mmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.940.382.4214
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.linux-foundation.org/mailman/listinfo/containers
___
Paul M wrote:
> So, thoughts?
The cpuset portions seem reasonable to me, at first glance.
But cpusets are easy, as you note.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]
> But it's better to document this.
Good idea.
Acked-by: Paul Jackson <[EMAIL PROTECTED]>
You (Li Zefan) might want to resend this as a patch, in case Andrew
doesn't happen to see this embedded here.
Something like the following:
Subject: [PATCH] cgroup: document zero pid
't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.940.382.4214
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.linux-
Comments variable declarations.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.940.382.4214
___
Containers mailing list
[EMAI
Matt wrote:
> OK, I renamed it signal.send
I'm not familiar with the cgroup subsystem naming conventions,
but modulo that, this looks good to me - thanks!
--
I won't rest till it's the best ...
Programmer, Linux Scalability
hat more people, on seeing this file in a cgroup
directory, will guess correctly what it does if it were named
"signal" or "send_signal" or some such.
--
I won't rest till it's the best ...
Programmer, Linux Scalab
de path,
or while holding inconvenient locks.
So cpusets shouldn't be the driving motivation
for this, but it will likely be happy to go along
for the ride.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul
words to describe each patch.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.940.382.4214
___
Devel mailing list
Devel@openvz.o
Paul M, even including tasks to cgroup.tasks
or whatever, and then (2) adding symlinks for the legacy names, such as:
tasks -> cgroup.tasks
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Pa
/dev/cpuset. They do so
without even a suggestion from myself, and without any consultation
amongst themselves; just seems a convenient and sensible thing to do.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[
tern such as "[a-z]+\.[a-z]+" I consider above?
Perhaps I'm missing some reason to share in your revulsion.
> but if people seem to prefer that approach we can go for it.
So long as /dev/cpuset is unscathed, I'm ok either way. Let's
see what others think.
--
ted names, with no risk of future collision.
And did I say incompatible with released versions?
Hopefully Paul M isn't too surprised that I'm not endorsing this one ;).
--
I won't rest till it's the best ...
Programmer, Linux Scalability
ling disaster forcing a change.
But generic cgroup infrastructure files, such as "tasks", have not had
such adornments. And now, that is what it is -- released, and sufficient
to remain as it is.
> No, I don't like that idea either.
Good (and extra credit for saying so with
ust enough to comfortably do
what's needed; not some overly formalized and unnecessarily robust
complication beyond what's practically needed. More people can
comfortably understand it this way.
Design interfaces, and write code, for humans. Resists making
concessions to the limitations of computers (o
P_NOTIFY_ON_RELEASE, &cgrp->flags);
Good catch, Li Zefan - thanks.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.940.382.4214
___
itical use or user was; who found this
essential, not just nice to have.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.940.382.4214
_
d man
pages; good enough for my granddad, good enough for me ;).
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.940.382.4214
___
Container
release
is now working ... no longer disabled. I believe the above line from
the documentation is out of date.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL
.
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.940.382.4214
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.linux-foundation.org/mailman/listinfo/containers
__
inor change in (1) pass without further comment.
I'd like to recommend consideration of the following patch, to address the
minor inconsistency of (2), and to save a few bytes of kernel text space.
===
From: Paul Jackson <[EMAIL PROTECTED]>
Strip all trailing whitespace (such as carriage r
puset subsystem would
just not request this.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.940.382.4214
___
Containers
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.940.382.4214
___
Containers mailing list
[EMAIL PROTECTED]
http
> useful to have a filesystem visibility control group.
idle minds would like to know ... what is one of these?
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]
Paul M wrote:
> -LL=cgroup_mutex
> +(cgroup_mutex held by caller)
Thanks.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECT
to David without all the CC list above.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing li
> Replace "cont" with "cgrp" and other misc renaming
Acked-by: Paul Jackson <[EMAIL PROTECTED]>
Builds, boots, and I approve the 'cgrp' renaming - thanks.
--
I won't rest till it's the best ...
Programmer,
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.linux-foundatio
ing for cpumasks that didn't match, and then not noticing that it
was failing to set them so as they would match.
... it needs work ... or the alternative solution from Paul M.
--
I won't rest till it's the b
allowed of each task in that cpuset, then
I'm ok.
Right now, that goal is not met, with the cgroup patches lined up in
*-mm for what will become 2.6.24.
