On Sat, 2007-01-13 at 00:03 +0300, Michael Tokarev wrote:
[snip]
> And sure thing, withOUT O_DIRECT, the whole system is almost dead under this
> load - because everything is thrown away from the cache, even caches of /bin
> /usr/bin etc... ;) (For that, fadvise() seems to help a bit, but not
I've reworked this patch to resolve the problem I was seeing. I will
post the new patch in a separate, new posting with subject line of
"[PATCH] Cell SPU task notification".
-Maynard
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL
On Fri, 12 Jan 2007, Paul Jackson wrote:
> It might look clearer to someone who is focused on that particular
> change, but it adds unnecessary noise for the other 90% of the readers
> of that code who are not concerned with cpusets at that point in time.
This is in NUMA specific code. And they
> Sorry but there will be number of those once we get the dirty writeback
> for cpusets fixed. Did you review that patchset (only internally mailed
> so far).
I haven't reviewed it - sorry. Too much stuff; too little time.
If only I had Alan's bots, which are apparently on loan now to Andrew.
I'm working on an embedded PPC setup with 64M of memory and no swap.
I'm trying to figure out how best to tune the VM for an OOM situation
I'm running into.
I'm running a 2.6.16.35 kernel and have a bittorrent app that appears
to be initializing a large file for it to download into. What
> Eric Sandeen (ES) writes:
ES> I tend to agree, chatting w/ Al I think he does too. :) I'll test
ES> a patch that kicks out ext3_link() with -ENOENT at the top, and resubmit
ES> that if things go well.
shouldn't VFS do that?
thanks, Alex
-
To unsubscribe from this list: send the line
Linus Torvalds wrote:
[]
> My point is that you can get basically ALL THE SAME GOOD BEHAVIOUR without
> having all the BAD behaviour that O_DIRECT adds.
*This* point I got from the beginning, once I tried to think how it all
is done internally (I never thought about that, because I'm not a
On Fri, Jan 12, 2007 at 09:42:16PM +, Russell King wrote:
> On Fri, Jan 12, 2007 at 09:00:15PM +, Russell King wrote:
> > Could we please have this (or a proper fix) in before 2.6.20 to resolve
> > the regression please?
>
> Actually, this remaining regression is not caused by this patch
Alex Tomas wrote:
>> Eric Sandeen (ES) writes:
>
> ES> so I think it's possible that link can sneak in there & find it after
> ES> the mutex is dropped...? Is this ok? :) It's certainly -happening-
> ES> anyway
>
> yes, but it shouldn't allow to re-link such inode back, IMHO.
> a
On Fri, 12 Jan 2007 21:00:15 +
Russell King <[EMAIL PROTECTED]> wrote:
> Could we please have this (or a proper fix) in before 2.6.20 to resolve
> the regression please?
>
>
> ...
>
> --- a/drivers/hid/Kconfig
> +++ b/drivers/hid/Kconfig
> @@ -6,6 +6,7 @@ menu "HID Devices"
>
> config HID
On Fri, 12 Jan 2007, Ravikiran G Thirumalai wrote:
> > Does the system scale the right way if you stay within the bounds of node
> > memory? I.e. allocate 1.5GB from each process?
>
> Yes. We see problems only when we oversubscribe memory.
Ok in that case we can have more than 2 processors
On Fri, Jan 12, 2007 at 09:00:15PM +, Russell King wrote:
> Could we please have this (or a proper fix) in before 2.6.20 to resolve
> the regression please?
Actually, this remaining regression is not caused by this patch not being
integrated, but this:
config USB_HID
tristate "USB
On Fri, Jan 12, 2007 at 11:46:22AM -0800, Christoph Lameter wrote:
> On Fri, 12 Jan 2007, Ravikiran G Thirumalai wrote:
>
> > The test was simple, we have 16 processes, each allocating 3.5G of memory
> > and and touching each and every page and returning. Each of the process is
> > bound to a
On Sat, 13 Jan 2007, Al Boldi wrote:
> Justin Piszcz wrote:
> > Btw, max sectors did improve my performance a little bit but
> > stripe_cache+read_ahead were the main optimizations that made everything
> > go faster by about ~1.5x. I have individual bonnie++ benchmarks of
> > [only] the
On Fri, 12 Jan 2007, Paul Jackson wrote:
> Argh - minor detail, but this is the first (outside of fs/proc/base.c)
> "#ifdef CONFIG_CPUSETS" in a kernel *.c file. I prefer to avoid that.
