Accéder au contenu.
Menu Sympa

starpu-devel - Re: [Starpu-devel] Starpu stats about disk, OOC, and swapping

Objet : Developers list for StarPU

Archives de la liste

Re: [Starpu-devel] Starpu stats about disk, OOC, and swapping


Chronologique Discussions 
    < Chronologique >      < Discussions >
  • From: Samuel Thibault <samuel.thibault@inria.fr>
  • To: Amani Alonazi <amani.alonazi@kaust.edu.sa>
  • Cc: "starpu-devel@lists.gforge.inria.fr" <starpu-devel@lists.gforge.inria.fr>, Hatem Ltaief <Hatem.Ltaief@kaust.edu.sa>
  • Subject: Re: [Starpu-devel] Starpu stats about disk, OOC, and swapping
  • Date: Mon, 14 Jan 2019 18:52:36 +0100
  • List-archive: <http://lists.gforge.inria.fr/pipermail/starpu-devel/>
  • List-id: "Developers list. For discussion of new features, code changes, etc." <starpu-devel.lists.gforge.inria.fr>
  • Organization: I am not organized
Amani Alonazi, le lun. 14 janv. 2019 20:46:45 +0300, a ecrit:
> Indeed. But, StarPU statistics reports more than 90 MB/s, which is the
> sustained BW.

Ah, ok (please always specify what you think looks wrong :) ).

Yes, that may look a bit odd. But that can happen if you are not using
the unistd_o_direct backend, in which case the OS makes some caching.
Even with unistd_o_direct I wouldn't be surprised that the measurements
differ noticeably, since the Linux block scheduler also comes in etc.

Samuel


Archives gérées par MHonArc 2.6.19+.

Haut de le page