lkml.org 
[lkml]   [2009]   [Feb]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: [RFC][PATCH] signals: don't copy siginfo_t on dequeue
From
2009/2/26 Ingo Molnar <mingo@elte.hu>:
>
> * Vegard Nossum <vegard.nossum@gmail.com> wrote:
>
>> >From 60fc9a464377159ab807aec63277d4970019d631 Mon Sep 17 00:00:00 2001
>> From: Vegard Nossum <vegard.nossum@gmail.com>
>> Date: Thu, 26 Feb 2009 19:17:58 +0100
>> Subject: [PATCH] signals: don't copy siginfo_t on dequeue
>>
>> Instead of copying the siginfo_t whenever a signal is dequeued, just
>> get the pointer to the struct sigqueue, which can be freed by the
>> caller when the signal has been delivered.
>>
>> We can save kernel text (x86, 32-bit):
>>
>> $ scripts/bloat-o-meter vmlinux-unpatched vmlinux
>> add/remove: 0/0 grow/shrink: 3/7 up/down: 81/-538 (-457)
>> function                                     old     new   delta
>> get_signal_to_deliver                        871     922     +51
>> release_console_sem                          459     481     +22
>> generate_resume_trace                        611     619      +8
>> send_sigqueue                                257     253      -4
>> vma_adjust                                  1101    1093      -8
>> sys_rt_sigtimedwait                          548     531     -17
>> dequeue_signal                               415     372     -43
>> __dequeue_signal                             388     259    -129
>> signalfd_read                               1290    1139    -151
>> do_notify_resume                            2216    2030    -186
>>
>> And we reduce stack pressure; In handle_signal() (in x86 code), we
>> replace a siginfo_t (128 bytes) with a pointer (8 bytes on x86_64),
>> and the same in signalfd_read().
>>
>> There is a slight slowdown (2.02% relative increase in CPU time):
>>
>>               unpatched       patched
>> ----------------------------------------
>> mean:         3.078500        3.140800
>> stddev:       0.074624        0.168989
>>
>> (Numbers are: CPU time in seconds, for two processes to
>> ping-pong in total 655360 SIGUSR1/SIGUSR2 signals between each
>> other. This was repeated 100 times for each kernel.)
>
> hm, does this SIGUSR1/SIGUSR2 test actually make use siginfo?

The delivery of a signal requires one copy_siginfo(). Likewise for
e.g. sys_kill(), which also requires one copy_siginfo(). So with this
patch, we have saved only the copy_siginfo() of the delivery path.

> I.e. shouldnt we have seen a speedup, due to not having to copy
> the siginfo structure?

Actually, no. Because copy_siginfo() does not copy the whole (128
byte) structure if the signal was generated by the user, just probably
the first 24 bytes or so. So I would expect the "kernel generated
signal" path to be faster, but that is not tested by my SIGUSR test.

Besides, I think there is a small overhead in now having an extra
level of indirection for getting our hands on the signal number.

But we might able to speed up the user->user case a little bit by
fixing sys_kill() not to use copy_siginfo() too.


Vegard

--
"The animistic metaphor of the bug that maliciously sneaked in while
the programmer was not looking is intellectually dishonest as it
disguises that the error is the programmer's own creation."
-- E. W. Dijkstra, EWD1036
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2009-02-26 20:13    [W:0.081 / U:0.760 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site