[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] sedf oversubscription


  • To: xen-devel@xxxxxxxxxxxxxxxxxxx
  • From: Diwaker Gupta <diwaker.lists@xxxxxxxxx>
  • Date: Mon, 29 Aug 2005 16:49:02 -0700
  • Delivery-date: Mon, 29 Aug 2005 23:47:03 +0000
  • Domainkey-signature: a=rsa-sha1; q=dns; c=nofws; s=beta; d=gmail.com; h=received:message-id:date:from:to:subject:mime-version:content-type:content-transfer-encoding:content-disposition; b=cTjpSWlAEk5e7xFEJYH2jxPti7NS9YiAWDeVZgv/GTzy1qXtTMy5Vpg9BoGNxZhplof/1NID35N+akElOZGr8VQZyFOKaHpyiYB8oy2Cd3R1Q8/t17PiOMODok5n5sJZ9Sj5L+oq/4J2p6c21jfYfM2uwtXZm0xf+mdMejSb9mw=
  • List-id: Xen developer discussion <xen-devel.lists.xensource.com>

I looked around but haven't found a definitive answer to this on the
mailing list archives -- how does SEDF handle oversubscription? I'm
not using weights at all -- just period/slice specifications for each
domain. So what happens if a user tries to give a specification where
sum(period/slice over all domains) > 1?

Looking at the code it seems that SEDF just *assumes* that the
specification will be valid. Is that correct? Does anyone have a
handle on how the scheduler will behave if an invalid spec is given? I
guess I could just try for myself....

-- 
Web/Blog/Gallery: http://floatingsun.net

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.