This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
Home Products Support Community News


[Xen-devel] SEDF Scheduler slice time fix

To: xen-devel@xxxxxxxxxxxxxxxxxxx
Subject: [Xen-devel] SEDF Scheduler slice time fix
From: Atsushi SAKAI <sakaia@xxxxxxxxxxxxxx>
Date: Fri, 19 May 2006 11:46:31 +0900
Delivery-date: Thu, 18 May 2006 19:47:17 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
Hi, All

This is a patch for SEDF Scheduler slice time fix.
At real-time domain, the slice time is relative time (from "s_time_t now").
But current code, slice time is caliculated from 0(absolute time)

It needs to be fix the code to compare relative time from "s_time_t now"

On each value meanings, You should read the comment on sched-sedf.c
(the comment also exists in patch.)

 In case of "CPU slice time < waitq time",
 Time slice is selected to CPU slice time by this patch.

 Without this patch, CPU slice time is over allocated.
 (Because CPU slice time is absolute time at this moment(large value),
 but waitq time is relative time(small value),
 and MIN() selects smaller value(waitq).)

Signed-off-by: Atsushi SAKAI <sakaia@xxxxxxxxxxxxxx>


Atsushi SAKAI

富士通(株) プラットフォーム技術開発本部 仮想システム開発統括部
酒井 敦    Email   sakaia@xxxxxxxxxxxxxx
                TEL     7124-4167(4月7日より)

Attachment: sedf0519.patch
Description: Binary data

Xen-devel mailing list
<Prev in Thread] Current Thread [Next in Thread>