Sorry but there will be number of those once we get the dirty writeback
for cpusets fixed. Did you review
> Eric Sandeen (ES) writes:
ES> so I think it's possible that link can sneak in there & find it after
ES> the mutex is dropped...? Is this ok? :) It's certainly -happening-
ES> anyway
yes, but it shouldn't allow to re-link such inode back, IMHO.
a filesystem may start some
On Fri, 12 Jan 2007 11:46:22 -0800 (PST)
Christoph Lameter <[EMAIL PROTECTED]> wrote:
> > While the softlockups and the like went away by enabling interrupts during
> > spinning, as mentioned in http://lkml.org/lkml/2007/1/3/29 ,
> > Andi thought maybe this is exposing a problem with
OFF TOPIC:
The 50th show of TVLinux is coming up at the end of February. I would
invite all the active kernel developers in the Portland area, to be in a
round table discussion about Linux and Open Source. The program will be
filmed at the studio of TVCTV in Beaverton Oregon. I want to make the
Andrew, regarding a patch by Andy:
> + nodemask_t allowed_nodes;
>
> err = get_nodes(, nmask, maxnode);
> - nodes_and(nodes, nodes, current->mems_allowed);
> + allowed_nodes = cpuset_mems_allowed(current);
Not that it matters now, as we're messing with other variations,
but I
On Sat, 2007-01-13 at 00:02 +0300, Alex Tomas wrote:
> interesting ..
>
> I thought VFS doesn't allow concurrent operations.
> if unlink goes first, then link should wait on the
> parent's i_mutex and then found no source name.
I don't think the VFS ever takes the source's parent's i_mutex.
On Sat, 13 Jan 2007, Michael Tokarev wrote:
>
> (No, really - this load isn't entirely synthetic. It's a typical database
> workload - random I/O all over, on a large file. If it can, it combines
> several I/Os into one, by requesting more than a single block at a time,
> but overall it is
Christoph wrote:
> +++ linux-2.6.20-rc4-mm1/mm/mempolicy.c 2007-01-12 13:21:30.220968608
> -0600
> ...
> +#ifdef CONFIG_CPUSETS
Argh - minor detail, but this is the first (outside of fs/proc/base.c)
"#ifdef CONFIG_CPUSETS" in a kernel *.c file. I prefer to avoid that.
How about doing
ah, it seems vfs_link() doesn't check whether source is still alive.
for example, in mkdir case vfs_mkdir() calls may_create() and
checks the parent is still there:
if (IS_DEADDIR(dir))
return -ENOENT;
VFS doesn't set S_DEAD on regular files, but we could check i_nlink.
Alex Tomas wrote:
> interesting ..
>
> I thought VFS doesn't allow concurrent operations.
> if unlink goes first, then link should wait on the
> parent's i_mutex and then found no source name.
>
> thanks, Alex
Well... I was wondering that myself, whether this race should even
happen. But the
The following configuration:
CONFIG_JFFS2_FS=y
CONFIG_JFFS2_FS_DEBUG=2
# CONFIG_JFFS2_FS_NAND is not set
# CONFIG_JFFS2_FS_NOR_ECC is not set
# CONFIG_JFFS2_COMPRESSION_OPTIONS is not set
CONFIG_JFFS2_ZLIB=y
CONFIG_JFFS2_RTIME=y
# CONFIG_JFFS2_RUBIN is not set
results in these build errors:
Michael Tokarev wrote:
> Michael Tokarev wrote:
> By the way. I just ran - for fun - a read test of a raid array.
>
> Reading blocks of size 512kbytes, starting at random places on a 400Gb
> array, doing 64threads.
>
> O_DIRECT: 336.73 MB/sec.
> !O_DIRECT: 146.00 MB/sec.
And when turning off
interesting ..
