mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "Michael K. Edwards" <medwards.linux@gmail.com>
To: "Benjamin LaHaise" <bcrl@kvack.org>
Cc: "Davide Libenzi" <davidel@xmailserver.org>,
	"Russell King" <rmk+lkml@arm.linux.org.uk>,
	"Ingo Molnar" <mingo@elte.hu>,
	"Linux Kernel Mailing List" <linux-kernel@vger.kernel.org>,
	"Linus Torvalds" <torvalds@linux-foundation.org>,
	"Arjan van de Ven" <arjan@infradead.org>,
	"Christoph Hellwig" <hch@infradead.org>,
	"Andrew Morton" <akpm@zip.com.au>,
	"Alan Cox" <alan@lxorguk.ukuu.org.uk>,
	"Ulrich Drepper" <drepper@redhat.com>,
	"Zach Brown" <zach.brown@oracle.com>,
	"Evgeniy Polyakov" <johnpol@2ka.mipt.ru>,
	"David S. Miller" <davem@davemloft.net>,
	"Suparna Bhattacharya" <suparna@in.ibm.com>,
	"Thomas Gleixner" <tglx@linutronix.de>
Subject: Re: [patch 06/11] syslets: core, documentation
Date: Wed, 14 Feb 2007 17:32:33 -0800	[thread overview]
Message-ID: <f2b55d220702141732k642f17ccnc2256e54383e713@mail.gmail.com> (raw)
In-Reply-To: <20070214214409.GM32271@kvack.org>

On 2/14/07, Benjamin LaHaise <bcrl@kvack.org> wrote:
> My opinion of this whole thread is that it implies that our thread creation
> and/or context switch is too slow.  If that is the case, improve those
> elements first.  At least some of those optimizations have to be done in
> hardware on x86, while on other platforms are probably unnecessary.

Not necessarily too slow, but too opaque in terms of system-wide
impact and global flow control.  Here are the four practical use cases
that I have seen come up in this discussion:

1) Databases that want to parallelize I/O storms, with an emphasis on
getting results that are already cache-hot immediately (not least so
they don't get evicted by other I/O results); there is also room to
push some of the I/O clustering and sequencing logic down into the
kernel.

2) Static-content-intensive network servers, with an emphasis on
servicing those requests that can be serviced promptly (to avoid a
ballooning connection backlog) and avoiding duplication of I/O effort
when many clients suddenly want the same cold content; the real win
may be in "smart prefetch" initiated from outside the network server
proper.

3) Network information gathering GUIs, which want to harvest as much
information as possible for immediate display and then switch to an
event-based delivery mechanism for tardy responses; these need
throttling of concurrent requests (ideally, in-kernel traffic shaping
by request group and destination class) and efficient cancellation of
no-longer-interesting requests.

4) Document search facilities, which need all of the above (big
surprise there) as well as a rich diagnostic toolset, including a
practical snooping and profiling facility to guide tuning for
application responsiveness.

Even if threads were so cheap that you could just fire off one per I/O
request, they're a poor solution to the host of flow control issues
raised in these use cases.  A sequential thread of execution per I/O
request may be the friendliest mental model for the individual delayed
I/Os, but the global traffic shaping and scheduling is a data
structure problem.

The right question to be asking is, what are the operations that need
to be supported on the system-wide pool of pending AIOs, and on what
data structure can they be implemented efficiently?  For instance, can
we provide an RCU priority queue implementation (perhaps based on
splay trees) so that userspace can scan a coherent read-only snapshot
of the structure and select candidates for cancellation, etc., without
interfering with kernel completions?  Or is it more important to have
a three-sided query operation (characteristic of priority search
trees), or perhaps a lower amortized cost bulk delete?

Once you've thought through the data structure manipulation, you'll
know what AIO submission / cancellation / reprioritization interfaces
are practical.  Then you can work on a programming model for
application-level "I/O completions" that is library-friendly and
allows a "fast path" optimization for the fraction of requests that
can be served synchronously.  Then and only then does it make sense to
code-bum the asynchronous path.  Not that it isn't interesting to
think in advance about what stack space completions will run in and
which bits of the task struct needn't be in a coherent condition; but
that's probably not going to guide you to the design that meets the
application needs.

