All of lore.kernel.org
 help / color / mirror / Atom feed
From: Balbir Singh <balbir@in.ibm.com>
To: Matt Helsley <matthltc@us.ibm.com>
Cc: Paul Menage <menage@google.com>,
	vatsa@in.ibm.com, Pavel Emelianov <xemul@openvz.org>,
	dev@openvz.org, sekharan@us.ibm.com,
	ckrm-tech@lists.sourceforge.net, haveblue@us.ibm.com,
	linux-kernel@vger.kernel.org, pj@sgi.com, dipankar@in.ibm.com,
	rohitseth@google.com
Subject: Re: [ckrm-tech] [RFC] Resource Management - Infrastructure choices
Date: Thu, 02 Nov 2006 11:03:30 +0530	[thread overview]
Message-ID: <4549832A.2040400@in.ibm.com> (raw)
In-Reply-To: <1162427450.12419.184.camel@localhost.localdomain>

Matt Helsley wrote:
> On Wed, 2006-11-01 at 15:50 -0800, Paul Menage wrote:
>> On 11/1/06, Matt Helsley <matthltc@us.ibm.com> wrote:
>>> On Wed, 2006-11-01 at 23:42 +0530, Srivatsa Vaddagiri wrote:
>>>> On Wed, Nov 01, 2006 at 12:30:13PM +0300, Pavel Emelianov wrote:
>>> <snip>
>>>
>>>>>>   - Support movement of all threads of a process from one group
>>>>>>     to another atomically?
>>>>> I propose such a solution: if a user asks to move /proc/<pid>
>>>>> then move the whole task with threads.
>>>>> If user asks to move /proc/<pid>/task/<tid> then move just
>>>>> a single thread.
>>>>>
>>>>> What do you think?
>>>> Isnt /proc/<pid> listed also in /proc/<pid>/task/<tid>?
>>>>
>>>> For ex:
>>>>
>>>>       # ls /proc/2906/task
>>>>       2906  2907  2908  2909
>>>>
>>>> 2906 is the main thread which created the remaining threads.
>>>>
>>>> This would lead to an ambiguity when user does something like below:
>>>>
>>>>       echo 2906 > /some_res_file_system/some_new_group
>>>>
>>>> Is he intending to move just the main thread, 2906, to the new group or
>>>> all the threads? It could be either.
>>>>
>>>> This needs some more thought ...
>>>         I thought the idea was to take in a proc path instead of a single
>>> number. You could then distinguish between the whole thread group and
>>> individual threads by parsing the string. You'd move a single thread if
>>> you find both the tgid and the tid. If you only get a tgid you'd move
>>> the whole thread group. So:
>>>
>>> <pid>                   -> if it's a thread group leader move the whole
>>>                            thread group, otherwise just move the thread
>>> /proc/<tgid>            -> move the whole thread group
>>> /proc/<tgid>/task/<tid> -> move the thread
>>>
>>>
>>>         Alternatives that come to mind are:
>>>
>>> 1. Read a flag with the pid
>>> 2. Use a special file which expects only thread groups as input
>> I think that having a "tasks" file and a "threads" file in each
>> container directory would be a clean way to handle it:
>>
>> "tasks" : read/write complete process members
>> "threads" : read/write individual thread members
>>
>> Paul
> 
> Seems like a good idea to me -- that certainly avoids complex parsing.
> 
> Cheers,
> 	-Matt Helsley
> 

Yeah, sounds like a good idea. We need to give the controllers some control
over whether they support task movement, thread movement or both.

-- 

	Balbir Singh,
	Linux Technology Center,
	IBM Software Labs

  reply	other threads:[~2006-11-02  5:35 UTC|newest]