I thought VFS doesn't allow concurrent operations.
if unlink goes first, then link should wait on the
parent's i_mutex and then found no source name.
thanks, Alex
> Eric Sandeen (ES) writes:
ES> )
ES> I've been looking at a case where many threads are opening, unlinking,
Hi Venkatesh,
I have an IBM IntelliStation Z30 with two Dempsey CPUs. When I try to
boot 2.6.20-rc4 on it, the system prints messages about NMI watchdog
lockups. git-bisect determined that the patch "[PATCH] x86-64: Fix
interrupt race in idle callback (3rd try)" was the source of these
Could we please have this (or a proper fix) in before 2.6.20 to resolve
the regression please?
- Forwarded message from Russell King <[EMAIL PROTECTED]> -
Date: Fri, 22 Dec 2006 17:09:16 +
From: Russell King <[EMAIL PROTECTED]>
To: Linux Kernel List
Cc: [EMAIL PROTECTED], [EMAIL
Justin Piszcz wrote:
> Btw, max sectors did improve my performance a little bit but
> stripe_cache+read_ahead were the main optimizations that made everything
> go faster by about ~1.5x. I have individual bonnie++ benchmarks of
> [only] the max_sector_kb tests as well, it improved the times from
Michael Tokarev wrote:
[]
> After all the explanations, I still don't see anything wrong with the
> interface itself. O_DIRECT isn't "different semantics" - we're still
> writing and reading some data. Yes, O_DIRECT and non-O_DIRECT usages
> somewhat contradicts with each other, but there are
Andrew Morton wrote:
On Tue, 07 Nov 2006 16:45:07 -0600
Eric Sandeen <[EMAIL PROTECTED]> wrote:
Andrew Morton wrote:
--- linux-2.6.19-rc4.orig/fs/buffer.c 2006-11-07 17:06:20.0 +
+++ linux-2.6.19-rc4/fs/buffer.c2006-11-07 17:26:04.0 +
@@ -188,7
Chris Mason wrote:
[]
> I recently spent some time trying to integrate O_DIRECT locking with
> page cache locking. The basic theory is that instead of using
> semaphores for solving O_DIRECT vs buffered races, you put something
> into the radix tree (I call it a placeholder) to keep the page
I've been looking at a case where many threads are opening, unlinking, and
hardlinking files on ext3 . At unmount time I see an oops, because the
superblock's
orphan list points to a freed inode.
I did some tracing of the inodes, and it looks like this:
Justin Piszcz wrote:
# echo 3 > /proc/sys/vm/drop_caches
# dd if=/dev/md3 of=/dev/null bs=1M count=10240
10240+0 records in
10240+0 records out
10737418240 bytes (11 GB) copied, 399.352 seconds, 26.9 MB/s
# for i in sde sdg sdi sdk; do echo 192 >
/sys/block/"$i"/queue/max_sectors_kb; echo
On Fri, Jan 12, 2007 at 10:06:22AM -0800, Linus Torvalds wrote:
> > looking at the splice(2) api it seems like it'll be difficult to implement
> > O_DIRECT pread/pwrite from userland using splice... so there'd need to be
> > some help there.
>
> You'd use vmsplice() to put the write buffers
Btw, max sectors did improve my performance a little bit but
stripe_cache+read_ahead were the main optimizations that made everything
go faster by about ~1.5x. I have individual bonnie++ benchmarks of
[only] the max_sector_kb tests as well, it improved the times from 8min/bonnie
run -> 7min
On Friday 12 January 2007 8:38 am, Russell King wrote:
> A more correct test would be that found in kallsyms.c:
Good point. Updated patch appended.
- Dave
=== CUT HERE
This patch stops "modpost" from issuing erroneous modpost warnings on ARM
builds, which it's been doing simce
Pavel Machek <[EMAIL PROTECTED]> wrote on 01/11/2007 09:35:37 AM:
> Hi!
>
> > SLIM implements dynamic process labels, so when a process
> > is demoted, we must be able to revoke write access to some
> > resources to which it has previously valid handles.
