From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Steve Wise" Subject: RE: [PATCH V6 9/9] isert: Support iWARP transports using FRMRs Date: Fri, 24 Jul 2015 14:57:45 -0500 Message-ID: <00db01d0c64b$01f40300$05dc0900$@opengridcomputing.com> References: <20150724161331.25617.8475.stgit@build2.ogc.int> <20150724161904.25617.85015.stgit@build2.ogc.int> <20150724165721.GC25480@obsidianresearch.com> <00ce01d0c641$493ea300$dbbbe900$@opengridcomputing.com> <20150724192411.GC26225@obsidianresearch.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20150724192411.GC26225@obsidianresearch.com> Content-Language: en-us Sender: target-devel-owner@vger.kernel.org To: 'Jason Gunthorpe' Cc: dledford@redhat.com, infinipath@intel.com, sagig@mellanox.com, ogerlitz@mellanox.com, roid@mellanox.com, linux-rdma@vger.kernel.org, eli@mellanox.com, target-devel@vger.kernel.org, linux-nfs@vger.kernel.org, bfields@fieldses.org List-Id: linux-rdma@vger.kernel.org > -----Original Message----- > From: Jason Gunthorpe [mailto:jgunthorpe@obsidianresearch.com] > Sent: Friday, July 24, 2015 2:24 PM > To: Steve Wise > Cc: dledford@redhat.com; infinipath@intel.com; sagig@mellanox.com; ogerlitz@mellanox.com; roid@mellanox.com; linux- > rdma@vger.kernel.org; eli@mellanox.com; target-devel@vger.kernel.org; linux-nfs@vger.kernel.org; bfields@fieldses.org > Subject: Re: [PATCH V6 9/9] isert: Support iWARP transports using FRMRs > > On Fri, Jul 24, 2015 at 01:48:09PM -0500, Steve Wise wrote: > > > The use of FRWR for RDMA READ should be iWarp specific, IB shouldn't > > > pay that overhead. I am expecting to see a cap_rdma_read_rkey or > > > something in here ? > > > > Ok. But cap_rdma_read_rkey() doesn't really describe the > > requirement. The requirement is rkey + REMOTE_WRITE. So it is more > > like rdma_cap_read_requires_remote_write() which is ugly and too > > long (but descriptive)... > > I don't care much what name you pick, just jam something like this in > the description > > If set then RDMA_READ must be performed by mapping the local > buffers through a rkey MR with ACCESS_REMOTE_WRITE enabled. > The rkey of this MR should be passed in as the sg_lists's lkey for > IB_WR_RDMA_READ_WITH_INV. > > FRWR should be used to register the buffer in the send queue, > and the read should be issued using IB_WR_RDMA_READ_WITH_INV (xx > can we just implicitly rely on this? Are there any iWarp cards that > support FRWR but not WITH_INV?) > No. And iWARP devices must support READ_WITH_INV from my reading of the iWARP verbs spec. I will add all these comments and make use of READ_WITH_INV. > Finally, only a single SGE can be used with RDMA_READ, all scattering > must be accomplished with the MR. > > This quite dramatically changes what is an allowed scatter for the > transfer, IB can support arbitary unaligned S/G lists, while this is > now forced into gapless page aligned elements. > > Your patch takes care of this? And only impacts IB? Did you mean "only impacts iWARP?" Yes the patch takes care of sg->fr page list packing. And it uses the existing isert_map_fr_pagelist() to pack the sg into the fastreg page list. This same routine is used by the IB FRMR/PI reg/unreg routines as well. None of this impacts isert over IB, assuming the suggested change above to only use the new reg/unreg functions for devices that need the iwarp style of read. IE IB devices will either use the existing FRMR/PI methods if they support FRMR/LOCAL_DMA_LKEY/PI (mlx5) or they will use the existing DMA_MR methods (all the rest of the IB devices). IW devices will get my new reg/unreg methods... Steve. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from smtp.opengridcomputing.com ([72.48.136.20]:51390 "EHLO smtp.opengridcomputing.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751824AbbGXT5i (ORCPT ); Fri, 24 Jul 2015 15:57:38 -0400 From: "Steve Wise" To: "'Jason Gunthorpe'" Cc: , , , , , , , , , References: <20150724161331.25617.8475.stgit@build2.ogc.int> <20150724161904.25617.85015.stgit@build2.ogc.int> <20150724165721.GC25480@obsidianresearch.com> <00ce01d0c641$493ea300$dbbbe900$@opengridcomputing.com> <20150724192411.GC26225@obsidianresearch.com> In-Reply-To: <20150724192411.GC26225@obsidianresearch.com> Subject: RE: [PATCH V6 9/9] isert: Support iWARP transports using FRMRs Date: Fri, 24 Jul 2015 14:57:45 -0500 Message-ID: <00db01d0c64b$01f40300$05dc0900$@opengridcomputing.com> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Sender: linux-nfs-owner@vger.kernel.org List-ID: > -----Original Message----- > From: Jason Gunthorpe [mailto:jgunthorpe@obsidianresearch.com] > Sent: Friday, July 24, 2015 2:24 PM > To: Steve Wise > Cc: dledford@redhat.com; infinipath@intel.com; sagig@mellanox.com; ogerlitz@mellanox.com; roid@mellanox.com; linux- > rdma@vger.kernel.org; eli@mellanox.com; target-devel@vger.kernel.org; linux-nfs@vger.kernel.org; bfields@fieldses.org > Subject: Re: [PATCH V6 9/9] isert: Support iWARP transports using FRMRs > > On Fri, Jul 24, 2015 at 01:48:09PM -0500, Steve Wise wrote: > > > The use of FRWR for RDMA READ should be iWarp specific, IB shouldn't > > > pay that overhead. I am expecting to see a cap_rdma_read_rkey or > > > something in here ? > > > > Ok. But cap_rdma_read_rkey() doesn't really describe the > > requirement. The requirement is rkey + REMOTE_WRITE. So it is more > > like rdma_cap_read_requires_remote_write() which is ugly and too > > long (but descriptive)... > > I don't care much what name you pick, just jam something like this in > the description > > If set then RDMA_READ must be performed by mapping the local > buffers through a rkey MR with ACCESS_REMOTE_WRITE enabled. > The rkey of this MR should be passed in as the sg_lists's lkey for > IB_WR_RDMA_READ_WITH_INV. > > FRWR should be used to register the buffer in the send queue, > and the read should be issued using IB_WR_RDMA_READ_WITH_INV (xx > can we just implicitly rely on this? Are there any iWarp cards that > support FRWR but not WITH_INV?) > No. And iWARP devices must support READ_WITH_INV from my reading of the iWARP verbs spec. I will add all these comments and make use of READ_WITH_INV. > Finally, only a single SGE can be used with RDMA_READ, all scattering > must be accomplished with the MR. > > This quite dramatically changes what is an allowed scatter for the > transfer, IB can support arbitary unaligned S/G lists, while this is > now forced into gapless page aligned elements. > > Your patch takes care of this? And only impacts IB? Did you mean "only impacts iWARP?" Yes the patch takes care of sg->fr page list packing. And it uses the existing isert_map_fr_pagelist() to pack the sg into the fastreg page list. This same routine is used by the IB FRMR/PI reg/unreg routines as well. None of this impacts isert over IB, assuming the suggested change above to only use the new reg/unreg functions for devices that need the iwarp style of read. IE IB devices will either use the existing FRMR/PI methods if they support FRMR/LOCAL_DMA_LKEY/PI (mlx5) or they will use the existing DMA_MR methods (all the rest of the IB devices). IW devices will get my new reg/unreg methods... Steve.