Thread overview: 151+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-10-30 10:33 [RFC] Resource Management - Infrastructure choices Srivatsa Vaddagiri
2006-10-30 10:34 ` RFC: Memory Controller Balbir Singh
2006-10-30 11:04   ` Paul Menage
2006-10-30 13:27     ` [ckrm-tech] " Balbir Singh
2006-10-30 18:14       ` Paul Menage
2006-10-31 17:07         ` Balbir Singh
2006-10-31 17:22           ` Paul Menage
2006-10-31 18:16             ` Badari Pulavarty
2006-11-01  7:05             ` Balbir Singh
2006-11-01  7:07               ` Paul Menage
2006-11-01  7:44                 ` Balbir Singh
2006-11-01 12:23                   ` Paul Jackson
2006-11-02  0:09                     ` Paul Menage
2006-11-02  0:39                       ` Paul Jackson
2006-10-30 15:58   ` Pavel Emelianov
2006-10-30 17:39     ` Balbir Singh
2006-10-30 18:07       ` Balbir Singh
2006-10-30 18:07         ` Balbir Singh
2006-10-31  8:57         ` Pavel Emelianov
2006-10-31  8:57           ` Pavel Emelianov
2006-10-31  9:19           ` Balbir Singh
2006-10-31  9:19             ` Balbir Singh
2006-10-31  9:25             ` Pavel Emelianov
2006-10-31  9:25               ` Pavel Emelianov
2006-10-31 10:10               ` Balbir Singh
2006-10-31 10:10                 ` Balbir Singh
2006-10-31 10:19                 ` Pavel Emelianov
2006-10-31 10:19                   ` Pavel Emelianov
2006-10-31  9:42             ` Andrew Morton
2006-10-31  9:42               ` Andrew Morton
2006-10-31 10:36               ` Balbir Singh
2006-10-31 10:36                 ` Balbir Singh
2006-10-31  8:48       ` Pavel Emelianov
2006-10-31 10:54         ` Balbir Singh
2006-10-31 10:54           ` Balbir Singh
2006-10-31 11:15           ` Pavel Emelianov
2006-10-31 11:15             ` Pavel Emelianov
2006-10-31 12:39             ` Balbir Singh
2006-10-31 12:39               ` Balbir Singh
2006-10-31 14:19               ` Pavel Emelianov
2006-10-31 14:19                 ` Pavel Emelianov
2006-10-31 16:54             ` Paul Menage
2006-10-31 16:54               ` Paul Menage
2006-11-01  6:00             ` David Rientjes
2006-11-01  6:00               ` David Rientjes
2006-11-01  8:05               ` Pavel Emelianov
2006-11-01  8:05                 ` Pavel Emelianov
2006-11-01  8:35                 ` David Rientjes
2006-11-01  8:35                   ` David Rientjes
2006-10-31 17:04         ` Dave Hansen
2006-11-01  7:57           ` Pavel Emelianov
2006-10-30 18:20     ` Paul Menage
2006-10-30 21:38       ` Paul Jackson
2006-10-30 10:43 ` [RFC] Resource Management - Infrastructure choices Paul Jackson
2006-10-30 14:19   ` [ckrm-tech] " Pavel Emelianov
2006-10-30 14:29     ` Paul Jackson
2006-10-30 17:09   ` Srivatsa Vaddagiri
2006-10-30 17:16     ` Dave McCracken
2006-10-30 18:07       ` Paul Menage
2006-10-30 20:41         ` Paul Jackson
2006-10-30 10:51 ` Paul Menage
2006-10-30 11:06   ` [ckrm-tech] " Paul Jackson
2006-10-30 12:07     ` Paul Menage
2006-10-30 12:28       ` Paul Jackson
2006-10-30 11:15   ` Paul Jackson
2006-10-30 12:04     ` Paul Menage
2006-10-30 12:27       ` Paul Jackson
2006-10-30 17:53         ` Paul Menage
2006-10-30 20:36           ` Paul Jackson
2006-10-30 20:47             ` Paul Menage
2006-10-30 20:56               ` Paul Jackson
2006-10-30 21:03               ` Paul Menage
2006-10-31 11:53               ` Srivatsa Vaddagiri
2006-10-31 13:31                 ` Srivatsa Vaddagiri
2006-10-31 16:46                 ` Paul Menage
2006-11-01 17:25                   ` Srivatsa Vaddagiri
2006-11-01 23:37                     ` Paul Menage
2006-11-06 12:49                       ` Srivatsa Vaddagiri
2006-11-06 20:23                         ` Paul Menage
2006-11-07 13:20                           ` Srivatsa Vaddagiri
2006-11-07 18:41                           ` Paul Jackson
2006-11-07 19:07                             ` Paul Menage
2006-11-07 19:11                               ` Paul Jackson
