On 12/13/2012 03:15 PM, Davidlohr Bueso wrote:
On Wed, 2012-12-12 at 20:49 -0800, Dave Hansen wrote:
How is that possible? If NUMA nodes are defined by distances from CPUs
to memory, how could a DIMM have more than a single distance to any
given CPU?
Can't this occur when interleaving
having an
arch/foo/Kconfig.debug-memory might be taking things a bit too far
Signed-off-by: Dave Hansen d...@linux.vnet.ibm.com
---
linux-2.6.git-dave/arch/x86/Kconfig.debug |2
linux-2.6.git-dave/lib/Kconfig.debug | 702 +++---
2 files changed, 357 insertions
These were in two different places, and taking up too much of my
valuable screen real-estate. Banish them to their own menu.
Signed-off-by: Dave Hansen d...@linux.vnet.ibm.com
---
linux-2.6.git-dave/lib/Kconfig.debug | 160 +--
1 file changed, 82 insertions
the actual menu option.
Signed-off-by: Dave Hansen d...@linux.vnet.ibm.com
---
linux-2.6.git-dave/arch/blackfin/Kconfig |1 +
linux-2.6.git-dave/arch/blackfin/Kconfig.debug |7 ---
linux-2.6.git-dave/arch/frv/Kconfig|1 +
linux-2.6.git-dave/arch/frv/Kconfig.debug
. This menu should only be used for tests
that do not have a more appropriate home.
Signed-off-by: Dave Hansen d...@linux.vnet.ibm.com
---
linux-2.6.git-dave/lib/Kconfig.debug | 151 ++-
1 file changed, 78 insertions(+), 73 deletions(-)
diff -puN lib/Kconfig.debug
, configfs, or /proc.
Also, Debug filesystem sounds like a debugging option _for_
filesystems code, not a filesystem for debugging. We also never call
it the debug filesystem. We always say debugfs, so reflect the
fact that we _call_ it debugfs in the menu text.
Signed-off-by: Dave Hansen d
even though I'm actually moving the options on
either side of it.
Signed-off-by: Dave Hansen d...@linux.vnet.ibm.com
---
linux-2.6.git-dave/lib/Kconfig.debug | 156 +--
1 file changed, 80 insertions(+), 76 deletions(-)
diff -puN lib/Kconfig.debug~consolidate
I think the Kernel Hacking menu has gotten a bit out of hand. It
is over 120 lines long on my system with everything enabled and
options are scattered around it haphazardly.
http://sr71.net/~dave/linux/kconfig-horror.png
Let's try to introduce some sanity.
--
To unsubscribe from this
There are quite a few of these, and we want to make sure that
there is one-stop-shopping for lock debugging.
Signed-off-by: Dave Hansen d...@linux.vnet.ibm.com
---
linux-2.6.git-dave/lib/Kconfig.debug | 120 ++-
1 file changed, 62 insertions(+), 58 deletions
On 01/10/2013 07:30 AM, James Hogan wrote:
+pte_t *huge_pte_alloc(struct mm_struct *mm,
+ unsigned long addr, unsigned long sz)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = pgd_offset(mm, addr);
+ pud = pud_offset(pgd,
On 01/10/2013 01:58 PM, paul.sz...@sydney.edu.au wrote:
I developed a workaround patch for this particular OOM demo, dropping
filesystem caches when about to exhaust lowmem. However, subsequently
I observed OOM when running many processes (as yet I do not have an
easy-to-reproduce demo of
On 01/10/2013 04:46 PM, paul.sz...@sydney.edu.au wrote:
Your configuration has never worked. This isn't a regression ...
... does not mean that we expect it to work.
Do you mean that CONFIG_HIGHMEM64G is deprecated, should not be used;
that all development is for 64-bit only?
My last 4GB
On 01/10/2013 05:46 PM, paul.sz...@sydney.edu.au wrote:
... I don't believe 64GB of RAM has _ever_ been booted on a 32-bit
kernel without either violating the ABI (3GB/1GB split) or doing
something that never got merged upstream ...
Sorry to be so contradictory:
psz@como:~$ uname -a
a bunch of
duplication and adds consistency across arches.
