On Mon, 13 Jul 2009 11:03:03 +0800
Li Zefan l...@cn.fujitsu.com wrote:
Ben Blum wrote:
Quick vmalloc vs kmalloc fix to the case where array size is too large
Separates all pidlist allocation requests to a separate function that judges
based on the requested size whether or not the array
* men...@google.com men...@google.com [2009-07-10 16:58:23]:
On Sat, Jul 4, 2009 at 11:38 PM, Balbir Singhbal...@linux.vnet.ibm.com
wrote:
Paul, I don't see an interface to migrate all procs or at-least I
can't read it in the changelog. As discussed in the containers
mini-summit in
These lists record which futexes the task holds. To keep the overhead of
robust futexes low the list is kept in userspace. When the task exits the
kernel carefully walks these lists to recover held futexes that
other tasks may be attempting to acquire with FUTEX_WAIT.
Because they point to
Restore the pids since robust and pi futexes rely on the pids to
determine which task has the futex. Also use --copy-status to ensure
that the exit code from the restarted processes propagate to run.sh
Signed-off-by: Matt Helsley matth...@us.ibm.com
---
I believe this is the most important fix
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/affs/dir.c |1 +
fs/affs/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/affs/dir.c b/fs/affs/dir.c
index 8ca8f3a..6cc5e43 100644
--- a/fs/affs/dir.c
+++
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/hfs/dir.c |1 +
fs/hfs/inode.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 7c69b98..8d90a24 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/hfsplus/dir.c |1 +
fs/hfsplus/inode.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/hfsplus/dir.c b/fs/hfsplus/dir.c
index 5f40236..41fbf2d 100644
--- a/fs/hfsplus/dir.c
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: Christoph Hellwig h...@infradead.org
Cc: linux-fsde...@vger.kernel.org
---
fs/sysv/dir.c |1 +
fs/sysv/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c
index 4e50286..53acd29
Signed-off-by: Matt Helsley matth...@us.ibm.com
---
fs/efs/dir.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/fs/efs/dir.c b/fs/efs/dir.c
index 7ee6f7e..da344b8 100644
--- a/fs/efs/dir.c
+++ b/fs/efs/dir.c
@@ -13,6 +13,7 @@ const struct file_operations
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/cramfs/inode.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index dd3634e..0927503 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/hppfs/hppfs.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index a5089a6..f132fa2 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/qnx4/dir.c |1 +
fs/qnx4/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c
index 003c68f..ca99e01 100644
--- a/fs/qnx4/dir.c
+++
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/bfs/dir.c |1 +
fs/bfs/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c
index 54bd07d..6143810 100644
--- a/fs/bfs/dir.c
+++ b/fs/bfs/dir.c
@@
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/hpfs/dir.c |1 +
fs/hpfs/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index 6916c41..e88bde6 100644
--- a/fs/hpfs/dir.c
+++
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/freevxfs/vxfs_lookup.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/fs/freevxfs/vxfs_lookup.c b/fs/freevxfs/vxfs_lookup.c
index aee049c..3a09132 100644
---
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: Anton Altaparmakov ai...@cantab.net
Cc: linux-ntfs-...@lists.sourceforge.net
Cc: linux-fsde...@vger.kernel.org
---
fs/ntfs/dir.c |1 +
fs/ntfs/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/ntfs/dir.c
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: Boaz Harrosh bharr...@panasas.com
Cc: Avishay Traeger avis...@gmail.com
Cc: linux-fsdevel linux-fsde...@vger.kernel.org
---
fs/exofs/dir.c |1 +
fs/exofs/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git
Signed-off-by: Matt Helsley matth...@us.ibm.com
---
fs/ufs/dir.c |1 +
fs/ufs/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index 6f671f1..9379010 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -668,4 +668,5 @@ const struct
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/ecryptfs/file.c|2 ++
fs/ecryptfs/miscdev.c |1 +
2 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 9e94405..e6d2523 100644
---
freevxfs, romfs, efs, cramfs, isofs, squashfs, befs
This generic filesystem operation definition includes a seek operation
and is thus restartable given the generic checkpoint operation.
