From: Andy Lutomirski <luto@amacapital.net>
To: David Ahern <dsahern@gmail.com>
Cc: Andrew Vagin <avagin@odin.com>, Andrey Vagin <avagin@openvz.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Linux API <linux-api@vger.kernel.org>,
Oleg Nesterov <oleg@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
Cyrill Gorcunov <gorcunov@openvz.org>,
Pavel Emelyanov <xemul@parallels.com>,
Roger Luethi <rl@hellgate.ch>, Arnd Bergmann <arnd@arndb.de>,
Arnaldo Carvalho de Melo <acme@kernel.org>,
Pavel Odintsov <pavel.odintsov@gmail.com>
Subject: Re: [PATCH 0/24] kernel: add a netlink interface to get information about processes (v2)
Date: Tue, 7 Jul 2015 09:24:05 -0700 [thread overview]
Message-ID: <CALCETrWRT--XO6jYyno_i0nUZEoRuq3S5_n-qFRSt2rmkd3jMQ@mail.gmail.com> (raw)
In-Reply-To: <559BFB9C.5010801@gmail.com>
On Tue, Jul 7, 2015 at 9:17 AM, David Ahern <dsahern@gmail.com> wrote:
> On 7/7/15 9:56 AM, Andy Lutomirski wrote:
>>
>> Netlink is fine for these use cases (if they were related to the
>> netns, not the pid ns or user ns), and it works. It's still tedious
>> -- I bet that if you used a syscall, the user code would be
>> considerable shorter, though. :)
>>
>> How would this be a problem if you used plain syscalls? The user
>> would make a request, and the syscall would tell the user that their
>> result buffer was too small if it was, in fact, too small.
>
>
> It will be impossible to tell a user what sized buffer is needed. The size
> is largely a function of the number of tasks and number of maps per thread
> group and both of those will be changing. With the growing size of systems
> (I was sparc systems with 1024 cpus) the workload can be 10's of thousands
> of tasks each with a lot of maps (e.g., java workloads). That amounts to a
> non-trivial amount of data that has to be pushed to userspace.
>
> One of the benefits of the netlink approach is breaking the data across
> multiple messages and picking up where you left off. That infrastructure is
> already in place.
>
How does picking up where you left off work? I assumed the interface
was something along the lines of "give me information starting from
pid N", but maybe I missed something.
--Andy
next prev parent reply other threads:[~2015-07-07 16:24 UTC|newest]
Thread overview: 90+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-07-06 8:47 [PATCH 0/24] kernel: add a netlink interface to get information about processes (v2) Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 01/24] kernel: define taststats commands in the one place Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 02/24] kernel: add a netlink interface to get information about tasks (v2) Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 03/24] kernel: make taskstats available from all net namespaces Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 04/24] kernel: move next_tgid from fs/proc Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 05/24] task_diag: add ability to get information about all tasks Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 06/24] task_diag: add ability to split per-task data on a few netlink messages Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 07/24] task_diag: add a new group to get process credentials Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 08/24] proc: pick out a function to iterate task children Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-14 18:02 ` Oleg Nesterov
2015-07-14 18:02 ` Oleg Nesterov
2015-07-17 15:57 ` Andrew Vagin
2015-07-17 15:57 ` Andrew Vagin
2015-07-18 21:22 ` Oleg Nesterov
2015-07-18 21:22 ` Oleg Nesterov
