From: fche@redhat.com (Frank Ch. Eigler)
To: Evgeniy Polyakov <johnpol@2ka.mipt.ru>
Cc: Christoph Hellwig <hch@lst.de>,
ksummit-2008-discuss@lists.linux-foundation.org,
systemtap@sources.redhat.com
Subject: Re: [Ksummit-2008-discuss] DTrace
Date: Sun, 06 Jul 2008 18:05:00 -0000 [thread overview]
Message-ID: <y0mwsjysxjw.fsf@ton.toronto.redhat.com> (raw)
In-Reply-To: <20080706163533.GA16721@2ka.mipt.ru> (Evgeniy Polyakov's message of "Sun, 6 Jul 2008 20:35:34 +0400")
Evgeniy Polyakov <johnpol@2ka.mipt.ru> writes:
>> > We don't add kernel interface for out of tree modules.
>>
>> That is a specific example of an attitude that I hope will be
>> reexamined if y'all want to support dtrace-level introspection.
>
> I believe the only answer you will get is 'no'. Both for dtrace-like
> stuff and ability to add unmaintained interfaces into the kernel.
>
> Out-of-tree stuff can appear and disappear, change its internal
> structures, API, ABI [...]
Yes, well, it turns out that the number of systemtap-specific kernel
interfaces we have requested is ... precisely ... zero.
We have on occasion asked that some established module interfaces
simply not be *unexported*, but almost all of those requests have been
turned down, requiring us to kludge. We have helped promote a
systemtap-neutral instrumentation mechanism (markers), along with a
project with a near-decade history of stable instrumentation (ltt/ng),
and one can see the progress (?) that this has made even since Karim's
"emperor is naked" note two (!) years ago.
>> > And thinking about it - having to compile out of tree kernel modules
>> > on the fly to trace user space processes is just braindead.
>>
>> I gladly grant "counterintuitive", especially if one's intuition is
>> limited to probing just one's own pet user-space process. It is a
>> different matter when one needs to seamlessly probe a mixture of
>> kernel activities, daemons, and user processes.
>
> Out of curiosity, how in the hell administrator or any other non kernel
> hacker person needs to have ability to tap into userspace process via
> kernel module?
Think about how a non-intrusive system-wide probing must work, if it
is desirable not to interfere with e.g. thread scheduling or VM state.
Specifically, if we don't want to context-switch from threads (thereby
interfering with contention effects we may want to measure), nor page
data in/out just to satisfy probe data (thereby generating more I/O
and associated distortions). It seems only kernel-side code can do
all of that. Do you have a better suggestion?
- FChE
next prev parent reply other threads:[~2008-07-06 18:05 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20080627150424.GB14894@parisc-linux.org>
[not found] ` <1214580213.3394.40.camel@localhost.localdomain>
[not found] ` <20080627155018.GC14894@parisc-linux.org>
[not found] ` <1214583502.7698.15.camel@weaponx>
[not found] ` <20080627163056.GB1416@lst.de>
[not found] ` <20080628072605.GA505@in.ibm.com>
[not found] ` <20080629084002.GA24131@lst.de>
[not found] ` <20080630051034.GA4970@in.ibm.com>
[not found] ` <20080630112913.GA18817@lst.de>
2008-06-30 19:27 ` Frank Ch. Eigler
2008-07-01 1:21 ` Jim Keniston
[not found] ` <20080706123414.GA9265@lst.de>
2008-07-06 15:47 ` Frank Ch. Eigler
2008-07-06 16:36 ` Evgeniy Polyakov
2008-07-06 18:05 ` Frank Ch. Eigler [this message]
2008-07-06 18:24 ` Evgeniy Polyakov
2008-07-06 21:46 ` Frank Ch. Eigler
2008-07-06 22:47 ` Karen Shaeffer
2008-07-06 23:15 ` Frank Ch. Eigler
2008-07-07 5:59 ` Evgeniy Polyakov
2008-07-07 11:19 ` Frank Ch. Eigler
[not found] ` <20080627182754.GB7549@mit.edu>
[not found] ` <1214597135.3394.82.camel@localhost.localdomain>
[not found] ` <aday74qlh08.fsf@cisco.com>
[not found] ` <4865B111.2040307@redhat.com>
[not found] ` <adavdzujh2u.fsf@cisco.com>
[not found] ` <20080704200055.GA11232@synapse.neuralscape.com>
[not found] ` <20080704224424.GA12454@synapse.neuralscape.com>
[not found] ` <1215273663.3439.34.camel@localhost.localdomain>
2008-07-06 23:33 ` Frank Ch. Eigler
2008-07-07 14:35 ` James Bottomley
2008-07-07 15:02 ` James Bottomley
2008-06-30 13:57 DTrace Frank Ch. Eigler
2008-06-30 19:00 ` [Ksummit-2008-discuss] DTrace Grant Grundler
2008-06-30 19:40 ` Theodore Tso
2008-06-30 20:00 ` Frank Ch. Eigler
2008-06-30 20:19 ` Theodore Tso
2008-06-30 21:12 ` Arnaldo Carvalho de Melo
2008-06-30 23:02 ` David Miller
2008-06-30 21:13 ` James Bottomley
2008-06-30 22:10 ` Frank Ch. Eigler
2008-07-01 2:42 ` Theodore Tso
2008-07-01 7:08 ` Roland McGrath
2008-07-01 10:15 ` Theodore Tso
2008-07-01 11:04 ` Sam Ravnborg
2008-07-01 12:13 ` Theodore Tso
2008-07-02 20:27 ` Sam Ravnborg
2008-07-01 20:06 ` Roland McGrath
2008-07-01 23:13 ` Theodore Tso
2008-07-02 2:23 ` Frank Ch. Eigler
2008-07-02 19:27 ` Frank Ch. Eigler
2008-07-02 20:08 ` Joel Becker
2008-07-02 20:17 ` J. Bruce Fields
2008-07-02 20:41 ` Frank Ch. Eigler
2008-07-02 21:19 ` H. Peter Anvin
2008-07-02 21:30 ` Theodore Tso
2008-07-02 21:46 ` J. Bruce Fields
2008-07-05 9:46 ` Peter Zijlstra
2008-07-05 10:07 ` Christoph Hellwig
2008-07-05 12:12 ` Frank Ch. Eigler
2008-07-05 18:08 ` Christoph Hellwig
2008-07-05 13:50 ` James Bottomley
2008-07-05 18:08 ` Christoph Hellwig
2008-07-05 18:05 ` K.Prasad
2008-07-07 14:36 ` Christoph Hellwig
2008-07-07 17:44 ` K.Prasad
2008-07-05 12:34 ` Theodore Tso
2008-07-01 5:29 ` Ananth N Mavinakayanahalli
2008-06-30 19:59 ` James Bottomley
2008-06-30 23:52 ` Masami Hiramatsu
2008-07-08 23:32 ` Eric W. Biederman
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=y0mwsjysxjw.fsf@ton.toronto.redhat.com \
--to=fche@redhat.com \
--cc=hch@lst.de \
--cc=johnpol@2ka.mipt.ru \
--cc=ksummit-2008-discuss@lists.linux-foundation.org \
--cc=systemtap@sources.redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).