From: Yumiko Sugita <email@example.com>
Cc: firstname.lastname@example.org, email@example.com,
Subject: Re: [Lkst-develop] Re: Release of LKST 1.3
Date: Thu, 03 Oct 2002 18:46:01 +0900 [thread overview]
Message-ID: <126.96.36.199.2.20021003183537.06a8ad90@sdl99c> (raw)
Hello, Mr. Karim
I'm Yumiko Sugita, a member of LKST developers.
I read your mail. Thank you for your advices.
The features for SMP are one of our important aims,
so we, LKST developpers, developed them. We welcome
IBM's work on them.
We think callback feature is useful for kernel developers.
Are there any problems? Are you going to remove callbacks
from LTT? Is the main reason security? If you have some
cases of security problems about callbacks, please teach
them and give some advice to us.
After future, we'll join community actively. We'll use LTT
and want to concern LTT, so we'll join the discussion of you
and other LTT developers about Linux RAS.
We hope to co-operate you and other developers about
Hitachi, Ltd., Systems Development Laboratory
Email : firstname.lastname@example.org
At 11:48 02/09/27 -0400, Karim Yaghmour wrote:
>Just a couple of general observations here.
>Yumiko Sugita wrote:
> > Consequently, LKST, which is oriented to enterprise systems,
> > has the following features different from those of LTT.
> > # These LKST features are also being enhanced at this time.
> > (1) Little overhead and good scalability when tracing on a large-scale
> > SMP system
> > * To make lock mechanism overhead as little as possible, we
> > designed that the buffers are not shared among CPUs.
>I was wondering whether you followed the recent discussion about LTT on the
>LKML? Clearly this is not a problem for LTT since we don't use any form
>of locking whatsoever anymore. IBM's work on the lockless scheme has
>solved this problem and their current work on the per-CPU buffering solves
>the rest of the issue.
> > (2) Easy to extend/expand the function (User-based extendibility)
> > * Without recompiling kernel, user can change/add/modify the kind
> > of events and information to be recorded at anytime.
>Ditto with LTT.
> > For example, LKST usually traces very few events for the purpose
> > of good performance. Once the kernel get into the particular status
> > that user specified, LKST will trace and record more detail information.
>This implies callbacks, which do exist in LTT and which Ingo Molnar explicitly
>asked us to remove.
> > (3) Preservation of trace information
> > * Recovery of trace information collected at the time of a system crash
> > in connection with LKCD.
>Connection with LKCD is really not a problem, but this points to the main
>purpose of the tool, which in the case of LKCD is kernel debugging. LTT isn't
>aimed as a kernel debugger, so although LKCD is on our to-do list, it's
>certainly not our priority.
>As for handling multiple output streams (which LKCD can be one of them), we
>already have very detailed plans on how LTT is going to integrate this (as I've
>mentioned a number of times before on this list). However, before we go down
>this road we need to make sure that the core tracing functionality is
>lightweight and fits the general requirements set for kernel code. Once this
>core lighweight functionality is there, we can build a rich and solid feature
>set around it.
> > * Saving of specific event information during tracing.
> > For example, switching to another buffer after the occurrence of
> > a specific event enables the information on that event to be left
> > in the previous buffer.
>Again, callbacks and triggers. A while back, I had written a state machine
>engine for LTT. Basically, you could provide it with an event-driven state
>machine and it would callback your functions depending on the sequence of
>events. All of this obviously implies callbacks, which, as I said earlier,
>we've been explicitly asked to remove.
> > (4) Collection of even more kernel event information
> > * Information on more than 50 kernel events can be collected for
> > kernel debugging.
>Well, I think this is where LTT and LKST cannot be compared. If LKST is
>a kernel debugging tool, as it has always been advertised, then any comparison
>of LKST should be made with the other tracing tools which are used for
>kernel debugging, such as the ones mentioned by Ingo and Andi earlier on
>LTT was built from the ground up to help users understand the dynamic
>behavior of the system. As such, it cannot be compared to any kernel
>debugging tool since it isn't one.
> > The demand for RAS functions in Linux should grow in the years to come.
> > It is our hope that LKST becomes one means of implementing such functions.
>There was a RAS BoF at the OLS this year where tracing was intensively
>All the attendees agreed to unify their efforts around LTT. At this meeting,
>Richard Moore of IBM presented a tracing to-do list
>(http://opersys.com/LTT/ltt-to-do-list.txt) which we are using a basic
>check list for our ongoing work. Instead of implementing yet another tracing
>system, I think that the LKST team would benefit much from contributing to
>LTT, which has already a proven track record and has been adopted by the
>community as much as the industry.
> Karim Yaghmour
> Embedded and Real-Time Linux Expert
>To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
>the body of a message to email@example.com
>More majordomo info at http://vger.kernel.org/majordomo-info.html
>Please read the FAQ at http://www.tux.org/lkml/
next prev parent reply other threads:[~2002-10-03 9:39 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-09-18 12:20 Release of LKST 1.3 Yumiko Sugita
2002-09-19 5:58 ` Robert Schwebel
2002-09-26 12:36 ` [Lkst-develop] " Yumiko Sugita
2002-09-27 15:48 ` Karim Yaghmour
2002-10-03 9:46 ` Yumiko Sugita [this message]
2002-10-09 18:05 ` Karim Yaghmour
2002-09-19 8:18 ` Vamsi Krishna S.
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:
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
* 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).