2015-07-06 8:47 ` [PATCH 09/24] proc: move task_next_child() from fs/proc Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 10/24] task_diag: add ability to dump children (v2) Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 11/24] task_diag: add a new group to get task statistics Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 12/24] task_diag: add a new group to get tasks memory mappings (v2) Andrey Vagin
2015-07-14 18:08 ` Oleg Nesterov
2015-07-14 18:08 ` Oleg Nesterov
2015-07-15 2:02 ` David Ahern
2015-07-15 2:02 ` David Ahern
2015-07-06 8:47 ` [PATCH 13/24] task_diag: shows memory consumption for " Andrey Vagin
2015-07-06 8:47 ` [PATCH 14/24] task_diag: add a marcos to enumirate memory mappings Andrey Vagin
2015-07-06 8:47 ` [PATCH 15/24] proc: give task_struct instead of pid into first_tid Andrey Vagin
2015-07-14 18:11 ` Oleg Nesterov
2015-07-06 8:47 ` [PATCH 16/24] proc: move first_tid and next_tid out of proc Andrey Vagin
2015-07-06 8:47 ` [PATCH 17/24] task_diag: add ability to dump theads Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 8:47 ` [PATCH 18/24] task_diag: add ability to handle one task in a continious mode Andrey Vagin
2015-07-06 8:47 ` [PATCH 19/24] task_diag: Add option to dump all threads for all tasks Andrey Vagin
2015-07-06 8:47 ` [PATCH 20/24] task_diag: Only add VMAs for thread_group leader Andrey Vagin
2015-07-14 17:47 ` Oleg Nesterov
2015-07-14 17:47 ` Oleg Nesterov
2015-07-15 2:01 ` David Ahern
2015-07-15 13:31 ` Oleg Nesterov
2015-07-15 13:31 ` Oleg Nesterov
2015-07-06 8:47 ` [PATCH 21/24] task diag: Add support for TGID attribute Andrey Vagin
2015-07-06 8:47 ` [PATCH 22/24] Documentation: add documentation for task_diag Andrey Vagin
2015-07-06 8:47 ` [PATCH 23/24] selftest: check the task_diag functinonality Andrey Vagin
2015-07-06 8:47 ` [PATCH 24/24] task_diag: Enhance fork tool to spawn threads Andrey Vagin
2015-07-06 8:47 ` Andrey Vagin
2015-07-06 17:10 ` [PATCH 0/24] kernel: add a netlink interface to get information about processes (v2) Andy Lutomirski
2015-07-07 15:43 ` Andrew Vagin
2015-07-07 15:56 ` Andy Lutomirski
2015-07-07 15:56 ` Andy Lutomirski
2015-07-07 16:17 ` David Ahern
2015-07-07 16:17 ` David Ahern
2015-07-07 16:24 ` Andy Lutomirski [this message]
2015-07-07 16:41 ` David Ahern
2015-07-07 16:41 ` David Ahern
2015-07-08 16:10 ` Andrew Vagin
2015-07-08 16:10 ` Andrew Vagin
2015-07-08 17:39 ` Andy Lutomirski
2015-07-08 22:49 ` Andrey Vagin
2015-07-08 23:48 ` Andy Lutomirski
2015-07-08 23:48 ` Andy Lutomirski
2015-07-07 16:25 ` Arnaldo Carvalho de Melo
2015-07-07 16:25 ` Arnaldo Carvalho de Melo
2015-07-07 16:27 ` Andy Lutomirski
2015-07-07 16:27 ` Andy Lutomirski
2015-07-07 16:56 ` David Ahern
2015-07-07 16:56 ` David Ahern
2015-11-24 15:18 ` Andrew Vagin
2015-11-24 15:18 ` Andrew Vagin
2015-12-03 23:20 ` Andy Lutomirski
2015-12-03 23:20 ` Andy Lutomirski
2015-12-03 23:43 ` Arnd Bergmann
2015-12-14 8:05 ` Andrew Vagin
2015-12-14 8:05 ` Andrew Vagin
2015-12-14 7:52 ` Andrew Vagin
2015-12-14 7:52 ` Andrew Vagin
2015-12-14 22:38 ` Andy Lutomirski
2015-12-15 15:53 ` Andrew Vagin
2015-12-15 15:53 ` Andrew Vagin
2015-12-15 16:43 ` Andy Lutomirski
2015-12-15 16:43 ` Andy Lutomirski
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=CALCETrWRT--XO6jYyno_i0nUZEoRuq3S5_n-qFRSt2rmkd3jMQ@mail.gmail.com \
--to=luto@amacapital.net \
--cc=acme@kernel.org \
--cc=akpm@linux-foundation.org \
--cc=arnd@arndb.de \
--cc=avagin@odin.com \
--cc=avagin@openvz.org \
--cc=dsahern@gmail.com \
--cc=gorcunov@openvz.org \
--cc=linux-api@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=oleg@redhat.com \
--cc=pavel.odintsov@gmail.com \
--cc=rl@hellgate.ch \
--cc=xemul@parallels.com \
/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.