2006-11-07 19:24                                 ` Paul Menage
2006-11-07 19:58                                   ` Paul Jackson
2006-11-07 20:00                                     ` Paul Menage
2006-11-07 20:02                               ` Paul Jackson
2006-11-08  2:47                                 ` Matt Helsley
2006-11-07 20:34                               ` Paul Jackson
2006-11-07 20:41                                 ` Paul Menage
2006-11-07 21:50                                   ` Paul Jackson
2006-11-07 22:21                               ` Paul Menage
2006-11-08  3:15                                 ` Paul Jackson
2006-11-08  4:15                                   ` Paul Menage
2006-11-08  4:16                                     ` Paul Jackson
2006-11-08 11:22                                     ` Paul Jackson
2006-11-08  5:12                                   ` Srivatsa Vaddagiri
2006-11-08  5:36                                     ` Paul Jackson
2006-11-09  5:39                                       ` Balbir Singh
2006-11-08 19:25                                     ` Chris Friesen
2006-11-09  3:54                                       ` Srivatsa Vaddagiri
2006-11-10 14:57                           ` Srivatsa Vaddagiri
2006-11-01  4:39               ` David Rientjes
2006-11-01  9:50                 ` Paul Jackson
2006-11-01  9:58                   ` David Rientjes
2006-11-01 15:59                 ` Srivatsa Vaddagiri
2006-11-01 16:31                   ` Srivatsa Vaddagiri
2006-11-01 21:05                   ` David Rientjes
2006-11-01 23:43                     ` Paul Menage
2006-11-01 18:19                 ` Srivatsa Vaddagiri
2006-11-01 17:33   ` Srivatsa Vaddagiri
2006-11-01 21:18     ` Chris Friesen
2006-11-01 23:01       ` [Devel] " Kir Kolyshkin
2006-11-02  0:31         ` Matt Helsley
2006-11-02  8:34           ` Kir Kolyshkin
2006-11-01 23:48       ` Paul Menage
2006-11-02  3:28         ` Chris Friesen
2006-11-02  7:40           ` Paul Menage
2006-10-30 14:08 ` Pavel Emelianov
2006-10-30 14:23   ` Paul Jackson
2006-10-30 14:38     ` Pavel Emelianov
2006-10-30 15:18       ` Paul Jackson
2006-10-30 15:26         ` Pavel Emelianov
2006-10-31  0:26           ` Matt Helsley
2006-10-31  8:34             ` Pavel Emelianov
2006-10-31 16:33           ` Chris Friesen
2006-10-30 18:01   ` Paul Menage
2006-10-31  8:31     ` Pavel Emelianov
2006-10-31 16:34       ` Paul Menage
2006-10-31 16:57         ` Srivatsa Vaddagiri
2006-11-01  7:58         ` Pavel Emelianov
2006-10-31 16:34   ` Srivatsa Vaddagiri
2006-11-01  8:01     ` Pavel Emelianov
2006-11-01 16:04       ` Matt Helsley
2006-11-01 17:51         ` Srivatsa Vaddagiri
2006-11-01 17:50       ` Srivatsa Vaddagiri
2006-11-02  8:42         ` Pavel Emelianov
2006-11-03  1:29           ` David Rientjes
2006-11-01  9:30 ` Pavel Emelianov
2006-11-01  9:53   ` David Rientjes
2006-11-01 22:23     ` Matt Helsley
2006-11-01 18:12   ` Srivatsa Vaddagiri
2006-11-01 22:19     ` Matt Helsley
2006-11-01 23:50       ` Paul Menage
2006-11-02  0:30         ` Matt Helsley
2006-11-02  5:33           ` Balbir Singh [this message]
2006-11-02  9:08         ` Pavel Emelianov
2006-11-02 11:26           ` Matt Helsley
2006-11-02 13:04             ` Pavel Emelianov
2006-11-03  1:29               ` David Rientjes
2006-11-02  8:52     ` Pavel Emelianov

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4549832A.2040400@in.ibm.com \
    --to=balbir@in.ibm.com \
    --cc=ckrm-tech@lists.sourceforge.net \
    --cc=dev@openvz.org \
    --cc=dipankar@in.ibm.com \
    --cc=haveblue@us.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=matthltc@us.ibm.com \
    --cc=menage@google.com \
    --cc=pj@sgi.com \
    --cc=rohitseth@google.com \
    --cc=sekharan@us.ibm.com \
    --cc=vatsa@in.ibm.com \
    --cc=xemul@openvz.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.