Messages in this thread | | | Date | Tue, 13 Sep 2005 00:26:42 +1000 | From | Nick Piggin <> | Subject | Re: 2.6.13-mm3 |
| |
Andrew Walrond wrote: > On Monday 12 September 2005 10:43, Andrew Morton wrote: > > >> - An update to the anticipatory scheduler to fix a performance problem >> where processes do a single read then exit, in the presence of >>competing I/O acticity. > > > Is there more discussion on this somewhere? When was the problem introduced? > Bit of a long shot, but it fits the description of some problems I have > noticed recently. >
It has been quite a while coming. The problem has been there for a long time, but there is no "regression" that would not exist in eg. deadline scheduler.
Basically it used to "miss" opportunities to do read anticipation where it should pay off, and now it misses less.
A description of / pointer to your problems would be interesting.
Nick
-- SUSE Labs, Novell Inc.
Send instant messages to your online friends http://au.messenger.yahoo.com
- 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/
| |