From patchwork Mon Jul 22 14:01:51 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: mrhines@linux.vnet.ibm.com X-Patchwork-Id: 260716 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [IPv6:2001:4830:134:3::11]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (Client did not present a certificate) by ozlabs.org (Postfix) with ESMTPS id D8AF02C0095 for ; Tue, 23 Jul 2013 00:03:39 +1000 (EST) Received: from localhost ([::1]:35009 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1V1Gi9-0002ra-K4 for incoming@patchwork.ozlabs.org; Mon, 22 Jul 2013 10:03:37 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:51869) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1V1GhN-0002QC-7i for qemu-devel@nongnu.org; Mon, 22 Jul 2013 10:03:00 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1V1GhH-0000WO-7e for qemu-devel@nongnu.org; Mon, 22 Jul 2013 10:02:49 -0400 Received: from e9.ny.us.ibm.com ([32.97.182.139]:37140) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1V1GhH-0000RA-0d for qemu-devel@nongnu.org; Mon, 22 Jul 2013 10:02:43 -0400 Received: from /spool/local by e9.ny.us.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Mon, 22 Jul 2013 10:02:20 -0400 Received: from d01dlp03.pok.ibm.com (9.56.250.168) by e9.ny.us.ibm.com (192.168.1.109) with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted; Mon, 22 Jul 2013 10:02:19 -0400 Received: from d01relay03.pok.ibm.com (d01relay03.pok.ibm.com [9.56.227.235]) by d01dlp03.pok.ibm.com (Postfix) with ESMTP id 4F6B9C90041 for ; Mon, 22 Jul 2013 10:02:17 -0400 (EDT) Received: from d01av01.pok.ibm.com (d01av01.pok.ibm.com [9.56.224.215]) by d01relay03.pok.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id r6ME2Hjl159082 for ; Mon, 22 Jul 2013 10:02:17 -0400 Received: from d01av01.pok.ibm.com (loopback [127.0.0.1]) by d01av01.pok.ibm.com (8.14.4/8.13.1/NCO v10.0 AVout) with ESMTP id r6ME2E9P005480 for ; Mon, 22 Jul 2013 10:02:14 -0400 Received: from mrhinesdev.klabtestbed.com (klinux.watson.ibm.com [9.2.208.21]) by d01av01.pok.ibm.com (8.14.4/8.13.1/NCO v10.0 AVin) with ESMTP id r6ME2DjR005369; Mon, 22 Jul 2013 10:02:14 -0400 From: mrhines@linux.vnet.ibm.com To: qemu-devel@nongnu.org Date: Mon, 22 Jul 2013 10:01:51 -0400 Message-Id: <1374501718-2581-2-git-send-email-mrhines@linux.vnet.ibm.com> X-Mailer: git-send-email 1.7.10.4 In-Reply-To: <1374501718-2581-1-git-send-email-mrhines@linux.vnet.ibm.com> References: <1374501718-2581-1-git-send-email-mrhines@linux.vnet.ibm.com> X-TM-AS-MML: No X-Content-Scanned: Fidelis XPS MAILER x-cbid: 13072214-7182-0000-0000-000007CED6C2 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.4.x-2.6.x [generic] X-Received-From: 32.97.182.139 Cc: aliguori@us.ibm.com, quintela@redhat.com, knoel@redhat.com, owasserm@redhat.com, abali@us.ibm.com, mrhines@us.ibm.com, gokul@us.ibm.com, pbonzini@redhat.com, chegu_vinod@hp.com Subject: [Qemu-devel] [PATCH v3 resend 1/8] rdma: update documentation to reflect new unpin support X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org From: "Michael R. Hines" As requested, the protocol now includes memory unpinning support. This has been implemented in a non-optimized manner, in such a way that one could devise an LRU or other workload-specific information on top of the basic mechanism to influence the way unpinning happens during runtime. The feature is not yet user-facing, and is thus can only be enabled at compile-time. Reviewed-by: Eric Blake Signed-off-by: Michael R. Hines --- docs/rdma.txt | 51 ++++++++++++++++++++++++++++++--------------------- 1 file changed, 30 insertions(+), 21 deletions(-) diff --git a/docs/rdma.txt b/docs/rdma.txt index 45a4b1d..45d1c8a 100644 --- a/docs/rdma.txt +++ b/docs/rdma.txt @@ -35,7 +35,7 @@ memory tracked during each live migration iteration round cannot keep pace with the rate of dirty memory produced by the workload. RDMA currently comes in two flavors: both Ethernet based (RoCE, or RDMA -over Convered Ethernet) as well as Infiniband-based. This implementation of +over Converged Ethernet) as well as Infiniband-based. This implementation of migration using RDMA is capable of using both technologies because of the use of the OpenFabrics OFED software stack that abstracts out the programming model irrespective of the underlying hardware. @@ -188,9 +188,9 @@ header portion and a data portion (but together are transmitted as a single SEND message). Header: - * Length (of the data portion, uint32, network byte order) - * Type (what command to perform, uint32, network byte