Signed-off-by: Dave Hansen d...@linux.vnet.ibm.com
Cc: Mike Frysinger vap...@gentoo.org
Cc: David Howells dhowe...@redhat.com
Cc: Hirokazu Takata tak...@linux-m32r.org
Cc: Ralf Baechle r...@linux-mips.org
Cc: Koichi Yasutake yasutake.koi
On 01/11/2013 07:31 PM, paul.sz...@sydney.edu.au wrote:
Seems that any i386 PAE machine will go OOM just by running a few
processes. To reproduce:
sh -c 'n=0; while [ $n -lt 1 ]; do sleep 600 ((n=n+1)); done'
My machine has 64GB RAM. With previous OOM episodes, it seemed that
running
On 01/11/2013 05:00 PM, Stephen Rothwell wrote:
On Fri, 11 Jan 2013 09:00:43 -0800 Dave Hansen d...@linux.vnet.ibm.com
wrote:
I'm looking for some Acked-bys on this from the various arch
maintainers that it affects. I'd like to send it up to Linus
in the next merge window. This is part
On 01/14/2013 12:36 PM, paul.sz...@sydney.edu.au wrote:
I understand that more RAM leaves less lowmem. What is unacceptable is
that PAE crashes or freezes with OOM: it should gracefully handle the
issue. Noting that (for a machine with 4GB or under) PAE fails where the
HIGHMEM4G kernel
On 01/07/2013 12:24 PM, Seth Jennings wrote:
+struct zswap_tree {
+ struct rb_root rbroot;
+ struct list_head lru;
+ spinlock_t lock;
+ struct zs_pool *pool;
+};
BTW, I spent some time trying to get this lock contended. You thought
the anon_vma locks would dominate and this
for the page fault (it
was injected by the host), assumed that the kernel had taken
a _real_ page fault, and panic()'d.
Signed-off-by: Dave Hansen d...@linux.vnet.ibm.com
---
linux-2.6.git-dave/arch/x86/kernel/kvm.c |9 +
linux-2.6.git-dave/arch/x86/kernel/kvmclock.c |4 ++--
2 files
(), which
walks the kernel page tables on x86 and should do precisely
the same logical thing as __pa(), but actually work on a wider
range of memory. It should work on the normal linear mapping,
vmalloc(), kmap(), etc...
Signed-off-by: Dave Hansen d...@linux.vnet.ibm.com
---
linux-2.6.git-dave/arch
The KVM code has some repeated bugs in it around use of __pa() on
per-cpu data. Those data are not in an area on which __pa() is
valid. However, they are also called early enough in boot that
__vmalloc_start_set is not set, and thus the CONFIG_DEBUG_VIRTUAL
debugging does not catch them.
This
On Fri, 2007-07-06 at 12:01 +0400, Pavel Emelianov wrote:
This is submition for inclusion of hierarchical, not kconfig
configurable, zero overheaded ;) pid namespaces.
Pavel, I'm a bit disappointed that you went ahead and sent this. I
thought that, perhaps, you might have brought up how
On Thu, 2007-07-05 at 22:20 -0700, Balbir Singh wrote:
+/*
+ * the core object. the container that wishes to account for some
+ * resource may include this counter into its structures and use
+ * the helpers described beyond
+ */
I'm going to nitpick a bit here. Nothing major, I promise. ;)
On Thu, 2007-07-05 at 22:21 -0700, Balbir Singh wrote:
+struct mem_container {
+ struct container_subsys_state css;
+ /*
+ * the counter to account for memory usage
+ */
+ struct res_counter res;
+};
How about we call it memory_usage? That would kill two birds with
On Fri, 2007-07-06 at 14:03 -0700, Balbir Singh wrote:
+ssize_t res_counter_read(struct res_counter *cnt, int member,
+const char __user *userbuf, size_t nbytes, loff_t
*pos)
+{
+unsigned long *val;
+char buf[64], *s;
+
+s = buf;
+val =
On Sat, 2007-07-07 at 00:26 +0200, Andrea Arcangeli wrote:
for the hack week at opensuse (see http://idea.opensuse.org/) I've
been working on a new feature called CONFIG_PAGE_SHIFT.
...