> > For example, if a shell reads an
On Fri, 12 Jan 2007, Al Boldi wrote:
> Justin Piszcz wrote:
> > RAID 5 TWEAKED: 1:06.41 elapsed @ 60% CPU
> >
> > This should be 1:14 not 1:06(was with a similarly sized file but not the
> > same) the 1:14 is the same file as used with the other benchmarks. and to
> > get that I used 256mb
On Fri, 12 Jan 2007, Serge E. Hallyn wrote:
> Hmm, would revokefs need to be explicitly stacked on top of the fs,
> or could we just swap out fdt[fd] for the revokefs file, and have
> the revokefs file's private data point to the original inode, with
> it's write function returning an error, and
Justin Piszcz wrote:
> RAID 5 TWEAKED: 1:06.41 elapsed @ 60% CPU
>
> This should be 1:14 not 1:06(was with a similarly sized file but not the
> same) the 1:14 is the same file as used with the other benchmarks. and to
> get that I used 256mb read-ahead and 16384 stripe size ++ 128
>
On Fri, 12 Jan 2007, Ravikiran G Thirumalai wrote:
> The test was simple, we have 16 processes, each allocating 3.5G of memory
> and and touching each and every page and returning. Each of the process is
> bound to a node (socket), with the local node being the preferred node for
> allocation
Horms wrote:
> Hi,
>
> this patch fills in the portions for ia64 kexec.
>
> I'm actually not sure what options are required for the dump-capture
> kernel, but "init 1 irqpoll maxcpus=1" has been working fine for me.
> Or more to the point, I'm not sure if irqpoll is needed or not.
>
> This
On Friday January 12, [EMAIL PROTECTED] wrote:
> > Are you really really double-plus sure that you are running a kernel
> > with the patch applied?
> > Because at the very least it should have changed the message to
>
> Oh, sorry. I recompiled & installed kernel and it output this new message:
>
On Fri, Jan 12, 2007 at 01:43:42PM +0100, Juergen Beisert wrote:
> does someone know how to forward a kernel command line option to configure the
> AMD Geode GX1 framebuffer?
>
> I tried with "video=gx1fb:[EMAIL PROTECTED]" but it does not work. On another
> machine with an SIS framebuffer the
Not-so-recently already, device directories in /sys started providing
files like modalias, which corresponds to $MODALIAS env. variable at
uevent time. Also not-so-recently, uevent file appeared, which, when
written, triggers re-execution of an uevent corresponding to the
device. So far so good.
Quoting Pekka Enberg ([EMAIL PROTECTED]):
> On 1/10/07, Serge E. Hallyn <[EMAIL PROTECTED]> wrote:
> >Now, what slim needs isn't "revoke all files for this inode",
> >but "revoke this task's write access to this fd". So two functions
> >which could be useful are
> >
> >int
Ok, there it is, in all its shining glory.
A lot of developers (including me) will be gone next week for
Linux.Conf.Au, so you have a week of rest and quiet to test this, and
report any problems.
Not that there will be any, right? You all behave now!
The patches here are pretty basic. Lots
On Fri, 12 Jan 2007, Paul Jackson wrote:
> I'll leave the honors to Christoph (added to CC), since this is his patch.
Ok. Here it is
mems_allowed only exists if CONFIG_CPUSETS is set. So put an #ifdef around
it. Also move the masking of the nodes behind the error check (looks
better) and add a
On Fri, Jan 12, 2007 at 10:33:34AM -0700, Eric W. Biederman wrote:
> > And I get:
> >
> > [ 1013.864201] PAGE 81000100 (pfn=0): flags=0, count=0
> >
> > So at least no one is using that page. Still it is not clear why it
> > doesn't have the reserve flag turned on.
>
> My hunch is that it
Quoting Paul Menage ([EMAIL PROTECTED]):
> Hi Serge,
>
> On 1/3/07, Serge E. Hallyn <[EMAIL PROTECTED]> wrote:
> >From: Serge E. Hallyn <[EMAIL PROTECTED]>
> >Subject: [RFC] [PATCH 1/1] container: define a namespace container
> >subsystem
> >
> >Here's a stab at a namespace container subsystem
On Sun, Jan 07, 2007 at 03:27:03PM +0900, Tejun Heo wrote:
> Mark Wagner wrote:
> [--snip--]
> >NETDEV WATCHDOG: eth0: transmit timed out
> >eth0: transmit timed out, tx_status 00 status e000.
