On 04/06, Oleg Nesterov wrote:
Perhaps,
--- t/kernel/exit.c~ 2007-04-06 23:31:31.0 +0400
+++ t/kernel/exit.c 2007-04-06 23:31:57.0 +0400
@@ -275,10 +275,7 @@ static void reparent_to_init(void)
remove_parent(current);
current-parent = child_reaper(current);
Oleg Nesterov [EMAIL PROTECTED] writes:
On 04/06, Oleg Nesterov wrote:
Perhaps,
--- t/kernel/exit.c~ 2007-04-06 23:31:31.0 +0400
+++ t/kernel/exit.c 2007-04-06 23:31:57.0 +0400
@@ -275,10 +275,7 @@ static void reparent_to_init(void)
remove_parent(current);
Linus Torvalds wrote:
On Fri, 6 Apr 2007, Jeff Garzik wrote:
I would rather change the implementation under the hood to start per-CPU
threads on demand, similar to a thread-pool implementation.
Boxes with $BigNum CPUs probably won't ever use half of those threads.
The counter-argument is
On Fri, 6 Apr 2007, Linus Torvalds wrote:
>
>
> On Fri, 6 Apr 2007, Davide Libenzi wrote:
>
> > On Fri, 6 Apr 2007, Linus Torvalds wrote:
> > >
> > > I don't really see the point. It's not even *true*. A "process" includes
> > > more than the shared signal-handling - it would include files
On Fri, 6 Apr 2007, Jeff Garzik wrote:
>
> I would rather change the implementation under the hood to start per-CPU
> threads on demand, similar to a thread-pool implementation.
>
> Boxes with $BigNum CPUs probably won't ever use half of those threads.
The counter-argument is that boxes with
On Fri, 6 Apr 2007, Davide Libenzi wrote:
> On Fri, 6 Apr 2007, Linus Torvalds wrote:
> >
> > I don't really see the point. It's not even *true*. A "process" includes
> > more than the shared signal-handling - it would include files and fs etc
> > too.
> >
> > So it's actually *more*
Robin Holt wrote:
We have been testing a new larger configuration and we are seeing a very
large scan time of init's tsk->children list. In the cases we are seeing,
there are numerous kernel processes created for each cpu (ie: events/0
... events/, xfslogd/0 ... xfslogd/). These are
all on the
On Fri, 6 Apr 2007, Linus Torvalds wrote:
> On Fri, 6 Apr 2007, Davide Libenzi wrote:
> > >
> > > or lets just face it and name it what it is: process_struct ;-)
> >
> > That'd be fine too! Wonder if Linus would swallow a rename patch like
> > that...
>
> I don't really see the point. It's
On Fri, 6 Apr 2007, Davide Libenzi wrote:
> >
> > or lets just face it and name it what it is: process_struct ;-)
>
> That'd be fine too! Wonder if Linus would swallow a rename patch like
> that...
I don't really see the point. It's not even *true*. A "process" includes
more than the shared
On Fri, 6 Apr 2007, Ingo Molnar wrote:
>
> * Davide Libenzi wrote:
>
> > > > Ohhh, the "signal" struct! Funny name for something that nowadays
> > > > has probably no more than a 5% affinity with signal-related tasks
> > > > :/
> > >
> > > Hmm. I wonder if we should just rename it the
Jeremy Fitzhardinge wrote:
Eric W. Biederman wrote:
I'm guessing the issue is nash just calls wait and doesn't check the
returned pid value, assuming it is the only child it forked returning.
Which is valid except when you are running as pid == 1.
Hm, that's always a bug; a process can
Eric W. Biederman wrote:
> I'm guessing the issue is nash just calls wait and doesn't check the
> returned pid value, assuming it is the only child it forked returning.
> Which is valid except when you are running as pid == 1.
>
Hm, that's always a bug; a process can always have children it
* Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> Probably it is I who missed something :)
>
> But why can't we do both changes? I think it is just ugly to use init
> to reap the kernel thread. Ok, wait4() can find zombie quickly if we
> do the ->children split. But /sbin/init could be swapped
On 04/06, Ingo Molnar wrote:
>
> * Oleg Nesterov <[EMAIL PROTECTED]> wrote:
>
> > > I'd almost prefer to just not add kernel threads to any parent
> > > process list *at*all*.
