Hi Eric,
On Tue, 15 Oct 2013 07:06:25 -0700
Eric Dumazet wrote:
> On Tue, 2013-10-15 at 15:56 +0200, Sébastien Dugué wrote:
> > On Tue, 15 Oct 2013 15:33:36 +0200
> > Andi Kleen wrote:
> >
> > > > indeed, our typical workload is connected mode IP
On Tue, 15 Oct 2013 15:33:36 +0200
Andi Kleen wrote:
> > indeed, our typical workload is connected mode IPoIB on mlx4 QDR hardware
> > where one cannot benefit from hardware offloads.
>
> Is this with sendfile?
Tests were done with iperf at the time without any extra funky options, and
look
Hi Neil, Andi,
On Mon, 14 Oct 2013 16:25:28 -0400
Neil Horman wrote:
> On Sun, Oct 13, 2013 at 09:38:33PM -0700, Andi Kleen wrote:
> > Neil Horman writes:
> >
> > > Sébastien Dugué reported to me that devices implementing ipoib (which
> > > don't hav
Hi John,
On Tue, 04 Dec 2007 11:57:43 +0100 John Sigler <[EMAIL PROTECTED]> wrote:
> Hello everyone,
>
> I have an x86 system, running Linux 2.6.22.1-rt9, in which I plug one
> or two PCI I/O boards. I had been experiencing complete system lock-ups
> until I sent the system to the board manuf
Andrew, due to mailer problems, I'm not sure you received my previous mail
titled: "[PATCH] V2 - quirk: Enable MSI Mapping on HT1000" if you did,
then forget it and use this one instead. Or if you already merged V2 then
drop this one.
Sorry for the inconvenience.
Sebastien.
From: Sebastie
On Sun, 25 Nov 2007 11:21:48 +0800 "peerchen" <[EMAIL PROTECTED]> wrote:
> According to the HyperTransport spec, 'En' indicate if the MSI Mapping is
> active. So it should be set when enable the MSI.
>
Cool, I had a patch that added a quirk to enable MSI Mapping on Broadcom's
HT1000 so that th
) when
booting with a NUMA config or when using the Chelsio T3 (cxgb3) driver as
these seems to be the sole users.
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
---
include/linux/spinlock.h |2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Index: linux-2.6.23-rc9-rt2/include
Hi Francis,
On Wed, 1 Aug 2007 17:30:35 +0200 "Francis Moreau" <[EMAIL PROTECTED]> wrote:
> Hello Rene,
>
> On 8/1/07, Rene Herman <[EMAIL PROTECTED]> wrote:
> > On 08/01/2007 03:27 PM, Francis Moreau wrote:
> >
> > > I'm used to hack Linux on a ARM based board and would like to be
> > > invo
Hi all,
just a datapoint FWIW
On Wed, 01 Aug 2007 17:53:32 +0200 "<::.. Teresa_II ..::>" <[EMAIL PROTECTED]>
wrote:
> У чт, 2007-08-02 у 01:00 +1000, Matthew Hawkins пише:
>
> > Are you sure its not just a setting in Gnome/KDE for accessibility?
> > That tends to do crazy things like maki
Hi Pavel,
On Tue, 31 Jul 2007 15:58:31 +0200 Pavel Machek <[EMAIL PROTECTED]> wrote:
> Hi!
>
> I wanted to know if it is possible/okay to swap over AOE...