If you want to help/look here the patch:
On Mon, 2007-07-09 at 11:16 +0400, Pavel Emelianov wrote:
Dave Hansen wrote:
On Thu, 2007-07-05 at 22:20 -0700, Balbir Singh wrote:
+/*
+ * the core object. the container that wishes to account for some
+ * resource may include this counter into its structures and use
+ * the helpers
On Mon, 2007-07-09 at 09:58 +0400, Pavel Emelianov wrote:
Dave Hansen wrote:
On Fri, 2007-07-06 at 12:01 +0400, Pavel Emelianov wrote:
This is submition for inclusion of hierarchical, not kconfig
configurable, zero overheaded ;) pid namespaces.
Pavel, I'm a bit disappointed that you
operations on the three directories, including ones
that are expected to fail, like creating a file on the r/o
mount.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
-
To unsubscribe from this list: send the line unsubscribe linux-kernel in
the body of a message to [EMAIL PROTECTED]
More majordomo info
may_open() calls vfs_permission() before it does checks for
IS_RDONLY(inode). It checks _again_ inside of vfs_permission().
The check inside of vfs_permission() is going away eventually.
With the mnt_want/drop_write() functions, all of the r/o
checks (except for this one) are consistently done
I'm going to be modifying nfsd_rename() shortly to support
read-only bind mounts. This #ifdef is around the area I'm
patching, and it starts to get really ugly if I just try
to add my new code by itself. Using this little helper
makes things a lot cleaner to use.
Signed-off-by: Dave Hansen
. When that is complete, we can actually
introduce code that will safely check the counts before
allowing r/w-r/o transitions to occur.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/namespace.c| 46 +
lxc-dave/include/linux/mount.h
Pretty self-explanatory. Fits in with the rest of the series.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/namei.c|5 +
lxc-dave/fs/nfsd/nfs4recover.c |4
2 files changed, 9 insertions(+)
diff -puN fs/namei.c~elevate-mnt-writers-for-callers-of-vfs
This basically audits the callers of xattr_permission(), which
calls permission() and can perform writes to the filesystem.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/nfsd/nfs4proc.c |7 ++-
lxc-dave/fs/xattr.c | 16 ++--
2 files changed, 20
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/namei.c | 10 ++
1 file changed, 10 insertions(+)
diff -puN fs/namei.c~elevate-write-count-for-link-and-symlink-calls fs/namei.c
--- lxc/fs/namei.c~elevate-write-count-for-link-and-symlink-calls
2007-07-10 12:46
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/inode.c | 13 -
1 file changed, 12 insertions(+), 1 deletion(-)
diff -puN fs/inode.c~elevate-write-count-for-file_update_time fs/inode.c
--- lxc/fs/inode.c~elevate-write-count-for-file_update_time 2007-07-10
12:46
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/net/unix/af_unix.c | 16
1 file changed, 12 insertions(+), 4 deletions(-)
diff -puN
net/unix/af_unix.c~unix-find-other-elevate-write-count-for-touch-atime
net/unix/af_unix.c
--- lxc/net/unix/af_unix.c~unix-find
This area of code is currently #ifdef'd out, so add a comment
for the time when it is actually used.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/namespace.c |4
1 file changed, 4 insertions(+)
diff -puN fs/namespace.c~mount-is-safe-add-comment fs/namespace.c
--- lxc
This also uses the little helper in the NFS code to
make an if() a little bit less ugly. We introduced
the helper at the beginning of the series.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/namei.c|4
lxc-dave/fs/nfsd/vfs.c | 15 +++
2 files changed
outside of the switch.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/namei.c | 32 +---
lxc-dave/fs/nfsd/vfs.c |4
lxc-dave/net/unix/af_unix.c |4
3 files changed, 29 insertions(+), 11 deletions(-)
diff -puN fs/namei.c
Elevate the write count during the vfs_rmdir() call.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/namei.c |5 +
1 file changed, 5 insertions(+)
diff -puN fs/namei.c~do-rmdir-elevate-write-count fs/namei.c
--- lxc/fs/namei.c~do-rmdir-elevate-write-count 2007-07-10 12:46