> >
> > Yes sure, I didn't argue with that. However, "->exit_state = -1" does
> > matter, we can't detach process
Oleg Nesterov <[EMAIL PROTECTED]> writes:
> On 04/06, Oleg Nesterov wrote:
>>
>> --- t/kernel/exit.c~ 2007-04-06 23:31:31.0 +0400
>> +++ t/kernel/exit.c 2007-04-06 23:31:57.0 +0400
>> @@ -275,10 +275,7 @@ static void reparent_to_init(void)
>> remove_parent(current);
>>
On 04/06, Oleg Nesterov wrote:
>
> --- t/kernel/exit.c~ 2007-04-06 23:31:31.0 +0400
> +++ t/kernel/exit.c 2007-04-06 23:31:57.0 +0400
> @@ -275,10 +275,7 @@ static void reparent_to_init(void)
> remove_parent(current);
> current->parent = child_reaper(current);
>
* Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> > I'd almost prefer to just not add kernel threads to any parent
> > process list *at*all*.
>
> Yes sure, I didn't argue with that. However, "->exit_state = -1" does
> matter, we can't detach process unless we make it auto-reap.
> Off course, we
Christoph Hellwig <[EMAIL PROTECTED]> writes:
> As all kernel thread (1) should be converted to kthread anyway for
> proper containers support and general "let's get rid of a crappy API'
> cleanups I think that's enough. It would be nice to have SGI helping
> to convert more drivers over to the
On 04/06, Linus Torvalds wrote:
>
> On Fri, 6 Apr 2007, Oleg Nesterov wrote:
> >
> > Oops. I misread stop_machine(), it does kernel_thread(), not
> > kthread_create().
> > So "stopmachine" threads are all re-parented to init when the caller exits.
> > I think it makes sense to set ->exit_state
Eric W. Biederman wrote:
Are you saying waitpid() (wait4) *with a pid specified* can return another pid?
That definitely sounds like a bug.
No.
For the full context look back a couple of messages.
I'm guessing the issue is nash just calls wait and doesn't check the
returned pid value,
* Davide Libenzi wrote:
> > > Ohhh, the "signal" struct! Funny name for something that nowadays
> > > has probably no more than a 5% affinity with signal-related tasks
> > > :/
> >
> > Hmm. I wonder if we should just rename it the struct thread_group,
> > or struct task_group. Those seem
On Fri, 6 Apr 2007, Eric W. Biederman wrote:
> Davide Libenzi writes:
>
> > On Fri, 6 Apr 2007, Oleg Nesterov wrote:
> >
> >> Sure. It would be nice to move ->children into signal_struct at first.
> >> Except this change breaks (in fact fixes) ->pdeath_signal behaviour.
> >
> > Ohhh, the
"H. Peter Anvin" <[EMAIL PROTECTED]> writes:
> Eric W. Biederman wrote:
>>
>> Oleg is coming from a different case where it was found that exiting kernel
>> threads were causing problems for nash when nash was run as init in an
>> initramfs. While I think that case is likely a user space bug
Eric W. Biederman wrote:
Oleg is coming from a different case where it was found that exiting kernel
threads were causing problems for nash when nash was run as init in an
initramfs. While I think that case is likely a user space bug because
nash should check the pid from waidpid before
Davide Libenzi writes:
> On Fri, 6 Apr 2007, Oleg Nesterov wrote:
>
>> Sure. It would be nice to move ->children into signal_struct at first.
>> Except this change breaks (in fact fixes) ->pdeath_signal behaviour.
>
> Ohhh, the "signal" struct! Funny name for something that nowadays has
>
Ingo Molnar <[EMAIL PROTECTED]> writes:
> no. Two _completely separate_ lists.
>
> i.e. a to-be-reaped task will still be on the main list _too_. The main
> list is for all the PID semantics rules. The reap-list is just for
> wait4() processing. The two would be completely separate.
And what
On Fri, 6 Apr 2007, Oleg Nesterov wrote:
> Sure. It would be nice to move ->children into signal_struct at first.
> Except this change breaks (in fact fixes) ->pdeath_signal behaviour.