>
> According to
> http://www.coraid.com/support/linux/EtherDrive-2.6-HOWTO-5.html#ss5.20
> .. it runs OOM even during normal use, so I g
Hi Josh,
On Mon, 30 Jul 2007 14:50:34 -0700 Josh Triplett <[EMAIL PROTECTED]> wrote:
> On Tue, 2007-07-24 at 15:42 +0200, Sébastien Dugué wrote:
> > this one-liner fixes a bug in balance_rt_tasks() which sometimes
> > manifests by
> > having a lower prio task bei
On Wed, 25 Jul 2007 16:41:23 -0600 Bjorn Helgaas <[EMAIL PROTECTED]> wrote:
> On Wednesday 25 July 2007 07:32:53 am Sébastien Dugué wrote:
> > On Wed, 25 Jul 2007 07:16:44 -0600 Bjorn Helgaas <[EMAIL PROTECTED]> wrote:
> >
> > > The _DDN is a "DOS device
On Wed, 25 Jul 2007 15:32:53 +0200 Sébastien Dugué <[EMAIL PROTECTED]> wrote:
>
> Hi Bjorn,
>
> On Wed, 25 Jul 2007 07:16:44 -0600 Bjorn Helgaas <[EMAIL PROTECTED]> wrote:
>
> > On Wednesday 25 July 2007 01:45:54 am Sébastien Dugué wrote:
> >
Hi Bjorn,
On Wed, 25 Jul 2007 07:16:44 -0600 Bjorn Helgaas <[EMAIL PROTECTED]> wrote:
> On Wednesday 25 July 2007 01:45:54 am Sébastien Dugué wrote:
> > looks like the commit was dropped, nevertheless here is some more info
> > to try and understand what may be going
Hi Bjorn,
looks like the commit was dropped, nevertheless here is some more info
to try and understand what may be going on so it may benefit the posterity ;-)
On Tue, 24 Jul 2007 09:48:45 -0600 Bjorn Helgaas <[EMAIL PROTECTED]> wrote:
> On Tuesday 24 July 2007 08:28:05 am Sébast
Hi Bjorn,
your commit 7e92b4fc345f5b6f57585fbe5ffdb0f24d7c9b26 broke the serial console
on my box. Adding 'legacy_serial.force=1' to my boot param as a workaround
solves the issue, but this may be hiding bugs in Linux PnP support or
in my firmware.
The box is a dual HT Xeon running a vanill
x27; pulling tasks that are only garanteed to
have a higher priority than the 'next' picked before the loop.
Fix this to update 'next' to the last picked RT task.
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
---
kernel/sched.c |8
1 file changed,
Hi Josh,
On Thu, 12 Jul 2007 10:13:57 -0700 Josh Triplett <[EMAIL PROTECTED]> wrote:
> On Thu, 2007-07-12 at 09:41 -0700, Josh Triplett wrote:
> > On Wed, 2007-07-11 at 16:47 +0200, Sébastien Dugué wrote:
> > > there seems to be something wrong with the way the CFS
Hi Josh,
On Thu, 12 Jul 2007 09:41:55 -0700 Josh Triplett <[EMAIL PROTECTED]> wrote:
> On Wed, 2007-07-11 at 16:47 +0200, Sébastien Dugué wrote:
> > there seems to be something wrong with the way the CFS balances (or does
> > not
> > balance) RT tasks. T
On Wed, 11 Jul 2007 13:41:55 -0400 (EDT) Steven Rostedt <[EMAIL PROTECTED]>
wrote:
> > On Wed, 2007-07-11 at 16:47 +0200, Sébastien Dugué wrote:
> > >
> > > P.S. Thanks to Steven Rostedt for logdev which is proving invaluable in
> > >ca
On Wed, 11 Jul 2007 19:06:20 +0200 Thomas Gleixner <[EMAIL PROTECTED]> wrote:
> On Wed, 2007-07-11 at 16:47 +0200, Sébastien Dugué wrote:
> > The following patch fixes this by re-enabling the RT overload detection
> > for the CFS. It may not be the right solutio
ff-by: Sébastien Dugué <[EMAIL PROTECTED]>
---
kernel/sched_rt.c |4
1 file changed, 4 insertions(+)
Index: linux-2.6.21.5-rt20/kernel/sched_rt.c
===
--- linux-2.6.21.5-rt20.orig/kernel/sched_rt.c 2007-07-11 10:46:2
Hi Peter,
Only two sub-minor nits:
On Mon, 9 Jul 2007 19:52:01 -0700 "H. Peter Anvin" <[EMAIL PROTECTED]> wrote:
> From: H. Peter Anvin <[EMAIL PROTECTED]>
>
> Verify that the CPU has enough features to run the kernel. This may
> entail enabling features on some CPUs.
>
> By doing this i
On Wed, 04 Jul 2007 12:51:16 -0700 "H. Peter Anvin" <[EMAIL PROTECTED]> wrote:
> Sébastien Dugué wrote:
> >
> > One last thing, is there a git server as well for eu?