> [--snip--]
> >hda: DMA timeout error
> >hda: dma timeout error: status=0x58 { DriveReady SeekComplete
* Nick Piggin ([EMAIL PROTECTED]) wrote:
> OK, well one problem is that it can cause a resched event to be lost, so
> you might say it has more side-effects without checking resched.
>
Here is the patch that implements this. I also did a cosmetic change to
linux/marker.h. Preliminary tests of
On Thu, 11 Jan 2007, dean gaudet wrote:
>
> it seems to me that if splice and fadvise and related things are
> sufficient for userland to take care of things "properly" then O_DIRECT
> could be changed into splice/fadvise calls either by a library or in the
> kernel directly...
The problem
On 12/01/07, Michal Piotrowski <[EMAIL PROTECTED]> wrote:
On 12/01/07, Rafael J. Wysocki <[EMAIL PROTECTED]> wrote:
> On Friday, 12 January 2007 14:33, Michal Piotrowski wrote:
> > My system hangs on this
> > http://www.stardust.webpages.pl/files/tbf/euridica/2.6.20-rc4-mm1/bug2.jpg
> >
Suparna Bhattacharya schrieb:
> On Fri, Jan 12, 2007 at 12:55:18PM +0100, Tilman Schmidt wrote:
[...]
>> causes a sparse warning:
>>
>> > include/linux/sched.h:1313:29: warning: symbol '__mptr' shadows an earlier
>> > one
>> > include/linux/sched.h:1313:29: originally declared here
>>
>> for
* Mathieu Desnoyers ([EMAIL PROTECTED]) wrote:
> >
> > OK, well one problem is that it can cause a resched event to be lost, so
> > you might say it has more side-effects without checking resched.
> >
[...]
> If we are sure that we expect calls to preempt_schedule() from each of these
>
At Fri, 12 Jan 2007 14:49:57 +0100,
Oliver Neukum wrote:
>
> + } else {
> + if (idx < snd_ecards_limit) {
> + if (snd_cards_lock & (1 << idx))
> + err = -EBUSY; /* invalid */
> + } else if (idx < SNDRV_CARDS)
> +
On 12/01/07, Rafael J. Wysocki <[EMAIL PROTECTED]> wrote:
On Friday, 12 January 2007 14:33, Michal Piotrowski wrote:
> My system hangs on this
> http://www.stardust.webpages.pl/files/tbf/euridica/2.6.20-rc4-mm1/bug2.jpg
>
RAID 5 TWEAKED: 1:06.41 elapsed @ 60% CPU
This should be 1:14 not 1:06(was with a similarly sized file but not the
same) the 1:14 is the same file as used with the other benchmarks. and to
get that I used 256mb read-ahead and 16384 stripe size ++ 128
max_sectors_kb (same size as my sw raid5
Dan Aloni <[EMAIL PROTECTED]> writes:
> On Fri, Jan 12, 2007 at 06:43:40PM +0200, Dan Aloni wrote:
>> On Fri, Jan 12, 2007 at 06:28:00PM +0200, Dan Aloni wrote:
>> > On Fri, Jan 12, 2007 at 06:02:43PM +0200, Dan Aloni wrote:
>> > > On Fri, Jan 12, 2007 at 08:26:03AM -0700, Eric W. Biederman
On 1/12/07, Balbir Singh <[EMAIL PROTECTED]> wrote:
I understand that the features are exported to userspace. But from
the userspace POV only the mount options change - right?
The mount options, plus the fact that you can mount different
instances of containerfs with different resource
On 1/12/07, Alan <[EMAIL PROTECTED]> wrote:
> It seems that it821x_tune_chipset() is buggy since it sends SET FEATURES
> command even when in smart mode. Shouldn't there be "don't tune" flag
> in it812x_fixups() to tell it821x_tune_chipset() to not send SET FEATURES
> commands?