Ohhh, the "signal" struct! Funny name for something that nowadays has
probably no more than a 5% affinity with
Roland Dreier <[EMAIL PROTECTED]> writes:
> > no. Two _completely separate_ lists.
> >
> > i.e. a to-be-reaped task will still be on the main list _too_. The main
> > list is for all the PID semantics rules. The reap-list is just for
> > wait4() processing. The two would be completely
On Thu, Apr 05, 2007 at 06:29:16PM -0700, Linus Torvalds wrote:
> > The support angel on my shoulder says we should just put all the kernel
> > threads under a kthread subtree to shorten init's child list and minimize
> > impact.
>
> A number are already there, of course, since they use the
Oleg Nesterov <[EMAIL PROTECTED]> writes:
> On 04/06, Eric W. Biederman wrote:
>>
>> Thinking about it I do agree with Linus that two lists sounds like the
>> right solution because it ensures we always have O(1) time when
>> waiting for a zombie.
>
> Well. I bet this will be painful, and will
> no. Two _completely separate_ lists.
>
> i.e. a to-be-reaped task will still be on the main list _too_. The main
> list is for all the PID semantics rules. The reap-list is just for
> wait4() processing. The two would be completely separate.
I guess this means we add another list head
Linus Torvalds <[EMAIL PROTECTED]> writes:
> On Fri, 6 Apr 2007, Oleg Nesterov wrote:
>>
>> Oops. I misread stop_machine(), it does kernel_thread(), not
>> kthread_create().
>> So "stopmachine" threads are all re-parented to init when the caller exits.
>> I think it makes sense to set
* Oleg Nesterov <[EMAIL PROTECTED]> wrote:
> > Thinking about it I do agree with Linus that two lists sounds like
> > the right solution because it ensures we always have O(1) time when
> > waiting for a zombie.
>
> Well. I bet this will be painful, and will uglify the code even more.
>
>
* Ingo Molnar <[EMAIL PROTECTED]> wrote:
> putting the freshly reaped tasks at the 'head' of the list is just a
> fancy (and incomplete) way of splitting the list up into two lists, and
> i'd advocate a clean split. Just like have have split the ptrace_list
* Linus Torvalds <[EMAIL PROTECTED]> wrote:
> I'd almost prefer to just not add kernel threads to any parent process
> list *at*all*.
i think part of the problem is the legacy that the list is artificially
unified: tasks that 'will possibly exit' are on the same list as tasks
that 'have
On 04/06, Eric W. Biederman wrote:
>
> Thinking about it I do agree with Linus that two lists sounds like the
> right solution because it ensures we always have O(1) time when
> waiting for a zombie.
Well. I bet this will be painful, and will uglify the code even more.
do_wait() has to iterate
On Fri, 6 Apr 2007, Oleg Nesterov wrote:
>
> Oops. I misread stop_machine(), it does kernel_thread(), not kthread_create().
> So "stopmachine" threads are all re-parented to init when the caller exits.
> I think it makes sense to set ->exit_state = -1 in stopmachine(), regadless
> of any other
On 04/06, Eric W. Biederman wrote:
>
> Oleg Nesterov <[EMAIL PROTECTED]> writes:
>
> >> At first glance your patch looks reasonable.
> >>
> >> Unfortunately it only applies to the rare thread that calls daemonize,
> >> and not also to kernel/kthread/kthread() which means it will miss many of
>
On Fri, Apr 06, 2007 at 09:38:24AM -0600, Eric W. Biederman wrote:
> How hard is tasklist_lock hit on these systems?
The major hold-off we are seeing is from tasks reaping children,
especially tasks with very large children lists.
> How hard is the pid hash hit on these systems?
In the little
Oleg Nesterov <[EMAIL PROTECTED]> writes:
>> At first glance your patch looks reasonable.
>>
>> Unfortunately it only applies to the rare thread that calls daemonize,
>> and not also to kernel/kthread/kthread() which means it will miss many of
>> our current kernel threads.
>
> Note that a
Robin Holt <[EMAIL PROTECTED]> writes:
>> So I think we have some options once we get the kernel threads out
>> of the way. Getting the kernel threads out of the way would seem
>> to be the first priority.
>
> I think both avenues would probably be the right way to proceeed.
