From: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
To: Dave Hansen <haveblue@us.ibm.com>
Cc: "Frank Ch. Eigler" <fche@redhat.com>,
akpm@linux-foundation.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, mbligh@google.com
Subject: Re: [RFC PATCH] LTTng instrumentation mm (updated)
Date: Tue, 4 Dec 2007 15:05:58 -0500 [thread overview]
Message-ID: <20071204200558.GB1988@Krystal> (raw)
In-Reply-To: <1196797259.6073.17.camel@localhost>
* Dave Hansen (haveblue@us.ibm.com) wrote:
> On Tue, 2007-12-04 at 14:25 -0500, Mathieu Desnoyers wrote:
> >
> > - I also dump the equivalent of /proc/swaps (with kernel internal
> > information) at trace start to know what swap files are currently
> > used.
>
> What about just enhancing /proc/swaps so that this information can be
> useful to people other than those doing traces?
>
It includes an in-kernel struct file pointer, exporting it to userspace
would be somewhat ugly.
> Now that we have /proc/$pid/pagemap, we expose some of the same
> information about which userspace virtual addresses are stored where and
> in which swapfile.
>
The problems with /proc :
- It exports all the data in formatted text. What I need for my traces
is pure binary, compact representation.
- It's not very neat to export in-kernel pointer information like a
kernel tracer would need.
- The locking is very often wrong. I started correcting /proc/modules a
while ago, but I fear there are quite a few cases where a procfile
reader could release the locks between two consecutive reads of the
same list and therefore cause missing information or corruption. While
being manageable for a proc text file, this is _highly_ unwanted in a
trace. See my previous "seq file sorted" and "module.c sort module
list" patches about this. My tracer deals with addition/removal of
elements to a list between dumps done by "chunks" by tracing the
modifications done to the list at the same time. However, /proc seq
files will just get corrupted or forget about an element not touched
by the modification, which my tracer cannot cope with.
Mathieu
> -- Dave
>
--
Mathieu Desnoyers
Computer Engineering Ph.D. Student, Ecole Polytechnique de Montreal
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68
next prev parent reply other threads:[~2007-12-04 20:11 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-11-13 19:33 [RFC 0/7] LTTng Kernel Instrumentation (Architecture Independent) Mathieu Desnoyers
2007-11-13 19:33 ` [RFC 1/7] Include marker.h in kernel.h -- temporary, for code readability Mathieu Desnoyers
2007-11-13 19:33 ` [RFC 2/7] LTTng instrumentation fs Mathieu Desnoyers
2007-11-13 19:33 ` [RFC 3/7] LTTng instrumentation ipc Mathieu Desnoyers
2007-11-13 19:33 ` [RFC 4/7] LTTng instrumentation kernel Mathieu Desnoyers
2007-11-15 23:30 ` Mike Mason
2007-11-15 23:54 ` Mike Mason
2007-11-16 2:42 ` Mathieu Desnoyers
2007-11-16 2:22 ` Mathieu Desnoyers
2007-11-13 19:33 ` [RFC 5/7] LTTng instrumentation mm Mathieu Desnoyers
2007-11-15 21:06 ` Dave Hansen
2007-11-15 21:51 ` Mathieu Desnoyers
2007-11-15 22:16 ` Dave Hansen
2007-11-16 14:30 ` Mathieu Desnoyers
2007-11-19 18:04 ` Dave Hansen
2007-11-28 14:09 ` [RFC PATCH] LTTng instrumentation mm (using page_to_pfn) Mathieu Desnoyers
2007-11-28 16:54 ` Dave Hansen
2007-11-29 2:34 ` Mathieu Desnoyers
2007-11-29 6:25 ` Dave Hansen
2007-11-30 16:11 ` [RFC PATCH] LTTng instrumentation mm (updated) Mathieu Desnoyers
2007-11-30 17:46 ` Dave Hansen
2007-11-30 17:05 ` Mathieu Desnoyers
2007-11-30 18:42 ` Dave Hansen
2007-11-30 19:10 ` Mathieu Desnoyers
2007-12-04 19:15 ` Frank Ch. Eigler
2007-12-04 19:25 ` Mathieu Desnoyers
2007-12-04 19:40 ` Dave Hansen
2007-12-04 20:05 ` Mathieu Desnoyers [this message]
2007-12-04 20:24 ` Dave Hansen
2007-12-04 20:28 ` Dave Hansen
2007-11-16 14:47 ` [RFC 5/7] LTTng instrumentation mm Mathieu Desnoyers
2007-11-19 18:07 ` Dave Hansen
2007-11-19 18:52 ` Mathieu Desnoyers
2007-11-19 19:00 ` Mathieu Desnoyers
2007-11-19 19:43 ` Dave Hansen
2007-11-19 19:43 ` Dave Hansen
2007-11-19 19:52 ` [PATCH] Cast __page_to_pfn to unsigned long in CONFIG_SPARSEMEM Mathieu Desnoyers
2007-11-19 20:09 ` Dave Hansen
2007-11-19 20:20 ` [PATCH] Cast page_to_pfn " Mathieu Desnoyers
2007-11-19 21:08 ` Andrew Morton
2007-11-19 21:19 ` Dave Hansen
2007-11-19 21:26 ` Dave Hansen
2007-11-21 20:12 ` Christoph Lameter
2007-11-20 17:34 ` Mathieu Desnoyers
2007-11-13 19:33 ` [RFC 6/7] LTTng instrumentation net Mathieu Desnoyers
2007-11-13 19:33 ` [RFC 7/7] Add Markers Into Semaphore Primitives Mathieu Desnoyers
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=20071204200558.GB1988@Krystal \
--to=mathieu.desnoyers@polymtl.ca \
--cc=akpm@linux-foundation.org \
--cc=fche@redhat.com \
--cc=haveblue@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mbligh@google.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 NNTP newsgroup(s).