From: Alan Jenkins <alan-jenkins@tuffmail.co.uk>
To: linux-hotplug@vger.kernel.org
Subject: [GIT] Experimental threaded udev
Date: Thu, 28 May 2009 14:35:36 +0000 [thread overview]
Message-ID: <4A1EA138.10400@tuffmail.co.uk> (raw)
Now available for your delight and/or horror.
<http://github.com/sourcejedi/udev/commits/threading-v0.3>
For now, I'm still treating this as a patch series. That is, I may
publish future versions with a rewritten history. I'll preserve the old
branches though.
It turns out the MADV_DONTFORK hack I was so proud of is
implementation-dependant, i.e. a dirty hack. However, I'm confident
that glibc can and should be modified to do it for all programs. And it
is so worth it. On my test machine, threading alone goes from 2s
boot-time coldplug to 1.3-ish. MADV_DONTFORK takes it down to 0.7-ish.
The hack is contained in the last patch, "when forking a program, only
copy the stack of the _current_ thread".
Thanks for your time and encouragement
Alan
udevd: don't use alarm() for timeouts
Build udevd with pthreads
Protect selinux context against concurrent modification
Add close-on-exec wrappers for open(), fopen(), pipe() and socket()
Convert udevd and libudev to use close-on-exec wrapper functions
Add abstraction layer for udev event tasks
Run udev event tasks in threads
udevd: when forking a program, only copy the stack of the
_current_ thread
configure.ac | 15 ++
extras/ata_id/Makefile.am | 3 +-
extras/cdrom_id/Makefile.am | 3 +-
extras/collect/Makefile.am | 3 +-
extras/edd_id/Makefile.am | 3 +-
extras/floppy/Makefile.am | 1 +
extras/fstab_import/Makefile.am | 3 +-
extras/scsi_id/Makefile.am | 3 +-
extras/usb_id/Makefile.am | 3 +-
m4/acx_pthread.m4 | 280 ++++++++++++++++++++++++++++++
udev/Makefile.am | 8 +
udev/lib/Makefile.am | 1 +
udev/lib/libudev-cloexec.c | 226 ++++++++++++++++++++++++
udev/lib/libudev-ctrl.c | 2 +-
udev/lib/libudev-device-db-write.c | 2 +-
udev/lib/libudev-device.c | 6 +-
udev/lib/libudev-monitor.c | 4 +-
udev/lib/libudev-private.h | 13 ++
udev/lib/libudev-queue.c | 2 +-
udev/lib/libudev-sysdeps.h | 96 ++++++++++
udev/lib/libudev.c | 18 ++-
udev/test-udev.c | 7 -
udev/udev-event.c | 335
+++++++++++++++++++++++++++++++++++-
udev/udev-node.c | 2 +-
udev/udev-rules.c | 53 +++---
udev/udev-selinux.c | 9 +-
udev/udev-task.c | 295 +++++++++++++++++++++++++++++++
udev/udev-util.c | 211 -----------------------
udev/udev.h | 23 +++-
udev/udevd.c | 323
++++++++++++++++++-----------------
30 files changed, 1527 insertions(+), 426 deletions(-)
create mode 100644 m4/acx_pthread.m4
create mode 100644 udev/lib/libudev-cloexec.c
create mode 100644 udev/lib/libudev-sysdeps.h
create mode 100644 udev/udev-task.c
next reply other threads:[~2009-05-28 14:35 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-05-28 14:35 Alan Jenkins [this message]
2009-05-28 15:09 ` [GIT] Experimental threaded udev Kay Sievers
2009-05-28 15:39 ` Alan Jenkins
2009-05-29 17:53 ` Alan Jenkins
2009-05-29 18:11 ` Kay Sievers
2009-06-01 2:41 ` Kay Sievers
2009-06-01 9:29 ` Alan Jenkins
2009-06-01 11:32 ` Kay Sievers
2009-06-01 12:33 ` Kay Sievers
2009-06-01 13:30 ` Kay Sievers
2009-06-01 13:46 ` Alan Jenkins
2009-06-01 13:57 ` Kay Sievers
2009-06-01 16:22 ` Kay Sievers
2009-06-01 16:24 ` Alan Jenkins
2009-06-01 19:39 ` Kay Sievers
2009-06-02 4:58 ` Kay Sievers
2009-06-02 9:13 ` Alan Jenkins
2009-06-02 9:26 ` Alan Jenkins
2009-06-02 11:39 ` Kay Sievers
2009-06-02 14:05 ` Kay Sievers
2009-06-03 19:44 ` Kay Sievers
2009-06-03 20:46 ` Alan Jenkins
2009-06-03 22:20 ` Kay Sievers
2009-06-03 23:53 ` Kay Sievers
2009-06-06 14:20 ` Kay Sievers
2009-06-06 17:01 ` Bryan Kadzban
2009-06-08 11:45 ` Scott James Remnant
2009-06-08 16:29 ` Bryan Kadzban
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=4A1EA138.10400@tuffmail.co.uk \
--to=alan-jenkins@tuffmail.co.uk \
--cc=linux-hotplug@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;
as well as URLs for NNTP newsgroup(s).