I know I'm teaching my grandmother to suck eggs here.  But there are
application programmers high up the code stack whose code makes
implicit use of asynchronous I/O continuations.  In addition to the
GUI example I blathered about a few days ago, I have in mind Narrative
Javascript's "blocking operator" and Twisted Python's Deferred.  Those
folks would be well served by an async I/O interface to the kernel
which mates well to their language's closure/continuation facilities.
If it's usable from C, that's nice too.  :-)

Cheers,
- Michael

  parent reply	other threads:[~2007-02-15  1:32 UTC|newest]

Thread overview: 319+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-05-29 21:21 [patch 00/61] ANNOUNCE: lock validator -V1 Ingo Molnar
2006-05-29 21:22 ` [patch 01/61] lock validator: floppy.c irq-release fix Ingo Molnar
2006-05-30  1:32   ` Andrew Morton
2006-05-29 21:23 ` [patch 02/61] lock validator: forcedeth.c fix Ingo Molnar
2006-05-30  1:33   ` Andrew Morton
2006-05-31  5:40     ` Manfred Spraul
2006-05-29 21:23 ` [patch 03/61] lock validator: sound/oss/emu10k1/midi.c cleanup Ingo Molnar
2006-05-30  1:33   ` Andrew Morton
2006-05-30 10:51     ` Takashi Iwai
2006-05-30 11:03       ` Alexey Dobriyan
2006-05-29 21:23 ` [patch 04/61] lock validator: mutex section binutils workaround Ingo Molnar
2006-05-29 21:23 ` [patch 05/61] lock validator: introduce WARN_ON_ONCE(cond) Ingo Molnar
2006-05-30  1:33   ` Andrew Morton
2006-05-30 17:38     ` Steven Rostedt
2006-06-03 18:09       ` Steven Rostedt
2006-06-04  9:18         ` Arjan van de Ven
2006-06-04 13:43           ` Steven Rostedt
2006-05-29 21:23 ` [patch 06/61] lock validator: add __module_address() method Ingo Molnar
2006-05-30  1:33   ` Andrew Morton
2006-05-30 17:45     ` Steven Rostedt
2006-06-23  8:38     ` Ingo Molnar
2006-05-29 21:23 ` [patch 07/61] lock validator: better lock debugging Ingo Molnar
2006-05-30  1:33   ` Andrew Morton
2006-06-23 10:25     ` Ingo Molnar
2006-06-23 11:06       ` Andrew Morton
2006-06-23 11:04         ` Ingo Molnar
2006-05-29 21:23 ` [patch 08/61] lock validator: locking API self-tests Ingo Molnar
2006-05-29 21:23 ` [patch 09/61] lock validator: spin/rwlock init cleanups Ingo Molnar
2006-05-29 21:23 ` [patch 10/61] lock validator: locking init debugging improvement Ingo Molnar
2006-05-29 21:23 ` [patch 11/61] lock validator: lockdep: small xfs init_rwsem() cleanup Ingo Molnar
2006-05-30  1:33   ` Andrew Morton
2006-05-30  1:32     ` Nathan Scott
2006-05-29 21:24 ` [patch 12/61] lock validator: beautify x86_64 stacktraces Ingo Molnar
2006-05-30  1:33   ` Andrew Morton
2006-05-29 21:24 ` [patch 13/61] lock validator: x86_64: document stack frame internals Ingo Molnar
2006-05-29 21:24 ` [patch 14/61] lock validator: stacktrace Ingo Molnar
2006-05-29 21:24 ` [patch 15/61] lock validator: x86_64: use stacktrace to generate backtraces Ingo Molnar
2006-05-30  1:33   ` Andrew Morton
2006-05-29 21:24 ` [patch 16/61] lock validator: fown locking workaround Ingo Molnar
2006-05-30  1:34   ` Andrew Morton