> >
>
> FWIW, I've set up git.eu.kernel.org; right now it's an alias to
> git.kernel.org, but that might change in the futu
On Tue, 03 Jul 2007 16:16:01 -0700 "H. Peter Anvin" <[EMAIL PROTECTED]> wrote:
> Hi all,
>
> Thanks to HP, ISC and Umeå Universitet, kernel.org now has official
> servers in Europe. Specifically, we have www1.eu.kernel.org hosted at
> ISC Amsterdam, and www2.eu.kernel.org at UMU (Umeå, Sweden.
ocksource's vread method was lost in the x86_64 conversion
to clockevent. So here it is.
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
arch/i386/kernel/hpet.c | 10 ++
1 file changed, 10 insertions(+)
Index: linux-2.6.21.3-rt9/arch/i386/kernel/hpet.c
===
On Wed, 2 May 2007 16:28:27 +0200 (CEST) Geert Uytterhoeven <[EMAIL PROTECTED]>
wrote:
> + $warnings += search(qr/__FUNCION__/,
^__FUNCTION__ maybe?
> + "Should use C99 __func__ instead of GNU
> __FUNCTION__\n");
Sébas
Rusty,
On Thu, 22 Mar 2007 20:24:10 +1100 Rusty Russell <[EMAIL PROTECTED]> wrote:
> On Thu, 2007-03-22 at 09:10 +0100, Sébastien Dugué wrote:
> > Why not take on the opportunity to rename boot_gt_table to boot_gtd,
> > to avoid the duplicate T(able)?
>
> That
Hi Rusty,
On Thu, 22 Mar 2007 10:58:30 +1100 Rusty Russell <[EMAIL PROTECTED]> wrote:
> On Wed, 2007-03-21 at 10:51 -0600, Eric W. Biederman wrote:
> > Rusty Russell <[EMAIL PROTECTED]> writes:
> >
> > > On Wed, 2007-03-21 at 03:31 -0600, Eric W. Biederman wrote:
> > >> Rusty Russell <[EMAIL
On Wed, 7 Mar 2007 00:49:19 -0800 Andrew Morton <[EMAIL PROTECTED]> wrote:
> On Wed, 7 Mar 2007 09:39:48 +0100 Sébastien Dugué <[EMAIL PROTECTED]> wrote:
>
> >
> > Hi Andrew,
> >
> > On Tue, 6 Mar 2007 00:44:08 -0800 Andrew Morton <[EMAIL PROTEC
Hi Andrew,
On Tue, 6 Mar 2007 00:44:08 -0800 Andrew Morton <[EMAIL PROTECTED]> wrote:
>
> Temporarily at
>
> http://userweb.kernel.org/~akpm/2.6.21-rc2-mm2/
>
> Will appear later at
>
>
> ftp://ftp.kernel.org/pub/linux/kernel/people/akpm/patches/2.6/2.6.20-rc2/2.6.20-rc2-mm2/
>
>
>
Hi Laurent,
On Tue, 13 Feb 2007 10:29:59 +0100 Laurent Pinchart <[EMAIL PROTECTED]> wrote:
> Hi everybody,
>
> I'm trying to fetch from the Linux kernel repository at
> http://www.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git/. After
> downloading the objects, git failed while
On Fri, 9 Feb 2007 01:05:57 -0800 Andrew Morton <[EMAIL PROTECTED]> wrote:
> On Fri, 9 Feb 2007 09:26:11 +0100 Sébastien Dugué <[EMAIL PROTECTED]> wrote:
>
> > On Fri, 9 Feb 2007 11:02:28 +0530 "Bharata B Rao" <[EMAIL PROTECTED]> wrote:
> >
>
On Fri, 9 Feb 2007 11:02:28 +0530 "Bharata B Rao" <[EMAIL PROTECTED]> wrote:
> Andrew,
>
> On 2/9/07, Andrew Morton <[EMAIL PROTECTED]> wrote:
> > fsaio-add-a-wait-queue-arg-to-the-wait_bit-action-routine.patch
> > fsaio-add-a-wait-queue-arg-to-the-wait_bit-action-routine-gfs2-fix.patch
> > fsaio
Andrew, one more cleanup to aio_setup_sigevent() to make it more readable.
Sébastien.
From: Sébastien Dugué <[EMAIL PROTECTED]>
AIO completion signal notification small cleanup
This patch cleans up aio_setup_sigevent() to make it more readable.
aio.c | 15
On Tue, 6 Feb 2007 14:05:39 +0300 Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> On 02/06, S?bastien Dugu? wrote:
> >
> > @@ -970,8 +969,14 @@ static long aio_setup_sigevent(struct ai
> > rcu_read_lock();
> > target = sigevent_find_task(&event);
> >
> > - if (unlikely(!target))
> > + if
Andrew, here is another incremental patch which does a bit of cleanup
as well as fixing a possible release on a task ref that was not taken.
