All of lore.kernel.org
 help / color / mirror / Atom feed
From: Yann Dupont <Yann.Dupont@univ-nantes.fr>
To: Alexandre DERUMIER <aderumier@odiso.com>
Cc: Hannes Reinecke <hare@suse.de>,
	Stefan Priebe - Profihost AG <s.priebe@profihost.ag>,
	Mark Nelson <mark.nelson@inktank.com>,
	ceph-devel@vger.kernel.org, Stefan Majer <stefan.majer@gmail.com>
Subject: Re: Infiniband 40GB
Date: Mon, 04 Jun 2012 11:53:48 +0200	[thread overview]
Message-ID: <4FCC85AC.209@univ-nantes.fr> (raw)
In-Reply-To: <d1ba3477-a5ed-488a-8785-2a37f4301ffc@mailpro>

Le 04/06/2012 11:35, Alexandre DERUMIER a écrit :
> Hi,
> about this:
>>> Turning off Virtualisation extension in BIOS. Don't know why, but it
>>> gaves us crappy performance. We usually put it on, because we use KVM a
>>> lot. In our case, OSD are in bare metal and disabling virtualisation
>>> extension gives us a very big boost.
>>> It may be a BIOS bug in our machines (DELL M610).
>
> It could be related to iommu, if you pass intel_iommu=on in grub.
> I have already had this kind of problem.
>
> When intel_iommu=on, Linux (completely unrelated to KVM) adds a new level
> of protection which didn't exist without an IOMMU - the network card, which
> without an IOMMU could write (via DMA) to any memory location, now is
> not allowed - the card can only write to memory locates which the OS
> wanted it to write. Theoretically, this can protect the OS against
> various kinds of attacks. But what happens now is that every time that
> Linux passes a new buffer to the card, it needs to change the IOMMU
> mappings. This noticably slows down I/O, unfortunately.
>
>

Infortunately, this is not the case. The intel card supports it, but 
DELL M160 don't.
And I just checked, ou linux command line don't include intel_iommu=on.

BTW, it seems that turning on virtualization on bios kills performance 
on integrated ixgbe driver. Sourceforge one seems less affected. Our 
tests were circa kernel 3.2 , it may have changed since.

Cheers,



-- 
Yann Dupont - Service IRTS, DSI Université de Nantes
Tel : 02.53.48.49.20 - Mail/Jabber : Yann.Dupont@univ-nantes.fr


--
To unsubscribe from this list: send the line "unsubscribe ceph-devel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

  reply	other threads:[~2012-06-04  9:53 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-06-03  8:10 Infiniband 40GB Stefan Priebe
2012-06-03 12:56 ` Mark Nelson
2012-06-04  6:22   ` Hannes Reinecke
2012-06-04  7:26     ` Stefan Priebe - Profihost AG
2012-06-04  7:39       ` Hannes Reinecke
2012-06-04  7:53         ` Stefan Priebe - Profihost AG
2012-06-04  8:02           ` Hannes Reinecke
2012-06-04  8:23             ` Stefan Majer
2012-06-04  9:21               ` Yann Dupont
2012-06-04  9:35                 ` Alexandre DERUMIER
2012-06-04  9:53                   ` Yann Dupont [this message]
2012-06-04  9:47                 ` Amon Ott
2012-06-04  9:58                   ` Yann Dupont
2012-06-04 11:40                   ` Alexandre DERUMIER
2012-06-04 12:59                     ` Mark Nelson
2012-06-04 13:07                       ` Alexandre DERUMIER
2012-06-04 13:28                         ` Mark Nelson
2012-06-04 15:11                           ` Gregory Farnum
2012-06-04 15:34                             ` Mark Nelson
2012-06-06 16:05                       ` Alexandre DERUMIER
2012-06-06 16:43                         ` Mark Nelson
2012-06-04 15:42                   ` Stefan Priebe
2012-06-05  7:08                     ` Amon Ott
2012-06-05  7:46                       ` Stefan Priebe - Profihost AG
2012-06-06 10:48                   ` Stefan Priebe - Profihost AG
2012-06-06 10:57                     ` Amon Ott
2012-06-06 11:02                       ` Stefan Priebe - Profihost AG
2012-06-07 11:33                         ` Amon Ott
2012-06-07 12:44                           ` Stefan Priebe - Profihost AG
2012-06-05  8:54               ` Stefan Priebe - Profihost AG
2012-06-04 12:28     ` Mark Nelson
2012-06-04 12:34       ` Tomasz Paszkowski
2012-06-04 12:40         ` Mark Nelson
     [not found] <a81f3855-1c7d-447b-9bbf-6a891e372909@mailpro>
2012-06-07  3:31 ` Alexandre DERUMIER
2012-06-07 11:25   ` Alexandre DERUMIER
2012-06-07 17:15     ` Mark Nelson

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4FCC85AC.209@univ-nantes.fr \
    --to=yann.dupont@univ-nantes.fr \
    --cc=aderumier@odiso.com \
    --cc=ceph-devel@vger.kernel.org \
    --cc=hare@suse.de \
    --cc=mark.nelson@inktank.com \
    --cc=s.priebe@profihost.ag \
    --cc=stefan.majer@gmail.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.