Date: Fri, 30 May 2008 21:00:37 +0500 From: rihad <rihad@mail.ru> To: "Bruce M. Simpson" <bms@FreeBSD.org> Cc: freebsd-net@freebsd.org Subject: Re: if_var.h micro-optimization Message-ID: <484024A5.6080109@mail.ru> In-Reply-To: <4840200F.6070602@FreeBSD.org> References: <483FFE36.7050006@mail.ru> <4840200F.6070602@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Bruce M. Simpson wrote:
> rihad wrote:
>> Not sure if this is a worthwhile optimization? FreeBSD 7.0
>>
>> --- /usr/src/sys/net/if_var.h 2007-12-07 09:46:08.000000000 +0400
>> +++ if_var.h 2008-05-30 18:10:25.000000000 +0500
>> @@ -282,7 +282,8 @@
>> if (m) { \
>> if (((ifq)->ifq_head = (m)->m_nextpkt) == NULL) \
>> (ifq)->ifq_tail = NULL; \
>> - (m)->m_nextpkt = NULL; \
>> + else \
>> + (m)->m_nextpkt = NULL; \
>> (ifq)->ifq_len--; \
>> } \
>> } while (0)
>
> It could save dirtying an L2 data cache line at the expense of taking a
> conditional branch,
Whoa, why don't you take it easy on me :) I'm not that much into kernel
(or hardware) programming. It's just that reading Ch. 3 of TCP/IP
Illustrated Vol.2 by Rich Stevens got me digging around FreeBSD source
code dealing with struct ifnet, where this piece of code caught my
attention.
> but to evaluate your suggested change requires a lot
> more data. Do you plan to do this?
Perhaps there is already a framework for trying out changes in -CURRENT
and seeing their relative impact, so perhaps someone more experienced
than I am can see to this?
> Given how _IF_DEQUEUE() is normally
> used the impact is likely negligible.
Oh, I see. A nice first attempt of mine anyway ;) Thanks.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?484024A5.6080109>