Thanks,
Sébastien.
From: Sébastien Dugué <[EMAIL PROTECTED]>
AIO completion signal notification misc fixes and cleanups
This p
On Mon, 5 Feb 2007 20:13:35 +0300 Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> On 02/05, S?bastien Dugu? wrote:
> >
> > Make sure we only accept valid sigev_notify values in
> > aio_setup_sigevent(),
> > namely SIGEV_NONE, SIGEV_THREAD_ID or SIGEV_SIGNAL.
>
> I think this is correct, but I have
Andrew,
here is an incremental patch to fix a possible ref leak when users
do weird things with the ->sigev_notify flags.
Thanks Oleg for spotting this.
Sébastien.
From: Sébastien Dugué <[EMAIL PROTECTED]>
Fix AIO completion signal notification possible ref lea
: Sébastien Dugué <[EMAIL PROTECTED]>
Make good_sigevent() non-static and rename it
Move good_sigevent() from posix-timers.c to signal.c where it belongs,
clean it up, rename it to sigevent_find_task() to better describe what the
function does and make it non-static so that it
Hi Oleg,
thanks for your comments.
On Fri, 2 Feb 2007 21:00:39 +0300 Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> On 02/01, S?bastien Dugu? wrote:
> >
> > +struct task_struct * sigevent_find_task(sigevent_t * event)
> > +{
> > + struct task_struct *task = NULL;
> > +
> > + if (event->sig
From: Sébastien Dugué <[EMAIL PROTECTED]>
Fix access_ok() checks in sys_io_submit() and
compat_sys_io_submit()
sys_io_submit() and compat_sys_io_submit() check for the number of
requests (nr) being positive, but the following access_ok(
From: Sébastien Dugué <[EMAIL PROTECTED]>
Make __sigqueue_alloc() and __sigqueue_free() non static
Allow subsystems to directly call into __sigqueue_alloc() and __sigqueue_free.
This is used by the AIO signal notification patch.
include/linux/signal.h |3 +++
From: Sébastien Dugué <[EMAIL PROTECTED]>
Fix the double inclusion of linux/uio.h in linux/aio.h
aio.h |1 -
1 file changed, 1 deletion(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Index: linux-2.6.20-rc6-mm3/include
ompletion depending on the event argument.
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Signed-off-by: Laurent Vivier <[EMAIL PROTECTED]>
Signed-off-by: Bharata B Rao <[EMAIL PROTECTED]>
---
arch/i386/kernel/syscall_table.S |1
arch/x86_64/ia32/ia32entry.S |
From: Sébastien Dugué <[EMAIL PROTECTED]>
Make good_sigevent() non-static and rename it
Move good_sigevent() from posix-timers.c to signal.c where it belongs,
clean it up, rename it to sigevent_find_task() to better describe what the
function does and make it non-sta
From: Sébastien Dugué <[EMAIL PROTECTED]>
compat_sys_io_submit() cleanup
Cleanup compat_sys_io_submit by duplicating some of the native syscall
logic in the compat layer and directly calling io_submit_one() instead
of fooling the syscall into thinking it is called
Hi Andrew,
here is the latest rework of the aio notification and listio support
patches with comments from Oleg Nesterov and you addressed.
Sébastien.
This set now consists in 7 patches:
1. rework-compat-sys-io-submit: cleanup the sys_io_submit() compat
layer,
makin
From: Sébastien Dugué <[EMAIL PROTECTED]>
AIO completion signal notification
The current 2.6 kernel does not support notification of user space via
an RT signal upon an asynchronous IO completion. The POSIX specification
states that when an AIO request comple
On Fri, 26 Jan 2007 14:52:33 +0300 Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> On 01/26, S?bastien Dugu? wrote:
> >
> > On Thu, 25 Jan 2007 19:21:41 +0300 Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> >
> > > > + target = good_sigevent(&event);
> > > > +
> > > > + if (unlikely(!target ||
On Thu, 25 Jan 2007 19:21:41 +0300 Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> Sebastien Dugue wrote:
> >
> > +static long aio_setup_sigevent(struct aio_notify *notify,
> > + struct sigevent __user *user_event)
> > +{
> > + sigevent_t event;
> > + struct task_struct *ta
On Fri, 26 Jan 2007 13:08:01 +0300 Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> On 01/26, S?bastien Dugu? wrote:
> >
> > On Thu, 25 Jan 2007 18:43:24 +0300 Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> >
> > > SИbastien DuguИ wrote:
> > > >
> > > > +struct task_struct *good_sigevent(sigevent_t *event)
On Thu, 25 Jan 2007 18:43:24 +0300 Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> SИbastien DuguИ wrote:
> >
> > +struct task_struct *good_sigevent(sigevent_t *event)
> > +{
> > + struct task_struct *task = current->group_leader;
> > +
> > + if ((event->sigev_notify & SIGEV_THREAD_ID) == SIGEV_THR
; >
> > > Did this just leak a ref on the task_struct?