> Getting kthreads
> So I think we have some options once we get the kernel threads out
> of the way. Getting the kernel threads out of the way would seem
> to be the first priority.
I think both avenues would probably be the right way to proceeed.
Getting kthreads to not be parented by init would be an
On 04/06, Eric W. Biederman wrote:
>
> Oleg Nesterov <[EMAIL PROTECTED]> writes:
>
> > Robin Holt wrote:
> >>
> >> wait_task_zombie() is taking many seconds to get through the list.
> >> For the case of a modprobe, stop_machine creates one thread per cpu
> >> (remember big number). All are
Oleg Nesterov <[EMAIL PROTECTED]> writes:
> Robin Holt wrote:
>>
>> wait_task_zombie() is taking many seconds to get through the list.
>> For the case of a modprobe, stop_machine creates one thread per cpu
>> (remember big number). All are parented to init and their exit will
>> cause
Robin Holt wrote:
>
> wait_task_zombie() is taking many seconds to get through the list.
> For the case of a modprobe, stop_machine creates one thread per cpu
> (remember big number). All are parented to init and their exit will
> cause wait_task_zombie to scan multiple times most of the way
Robin Holt wrote:
wait_task_zombie() is taking many seconds to get through the list.
For the case of a modprobe, stop_machine creates one thread per cpu
(remember big number). All are parented to init and their exit will
cause wait_task_zombie to scan multiple times most of the way through
Oleg Nesterov [EMAIL PROTECTED] writes:
Robin Holt wrote:
wait_task_zombie() is taking many seconds to get through the list.
For the case of a modprobe, stop_machine creates one thread per cpu
(remember big number). All are parented to init and their exit will
cause wait_task_zombie to scan
On 04/06, Eric W. Biederman wrote:
Oleg Nesterov [EMAIL PROTECTED] writes:
Robin Holt wrote:
wait_task_zombie() is taking many seconds to get through the list.
For the case of a modprobe, stop_machine creates one thread per cpu
(remember big number). All are parented to init and
So I think we have some options once we get the kernel threads out
of the way. Getting the kernel threads out of the way would seem
to be the first priority.
I think both avenues would probably be the right way to proceeed.
Getting kthreads to not be parented by init would be an opportunity
Robin Holt [EMAIL PROTECTED] writes:
So I think we have some options once we get the kernel threads out
of the way. Getting the kernel threads out of the way would seem
to be the first priority.
I think both avenues would probably be the right way to proceeed.
Getting kthreads to not be
Oleg Nesterov [EMAIL PROTECTED] writes:
At first glance your patch looks reasonable.
Unfortunately it only applies to the rare thread that calls daemonize,
and not also to kernel/kthread/kthread() which means it will miss many of
our current kernel threads.
Note that a thread created by
On Fri, Apr 06, 2007 at 09:38:24AM -0600, Eric W. Biederman wrote:
How hard is tasklist_lock hit on these systems?
The major hold-off we are seeing is from tasks reaping children,
especially tasks with very large children lists.
How hard is the pid hash hit on these systems?
In the little bit
On 04/06, Eric W. Biederman wrote:
Oleg Nesterov [EMAIL PROTECTED] writes:
At first glance your patch looks reasonable.
Unfortunately it only applies to the rare thread that calls daemonize,
and not also to kernel/kthread/kthread() which means it will miss many of
our current kernel
On Fri, 6 Apr 2007, Oleg Nesterov wrote:
Oops. I misread stop_machine(), it does kernel_thread(), not kthread_create().
So stopmachine threads are all re-parented to init when the caller exits.
I think it makes sense to set -exit_state = -1 in stopmachine(), regadless
of any other changes.
On 04/06, Eric W. Biederman wrote:
Thinking about it I do agree with Linus that two lists sounds like the
right solution because it ensures we always have O(1) time when
waiting for a zombie.