We're getting short of time to fix this.
--
I won't rest till it's the best ...
Pr
it compels us to this much code, however.
Any chance you could provide a patch that works against cgroups?
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul J
t; isn't caught, and no error is reported to userspace.
Good point ... hmmm ...
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
__
ffeine intake?
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists
Paul M, David R, others -- how does this look?
From: Paul Jackson <[EMAIL PROTECTED]>
Update the per-task cpus_allowed of each task in a cgroup
whenever it has a cpuset whose 'cpus' mask changes.
The change to basing cpusets on the cgroup (aka container)
infrastructure broke an
7;t rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.linux-foun
see, and certainly doesn't seem to guard the
consistency of cpu_online_map with the tasks cpus_allowed masks.
... lurkers beware ... good chance I haven't a friggin clue ;).
In other words: Thirty minutes ago I couldn't even spell
sched_hotcpu_mutex, and now I'm pontific
ing the actual code
suggestions posted by yourself and David (thanks!) this last week.
I just couldn't resist a bit of philosophizing ... sorry.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[E
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.linux-foundation.
callback, called only by cgroup attach
() requests back to the same group. Then code that wants to do
something odd, such as cpusets, for what seems like a no-op, can do so.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
From: Paul Jackson <[EMAIL PROTECTED]>
Need to include kmod.h to define UMH_WAIT_EXEC, at least
for my configuration (sn2_defconfig).
Signed-off-by: Paul Jackson <[EMAIL PROTECTED]>
Cc: Paul Menage <[EMAIL PROTECTED]>
---
kernel/cgroup.c |1 +
1 file changed, 1 insert
x27;s the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.linux-foundation.org/mailman/listinfo/containers
___
Paul M wrote:
> I didn't notice any performance hit on a pure allocate/free memory
> benchmark relative to non-cgroup cpusets.
Good.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jack
)
Good - thanks.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.linux
think that it actually matters however.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
__
n exiting tasks
The downside of my writing too many comments ... its more of a
maintenance burden on those changing the code ;).
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <
any name. The question is
which name is most quickly and easily understood.
... yes ... I'm a stickler for names ... sorry.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PRO
Andrew - please kill this patch.
Looks like Paul Menage has a better solution
that I will be trying out.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]>
e involved on those issues.
Nice work - thanks.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Cont
re may be
more hotplug interest, and less container interest, than currently seen
on this threads cc list.
Any further suggestions, or embarrassing (;) questions?
Thanks!
--
I won't rest till it's the best ...
Programmer, Linux Scalability
k, and thereby visible
to the scheduler.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
_
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
ht
From: Paul Jackson <[EMAIL PROTECTED]>
The code in kernel/cgroup.c attach_task() which skips the
attachment of a task to the group it is already in has to be
removed. Cpusets depends on reattaching a task to its current
cpuset, in order to trigger updating the cpus_allowed mask in th
/cgroups.txt
- You can drop the cpuset mini-history at the top of cgroups.txt:
Modified by Paul Jackson <[EMAIL PROTECTED]>
Modified by Christoph Lameter <[EMAIL PROTECTED]>
- The "Definitions" section is well done, thanks.
- Could you change the present tense
rch/powerpc/configs/pseries_defconfig |1 +
But these are not commonly used configs, so that's not a big deal.
So ... yeah ... good enough.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.linux-foundation.org/mailman/l
> fixing this is on my todo list.
thanks!
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers
rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.linux-foundation.org/m
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.li
-include-fix.patch
That's a big stretch of forbidden territory for innocent bisecters.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTE
istory showed the correct name of 'cgroup' in these patch names.
Well ... nice in my view ... such a patch rename would create more work
for Andrew, so I can't claim to know what he will think of this patch
name detail.
--
I won't r
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists
Paul M wrote:
> In fact, that's exactly what the release agent
> patch already does.
I'm feeling lazy ;) What's the Subject of that
patch, for my easy searching?
--
I won't rest till it's the best ...
Programmer, Linux Sca
swered my questions.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.linux-founda
wouldn't
want to break it without good reason.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers
ebugged crashes from live customer systems
that were basically this race.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
ould go a long
way of your first name was Linus. For the rest of us ... ;).
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
it, to preserve ongoing compatibility.
That's not a very persuasive justification.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
_
dding a cpuset API for a single 2.6.N release.