It's
* Nick Piggin ([EMAIL PROTECTED]) wrote:
> Mathieu Desnoyers wrote:
> >* Nick Piggin ([EMAIL PROTECTED]) wrote:
> >
> >>Mathieu Desnoyers wrote:
> >>
> >>
> >>>+#define MARK(name, format, args...) \
> >>>+ do { \
> >>>+ static marker_probe_func *__mark_call_##name = \
> >>>+
On Fri, 2007-01-12 at 08:01 -0800, Ravikiran G Thirumalai wrote:
> Hi,
> We noticed high interrupt hold off times while running some memory intensive
> tests on a Sun x4600 8 socket 16 core x86_64 box. We noticed softlockups,
> lost ticks and even wall time drifting (which is probably a bug in
Soeren Sonnenburg wrote:
Dear all,
I'd like to try out SATA hotplugging using a SIL3114. Though I was
harvesting the web, I could not find any useful information how this is
done in practice.
Well I realized that I can still use scsiadd to print and remove
devices, e.g.:
For SIL3114, you
Ingo Molnar wrote:
* Ingo Molnar <[EMAIL PROTECTED]> wrote:
dyntick-enabled guest:
- reduce the load on the host when the guest is idling
(currently an idle guest consumes a few percent cpu)
yeah. KVM under -rt already works with dynticks enabled on both the
host and the guest.
Linus Torvalds wrote:
O_DIRECT is still crazily racy versus pagecache operations.
>>>
>>>Yes. O_DIRECT is really fundamentally broken. There's just no way to fix
>>>it sanely.
>>
>>How about aliasing O_DIRECT to POSIX_FADV_NOREUSE (sortof) ?
>
>
> That is what I think some users could do.
Linus Torvalds wrote:
>>OK, madvise() used with mmap'ed file allows to have reads from a file
>>with zero-copy between kernel/user buffers and don't pollute cache
>>memory unnecessarily. But how about writes? How is to do zero-copy
>>writes to a file and don't pollute cache memory without using
On Fri, Jan 12, 2007 at 06:43:40PM +0200, Dan Aloni wrote:
> On Fri, Jan 12, 2007 at 06:28:00PM +0200, Dan Aloni wrote:
> > On Fri, Jan 12, 2007 at 06:02:43PM +0200, Dan Aloni wrote:
> > > On Fri, Jan 12, 2007 at 08:26:03AM -0700, Eric W. Biederman wrote:
> > > > Dan Aloni <[EMAIL PROTECTED]>
On Fri, Jan 12, 2007 at 06:28:00PM +0200, Dan Aloni wrote:
> On Fri, Jan 12, 2007 at 06:02:43PM +0200, Dan Aloni wrote:
> > On Fri, Jan 12, 2007 at 08:26:03AM -0700, Eric W. Biederman wrote:
> > > Dan Aloni <[EMAIL PROTECTED]> writes:
> > >
> > > > I'm attaching the full logs.
> > >
> > >
qconf does not clear help text in search window
if previous search has been failed.
Signed-off-by: Cyrill V. Gorcunov <[EMAIL PROTECTED]>
---
diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc
index c0ae0a7..f9a63a4 100644
--- a/scripts/kconfig/qconf.cc
+++
On Fri, Jan 12, 2007 at 08:31:36AM -0800, David Brownell wrote:
> Index: at91/scripts/mod/modpost.c
> ===
> --- at91.orig/scripts/mod/modpost.c 2007-01-11 22:51:49.0 -0800
> +++ at91/scripts/mod/modpost.c2007-01-12
Hi,
Minor number 0 (under the raw major) is reserved for the rawctl device
file, which is used to query, set, and unset raw device bindings.
However, the ioctl interface does not protect the user from specifying
a raw device with minor number 0:
$ sudo ./raw /dev/raw/raw0 /dev/VolGroup00/swap
This patch stops "modpost" from issuing erroneous modpost warnings on ARM
builds, which it's been doing simce since maybe last summer. A canonical
example would be driver method table entries:
WARNING: - Section mismatch: reference to .exit.text:_remove
from .data after '$d' (at
On Fri, Jan 12, 2007 at 06:02:43PM +0200, Dan Aloni wrote:
> On Fri, Jan 12, 2007 at 08:26:03AM -0700, Eric W. Biederman wrote:
> > Dan Aloni <[EMAIL PROTECTED]> writes:
> >
> > > I'm attaching the full logs.