> > >
> >
> > No, the ref is released in really_put_req() when we dispose of
> > the iocb.
>
> And the code really needs a comment explaining this. I tripped over
> this before, and I think it&#
On Thu, 25 Jan 2007 05:42:42 + Christoph Hellwig <[EMAIL PROTECTED]> wrote:
> On Wed, Jan 24, 2007 at 12:11:30PM +0100, S?bastien Dugu? wrote:
> > > > + if (unlikely(!notify->sigq))
> > > > + return -EAGAIN;
> > >
> > > Did this just leak a ref on the task_struct?
> > >
>
On Tue, 23 Jan 2007 22:04:33 -0800 Andrew Morton <[EMAIL PROTECTED]> wrote:
> On Wed, 17 Jan 2007 10:55:54 +0100
> Sébastien Dugué <[EMAIL PROTECTED]> wrote:
>
> > +void lio_check(struct lio_event *lio)
> > +{
> > + int ret;
> > +
>
On Wed, 24 Jan 2007 10:52:58 +0100 Laurent Vivier <[EMAIL PROTECTED]> wrote:
> Andrew Morton wrote:
> > On Wed, 17 Jan 2007 10:55:54 +0100
> > Sébastien Dugué <[EMAIL PROTECTED]> wrote:
> >
> >> +struct lio_event *lio_create(struct sigevent __user *us
On Tue, 23 Jan 2007 21:50:47 -0800 Andrew Morton <[EMAIL PROTECTED]> wrote:
> On Wed, 17 Jan 2007 10:55:54 +0100
> Sébastien Dugué <[EMAIL PROTECTED]> wrote:
>
> > +asmlinkage long
> > +compat_sys_lio_submit(aio_context_t ctx_id, int mode, int nr, u32 __user
On Tue, 23 Jan 2007 21:35:13 -0800 Andrew Morton <[EMAIL PROTECTED]> wrote:
> On Wed, 17 Jan 2007 10:50:18 +0100
> Sébastien Dugué <[EMAIL PROTECTED]> wrote:
>
> > +static long aio_setup_sigevent(struct aio_notify *notify,
> > + s
ude/linux/aio_abi.h |3 -
kernel/signal.c |2
5 files changed, 144 insertions(+), 6 deletions(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Signed-off-by: Laurent Vivier <[EMAIL PROTECTED]>
Index: linux-2.
() to find the
sigevents.
compat.c | 61 ++---
1 file changed, 34 insertions(+), 27 deletions(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Index: linux-2.6.20-rc4-mm1/fs/co
| 24
3 files changed, 25 insertions(+), 17 deletions(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Index: linux-2.6.20-rc4-mm1/include/linux/signal.h
===
--- linux-2.6.20-rc4-mm
Fix the double inclusion of linux/uio.h in linux/aio.h
aio.h |1 -
1 file changed, 1 deletion(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Index: linux-2.6.20-rc4-mm1/include/linux/aio.h
===
--- linux-2.6.
ompletion depending on the event argument.
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Signed-off-by: Laurent Vivier <[EMAIL PROTECTED]>
Signed-off-by: Bharata B Rao <[EMAIL PROTECTED]>
---
arch/i386/kernel/syscall_table.S |1
arch/x86_64/ia32/ia32entry.S |
Hi,
Andrew, would you consider including this patchset in -mm for some more
testing. At least patches 1 - 4.