Well. I bet this will be painful, and will uglify the code even more.
do_wait() has to iterate over
* Linus Torvalds [EMAIL PROTECTED] wrote:
I'd almost prefer to just not add kernel threads to any parent process
list *at*all*.
i think part of the problem is the legacy that the list is artificially
unified: tasks that 'will possibly exit' are on the same list as tasks
that 'have already
* Ingo Molnar [EMAIL PROTECTED] wrote:
putting the freshly reaped tasks at the 'head' of the list is just a
fancy (and incomplete) way of splitting the list up into two lists, and
i'd advocate a clean split. Just like have have split the ptrace_list
* Oleg Nesterov [EMAIL PROTECTED] wrote:
Thinking about it I do agree with Linus that two lists sounds like
the right solution because it ensures we always have O(1) time when
waiting for a zombie.
Well. I bet this will be painful, and will uglify the code even more.
do_wait() has
Linus Torvalds [EMAIL PROTECTED] writes:
On Fri, 6 Apr 2007, Oleg Nesterov wrote:
Oops. I misread stop_machine(), it does kernel_thread(), not
kthread_create().
So stopmachine threads are all re-parented to init when the caller exits.
I think it makes sense to set -exit_state = -1 in
no. Two _completely separate_ lists.
i.e. a to-be-reaped task will still be on the main list _too_. The main
list is for all the PID semantics rules. The reap-list is just for
wait4() processing. The two would be completely separate.
I guess this means we add another list head to
Oleg Nesterov [EMAIL PROTECTED] writes:
On 04/06, Eric W. Biederman wrote:
Thinking about it I do agree with Linus that two lists sounds like the
right solution because it ensures we always have O(1) time when
waiting for a zombie.
Well. I bet this will be painful, and will uglify the code
Roland Dreier [EMAIL PROTECTED] writes:
no. Two _completely separate_ lists.
i.e. a to-be-reaped task will still be on the main list _too_. The main
list is for all the PID semantics rules. The reap-list is just for
wait4() processing. The two would be completely separate.
I
On Thu, Apr 05, 2007 at 06:29:16PM -0700, Linus Torvalds wrote:
The support angel on my shoulder says we should just put all the kernel
threads under a kthread subtree to shorten init's child list and minimize
impact.
A number are already there, of course, since they use the kthread
On Fri, 6 Apr 2007, Oleg Nesterov wrote:
Sure. It would be nice to move -children into signal_struct at first.
Except this change breaks (in fact fixes) -pdeath_signal behaviour.
Ohhh, the signal struct! Funny name for something that nowadays has
probably no more than a 5% affinity with
Ingo Molnar [EMAIL PROTECTED] writes:
no. Two _completely separate_ lists.
i.e. a to-be-reaped task will still be on the main list _too_. The main
list is for all the PID semantics rules. The reap-list is just for
wait4() processing. The two would be completely separate.
And what pray
Davide Libenzi davidel@xmailserver.org writes:
On Fri, 6 Apr 2007, Oleg Nesterov wrote:
Sure. It would be nice to move -children into signal_struct at first.
Except this change breaks (in fact fixes) -pdeath_signal behaviour.
Ohhh, the signal struct! Funny name for something that nowadays
Eric W. Biederman wrote:
Oleg is coming from a different case where it was found that exiting kernel
threads were causing problems for nash when nash was run as init in an
initramfs. While I think that case is likely a user space bug because
nash should check the pid from waidpid before
H. Peter Anvin [EMAIL PROTECTED] writes:
Eric W. Biederman wrote:
Oleg is coming from a different case where it was found that exiting kernel
threads were causing problems for nash when nash was run as init in an
initramfs. While I think that case is likely a user space bug because
nash
On Fri, 6 Apr 2007, Eric W. Biederman wrote:
Davide Libenzi davidel@xmailserver.org writes:
On Fri, 6 Apr 2007, Oleg Nesterov wrote:
Sure. It would be nice to move -children into signal_struct at first.
Except this change breaks (in fact fixes) -pdeath_signal behaviour.
Ohhh, the
* Davide Libenzi davidel@xmailserver.org wrote:
Ohhh, the signal struct! Funny name for something that nowadays
has probably no more than a 5% affinity with signal-related tasks
:/
Hmm. I wonder if we should just rename it the struct thread_group,
or struct task_group. Those
Eric W. Biederman wrote:
Are you saying waitpid() (wait4) *with a pid specified* can return another pid?
That definitely sounds like a bug.
No.
For the full context look back a couple of messages.