2006-06-23  9:10     ` Ingo Molnar
2006-05-29 21:24 ` [patch 17/61] lock validator: sk_callback_lock workaround Ingo Molnar
2006-05-30  1:34   ` Andrew Morton
2006-06-23  9:19     ` Ingo Molnar
2006-05-29 21:24 ` [patch 18/61] lock validator: irqtrace: core Ingo Molnar
2006-05-30  1:34   ` Andrew Morton
2006-06-23 10:42     ` Ingo Molnar
2006-05-29 21:24 ` [patch 19/61] lock validator: irqtrace: cleanup: include/asm-i386/irqflags.h Ingo Molnar
2006-05-29 21:24 ` [patch 20/61] lock validator: irqtrace: cleanup: include/asm-x86_64/irqflags.h Ingo Molnar
2006-05-29 21:24 ` [patch 21/61] lock validator: lockdep: add local_irq_enable_in_hardirq() API Ingo Molnar
2006-05-30  1:34   ` Andrew Morton
2006-06-23  9:28     ` Ingo Molnar
2006-06-23  9:52       ` Andrew Morton
2006-06-23 10:20         ` Ingo Molnar
2006-05-29 21:24 ` [patch 22/61] lock validator: add per_cpu_offset() Ingo Molnar
2006-05-30  1:34   ` Andrew Morton
2006-06-23  9:30     ` Ingo Molnar
2006-05-29 21:25 ` [patch 23/61] lock validator: core Ingo Molnar
2006-05-29 21:25 ` [patch 24/61] lock validator: procfs Ingo Molnar
2006-05-29 21:25 ` [patch 25/61] lock validator: design docs Ingo Molnar
2006-05-30  9:07   ` Nikita Danilov
2006-05-29 21:25 ` [patch 26/61] lock validator: prove rwsem locking correctness Ingo Molnar
2006-05-29 21:25 ` [patch 27/61] lock validator: prove spinlock/rwlock " Ingo Molnar
2006-05-30  1:35   ` Andrew Morton
2006-06-23 10:44     ` Ingo Molnar
2006-05-29 21:25 ` [patch 28/61] lock validator: prove mutex " Ingo Molnar
2006-05-29 21:25 ` [patch 29/61] lock validator: print all lock-types on SysRq-D Ingo Molnar
2006-05-29 21:25 ` [patch 30/61] lock validator: x86_64 early init Ingo Molnar
2006-05-29 21:25 ` [patch 31/61] lock validator: SMP alternatives workaround Ingo Molnar
2006-05-29 21:25 ` [patch 32/61] lock validator: do not recurse in printk() Ingo Molnar
2006-05-29 21:25 ` [patch 33/61] lock validator: disable NMI watchdog if CONFIG_LOCKDEP Ingo Molnar
2006-05-29 22:49   ` Keith Owens
2006-05-29 21:25 ` [patch 34/61] lock validator: special locking: bdev Ingo Molnar
2006-05-30  1:35   ` Andrew Morton
2006-05-30  5:13     ` Arjan van de Ven
2006-05-30  9:58     ` Al Viro
2006-05-30 10:45     ` Arjan van de Ven
2006-05-29 21:25 ` [patch 35/61] lock validator: special locking: direct-IO Ingo Molnar
2006-05-29 21:26 ` [patch 36/61] lock validator: special locking: serial Ingo Molnar
2006-05-30  1:35   ` Andrew Morton
2006-06-23  9:49     ` Ingo Molnar
2006-06-23 10:04       ` Andrew Morton
2006-06-23 10:18         ` Ingo Molnar
2006-05-29 21:26 ` [patch 37/61] lock validator: special locking: dcache Ingo Molnar
2006-05-30  1:35   ` Andrew Morton
2006-05-30 20:51     ` Steven Rostedt
2006-05-30 21:01       ` Ingo Molnar
2006-06-23  9:51       ` Ingo Molnar
2006-05-29 21:26 ` [patch 38/61] lock validator: special locking: i_mutex Ingo Molnar
2006-05-30 20:53   ` Steven Rostedt
2006-05-30 21:06     ` Ingo Molnar
2006-05-29 21:26 ` [patch 39/61] lock validator: special locking: s_lock Ingo Molnar