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/inode.c | 20
1 file changed, 12 insertions(+), 8 deletions(-)
diff -puN fs/inode.c~elevate-write-count-for-do-sys-utime-and-touch-atime
fs/inode.c
--- lxc/fs/inode.c~elevate-write-count-for-do-sys-utime
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/open.c | 16 +---
1 file changed, 9 insertions(+), 7 deletions(-)
diff -puN fs/open.c~elevate-writer-count-for-do-sys-truncate fs/open.c
--- lxc/fs/open.c~elevate-writer-count-for-do-sys-truncate 2007-07-10
12:46
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/namei.c |4
lxc-dave/ipc/mqueue.c |5 -
2 files changed, 8 insertions(+), 1 deletion(-)
diff -puN fs/namei.c~elevate-mnt-writers-for-vfs-unlink-callers fs/namei.c
--- lxc/fs/namei.c~elevate-mnt-writers-for-vfs
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/utimes.c | 15 +--
1 file changed, 9 insertions(+), 6 deletions(-)
diff -puN fs/utimes.c~elevate-write-count-for-do-utimes fs/utimes.c
--- lxc/fs/utimes.c~elevate-write-count-for-do-utimes 2007-07-10
12:46
two are probably unnecessary and duplicate existing
checks in the VFS. This won't make them better checks than
before, but it will make them detect r/o mounts.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/nfs/dir.c |3 ++-
lxc-dave/fs/nfsd/vfs.c |4 ++--
2 files changed, 4
Some ioctls need write access, but others don't. Make a helper
function to decide when write access is needed, and take it.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/ncpfs/ioctl.c | 55 +-
1 file changed, 54 insertions(+), 1
It is OK to let access() go without using a mnt_want/drop_write()
pair because it doesn't actually do writes to the filesystem,
and it is inherently racy anyway. This is a rare case when it is
OK to use __mnt_is_readonly() directly.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs
chown/chmod,etc... don't call permission in the same way
that the normal open for write calls do. They still
write to the filesystem, so bump the write count during
these operations.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/open.c | 39
-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/ext2/ioctl.c | 46 +-
lxc-dave/fs/ext3/ioctl.c | 100 +---
lxc-dave/fs/ext4/ioctl.c | 105 +-
lxc-dave/fs/fat/file.c
a unified place
which the r/o bind mount code may patch.
Also, rename an existing, static-scope init_file() to a less
generic name.
Signed-off-by: Dave Hansen [EMAIL PROTECTED]
---
lxc-dave/fs/configfs/dir.c|5 +++--
lxc-dave/fs/file_table.c | 34
file,
while the vfsmount is ro. That is bad.
Some filesystems forego the use of normal vfs calls to create
struct files. Make sure that these users elevate the mnt writer
count because they will get __fput(), and we need to make
sure they're balanced.
Signed-off-by: Dave Hansen [EMAIL PROTECTED
On Thu, 2007-07-12 at 18:31 +0200, Andrea Arcangeli wrote:
On Fri, Jul 13, 2007 at 12:44:49AM +1000, David Chinner wrote:
That's crap. Just because a machine has lots of memory does not
make it OK to waste lots of memory.
It's not just wasted, it lowers overhead all over the place. Yes,
On Wed, 2007-06-13 at 17:06 +0200, holzheu wrote:
The operation of a Linux system sometimes requires to decode the
meaning of a specific kernel message, e.g. an error message of a
driver. Especially on our mainframe zSeries platform system
administrators want to have descriptions for Linux
On Wed, 2007-06-13 at 11:32 -0700, Greg KH wrote:
dev_printk() and friends are great, since they already define
something
like KMSG_COMPONENT: The driver name.
They provide way more than that, they also provide the explicit device
that is being discussed, as well as other things
Andy and Joel, very cool that you got this in-tree!
I have a patch touching a bunch of fs ioctl functions.
Things like ext2_ioctl() look like this:
foo_ioctl()
{
switch(ioctl) {
case FOO:
lots
of
code
error:
On Fri, 2007-06-22 at 12:54 -0500, Joel Schopp wrote:
If it is kinda like a mini function why not make it actually a mini
function and call it?