> >
> > Thanks.
> >
> > > [ 8656.272980] ACPI Error (tbxfroot-0512): Could not map
Hello,
> This may help
> http://lkml.org/lkml/2007/1/12/45
True. Now it boots fine. Tanks for the tip.
Dzięki Michał.
--
Regards,
Mariusz Kozlowski
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo
On Fri, Jan 12, 2007 at 08:26:03AM -0700, Eric W. Biederman wrote:
> Dan Aloni <[EMAIL PROTECTED]> writes:
>
> > I'm attaching the full logs.
>
> Thanks.
>
> > [ 8656.272980] ACPI Error (tbxfroot-0512): Could not map memory at 040E
> > for length 2 [20060707]
>
> Ok. This looks like the
Hi,
We noticed high interrupt hold off times while running some memory intensive
tests on a Sun x4600 8 socket 16 core x86_64 box. We noticed softlockups,
lost ticks and even wall time drifting (which is probably a bug in the
x86_64 timer subsystem).
The test was simple, we have 16 processes,
Mark Hounschell wrote:
> I have a Tyan S4881 Thunder K8QW 4 processor (8 cores). Kernel 2.6.16.37 boots
> and runs fine.
> However kernel 2.6.17 and up doesn't. Here is my boot error msg.
>
>
> kernel /vmlinuz-2.6.17-smp root=/dev/sda5inux version 2.6.17-smp ([EMAIL
> PROTECTED])
> (gcc
On Friday, 12 January 2007 14:33, Michal Piotrowski wrote:
> My system hangs on this
> http://www.stardust.webpages.pl/files/tbf/euridica/2.6.20-rc4-mm1/bug2.jpg
> http://www.stardust.webpages.pl/files/tbf/euridica/2.6.20-rc4-mm1/mm-config
>
> Debug plan:
> - revert md-* patches
> - binary search
I have a Tyan S4881 Thunder K8QW 4 processor (8 cores). Kernel 2.6.16.37 boots
and runs fine.
However kernel 2.6.17 and up doesn't. Here is my boot error msg.
kernel /vmlinuz-2.6.17-smp root=/dev/sda5inux version 2.6.17-smp ([EMAIL
PROTECTED])
(gcc version 4.1.0 (SUSE Linux)) #1 SMP PREEMPT
Hi,
> > + if (my_cq->ownpid != cur_pid) {
> > + ehca_err(device, "Invalid caller pid=%x ownpid=%x "
> > +"cq_num=%x",
> > +cur_pid, my_cq->ownpid, my_cq->cq_number);
> > + return -EINVAL;
> > +
dean gaudet wrote:
it seems to me that if splice and fadvise and related things are
sufficient for userland to take care of things "properly" then O_DIRECT
could be changed into splice/fadvise calls either by a library or in the
kernel directly...
No, because the semantics are entirely
Hi Roland!
> > > spin_lock_irqsave(_cq_idr_lock, flags);
> > > while (my_cq->nr_callbacks)
> > > yield();
>
> > Isn't that code outright buggy? Calling into the scheduler with a
> > spinlock held and local interrupts disabled...
>
> Yes, absolutely -- if
Dan Aloni <[EMAIL PROTECTED]> writes:
> I'm attaching the full logs.
Thanks.
> [ 8656.272980] ACPI Error (tbxfroot-0512): Could not map memory at 040E
> for length 2 [20060707]
Ok. This looks like the first sign of trouble.
Normally I would suspect a memory map issue but your e820 memory
Hua Zhong wrote:
The other problem besides the inability to handle IO errors is that
mmap()+msync() is synchronous. You need to go async to keep
the pipelines full.
msync(addr, len, MS_ASYNC); doesn't do what you want?
No, because there is no notification of completion. In fact, does
Quoting Pekka Enberg ([EMAIL PROTECTED]):
> On 1/11/07, Serge E. Hallyn <[EMAIL PROTECTED]> wrote:
> >Right, but is returning -EINVAL to userspace on munmap a problem?