order) - * Repeat (Number of commands in data portion, same type only) + * Length (of the data portion, uint32, network byte order) + * Type (what command to perform, uint32, network byte order) + * Repeat (Number of commands in data portion, same type only) The 'Repeat' field is here to support future multiple page registrations in a single message without any need to change the protocol itself @@ -202,17 +202,19 @@ The maximum number of repeats is hard-coded to 4096. This is a conservative limit based on the maximum size of a SEND message along with emperical observations on the maximum future benefit of simultaneous page registrations. -The 'type' field has 10 different command values: - 1. Unused - 2. Error (sent to the source during bad things) - 3. Ready (control-channel is available) - 4. QEMU File (for sending non-live device state) - 5. RAM Blocks request (used right after connection setup) - 6. RAM Blocks result (used right after connection setup) - 7. Compress page (zap zero page and skip registration) - 8. Register request (dynamic chunk registration) - 9. Register result ('rkey' to be used by sender) - 10. Register finished (registration for current iteration finished) +The 'type' field has 12 different command values: + 1. Unused + 2. Error (sent to the source during bad things) + 3. Ready (control-channel is available) + 4. QEMU File (for sending non-live device state) + 5. RAM Blocks request (used right after connection setup) + 6. RAM Blocks result (used right after connection setup) + 7. Compress page (zap zero page and skip registration) + 8. Register request (dynamic chunk registration) + 9. Register result ('rkey' to be used by sender) + 10. Register finished (registration for current iteration finished) + 11. Unregister request (unpin previously registered memory) + 12. Unregister finished (confirmation that unpin completed) A single control message, as hinted above, can contain within the data portion an array of many commands of the same type. If there is more than @@ -243,7 +245,7 @@ qemu_rdma_exchange_send(header, data, optional response header & data): from the receiver to tell us that the receiver is *ready* for us to transmit some new bytes. 2. Optionally: if we are expecting a response from the command - (that we have no yet transmitted), let's post an RQ + (that we have not yet transmitted), let's post an RQ work request to receive that data a few moments later. 3. When the READY arrives, librdmacm will unblock us and we immediately post a RQ work request @@ -293,8 +295,10 @@ librdmacm provides the user with a 'private data' area to be exchanged at connection-setup time before any infiniband traffic is generated. Header: - * Version (protocol version validated before send/recv occurs), uint32, network byte order - * Flags (bitwise OR of each capability), uint32, network byte order + * Version (protocol version validated before send/recv occurs), + uint32, network byte order + * Flags (bitwise OR of each capability), + uint32, network byte order There is no data portion of this header right now, so there is no length field. The maximum size of the 'private data' section @@ -313,7 +317,7 @@ If the version is invalid, we throw an error. If the version is new, we only negotiate the capabilities that the requested version is able to perform and ignore the rest. -Currently there is only *one* capability in Version #1: dynamic page registration +Currently there is only one capability in Version #1: dynamic page registration Finally: Negotiation happens with the Flags field: If the primary-VM sets a flag, but the destination does not support this capability, it @@ -326,8 +330,8 @@ QEMUFileRDMA Interface: QEMUFileRDMA introduces a couple of new functions: -1. qemu_rdma_get_buffer() (QEMUFileOps rdma_read_ops) -2. qemu_rdma_put_buffer() (QEMUFileOps rdma_write_ops) +1. qemu_rdma_get_buffer() (QEMUFileOps rdma_read_ops) +2. qemu_rdma_put_buffer() (QEMUFileOps rdma_write_ops) These two functions are very short and simply use the protocol describe above to deliver bytes without changing the upper-level @@ -413,3 +417,8 @@ TODO: the use of KSM and ballooning while using RDMA. 4. Also, some form of balloon-device usage tracking would also help alleviate some issues. +5. Move UNREGISTER requests to a separate thread. +6. Use LRU to provide more fine-grained direction of UNREGISTER + requests for unpinning memory in an overcommitted environment. +7. Expose UNREGISTER support to the user by way of workload-specific + hints about application behavior.