Several of our on-disk filesystems have an ioctl function that already
has indented goto labels. I don't think it's quite worth churning all
of these
On Wed, 2007-06-06 at 13:37 +0200, Mark Pflueger wrote:
hi everyone!
i'm not subscribed to the list, so if you care to flame because of my noob
question, just do it to the list, otherwise please cc me.
i'm trying to write a checkpoint/restore module for processes and so have
a basic
On Wed, 2007-06-06 at 23:33 +0200, Martin Peschke wrote:
struct statistic_interface {
/* private: */
struct list_head list;
- struct dentry *debugfs_dir;
- struct dentry *data_file;
- struct dentry *def_file;
+ void
On Fri, 2007-05-25 at 10:41 +0200, Ingo Molnar wrote:
* William Lee Irwin III [EMAIL PROTECTED] wrote:
yes, that's what i meant under 'slightly async'. Some AMD CPUs are
like that too and sched_clock() now handles that fine. So we should
try my patch.
Sorry, then. I took slight to
On Tue, 2007-07-17 at 08:49 -0700, Paul (宝瑠) Menage wrote:
Because as soon as you do the atomic_dec_and_test() on css-refcnt and
the refcnt hits zero, then theoretically someone other thread (that
already holds container_mutex) could check that the refcount is zero
and free the container
On Mon, 2007-05-14 at 21:22 +0800, Ian Kent wrote:
I've sent mail to Dave but he must be to busy, on leave or not keen on
getting these patches included any more as I've not had a response.
I'm just now catching up on email. I was out for a couple of weeks.
I'm planning on refreshing the
On Mon, 2007-05-14 at 23:55 +0800, Ian Kent wrote:
Anything I can do to help?
If so maybe we could reduce the time to posting a bit.
Probably nothing to actually speed up the development, but I'd really
appreciate some testing once I do post them. How about I send you an
advance copy, or cc
On 08/02/2013 09:04 AM, Rob Landley wrote:
I'd be surprised if anybody who does this sees the printk and thinks
hey, I'll dig into the VM's balancing logic and come up to speed on the
tradeoffs sufficient to contribute to kernel development because of
something in dmesg. Anybody actually
On 08/05/2013 11:42 PM, Krzysztof Kozlowski wrote:
+#ifdef CONFIG_ZBUD
+ /* Allocated by zbud. Flag is necessary to find zbud pages to unuse
+ * during migration/compaction.
+ */
+ PG_zbud,
+#endif
Do you _really_ need an absolutely new, unshared page flag?
The zbud code
On 08/03/2013 07:17 PM, Kirill A. Shutemov wrote:
+ if (PageTransTailCache(page)) {
+ /* part of already handled huge page */
+ if (!page-mapping)
+ continue;
+
On 08/03/2013 07:17 PM, Kirill A. Shutemov wrote:
If a huge page is only partly in the range we zero out the part,
exactly like we do for partial small pages.
What's the logic behind this behaviour? Seems like the kind of place
that we would really want to be splitting pages.
+ if
On 08/07/2013 06:40 AM, Jan Kara wrote:
One question before I look at the patches: Why don't you use fallocate()
in your application? The functionality you require seems to be pretty
similar to it - writing to an already allocated block is usually quick.
One problem I've seen is that it
On 07/24/2013 02:29 PM, K. Y. Srinivasan wrote:
/*
- * Wait for the memory block to be onlined.
- * Since the hot add has succeeded, it is ok to
- * proceed even if the pages in the hot added region
- * have not been onlined
On 07/25/2013 04:14 AM, KY Srinivasan wrote:
As promised, I have sent out the patches for (a) an implementation of an
in-kernel API
for onlining and a consumer for this API. While I don't know the exact
reason why the
user mode code is delayed (under some low memory conditions), what is
On 07/25/2013 08:15 AM, Kay Sievers wrote:
Complexity, well, it's just a bit of code which belongs in the kernel.