... gid's -- why not?
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
w what kind of purpose
you have in mind for such a hook. Could you say a few words to
that? Thanks.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackso
eeds that between two brains.
But since I'm not volunteering to do the work, I should not waste
too much more time of those who are.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul
ainer
framework' ... I'm clueless.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Devel mailing list
Devel@openvz.org
https://openvz.org/mailman/listinfo/devel
Balbir wrote:
> Aaah.. I see, that makes sense from a cpusets/containers perspective.
Agreed.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]
es in
Python.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https://lists.lin
ommunity's) cpusets.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containe
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Containers mailing list
[EMAIL PROTECTED]
https:
Could someone explain how these directions impact Paul Menage's
container patches and, the one I care about the most, kernel/cpuset.c?
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson &l
clusive cpus or mems, the new container's
> cpus and mems are inherited from the parent container.
I'm ok with this part.
Acked-by: Paul Jackson <[EMAIL PROTECTED]>
--
I won't rest till it's the best ...
Programmer, Linux Scalab
Serge wrote:
> Paul (Jackson), is this comment added in cpusets close enough to what
> you were asking for?
This comment?
+ * Currently we refuse to set up the container - thereby
+ * refusing the task to be entered, and as a result refusing
+ * the sys_unshare() or clone() which initia
code, saying something like the
above, so whomever does this will realize they are traveling in
unchartered territory.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson &l
on't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Devel mailing list
Devel@openvz.org
https://openvz.org/mailman/listinfo/devel
sell your
interests down the river.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Devel mailing list
Devel@openvz.org
https://openvz.org/mailman/listinfo/devel
with cloning.
Now if the above classic code must be encoded using cloning under
the covers, then we've got problems, probably more problems than
just this.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
?
Could you explain -- I still don't understand why you need this option.
I still don't understand why you can't do it in two steps - make the
container, then add cpu/mem separately.
--
I won't rest till it's the best ...
Programmer, Linu
ondering
what all the complaining is about.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Devel mailing lis
which
have all files coming and going automagically in
the middle of the night, and only allow mkdir and
rmdir operations, not creat or unlink.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Devel mailing list
Devel@openvz.org
https://openvz.org/mailman/listinfo/devel
inux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Devel mailing list
Devel@openvz.org
https://openvz.org/mailman/listinfo/devel
he cpus or memory, respectively, of any of its sibling
cpusets.
So we changed it to creating new cpusets empty of cpus or memory.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
iour of each test, and it would be surprising
if this test happen already to conform to LTP's requirements.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
P
omments within the test script itself.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
cpuset_test
Description: Binary data
y, then
we must find a way to ensure that one of these batch schedulers, using
cpusets on a NUMA box, still works.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.04
t; mems
echo 0-1 > mems
echo 1 > mems
On that last one, "echo 1 > mems", I did not do the echo to cpus first.
The test system had 8 cpus, numbered 0-7, and 4 mems, numbered 0-3.
--
I won't rest till it's the best ...
unsigned int', but argument 3 has type 'u64'
kernel/container.c:1025: warning: format '%llu' expects type 'long long
unsigned int', but argument 3 has type 'u64'
--
I won't rest till it's the best ...
Pr
dutils utility is a concern, then the
next best alternative would be:
taskgroups
This is the next shortest way to spell this "Something-Collection" form.
--
I won't rest till it's the best ...
Programmer, Linu
t ... though for the purposes of the
present thread, this is probably not an interesting detail.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
__
ase(oldcs_tobe_released, ppathbuf);
return 0;
}
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Devel mailing list
Devel@openvz.org
https://openvz.org/mailman/listinfo/devel
> I will try to send out a patch later today to fix
Thanks!
> Agreed, but good to keep code clean isn't it? :)
Definitely.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PR
, this would be a difficult race to trigger.
Thanks for finding this.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
__
o ... ?
I don't know of any sequence where that causes any problem.
Do you see one?
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[EMAIL PROTECTED]> 1.925.600.0401
___
Devel mailing list
Devel@openvz.org
https://openvz.org/mailman/listinfo/devel
task_unlock(tsk);
mutex_unlock(&callback_mutex);
put_task_struct(tsk);
return -ESRCH;
}
--
I won't rest till it's the best ...
Programmer, Linux Scalability
1 - 100 of 119 matches
Mail list logo