Patch 5 is the new listio syscall approach from Bharata B Rao which is much
cleaner than overloading sys_io_submit() with a new opcode but maybe needs some
more discussion before b
On Wed, 20 Dec 2006 13:19:09 +0200 "Pekka Enberg" <[EMAIL PROTECTED]> wrote:
> On 12/20/06, Sébastien Dugué <[EMAIL PROTECTED]> wrote:
> > set_param_str() cannot use kstrdup() to duplicate the parameter. That's
> > fine when the driver is compiled as
deletions(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Index: linux-2.6.20-rc1/drivers/char/ipmi/ipmi_watchdog.c
===
--- linux-2.6.20-rc1.orig/drivers/char/ipmi/ipmi_watchdog.c 2006-12-14
02:14:23.0 +0100
+++
On Mon, 4 Dec 2006 22:43:13 +0530 Bharata B Rao <[EMAIL PROTECTED]> wrote:
> On Wed, Nov 29, 2006 at 11:32:34AM +0100, Sébastien Dugué wrote:
> >
> >
> > +/***
> > + * good_sigevent - check and get target task from a sigevent.
> > + * @event: the sige
Hi
Here is the latest rework of the AIO completion signal notification patches.
This set consists in 5 patches:
1. rework-compat-sys-io-submit: cleanup the sys_io_submit() compat
layer,
making it more efficient and laying out the base for the following
patches
| 24
3 files changed, 25 insertions(+), 17 deletions(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Index: linux-2.6.19-rc6-mm2/include/linux/signal.h
===
--- linux-2.6.19-rc6-mm
Fix the double inclusion of linux/uio.h in linux/aio.h
aio.h |1 -
1 file changed, 1 deletion(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Index: linux-2.6.19-rc6-mm2/include/linux/aio.h
===
--- linux-2.6.
ude/linux/aio_abi.h |3 -
kernel/signal.c |2
5 files changed, 144 insertions(+), 6 deletions(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Signed-off-by: Laurent Vivier <[EMAIL PROTECTED]>
Index: linux-2.
() to find the
sigevents.
compat.c | 61 ++---
1 file changed, 34 insertions(+), 27 deletions(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Index: linux-2.6.19-rc6-mm2/fs/co
| 123 ++--
fs/compat.c | 62 +++-
include/linux/aio.h | 15 +
include/linux/aio_abi.h |1
4 files changed, 192 insertions(+), 9 deletions(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Signed-off-by: Laurent
On Thu, 30 Nov 2006 13:55:36 +0530, Suparna Bhattacharya <[EMAIL PROTECTED]>
wrote:
>
> Could you mention changes in this patch since your last post ?
Aside from adding compat support, nothing changed here.
>
> BTW, if I try to apply your patches, I get the following error (diffstat
> work
On Wed, 29 Nov 2006 16:47:47 -0800, Zach Brown <[EMAIL PROTECTED]> wrote:
> On Nov 29, 2006, at 2:32 AM, Sébastien Dugué wrote:
>
> > compat_sys_io_submit() cleanup
> >
> >
> > Cleanup compat_sys_io_submit by duplicating some of the native
On Wed, 29 Nov 2006 14:54:25 +, Christoph Hellwig <[EMAIL PROTECTED]> wrote:
> > +/***
> > + * good_sigevent - check and get target task from a sigevent.
> > + * @event: the sigevent to be checked
> > + *
> > + * This function must be called with tasklist_lock held for reading.
> > + */
> > +s
On Wed, 29 Nov 2006 13:50:12 +, Christoph Hellwig <[EMAIL PROTECTED]> wrote:
> On Wed, Nov 29, 2006 at 02:08:01PM +0100, S?bastien Dugu? wrote:
> > On Wed, 29 Nov 2006 10:51:50 +, Christoph Hellwig <[EMAIL PROTECTED]>
> > wrote:
> >
> > > I'm a little bit unhappy about the usage of the n
On Wed, 29 Nov 2006 06:33:35 -0500, Jakub Jelinek <[EMAIL PROTECTED]> wrote:
> On Wed, Nov 29, 2006 at 11:33:01AM +0100, S?bastien Dugu? wrote:
> > AIO completion signal notification
> >
> > The current 2.6 kernel does not support notification of user space via
> > an RT s
On Wed, 29 Nov 2006 10:51:50 +, Christoph Hellwig <[EMAIL PROTECTED]> wrote:
> I'm a little bit unhappy about the usage of the notify flag. The usage
> seems correct but very confusing:
Well, I followed the logic from posix-timers.c, but it may be a poor
choice ;-)
For a start, the SIGE
On Wed, 29 Nov 2006 10:38:25 +
Christoph Hellwig <[EMAIL PROTECTED]> wrote:
> On Wed, Nov 29, 2006 at 11:32:34AM +0100, S?bastien Dugu? wrote:
> >
> > Export good_sigevent()
> >
> >
> > Move good_sigevent() from posix-timers.c to signal.c where it belongs,
> > and ex
Hi
Here is the latest rework of the AIO completion signal notification patches.