2006-05-29 21:26 ` [patch 40/61] lock validator: special locking: futex Ingo Molnar
2006-05-29 21:26 ` [patch 41/61] lock validator: special locking: genirq Ingo Molnar
2006-05-29 21:26 ` [patch 42/61] lock validator: special locking: kgdb Ingo Molnar
2006-05-29 21:26 ` [patch 43/61] lock validator: special locking: completions Ingo Molnar
2006-05-29 21:26 ` [patch 44/61] lock validator: special locking: waitqueues Ingo Molnar
2006-05-29 21:26 ` [patch 45/61] lock validator: special locking: mm Ingo Molnar
2006-05-29 21:26 ` [patch 46/61] lock validator: special locking: slab Ingo Molnar
2006-05-30  1:35   ` Andrew Morton
2006-06-23  9:54     ` Ingo Molnar
2006-05-29 21:26 ` [patch 47/61] lock validator: special locking: skb_queue_head_init() Ingo Molnar
2006-05-29 21:26 ` [patch 48/61] lock validator: special locking: timer.c Ingo Molnar
2006-05-29 21:27 ` [patch 49/61] lock validator: special locking: sched.c Ingo Molnar
2006-05-29 21:27 ` [patch 50/61] lock validator: special locking: hrtimer.c Ingo Molnar
2006-05-30  1:35   ` Andrew Morton
2006-06-23 10:04     ` Ingo Molnar
2006-06-23 10:38       ` Andrew Morton
2006-06-23 10:52         ` Ingo Molnar
2006-06-23 11:52           ` Ingo Molnar
2006-06-23 12:06             ` Andrew Morton
2006-05-29 21:27 ` [patch 51/61] lock validator: special locking: sock_lock_init() Ingo Molnar
2006-05-30  1:36   ` Andrew Morton
2006-06-23 10:06     ` Ingo Molnar
2006-05-29 21:27 ` [patch 52/61] lock validator: special locking: af_unix Ingo Molnar
2006-05-30  1:36   ` Andrew Morton
2006-06-23 10:07     ` Ingo Molnar
2006-05-29 21:27 ` [patch 53/61] lock validator: special locking: bh_lock_sock() Ingo Molnar
2006-05-29 21:27 ` [patch 54/61] lock validator: special locking: mmap_sem Ingo Molnar
2006-05-29 21:27 ` [patch 55/61] lock validator: special locking: sb->s_umount Ingo Molnar
2006-05-30  1:36   ` Andrew Morton
2006-06-23 10:55     ` Ingo Molnar
2006-05-29 21:27 ` [patch 56/61] lock validator: special locking: jbd Ingo Molnar
2006-05-29 21:27 ` [patch 57/61] lock validator: special locking: posix-timers Ingo Molnar
2006-05-29 21:27 ` [patch 58/61] lock validator: special locking: sch_generic.c Ingo Molnar
2006-05-29 21:27 ` [patch 59/61] lock validator: special locking: xfrm Ingo Molnar
2006-05-30  1:36   ` Andrew Morton
2006-05-29 21:27 ` [patch 60/61] lock validator: special locking: sound/core/seq/seq_ports.c Ingo Molnar
2006-05-29 21:28 ` [patch 61/61] lock validator: enable lock validator in Kconfig Ingo Molnar
2006-05-30  1:36   ` Andrew Morton
2006-05-30 13:33   ` Roman Zippel
2006-06-23 11:01     ` Ingo Molnar
2006-06-26 11:37       ` Roman Zippel
2006-05-29 22:28 ` [patch 00/61] ANNOUNCE: lock validator -V1 Michal Piotrowski
2006-05-29 22:41   ` Ingo Molnar
2006-05-29 23:09     ` Dave Jones
2006-05-30  5:45       ` Arjan van de Ven
2006-05-30  6:07         ` Michal Piotrowski
2006-05-30 14:10         ` Dave Jones
2006-05-30 14:19           ` Arjan van de Ven
2006-05-30 14:58             ` Dave Jones
2006-05-30 17:11               ` Dominik Brodowski