The mentioned unconditional hotplug loop through userspace is
absolutely pointless. Such defaults never belong in userspace tools if
they do not involve data that is only available
On 07/25/2013 10:21 AM, Robert Jennings wrote:
+static void zap_buf_page(unsigned long useraddr)
+{
+ struct vm_area_struct *vma;
+
+ down_read(current-mm-mmap_sem);
+ vma = find_vma_intersection(current-mm, useraddr,
+ useraddr + PAGE_SIZE);
+ if
I've got a relatively new system that doesn't seem to be able to hotplug
SATA disks. I see the same behavior on 3.10, 3.11-rc2, and Ubuntu's
3.8.0-25-generic. The disks are detected right away on reboots, but
even after poking the /sys/class/scsi_host/host*/scan files, new disks
are never
On 07/26/2013 08:16 AM, Robert Jennings wrote:
+ if ((spd-flags SPLICE_F_MOVE)
+ !buf-offset (buf-len ==
PAGE_SIZE))
+ /* Can move page aligned buf */
+
On 07/25/2013 06:51 PM, Aaron Lu wrote:
On 07/26/2013 07:15 AM, Dave Hansen wrote:
I've got a relatively new system that doesn't seem to be able to hotplug
SATA disks. I see the same behavior on 3.10, 3.11-rc2, and Ubuntu's
3.8.0-25-generic. The disks are detected right away on reboots
On 07/25/2013 06:51 PM, Aaron Lu wrote:
On 07/26/2013 07:15 AM, Dave Hansen wrote:
I've got a relatively new system that doesn't seem to be able to hotplug
SATA disks. I see the same behavior on 3.10, 3.11-rc2, and Ubuntu's
3.8.0-25-generic. The disks are detected right away on reboots
From: Dave Hansen dave.han...@linux.intel.com
I got a bug report from a couple of users who said
checkpatch.pl was broken for them. It was erroring out on
fairly random lines most commonly with messages like:
Nested quantifiers in regex; marked by --HERE in m/(\((?:[^\(\)]++ --
HERE
On 08/19/2013 08:17 AM, Jerome Marchand wrote:
Some applications that run on HPC clusters are designed around the
availability of RAM and the overcommit ratio is fine tuned to get the
maximum usage of memory without swapping. With growing memory, the
1%-of-all-RAM grain provided by
On 08/19/2013 07:44 PM, Libin wrote:
When kmemcheck kernel support configured??we encountered random kernel panic
(sometimes can be booted) during system boot process in our environment. I
have tested the mainline kernel version from v3.0 to v3.11-rc6, they also
have this problem. And the
On 08/19/2013 02:25 PM, Dave Jones wrote:
* This bug last seen: 2013-08-17
Also useful here would be something like:
Seen on: 3.2-rc2, 3.10-rc10 (You can probably just list earliest/latest
rather than
every single kernel it's been seen on, unless you want a 'show all' button)
Once
On 08/20/2013 07:45 PM, Libin wrote:
[3.158023] [ cut here ]
[3.162626] WARNING: CPU: 0 PID: 1 at
arch/x86/mm/kmemcheck/kmemcheck.c:634 kmemcheck_fault+0xb1/0xc0()
...
[3.314877] [81046aa7] ? kmemcheck_trap+0x17/0x30
[3.320507] EOE #DB
On 08/21/2013 08:22 AM, Jerome Marchand wrote:
Instead of introducing yet another tunable, why don't we just make the
ratio that comes in from the user more fine-grained?
sysctl overcommit_ratio=0.2
We change the internal 'sysctl_overcommit_ratio' to store tenths or
hundreths of
On 08/21/2013 08:58 PM, Libin wrote:
I test it on IBM System x3850 X5 platform, and also trigger oops in boot
process. But if don't config the kmemcheck, it can boot up normally.
Hardware information and oops information as following:
[0.205976] BUG: unable to handle kernel paging
cc'ing Al and Kay who have the most commits in devtmpfs...
On 05/14/2013 05:02 AM, Tetsuo Handa wrote:
I got below warning.
WARNING: kmemcheck: Caught 8-bit read from uninitialized memory
(88007ae384d8)
d884e37a0088006f665f64657669
i i i i i
We talked a little about this issue in this thread:
http://marc.info/?l=linux-mmm=137573185419275w=2
but I figured I'd follow up with a full comparison. ext4 is about 20%
slower in handling write page faults than ext3. xfs is about 30% slower
than ext3. I'm running on an 8-socket /
On 08/14/2013 12:43 PM, Greg Kroah-Hartman wrote:
On Wed, Aug 14, 2013 at 02:31:45PM -0500, Seth Jennings wrote:
ppc64 has a normal memory block size of 256M (however sometimes as low
as 16M depending on the system LMB size), and (I think) x86 is 128M. With
1TB of RAM and a 256M block size,
On 08/14/2013 12:31 PM, Seth Jennings wrote:
There was a significant amount of refactoring to allow for this but
IMHO, the code is much easier to understand now.
