From: Ingo Molnar <mingo@elte.hu>
To: Ulrich Drepper <drepper@redhat.com>
Cc: Jamie Lokier <jamie@shareable.org>,
john stultz <johnstul@us.ibm.com>,
lkml <linux-kernel@vger.kernel.org>
Subject: Re: [RFC][PATCH] linux-2.6.2-rc2_vsyscall-gtod_B1.patch
Date: Fri, 30 Jan 2004 10:29:39 +0100 [thread overview]
Message-ID: <20040130092939.GB3841@elte.hu> (raw)
In-Reply-To: <4019E713.1010107@redhat.com>
* Ulrich Drepper <drepper@redhat.com> wrote:
> If gettimeofday() is the only optimized syscall, just add a simple
>
> cmp $__NR_gettimeofday, %eax
> je __vsyscall_gettimeofday
>
> to the __kernel_vsyscall code. With correct static branch prediction
> you'll not be able to measure the effect. The correct way is IMO to
> completely hide the optimizations since otherwise the increased
> dependencies between kernel and libc only create more friction and
> cost and loss of speed.
agreed 100%. Once the # of vsyscalls grows to above a certain treshold,
a table can be used just like we do in kernel-mode.
but i'm a bit worried about the apparent fact that adding 200 more
symbols (and making the vDSO a real DSO in essence) to abstract the
kernel syscalls is apparently unacceptable performance-wise. If this is
true then the whole dynamic linking architecture is much slower than it
should be, isnt it? Why cannot the same argument be made about the ~1400
symbols libc itself provides? Wouldnt a tighter libc API avoid all the
overhead (in fact 7x overhead) you described wrt. adding 200+ kernel
symbols? Why is the kernel vDSO so special [assuming, for the sake of
argument, a clean, versioned function API between libc and the kernel
vDSO]?
Ingo
next prev parent reply other threads:[~2004-01-30 13:05 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-01-29 2:46 john stultz
2004-01-29 5:06 ` Ulrich Drepper
2004-01-29 13:26 ` Jamie Lokier
2004-01-29 18:05 ` Ulrich Drepper
2004-01-29 19:15 ` Jamie Lokier
2004-01-29 23:59 ` john stultz
2004-01-30 0:40 ` Ulrich Drepper
2004-01-30 0:31 ` Ulrich Drepper
2004-01-30 4:17 ` Jamie Lokier
2004-01-30 5:09 ` Ulrich Drepper
2004-01-30 9:29 ` Ingo Molnar [this message]
2004-02-03 4:38 ` Ulrich Drepper
2004-01-30 17:34 ` Jamie Lokier
2004-01-30 8:33 ` Jakub Jelinek
2004-01-30 17:21 ` Jamie Lokier
2004-01-31 0:10 ` Eric W. Biederman
2004-01-31 2:41 ` Jamie Lokier
2004-01-31 5:54 ` Eric W. Biederman
2004-02-01 1:28 ` Andrea Arcangeli
2004-02-03 4:35 ` Ulrich Drepper
2004-02-03 5:34 ` Andrea Arcangeli
2004-02-03 8:52 ` Jamie Lokier
2004-02-03 16:25 ` Andrea Arcangeli
2004-02-03 17:37 ` Jamie Lokier
2004-02-03 18:10 ` Andrea Arcangeli
2004-02-03 18:23 ` Jamie Lokier
2004-02-03 18:34 ` Andrea Arcangeli
2004-01-31 0:17 ` Eric W. Biederman
2004-01-31 2:20 ` john stultz
[not found] <1075344395.1592.87.camel@cog.beaverton.ibm.com.suse.lists.linux.kernel>
[not found] ` <401894DA.7000609@redhat.com.suse.lists.linux.kernel>
[not found] ` <20040201012803.GN26076@dualathlon.random.suse.lists.linux.kernel>
[not found] ` <401F251C.2090300@redhat.com.suse.lists.linux.kernel>
[not found] ` <20040203085224.GA15738@mail.shareable.org.suse.lists.linux.kernel>
[not found] ` <20040203162515.GY26076@dualathlon.random.suse.lists.linux.kernel>
[not found] ` <20040203173716.GC17895@mail.shareable.org.suse.lists.linux.kernel>
[not found] ` <20040203181001.GA26076@dualathlon.random.suse.lists.linux.kernel>
[not found] ` <20040203182310.GA18326@mail.shareable.org.suse.lists.linux.kernel>
2004-02-04 2:27 ` Andi Kleen
2004-02-04 2:40 ` Andrea Arcangeli
2004-02-04 4:21 ` Jamie Lokier
2004-02-05 21:43 ` Andrea Arcangeli
2004-02-06 4:15 ` Rik van Riel
2004-02-06 4:28 ` Andrea Arcangeli
2004-02-06 9:23 ` Ulrich Drepper
2004-02-06 15:49 ` Andrea Arcangeli
2004-02-07 0:37 ` Ulrich Drepper
2004-02-07 2:19 ` Andrea Arcangeli
2004-02-07 3:37 ` Daniel Jacobowitz
2004-02-07 4:36 ` Andrea Arcangeli
2004-02-07 4:53 ` Jamie Lokier
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=20040130092939.GB3841@elte.hu \
--to=mingo@elte.hu \
--cc=drepper@redhat.com \
--cc=jamie@shareable.org \
--cc=johnstul@us.ibm.com \
--cc=linux-kernel@vger.kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®