:12 ` Ingo Molnar
2004-09-14 16:31 ` William Lee Irwin III
2004-09-14 16:39 ` Andrea Arcangeli
2004-09-14 14:54 ` Ingo Molnar
2004-09-14 22:55 ` Nick Piggin
2004-09-15 6:19 ` Ingo Molnar [this message]
2004-09-15 8:23 ` Nick Piggin
2004-09-15 8:43 ` Ingo Molnar
2004-09-15 10:09 ` William Lee Irwin III
2004-09-15 10:21 ` Ingo Molnar
2004-09-16 1:03 ` Nick Piggin
2004-09-16 6:14 ` Ingo Molnar
2004-09-15 0:35 ` Lee Revell
2004-09-14 13:25 ` [patch] sched: fix scheduling latencies in mtrr.c Ingo Molnar
2004-09-14 13:15 ` Alan Cox
2004-09-14 15:00 ` Ingo Molnar
2004-09-14 18:22 ` Zwane Mwaikambo
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=20040915061922.GA11683@elte.hu \
--to=mingo@elte.hu \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nickpiggin@yahoo.com.au \
/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.