lkml.org 
[lkml]   [2001]   [Apr]   [5]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: [PATCH for 2.5] preemptible kernel
Date
In message <3AC8D95E.7E3A68B0@mvista.com> you write:
> On a higher level, I think the scanning of the run list to set flags and
> counters is a bit off.

[snip standard refcnt scheme]

For most things, refcnts are great. I use them in connection
tracking. But when writes can be insanely slow (eg. once per hour),
those two atomic ops just hurt scalability, and are invasive.

In particular, they suck HARD for modules, which is where my initial
quiescent wait implementation came from, only I didn't call it that
because Andi hadn't posted the Sequent paper URL yet and I hadn't
figured out that this was a generically useful scheme that can be
implemented in 20 lines...

Rusty.
--
Premature optmztion is rt of all evl. --DK
-
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: 2005-03-22 13:24    [W:0.107 / U:8.836 seconds]
©2003-2018 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site