...
drivers/base/memory.c | 248
+
include/linux/memory.h | 1 -
2 files
On 08/14/2013 12:43 PM, Theodore Ts'o wrote:
Thanks dave for doing this comparison. Is there any chance you can
check whether lockstats shows anything interesting?
Test case is this:
https://github.com/antonblanchard/will-it-scale/blob/master/tests/page_fault3.c
One interesting
On 08/14/2013 02:14 PM, Seth Jennings wrote:
On Wed, Aug 14, 2013 at 01:47:27PM -0700, Dave Hansen wrote:
On 08/14/2013 12:31 PM, Seth Jennings wrote:
+static unsigned long *memblock_present;
+static bool largememory_enable __read_mostly;
How would you see this getting used in practice
On 08/14/2013 02:37 PM, Cody P Schafer wrote:
Also, I'd expect userspace tools might use readdir() to find out what
memory blocks a system has (unless they just stat(memory0),
stat(memory1)...). I don't think filesystem tricks (at least within
sysfs) are going to let this magically be solved
On 08/14/2013 05:24 PM, Dave Chinner wrote:
On Wed, Aug 14, 2013 at 10:10:07AM -0700, Dave Hansen wrote:
We talked a little about this issue in this thread:
http://marc.info/?l=linux-mmm=137573185419275w=2
but I figured I'd follow up with a full comparison. ext4 is about 20%
slower
On 08/14/2013 06:11 PM, Theodore Ts'o wrote:
The point is that if the goal is to measure page fault scalability, we
shouldn't have this other stuff happening as the same time as the page
fault workload.
will-it-scale does several different tests probing at different parts of
the fault path:
On 08/14/2013 09:29 PM, Dave Chinner wrote:
On Wed, Aug 14, 2013 at 07:24:01PM -0700, Andi Kleen wrote:
And FWIW, it's no secret that XFS has more per-operation overhead
than ext4 through the write path when it comes to allocation, so
it's no surprise that on a workload that is highly
On 08/15/2013 08:05 AM, Theodore Ts'o wrote:
IOW, if it really is about write page fault handling, the simplest
test to do is to mmap /dev/zero and then start dirtying pages. At
that point we will be measuring the VM level write page fault code.
As I mentioned in some of the other replies,
) {
- free_pmds(pmds);
- return -ENOMEM;
- }
-
return 0;
+err:
+ free_pmds(pmds);
+ return -ENOMEM;
}
I don't have a problem with what you have, though. It's better than
what was there, so:
Reviewed-by: Dave Hansen dave.han...@linux.intel.com
On 08/14/2013 05:31 PM, Wanpeng Li wrote:
After commit 9bdac91424075(sparsemem: Put mem map for one node together.),
vmemmap for one node will be allocated together, its logic is similiar as
memory allocation for pageblock flags. This patch introduce
alloc_usemap_and_memmap
to extract the
On 08/14/2013 05:31 PM, Wanpeng Li wrote:
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 93d3182..553368c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1553,7 +1553,7 @@ static void *__vmalloc_area_node(struct vm_struct
*area, gfp_t gfp_mask,
unsigned int nr_pages, array_size, i;
Hey Nathan,
Could you post your boot timing patches? My machines are much smaller
than yours, but I'm curious how things behave here as well.
I did some very imprecise timings (strace -t on a telnet attached to the
serial console). The 'struct page' initializations take about a minute
of boot
On 08/16/2013 07:33 AM, Alex Thorlton wrote:
---
mm/huge_memory.c | 8
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a92012a..55ec681 100644
Could you add some actual descriptions to these patches that say why you
are doing
On 08/16/2013 07:34 AM, Alex Thorlton wrote:
+#if ARCH_HAS_USER_NOCACHE == 0
+#define clear_user_highpage_nocache clear_user_highpage
+#endif
...
cond_resched();
- clear_user_highpage(p, addr + i * PAGE_SIZE);
+ vaddr = haddr + i*PAGE_SIZE;
+
701 - 800 of 9737 matches
Mail list logo