2006-05-30 19:02                 ` Dave Jones
2006-05-30 19:25                   ` Roland Dreier
2006-05-30 19:34                     ` Dave Jones
2006-05-30 20:41                     ` Ingo Molnar
2006-05-30 20:44                       ` Ingo Molnar
2006-05-30 21:58                       ` Paolo Ciarrocchi
2006-05-31  8:40                         ` Ingo Molnar
2006-05-30 19:39                 ` Dave Jones
2006-05-30 19:53                   ` Ashok Raj
2006-06-01  5:50                     ` Nathan Lynch
2006-05-30 20:54         ` [patch, -rc5-mm1] lock validator: select KALLSYMS_ALL Ingo Molnar
2006-05-30  5:52       ` [patch 00/61] ANNOUNCE: lock validator -V1 Michal Piotrowski
2006-05-30  5:20   ` Arjan van de Ven
2006-05-30  1:35 ` Andrew Morton
2006-06-23  9:41   ` Ingo Molnar
2006-05-30  4:52 ` Mike Galbraith
2006-05-30  6:20   ` Arjan van de Ven
2006-05-30  6:35   ` Arjan van de Ven
2006-05-30  7:47     ` Ingo Molnar
2006-05-30  6:37   ` Ingo Molnar
2006-05-30  9:25     ` Mike Galbraith
2006-05-30 10:57       ` Ingo Molnar
2006-05-30  9:14 ` Benoit Boissinot
2006-05-30 10:26   ` Arjan van de Ven
2006-05-30 11:42     ` Benoit Boissinot
2006-05-30 12:13       ` Ingo Molnar
2006-06-01 14:42   ` [patch mm1-rc2] lock validator: netlink.c netlink_table_grab fix Frederik Deweerdt
2006-06-02  3:10     ` Zhu Yi
2006-06-02  9:53       ` Frederik Deweerdt
2006-06-05  3:40         ` Zhu Yi
2007-02-13 14:20 ` [patch 00/11] ANNOUNCE: "Syslets", generic asynchronous system call support Ingo Molnar
2007-02-13 15:00   ` Alan
2007-02-13 14:58     ` Benjamin LaHaise
2007-02-13 15:09       ` Arjan van de Ven
2007-02-13 16:24       ` bert hubert
2007-02-13 16:56       ` Ingo Molnar
2007-02-13 18:56         ` Evgeniy Polyakov
2007-02-13 19:12           ` Evgeniy Polyakov
2007-02-13 22:19             ` Ingo Molnar
2007-02-13 22:18           ` Ingo Molnar
2007-02-14  8:59             ` Evgeniy Polyakov
2007-02-14 10:37               ` Ingo Molnar
2007-02-14 11:10                 ` Evgeniy Polyakov
2007-02-14 17:17                 ` Davide Libenzi
2007-02-13 20:34       ` Ingo Molnar
2007-02-13 15:46     ` Dmitry Torokhov
2007-02-13 20:39       ` Ingo Molnar
2007-02-13 22:36         ` Dmitry Torokhov
2007-02-14 11:07         ` Alan
2007-02-13 16:39     ` Andi Kleen
2007-02-13 16:26       ` Linus Torvalds
2007-02-13 17:03         ` Ingo Molnar
2007-02-13 20:26         ` Davide Libenzi
2007-02-13 16:49       ` Ingo Molnar
2007-02-13 16:42     ` Ingo Molnar
2007-02-13 20:22   ` Davide Libenzi
2007-02-13 21:24     ` Davide Libenzi
2007-02-13 22:10       ` Ingo Molnar
2007-02-13 23:28         ` Davide Libenzi
2007-02-13 21:57     ` Ingo Molnar
2007-02-13 22:50       ` Olivier Galibert
2007-02-13 22:59       ` Ulrich Drepper
2007-02-13 23:24       ` Davide Libenzi
2007-02-13 23:25       ` Andi Kleen
2007-02-13 22:26         ` Ingo Molnar
2007-02-13 22:32           ` Andi Kleen
2007-02-13 22:43             ` Ingo Molnar
2007-02-13 22:47               ` Andi Kleen
2007-02-14  3:28   ` Davide Libenzi