I'm guessing the issue is nash just calls wait and doesn't check the
returned pid value,
On 04/06, Linus Torvalds wrote:
On Fri, 6 Apr 2007, Oleg Nesterov wrote:
Oops. I misread stop_machine(), it does kernel_thread(), not
kthread_create().
So stopmachine threads are all re-parented to init when the caller exits.
I think it makes sense to set -exit_state = -1 in
Christoph Hellwig [EMAIL PROTECTED] writes:
As all kernel thread (1) should be converted to kthread anyway for
proper containers support and general let's get rid of a crappy API'
cleanups I think that's enough. It would be nice to have SGI helping
to convert more drivers over to the proper
* Oleg Nesterov [EMAIL PROTECTED] wrote:
I'd almost prefer to just not add kernel threads to any parent
process list *at*all*.
Yes sure, I didn't argue with that. However, -exit_state = -1 does
matter, we can't detach process unless we make it auto-reap.
Off course, we also need to
On 04/06, Oleg Nesterov wrote:
--- t/kernel/exit.c~ 2007-04-06 23:31:31.0 +0400
+++ t/kernel/exit.c 2007-04-06 23:31:57.0 +0400
@@ -275,10 +275,7 @@ static void reparent_to_init(void)
remove_parent(current);
current-parent = child_reaper(current);
Oleg Nesterov [EMAIL PROTECTED] writes:
On 04/06, Oleg Nesterov wrote:
--- t/kernel/exit.c~ 2007-04-06 23:31:31.0 +0400
+++ t/kernel/exit.c 2007-04-06 23:31:57.0 +0400
@@ -275,10 +275,7 @@ static void reparent_to_init(void)
remove_parent(current);
current-parent
On 04/06, Ingo Molnar wrote:
* Oleg Nesterov [EMAIL PROTECTED] wrote:
I'd almost prefer to just not add kernel threads to any parent
process list *at*all*.
Yes sure, I didn't argue with that. However, -exit_state = -1 does
matter, we can't detach process unless we make it
* Oleg Nesterov [EMAIL PROTECTED] wrote:
Probably it is I who missed something :)
But why can't we do both changes? I think it is just ugly to use init
to reap the kernel thread. Ok, wait4() can find zombie quickly if we
do the -children split. But /sbin/init could be swapped out, we
Eric W. Biederman wrote:
I'm guessing the issue is nash just calls wait and doesn't check the
returned pid value, assuming it is the only child it forked returning.
Which is valid except when you are running as pid == 1.
Hm, that's always a bug; a process can always have children it
Jeremy Fitzhardinge wrote:
Eric W. Biederman wrote:
I'm guessing the issue is nash just calls wait and doesn't check the
returned pid value, assuming it is the only child it forked returning.
Which is valid except when you are running as pid == 1.
Hm, that's always a bug; a process can
On Fri, 6 Apr 2007, Ingo Molnar wrote:
* Davide Libenzi davidel@xmailserver.org wrote:
Ohhh, the signal struct! Funny name for something that nowadays
has probably no more than a 5% affinity with signal-related tasks
:/
Hmm. I wonder if we should just rename it the
On Fri, 6 Apr 2007, Davide Libenzi wrote:
or lets just face it and name it what it is: process_struct ;-)
That'd be fine too! Wonder if Linus would swallow a rename patch like
that...
I don't really see the point. It's not even *true*. A process includes
more than the shared
On Fri, 6 Apr 2007, Linus Torvalds wrote:
On Fri, 6 Apr 2007, Davide Libenzi wrote:
or lets just face it and name it what it is: process_struct ;-)
That'd be fine too! Wonder if Linus would swallow a rename patch like
that...
I don't really see the point. It's not even *true*.
Robin Holt wrote:
We have been testing a new larger configuration and we are seeing a very
large scan time of init's tsk-children list. In the cases we are seeing,
there are numerous kernel processes created for each cpu (ie: events/0
... events/big number, xfslogd/0 ... xfslogd/big number).
On Fri, 6 Apr 2007, Davide Libenzi wrote:
On Fri, 6 Apr 2007, Linus Torvalds wrote:
I don't really see the point. It's not even *true*. A process includes
more than the shared signal-handling - it would include files and fs etc
too.