Signed-off-by: Matt Helsley matth...@us.ibm.com
---
fs/read_write.c |1 +
1 files changed, 1
These patches extend the use of the generic file checkpoint operation to
non-extX filesystems which have lseek operations that ensure we can save
and restore the files for later use. Note that this does not include
things like FUSE, network filesystems, or pseudo-filesystem kernel
interfaces.
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: Dave Kleikamp sha...@austin.ibm.com
Cc: jfs-discuss...@lists.sourceforge.net
Cc: linux-fsde...@vger.kernel.org
---
fs/jfs/file.c |1 +
fs/jfs/namei.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/jfs/file.c
Signed-off-by: Matt Helsley matth...@us.ibm.com
---
fs/minix/dir.c |1 +
fs/minix/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/minix/dir.c b/fs/minix/dir.c
index d407e7a..9cf04af 100644
--- a/fs/minix/dir.c
+++ b/fs/minix/dir.c
@@ -23,6 +23,7 @@ const
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/romfs/mmap-nommu.c |1 +
fs/romfs/super.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/romfs/mmap-nommu.c b/fs/romfs/mmap-nommu.c
index f0511e8..03c24d9 100644
---
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: xfs-mast...@oss.sgi.com
Cc: x...@oss.sgi.com
Cc: linux-fsde...@vger.kernel.org
---
fs/xfs/linux-2.6/xfs_file.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: reiserfs-de...@vger.kernel.org
Cc: linux-fsde...@vger.kernel.org
---
fs/reiserfs/dir.c |1 +
fs/reiserfs/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c
index
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: Trond Myklebust trond.mykleb...@netapp.com
Cc: linux-...@vger.kernel.org
Cc: linux-fsde...@vger.kernel.org
---
fs/nfs/dir.c |1 +
fs/nfs/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/nfs/dir.c
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: KONISHI Ryusuke konishi.ryus...@lab.ntt.co.jp
Cc: us...@nilfs.org
Cc: linux-fsde...@vger.kernel.org
---
fs/nilfs2/dir.c |2 +-
fs/nilfs2/file.c |1 +
2 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/fs/nilfs2/dir.c
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/fat/dir.c |1 +
fs/fat/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/fat/dir.c b/fs/fat/dir.c
index 38ff75a..a144f64 100644
--- a/fs/fat/dir.c
+++ b/fs/fat/dir.c
@@
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/isofs/dir.c |1 +
1 files changed, 1 insertions(+), 0 deletions(-)
diff --git a/fs/isofs/dir.c b/fs/isofs/dir.c
index 8ba5441..848059d 100644
--- a/fs/isofs/dir.c
+++ b/fs/isofs/dir.c
@@ -273,6 +273,7 @@
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/adfs/dir.c |1 +
fs/adfs/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c
index 23aa52f..7106f32 100644
--- a/fs/adfs/dir.c
+++
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/openpromfs/inode.c |2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/openpromfs/inode.c b/fs/openpromfs/inode.c
index ffcd04f..d1f0677 100644
--- a/fs/openpromfs/inode.c
+++
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: Phillip Lougher phil...@lougher.demon.co.uk
Cc: linux-fsde...@vger.kernel.org
---
fs/squashfs/dir.c |3 ++-
1 files changed, 2 insertions(+), 1 deletions(-)
diff --git a/fs/squashfs/dir.c b/fs/squashfs/dir.c
index 566b0ea..b0c5336 100644
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: Jan Kara j...@suse.cz
Cc: linux-fsde...@vger.kernel.org
---
fs/udf/dir.c |1 +
fs/udf/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index 61d9a76..6586dbe 100644
---
I think the debug files will also work with the generic file
checkpoint helper but it needs a bit more investigation to be
certain.
