From: Greg KH <gregkh@linuxfoundation.org>
To: Andrii Nakryiko <andrii@kernel.org>
Cc: linux-fsdevel@vger.kernel.org, brauner@kernel.org,
viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
linux-kernel@vger.kernel.org, bpf@vger.kernel.org,
linux-mm@kvack.org
Subject: Re: [PATCH 5/5] selftests/bpf: a simple benchmark tool for /proc/<pid>/maps APIs
Date: Sat, 4 May 2024 17:32:53 +0200 [thread overview]
Message-ID: <2024050425-setting-enhance-3bcd@gregkh> (raw)
In-Reply-To: <20240504003006.3303334-6-andrii@kernel.org>
On Fri, May 03, 2024 at 05:30:06PM -0700, Andrii Nakryiko wrote:
> I also did an strace run of both cases. In text-based one the tool did
> 68 read() syscalls, fetching up to 4KB of data in one go.
Why not fetch more at once?
And I have a fun 'readfile()' syscall implementation around here that
needs justification to get merged (I try so every other year or so) that
can do the open/read/close loop in one call, with the buffer size set by
userspace if you really are saying this is a "hot path" that needs that
kind of speedup. But in the end, io_uring usually is the proper api for
that instead, why not use that here instead of slow open/read/close if
you care about speed?
> In comparison,
> ioctl-based implementation had to do only 6 ioctl() calls to fetch all
> relevant VMAs.
>
> It is projected that savings from processing big production applications
> would only widen the gap in favor of binary-based querying ioctl API, as
> bigger applications will tend to have even more non-executable VMA
> mappings relative to executable ones.
Define "bigger applications" please. Is this some "large database
company workload" type of thing, or something else?
thanks,
greg k-h
next prev parent reply other threads:[~2024-05-04 15:32 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-04 0:30 [PATCH 0/5] ioctl()-based API to query VMAs from /proc/<pid>/maps Andrii Nakryiko
2024-05-04 0:30 ` [PATCH 1/5] fs/procfs: extract logic for getting VMA name constituents Andrii Nakryiko
2024-05-04 0:30 ` [PATCH 2/5] fs/procfs: implement efficient VMA querying API for /proc/<pid>/maps Andrii Nakryiko
2024-05-04 15:28 ` Greg KH
2024-05-04 21:50 ` Andrii Nakryiko
2024-05-06 13:58 ` Arnaldo Carvalho de Melo
2024-05-06 18:05 ` Namhyung Kim
2024-05-06 18:51 ` Andrii Nakryiko
2024-05-06 18:53 ` Arnaldo Carvalho de Melo
2024-05-06 19:16 ` Arnaldo Carvalho de Melo
2024-05-07 21:55 ` Namhyung Kim
2024-05-06 18:41 ` Andrii Nakryiko
2024-05-06 20:35 ` Arnaldo Carvalho de Melo
2024-05-07 16:36 ` Andrii Nakryiko
2024-05-04 23:36 ` kernel test robot
2024-05-07 18:10 ` Liam R. Howlett
2024-05-07 18:52 ` Andrii Nakryiko
2024-05-04 0:30 ` [PATCH 3/5] tools: sync uapi/linux/fs.h header into tools subdir Andrii Nakryiko
2024-05-04 0:30 ` [PATCH 4/5] selftests/bpf: make use of PROCFS_PROCMAP_QUERY ioctl, if available Andrii Nakryiko
2024-05-04 0:30 ` [PATCH 5/5] selftests/bpf: a simple benchmark tool for /proc/<pid>/maps APIs Andrii Nakryiko
2024-05-04 15:29 ` Greg KH
2024-05-04 21:57 ` Andrii Nakryiko
2024-05-05 5:09 ` Ian Rogers
2024-05-06 18:32 ` Andrii Nakryiko
2024-05-06 18:43 ` Ian Rogers
2024-05-07 5:06 ` Andrii Nakryiko
2024-05-07 17:29 ` Andrii Nakryiko
2024-05-07 22:27 ` Namhyung Kim
2024-05-07 22:56 ` Andrii Nakryiko
2024-05-08 0:36 ` Arnaldo Carvalho de Melo
2024-05-04 15:32 ` Greg KH [this message]
2024-05-04 22:13 ` Andrii Nakryiko
2024-05-07 15:48 ` Liam R. Howlett
2024-05-07 16:10 ` Matthew Wilcox
2024-05-07 16:18 ` Liam R. Howlett
2024-05-07 16:27 ` Andrii Nakryiko
2024-05-07 18:06 ` Liam R. Howlett
2024-05-07 19:00 ` Andrii Nakryiko
2024-05-08 1:20 ` Liam R. Howlett
2024-05-04 11:24 ` [PATCH 0/5] ioctl()-based API to query VMAs from /proc/<pid>/maps Christian Brauner
2024-05-04 15:33 ` Greg KH
2024-05-04 21:50 ` Andrii Nakryiko
2024-05-04 21:50 ` Andrii Nakryiko
2024-05-05 5:26 ` Ian Rogers
2024-05-06 18:58 ` Andrii Nakryiko
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=2024050425-setting-enhance-3bcd@gregkh \
--to=gregkh@linuxfoundation.org \
--cc=akpm@linux-foundation.org \
--cc=andrii@kernel.org \
--cc=bpf@vger.kernel.org \
--cc=brauner@kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=viro@zeniv.linux.org.uk \
/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).