So it's actually *more* correct to call it
On Fri, 6 Apr 2007, Jeff Garzik wrote:
I would rather change the implementation under the hood to start per-CPU
threads on demand, similar to a thread-pool implementation.
Boxes with $BigNum CPUs probably won't ever use half of those threads.
The counter-argument is that boxes with
On Fri, 6 Apr 2007, Linus Torvalds wrote:
On Fri, 6 Apr 2007, Davide Libenzi wrote:
On Fri, 6 Apr 2007, Linus Torvalds wrote:
I don't really see the point. It's not even *true*. A process includes
more than the shared signal-handling - it would include files and fs etc
Linus Torvalds wrote:
On Fri, 6 Apr 2007, Jeff Garzik wrote:
I would rather change the implementation under the hood to start per-CPU
threads on demand, similar to a thread-pool implementation.
Boxes with $BigNum CPUs probably won't ever use half of those threads.
The counter-argument is
Linus Torvalds <[EMAIL PROTECTED]> writes:
> On Thu, 5 Apr 2007, Chris Snook wrote:
>
>> Linus Torvalds wrote:
>>
>> > Another thing we could do is to just make sure that kernel threads simply
>> > don't end up as children of init. That whole thing is silly, they're really
>> > not children of
On Thu, 5 Apr 2007, Chris Snook wrote:
> Linus Torvalds wrote:
>
> > Another thing we could do is to just make sure that kernel threads simply
> > don't end up as children of init. That whole thing is silly, they're really
> > not children of the user-space init anyway. Comments?
>
> Does
Chris Snook wrote:
Linus Torvalds wrote:
On Thu, 5 Apr 2007, Robin Holt wrote:
For testing, Jack Steiner create the following patch. All it does
is moves tasks which are transitioning to the zombie state from where
they are in the children list to the head of the list. In this way,
they
Linus Torvalds wrote:
On Thu, 5 Apr 2007, Robin Holt wrote:
For testing, Jack Steiner create the following patch. All it does
is moves tasks which are transitioning to the zombie state from where
they are in the children list to the head of the list. In this way,
they will be the first found
On Thu, 5 Apr 2007, Robin Holt wrote:
>
> For testing, Jack Steiner create the following patch. All it does
> is moves tasks which are transitioning to the zombie state from where
> they are in the children list to the head of the list. In this way,
> they will be the first found and reaping
We have been testing a new larger configuration and we are seeing a very
large scan time of init's tsk->children list. In the cases we are seeing,
there are numerous kernel processes created for each cpu (ie: events/0
... events/, xfslogd/0 ... xfslogd/). These are
all on the list ahead of the
We have been testing a new larger configuration and we are seeing a very
large scan time of init's tsk-children list. In the cases we are seeing,
there are numerous kernel processes created for each cpu (ie: events/0
... events/big number, xfslogd/0 ... xfslogd/big number). These are
all on the
On Thu, 5 Apr 2007, Robin Holt wrote:
For testing, Jack Steiner create the following patch. All it does
is moves tasks which are transitioning to the zombie state from where
they are in the children list to the head of the list. In this way,
they will be the first found and reaping does
Linus Torvalds wrote:
On Thu, 5 Apr 2007, Robin Holt wrote:
For testing, Jack Steiner create the following patch. All it does
is moves tasks which are transitioning to the zombie state from where
they are in the children list to the head of the list. In this way,
they will be the first found
Chris Snook wrote:
Linus Torvalds wrote:
On Thu, 5 Apr 2007, Robin Holt wrote:
For testing, Jack Steiner create the following patch. All it does
is moves tasks which are transitioning to the zombie state from where
they are in the children list to the head of the list. In this way,
they
On Thu, 5 Apr 2007, Chris Snook wrote:
Linus Torvalds wrote:
Another thing we could do is to just make sure that kernel threads simply
don't end up as children of init. That whole thing is silly, they're really
not children of the user-space init anyway. Comments?
Does anyone
Linus Torvalds [EMAIL PROTECTED] writes:
On Thu, 5 Apr 2007, Chris Snook wrote:
Linus Torvalds wrote:
Another thing we could do is to just make sure that kernel threads simply
don't end up as children of init. That whole thing is silly, they're really
not children of the user-space init
101 - 200 of 200 matches
Mail list logo