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: Artem Bityutskiy dedek...@infradead.org
Cc: Adrian Hunter ext-adrian.hun...@nokia.com
Cc:
Signed-off-by: Matt Helsley matth...@us.ibm.com
---
fs/ramfs/file-mmu.c |1 +
fs/ramfs/file-nommu.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c
index 78f613c..4430239 100644
--- a/fs/ramfs/file-mmu.c
+++
Signed-off-by: Matt Helsley matth...@us.ibm.com
---
fs/omfs/dir.c |1 +
fs/omfs/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/omfs/dir.c b/fs/omfs/dir.c
index c7275cf..5ed9cb3 100644
--- a/fs/omfs/dir.c
+++ b/fs/omfs/dir.c
@@ -502,4 +502,5 @@ struct
Signed-off-by: Matt Helsley matth...@us.ibm.com
Cc: linux-fsde...@vger.kernel.org
---
fs/jffs2/dir.c |1 +
fs/jffs2/file.c |1 +
2 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index 6f60cc9..c2b6487 100644
--- a/fs/jffs2/dir.c
+++
This is an automated email from the git hooks/post-receive script. It was
generated because a ref change was pushed to the repository containing
the project linux-cr.
The branch, ckpt-v17-rc1 has been updated
via 4cbbabe2c7c1ba884c685654cf52f9f1a79320a0 (commit)
from
On Mon, Jul 13, 2009 at 2:03 AM, KAMEZAWA
Hiroyukikamezawa.hir...@jp.fujitsu.com wrote:
why not using vmalloc() always ?
Thanks,
-Kame
The idea behind this patch is that in most cases, we want to use
kmalloc for performance, but sometimes the array will be too big. See
the previous
On Fri, Jul 10, 2009 at 09:56:21AM +0800, Gui Jianfeng wrote:
Hi Vivek,
This patch exports a cgroup based per group request limits interface.
and removes the global one. Now we can use this interface to perform
different request allocation limitation for different groups.
Thanks Gui. Few
On Mon, Jul 13, 2009 at 5:11 AM, Balbir Singhbal...@linux.vnet.ibm.com wrote:
How about lazy migration? Mark a group as to move when the kernel sees
it next for scheduling.
Waiting for the next scheduling point might be too long, since a
thread can block for arbitrary amounts of time and
Quoting Grzegorz Nosek (r...@localdomain.pl):
You are only seeing this with containers ?
Well, that's how I could reproduce it, didn't try any other way.
Multiple devpts instances don't matter here, but quite possibly
namespaces do.
I've tried but failed to reproduce. Do you have a script
JD Why? It seems that this would cause checkpoints to fail
JD unexpectedly,
Well, there are other places where the checkpoint will fail with EBUSY
because something is in a transitional state.
JD and is probably unnecessary in a migration scenario, because the
JD peer will retransmit the
On Mon, Jul 13, 2009 at 02:02:11PM -0500, Serge E. Hallyn wrote:
I've tried but failed to reproduce. Do you have a script or a more
precise recipe you can share?
I do have a script but all it does is starting and shutting down
a container in a loop. I can strip down and publish the virtualbox
Quoting Grzegorz Nosek (r...@localdomain.pl):
On Mon, Jul 13, 2009 at 02:02:11PM -0500, Serge E. Hallyn wrote:
I've tried but failed to reproduce. Do you have a script or a more
precise recipe you can share?
I do have a script but all it does is starting and shutting down
a container in
Vivek Goyal wrote, on 07/13/2009 12:03 PM:
On Fri, Jul 10, 2009 at 09:56:21AM +0800, Gui Jianfeng wrote:
Hi Vivek,
This patch exports a cgroup based per group request limits interface.
and removes the global one. Now we can use this interface to perform
different request allocation
KAMEZAWA Hiroyuki wrote:
On Wed, 08 Jul 2009 18:43:48 -0700
Vladislav D. Buzov vbu...@embeddedalley.com wrote:
KAMEZAWA Hiroyuki wrote:
2 points.