2007-02-14  4:49     ` Davide Libenzi
2007-02-14  8:26       ` Ingo Molnar
2007-02-14  4:42   ` Willy Tarreau
2007-02-14 12:37   ` Pavel Machek
2007-02-14 17:14     ` Linus Torvalds
2007-02-14 20:52   ` Jeremy Fitzhardinge
2007-02-14 21:36     ` Davide Libenzi
2007-02-15  0:08       ` Jeremy Fitzhardinge
2007-02-15  2:07         ` Davide Libenzi
2007-02-15  2:44   ` Zach Brown
2007-02-13 14:20 ` [patch 01/11] syslets: add async.h include file, kernel-side API definitions Ingo Molnar
2007-02-13 14:20 ` [patch 02/11] syslets: add syslet.h include file, user API/ABI definitions Ingo Molnar
2007-02-13 20:17   ` Indan Zupancic
2007-02-13 21:43     ` Ingo Molnar
2007-02-13 22:24       ` Indan Zupancic
2007-02-13 22:32         ` Ingo Molnar
2007-02-19  0:22   ` Paul Mackerras
2007-02-13 14:20 ` [patch 03/11] syslets: generic kernel bits Ingo Molnar
2007-02-13 14:20 ` [patch 04/11] syslets: core, data structures Ingo Molnar
2007-02-13 14:20 ` [patch 05/11] syslets: core code Ingo Molnar
2007-02-13 23:15   ` Andi Kleen
2007-02-13 22:24     ` Ingo Molnar
2007-02-13 22:30       ` Andi Kleen
2007-02-13 22:41         ` Ingo Molnar
2007-02-14  9:13           ` Evgeniy Polyakov
2007-02-14  9:46             ` Ingo Molnar
2007-02-14 10:09               ` Evgeniy Polyakov
2007-02-14 10:30                 ` Arjan van de Ven
2007-02-14 10:41                   ` Evgeniy Polyakov
2007-02-13 22:57       ` Andrew Morton
2007-02-14 12:43   ` Guillaume Chazarain
2007-02-14 13:17   ` Stephen Rothwell
2007-02-14 20:38   ` Linus Torvalds
2007-02-14 21:02     ` Ingo Molnar
2007-02-14 21:12       ` Ingo Molnar
2007-02-14 21:26       ` Linus Torvalds
2007-02-14 21:35         ` Ingo Molnar
2007-02-15  2:52           ` Zach Brown
2007-02-14 21:44         ` Ingo Molnar
2007-02-14 21:56         ` Alan
2007-02-14 22:32           ` Ingo Molnar
2007-02-15  1:01             ` Davide Libenzi
2007-02-15  1:28               ` Davide Libenzi
2007-02-18 20:01                 ` Pavel Machek
2007-02-18 20:37                   ` Davide Libenzi
2007-02-18 21:04                     ` Michael K. Edwards
2007-02-14 21:09     ` Davide Libenzi
2007-02-14 22:09     ` Ingo Molnar
2007-02-14 23:13       ` Linus Torvalds
2007-02-14 23:44         ` Ingo Molnar
2007-02-15  0:04           ` Ingo Molnar
2007-02-15 13:35     ` Evgeniy Polyakov
2007-02-15 16:09       ` Linus Torvalds
2007-02-15 16:37         ` Evgeniy Polyakov
2007-02-15 17:42           ` Linus Torvalds
2007-02-15 18:11             ` Evgeniy Polyakov
2007-02-15 18:25               ` Linus Torvalds
2007-02-15 19:04                 ` Evgeniy Polyakov
2007-02-15 19:28                   ` Linus Torvalds
2007-02-15 20:07                     ` Linus Torvalds
2007-02-15 21:17                       ` Davide Libenzi
2007-02-15 22:34                       ` Michael K. Edwards
2007-02-16 12:28                       ` Ingo Molnar
2007-02-16 13:28                         ` Evgeniy Polyakov
2007-02-16  8:57                     ` Evgeniy Polyakov
2007-02-16 15:54                       ` Linus Torvalds