This set consists in 5 patches:
1. rework-compat-sys-io-submit: rework the sys_io_submit() compat layer,
laying out the base for the following patches
2. aio-header-fix-includes: fix
the completion notification patch to avoid having
to rewrite each iocb on the caller stack for sys_io_submit() to find the
sigevents.
compat.c | 61 +++--
1 file changed, 35 insertions(+), 26 deletions(-)
Signed-off-by: Sébastien Dugué
ude/linux/aio_abi.h |3 -
kernel/signal.c |2
5 files changed, 144 insertions(+), 6 deletions(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Signed-off-by: Laurent Vivier <[EMAIL PROTECTED]>
Index: linux-2.
+++
3 files changed, 24 insertions(+), 17 deletions(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Index: linux-2.6.19-rc6-mm2/include/linux/signal.h
===
--- linux-2.6.19-rc6-mm2.orig/include/linux/si
| 123 ++--
fs/compat.c | 62 +++-
include/linux/aio.h | 15 +
include/linux/aio_abi.h |1
4 files changed, 192 insertions(+), 9 deletions(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Signed-off-by: Laurent
Fix the double inclusion of linux/uio.h in linux/aio.h
aio.h |1 -
1 file changed, 1 deletion(-)
Signed-off-by: Sébastien Dugué <[EMAIL PROTECTED]>
Index: linux-2.6.19-rc6-mm2/include/linux/aio.h
===
--- linux-2.6.
On Thu, 2005-07-28 at 12:52 -0400, Trond Myklebust wrote:
> to den 28.07.2005 Klokka 17:46 (+0200) skreiv Sébastien Dugué:
> >
> >
> >
> >
> >
> >
> >
> > ukjent vedlegg
> > (aiomaxevents)
>
> Please don't post these pa
On Thu, 2005-07-28 at 17:46 +0200, Sébastien Dugué wrote:
> infrastructure to be used by user level libraries aiming at implementing
> a POSIX compliant API on top of this kernel support.
>
> This patchset is comprised of 5 patches, each implementing a specific
>
aioevent
Description: Binary data
lioevent
Description: Binary data
liowait
Description: Binary data
order shown before.
--
--
Sébastien DuguéBULL/FREC:B1-247
phone: (+33) 476 29 77 70 Bullcom: 229-7770
mailto:[EMAIL PROTECTED]
Linux POSIX AIO: http://www.bullopensource.org/posix
aiomaxevents
Description: Binary data
cancelfd
Description: Binary data
for 2.6.12. I'm currently trying to trace it.
aio-stress shows no difference so it probably does not come from
kernel AIO.
Sébastien.
--
--
Sébastien DuguéBULL/FREC:B1-247
phone: (+33) 476 29 77 70
e
return value. The penalty incured by the trailing part going buffered
is the price to pay for not having a fully aligned file.
I think doing otherwise would break read(2) semantics.
Sébastien.
--
Sébastien DuguéBULL/FREC:B1-247
phone: (+33) 476 29 77 70 Bullcom:
> But from Sebastien's description it doesn't soound as if a concurrent
> truncate is involved.
Yes, you're right, there's no concurrent truncate here. My test case
as well as Daniel's is single threaded and is the only thread accessing
the file.
Regards,
Sébastien.
--
-
> But from Sebastien's description it doesn't soound as if a concurrent
> truncate is involved.
Yes, you're right, there's no concurrent truncate here. My test case
as well as Daniel's is single threaded and is the only thread accessing
the file.
Regards,
Sébastien.
--
-
re a check is made against the file size.
This patch does the same thing for the async path. It applies to
a vanilla 2.6.10 kernel.
Please CC: me any comments and/or suggestions.
Sébastien.
--
Sébastien DuguéBULL/FREC:B1-2
100 matches
Mail list logo
