qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Michael S. Tsirkin" <mst@redhat.com>
To: "Michael R. Hines" <mrhines@linux.vnet.ibm.com>
Cc: aliguori@us.ibm.com, michael.r.hines.mrhines@linux.vnet.ibm.com,
	qemu-devel@nongnu.org, owasserm@redhat.com, abali@us.ibm.com,
	mrhines@us.ibm.com, gokul@us.ibm.com, pbonzini@redhat.com
Subject: Re: [Qemu-devel] [RFC PATCH RDMA support v3: 03/10] documentation of RDMA protocol in docs/rdma.txt
Date: Mon, 11 Mar 2013 19:19:45 +0200	[thread overview]
Message-ID: <20130311171945.GA29167@redhat.com> (raw)
In-Reply-To: <513E119F.1010203@linux.vnet.ibm.com>

On Mon, Mar 11, 2013 at 01:17:19PM -0400, Michael R. Hines wrote:
> On 03/11/2013 01:05 PM, Michael S. Tsirkin wrote:
> >Well that's exactly the question. As far as I remember the RDMA
> >memory model, you need to know a key and address to execute RDMA
> >writes. Remote memory also needs to be locked, so you need some
> >mechanism to lock chunks of memory, do RDMA write and unlock when
> >done.
> 
> Yes, memory is registered before the write occurs - that's is all
> taken care of in rdma.c (patch #04/10)
> 
> Same answer for the SEND messages: memory for each send must be
> registered before you send.
> 
> The pinning (mlock()) is already handled by libibverbs (by calling
> the function ibv_reg_mr()) - standard infiniband protocol
> initialization.
> 
> - Michael

Yes but the document should describe when is the destination
memory registered and how are keys/addresses passed back to
source.

  reply	other threads:[~2013-03-11 17:19 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <1362976414-21396-1-git-send-email-mrhines@us.ibm.com>
     [not found] ` <1362976414-21396-4-git-send-email-mrhines@us.ibm.com>
2013-03-11 11:51   ` [Qemu-devel] [RFC PATCH RDMA support v3: 03/10] documentation of RDMA protocol in docs/rdma.txt Michael S. Tsirkin
2013-03-11 16:24     ` Michael R. Hines
2013-03-11 17:05       ` Michael S. Tsirkin
2013-03-11 17:17         ` Michael R. Hines
2013-03-11 17:19           ` Michael S. Tsirkin [this message]
2013-03-11 17:35             ` Michael R. Hines
     [not found] ` <1362976414-21396-3-git-send-email-mrhines@us.ibm.com>
2013-03-11 13:35   ` [Qemu-devel] [RFC PATCH RDMA support v3: 02/10] Link in new migration-rdma.c and rmda.c files Paolo Bonzini
2013-03-11 16:25     ` Michael R. Hines
     [not found] ` <1362976414-21396-9-git-send-email-mrhines@us.ibm.com>
2013-03-11 13:40   ` [Qemu-devel] [RFC PATCH RDMA support v3: 08/10] Introduce QEMUFileRDMA Paolo Bonzini
2013-03-11 16:26     ` Michael R. Hines
2013-03-11 16:26     ` Michael R. Hines
     [not found] ` <1362976414-21396-6-git-send-email-mrhines@us.ibm.com>
2013-03-11 13:41   ` [Qemu-devel] [RFC PATCH RDMA support v3: 05/10] RDMA connection establishment (migration-rdma.c) Paolo Bonzini
2013-03-11 16:28     ` Michael R. Hines
2013-03-11 20:20     ` Michael R. Hines
     [not found] ` <1362976414-21396-7-git-send-email-mrhines@us.ibm.com>
2013-03-11 13:49   ` [Qemu-devel] [RFC PATCH RDMA support v3: 06/10] Introduce 'max_iterations' and Call out to migration-rdma.c when requested Paolo Bonzini
2013-03-11 16:30     ` Michael R. Hines
     [not found] ` <1362976414-21396-8-git-send-email-mrhines@us.ibm.com>
2013-03-11 13:59   ` [Qemu-devel] [RFC PATCH RDMA support v3: 07/10] Send the actual pages over RDMA Paolo Bonzini
2013-03-11 16:31     ` Michael R. Hines
     [not found] ` <1362976414-21396-11-git-send-email-mrhines@us.ibm.com>
2013-03-11 14:00   ` [Qemu-devel] [RFC PATCH RDMA support v3: 10/10] Parse RDMA host/port out of the QMP string Paolo Bonzini
2013-03-11 16:32     ` Michael R. Hines
     [not found] ` <1362976414-21396-10-git-send-email-mrhines@us.ibm.com>
2013-03-11 14:07   ` [Qemu-devel] [RFC PATCH RDMA support v3: 09/10] Move RAMBlock to cpu-common.h Paolo Bonzini
2013-03-11 16:34     ` Michael R. Hines

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=20130311171945.GA29167@redhat.com \
    --to=mst@redhat.com \
    --cc=abali@us.ibm.com \
    --cc=aliguori@us.ibm.com \
    --cc=gokul@us.ibm.com \
    --cc=michael.r.hines.mrhines@linux.vnet.ibm.com \
    --cc=mrhines@linux.vnet.ibm.com \
    --cc=mrhines@us.ibm.com \
    --cc=owasserm@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    /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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).