2007-02-16 16:05                         ` Evgeniy Polyakov
2007-02-16 16:53                           ` Ray Lee
2007-02-16 16:58                             ` Evgeniy Polyakov
2007-02-16 20:20                               ` Cyrill V. Gorcunov
2007-02-17 10:02                                 ` Evgeniy Polyakov
2007-02-17 17:59                                   ` Cyrill V. Gorcunov
2007-02-17  4:54                               ` Ray Lee
2007-02-17 10:15                                 ` Evgeniy Polyakov
2007-02-15 18:46             ` bert hubert
2007-02-15 19:10               ` Evgeniy Polyakov
2007-02-15 19:16               ` Zach Brown
2007-02-15 19:26               ` Eric Dumazet
2007-02-15 17:05         ` Davide Libenzi
2007-02-15 17:17           ` Evgeniy Polyakov
2007-02-15 17:39             ` Davide Libenzi
2007-02-15 18:01               ` Evgeniy Polyakov
2007-02-15 17:17         ` Ulrich Drepper
2007-02-13 14:20 ` [patch 06/11] syslets: core, documentation Ingo Molnar
2007-02-13 20:18   ` Davide Libenzi
2007-02-13 21:34     ` Ingo Molnar
2007-02-13 23:21       ` Davide Libenzi
2007-02-14  0:18         ` Davide Libenzi
2007-02-14 10:36   ` Russell King
2007-02-14 10:50     ` Ingo Molnar
2007-02-14 11:04       ` Russell King
2007-02-14 17:52         ` Davide Libenzi
2007-02-14 18:03           ` Benjamin LaHaise
2007-02-14 19:45             ` Davide Libenzi
2007-02-14 20:03               ` Benjamin LaHaise
2007-02-14 20:14                 ` Davide Libenzi
2007-02-14 20:34                   ` Benjamin LaHaise
2007-02-14 21:06                     ` Davide Libenzi
2007-02-14 21:44                       ` Benjamin LaHaise
2007-02-14 23:17                         ` Davide Libenzi
2007-02-14 23:40                           ` Benjamin LaHaise
2007-02-15  0:35                             ` Davide Libenzi
2007-02-15  1:32                         ` Michael K. Edwards [this message]
2007-02-14 21:49                     ` [patch] x86: split FPU state from task state Ingo Molnar
2007-02-14 22:04                       ` Benjamin LaHaise
2007-02-14 22:10                         ` Arjan van de Ven
2007-02-13 14:20 ` [patch 07/11] syslets: x86, add create_async_thread() method Ingo Molnar
     [not found] ` <20061213130211.GT21847@elte.hu>
2007-02-15 10:13   ` [patch 19/31] clockevents: i386 drivers Andrew Morton

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=f2b55d220702141732k642f17ccnc2256e54383e713@mail.gmail.com \
    --to=medwards.linux@gmail.com \
    --cc=akpm@zip.com.au \
    --cc=alan@lxorguk.ukuu.org.uk \
    --cc=arjan@infradead.org \
    --cc=bcrl@kvack.org \
    --cc=davem@davemloft.net \
    --cc=davidel@xmailserver.org \
    --cc=drepper@redhat.com \
    --cc=hch@infradead.org \
    --cc=johnpol@2ka.mipt.ru \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=rmk+lkml@arm.linux.org.uk \
    --cc=suparna@in.ibm.com \
    --cc=tglx@linutronix.de \
    --cc=torvalds@linux-foundation.org \
    --cc=zach.brown@oracle.com \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®