- Do we have to check this always we account ?
What are the options? Every N pages? How to select N?
I think you
On Tue, Jul 7, 2009 at 5:56 PM, KAMEZAWA
Hiroyukikamezawa.hir...@jp.fujitsu.com wrote:
I know people likes to wait for file descriptor to get notification in these
days.
Can't we have event file descriptor in cgroup layer and make it reusable for
other purposes ?
I agree - rather than
On Mon, Jul 13, 2009 at 03:26:10PM -0500, Serge E. Hallyn wrote:
The container init is /bin/sh, and you
while [ 1 ]; do
virsh --connect lxc:/// start vm1
virsh --connect lxc:/// destroy vm1
done
? (I thought there was something about stracing the container
init too, so i was
This is an automated email from the git hooks/post-receive script. It was
generated because a ref change was pushed to the repository containing
the project linux-cr.
The branch, ckpt-v17-rc1 has been updated
via e428694a8f6857a10afbd99660bc695c353aa74b (commit)
via
Got it.
I added another change to allow taking the headers from
the install directory (variable: KERNELHDR, defaulf it
$(KERNELSRC)/usr/include).
Hopefully I didn't break anything...
Oren.
Matt Helsley wrote:
Support kernel builds such as:
make O=../kbuild bzImage
The Makefile
On Thu, Jul 2, 2009 at 7:32 PM, Li Zefanl...@cn.fujitsu.com wrote:
cgroup_set_super() is called with spinlock held, so we
can't do kmalloc(GFP_KERNEL).
Good point. I'll have to go back to pre-allocating the root before
calling sget()
Paul
___
On Mon, 13 Jul 2009 11:27:43 -0400
Benjamin Blum bb...@google.com wrote:
On Mon, Jul 13, 2009 at 2:03 AM, KAMEZAWA
Hiroyukikamezawa.hir...@jp.fujitsu.com wrote:
why not using vmalloc() always ?
Thanks,
-Kame
The idea behind this patch is that in most cases, we want to use
This patch updates the Memory Controller Control Group to add a
configurable memory usage limit notification. The feature was
presented at the April 2009 Embedded Linux Conference.
Signed-off-by: Vladislav Buzov vbu...@embeddedalley.com
Signed-off-by: Dan Malek d...@embeddedalley.com
---
The following sequence of patches introduce memory usage limit notification
capability to the Memory Controller cgroup.
This is v3 of the implementation. The major difference between previous
version is it is based on the the Resource Counter extension to notify the
Resource Controller when the
This patch updates the Resource Counter to add a configurable resource usage
threshold notification mechanism.
Signed-off-by: Vladislav Buzov vbu...@embeddedalley.com
Signed-off-by: Dan Malek d...@embeddedalley.com
---
Documentation/cgroups/resource_counter.txt | 21 -
On Mon, Jul 13, 2009 at 5:16 PM, Vladislav
Buzovvbu...@embeddedalley.com wrote:
The following sequence of patches introduce memory usage limit notification
capability to the Memory Controller cgroup.
This is v3 of the implementation. The major difference between previous
version is it is
On Mon, Jul 13, 2009 at 5:16 PM, Vladislav
Buzovvbu...@embeddedalley.com wrote:
The following sequence of patches introduce memory usage limit notification
capability to the Memory Controller cgroup.
This is v3 of the implementation. The major difference between previous
version is
On Mon, 13 Jul 2009 17:16:20 -0700
Vladislav Buzov vbu...@embeddedalley.com wrote:
This patch updates the Resource Counter to add a configurable resource usage
threshold notification mechanism.
Signed-off-by: Vladislav Buzov vbu...@embeddedalley.com
Signed-off-by: Dan Malek
As I mentioned in another thread, I think that associating the
threshold with the res_counter rather than with each individual waiter
is a mistake, since it creates global state and makes it hard to have
multiple waiters on the same cgroup.