>
> Yes, because an application has no way of reusing the revoked mapping
> range. The current patch should get this right,
On 12/01/07, Mariusz Kozlowski <[EMAIL PROTECTED]> wrote:
Hello,
> That's because mmc_lock_unlock should depend on CONFIG_KEYS, it uses struct
key.
> Could you try the following patch (compile tested)?
Thanks. Compiles ok but now I run into another problem and the laptop doesn't
boot.
The
Hello,
> That's because mmc_lock_unlock should depend on CONFIG_KEYS, it uses struct
> key.
> Could you try the following patch (compile tested)?
Thanks. Compiles ok but now I run into another problem and the laptop doesn't
boot.
The last thing I see is grub. So no way to test it now. Time to
> It seems that it821x_tune_chipset() is buggy since it sends SET FEATURES
> command even when in smart mode. Shouldn't there be "don't tune" flag
> in it812x_fixups() to tell it821x_tune_chipset() to not send SET FEATURES
> commands?
It's itdev->smart but falls through to ide_config_drive_speed
On Fri, Jan 12, 2007 at 06:55:32PM +0530, Sunil Naidu wrote:
> There are 2 cases:-
>
> #1 Intel Pentium 4 Workstation with HyperThreading
>
> Since kernel takes HT as 2 processors, I did say in KConfig as:
>
> CONFIG_SMP= y
> CONFIG_NR_CPUS=2
> CONFIG_SCHED_MC=not set
> CONFIG_MPENTIUM4=y (Or
Aubrey wrote:
On 1/12/07, Nick Piggin <[EMAIL PROTECTED]> wrote:
Linus Torvalds wrote:
>
> On Fri, 12 Jan 2007, Nick Piggin wrote:
>
>>We are talking about about fragmentation. And limiting pagecache to
try to
>>avoid fragmentation is a bandaid, especially when the problem can
be solved
On Fri, Jan 12, 2007 at 07:05:09AM -0700, Eric W. Biederman wrote:
> Dan Aloni <[EMAIL PROTECTED]> writes:
>
> > Hello,
> >
> > After upgrading from 2.6.18.3 to 2.6.19.2 on an x86_64 machine I noticed
> > that the EHCI USB host is unable to work properly after a kexec invocation.
> > This makes
On Fri, Jan 12, 2007 at 07:05:09AM -0700, Eric W. Biederman wrote:
> Dan Aloni <[EMAIL PROTECTED]> writes:
>
> > Hello,
> >
> > After upgrading from 2.6.18.3 to 2.6.19.2 on an x86_64 machine I noticed
> > that the EHCI USB host is unable to work properly after a kexec invocation.
> > This makes
On 1/12/07, Alan <[EMAIL PROTECTED]> wrote:
> if(strstr(id->model, "Integrated Technology Express")) {
> /* In raid mode the ident block is slightly buggy
> We need to set the bits so that the IDE layer knows
>
On Fri, Jan 12, 2007 at 09:27:01AM -0500, linux-os (Dick Johnson) wrote:
> Sometimes a idiot boss will say; "You need to read or write files from
> within the driver. If you don't do what I tell you, you are fired!"
Sometimes PHBs want you to break the laws of physics. I suggest you
read Dilbert
On Fri, 12 Jan 2007, Michael Tokarev wrote:
> Justin Piszcz wrote:
> > Using 4 raptor 150s:
> >
> > Without the tweaks, I get 111MB/s write and 87MB/s read.
> > With the tweaks, 195MB/s write and 211MB/s read.
> >
> > Using kernel 2.6.19.1.
> >
> > Without the tweaks and with the tweaks:
> >
On Fri, 12 Jan 2007, Erik Mouw wrote:
> On Fri, Jan 12, 2007 at 11:27:01AM +0100, Jesper Juhl wrote:
>> On 12/01/07, congwen <[EMAIL PROTECTED]> wrote:
>>> Hello everyone, I want to create and read/write a file in Linux kernel or
>>> device driver,
>>
>> Don't read/write user space files from
101 - 200 of 520 matches
Mail list logo