Paul
On Mon, Jul 13, 2009 at 5:16 PM, Vladislav
On Mon, 13 Jul 2009 17:36:40 -0700
Paul Menage men...@google.com wrote:
As I mentioned in another thread, I think that associating the
threshold with the res_counter rather than with each individual waiter
is a mistake, since it creates global state and makes it hard to have
multiple waiters
On Fri, Jul 3, 2009 at 1:58 AM, Li Zefanl...@cn.fujitsu.com wrote:
If it's not per cgroup, it can be a global value.
No it can't, since the notes subsystem can be mounted on multiple
hierarchies simultaneously.
But why not make it per cgroup?
Setting notes.size to a large value allows
Paul Menage wrote:
On Tue, Jul 7, 2009 at 5:56 PM, KAMEZAWA
Hiroyukikamezawa.hir...@jp.fujitsu.com wrote:
I know people likes to wait for file descriptor to get notification in these
days.
Can't we have event file descriptor in cgroup layer and make it reusable
for
other purposes ?
On Mon, 13 Jul 2009 18:00:53 -0700
Vladislav D. Buzov vbu...@embeddedalley.com wrote:
Paul Menage wrote:
On Tue, Jul 7, 2009 at 5:56 PM, KAMEZAWA
Hiroyukikamezawa.hir...@jp.fujitsu.com wrote:
I know people likes to wait for file descriptor to get notification in
these days.
Can't
On Tue, Jul 7, 2009 at 5:56 PM, KAMEZAWA
Hiroyukikamezawa.hir...@jp.fujitsu.com wrote:
I know people likes to wait for file descriptor to get notification in
these days.
Can't we have event file descriptor in cgroup layer and make it reusable
for
other purposes ?
I agree -
On Mon, 13 Jul 2009 18:29:01 -0700
Vladislav D. Buzov vbu...@embeddedalley.com wrote:
KAMEZAWA Hiroyuki wrote:
On Mon, 13 Jul 2009 17:16:20 -0700
Vladislav Buzov vbu...@embeddedalley.com wrote:
This patch updates the Resource Counter to add a configurable resource
usage
On Mon, Jul 13, 2009 at 4:49 PM, KAMEZAWA
Hiroyukikamezawa.hir...@jp.fujitsu.com wrote:
IIUC, this place, .../procs interface is not so important for performance
as to being allowed this ugly conding.
It's not just the calling thread that suffers from the overhead -
we've seen performance hits
On Mon, 13 Jul 2009 20:50:33 -0700
Paul Menage men...@google.com wrote:
On Mon, Jul 13, 2009 at 4:49 PM, KAMEZAWA
Hiroyukikamezawa.hir...@jp.fujitsu.com wrote:
IIUC, this place, .../procs interface is not so important for performance
as to being allowed this ugly conding.
It's not just
On Mon, Jul 13, 2009 at 8:53 PM, KAMEZAWA
Hiroyukikamezawa.hir...@jp.fujitsu.com wrote:
Hmm, ok...then, if too much pids, you hit vmalloc()/vfree() problem again.
So, it's not good idea to use vmalloc/vfree here after all.
Agreed, using vmalloc()/vfree() isn't a perfect solution, but at least
On Mon, 13 Jul 2009 21:04:32 -0700
Paul Menage men...@google.com wrote:
On Mon, Jul 13, 2009 at 8:53 PM, KAMEZAWA
Hiroyukikamezawa.hir...@jp.fujitsu.com wrote:
Hmm, ok...then, if too much pids, you hit vmalloc()/vfree() problem again.
So, it's not good idea to use vmalloc/vfree here after
* men...@google.com men...@google.com [2009-07-13 09:26:26]:
On Mon, Jul 13, 2009 at 5:11 AM, Balbir Singhbal...@linux.vnet.ibm.com
wrote:
How about lazy migration? Mark a group as to move when the kernel sees
it next for scheduling.
Waiting for the next scheduling point might be too
72 matches
Mail list logo