From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Gunthorpe Subject: Re: [pull request][for-next 0/9] Generic DIM lib for netdev and RDMA Date: Fri, 7 Jun 2019 15:57:49 -0300 Message-ID: <20190607185749.GQ14802@ziepe.ca> References: <20190605232348.6452-1-saeedm@mellanox.com> <20190606071427.GU5261@mtr-leonro.mtl.com> <898e0df0-b73c-c6d7-9cbe-084163643236@mellanox.com> <20190606130713.GC17392@mellanox.com> <9faeadac971aaf481b1066b1dde0fc9e77e893a5.camel@mellanox.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <9faeadac971aaf481b1066b1dde0fc9e77e893a5.camel@mellanox.com> Sender: netdev-owner@vger.kernel.org To: Saeed Mahameed Cc: Max Gurtovoy , "linux-rdma@vger.kernel.org" , "davem@davemloft.net" , "andy@greyhouse.net" , Tal Gilboa , "michael.chan@broadcom.com" , "netdev@vger.kernel.org" , "leon@kernel.org" , "dledford@redhat.com" List-Id: linux-rdma@vger.kernel.org On Fri, Jun 07, 2019 at 06:14:11PM +0000, Saeed Mahameed wrote: > On Thu, 2019-06-06 at 13:07 +0000, Jason Gunthorpe wrote: > > On Thu, Jun 06, 2019 at 10:19:41AM +0300, Max Gurtovoy wrote: > > > > > Solution: > > > > > - Common logic is declared in include/linux/dim.h and > > > > > implemented in > > > > > lib/dim/dim.c > > > > > - Net DIM (existing) logic is declared in > > > > > include/linux/net_dim.h and > > > > > implemented in lib/dim/net_dim.c, which uses the common > > > > > logic from dim.h > > > > > - Any new DIM logic will be declared in > > > > > "/include/linux/new_dim.h" and > > > > > implemented in "lib/dim/new_dim.c". > > > > > - This new implementation will expose modified versions of > > > > > profiles, > > > > > dim_step() and dim_decision(). > > > > > > > > > > Pros for this solution are: > > > > > - Zero impact on existing net_dim implementation and usage > > > > > - Relatively more code reuse (compared to two separate > > > > > solutions) > > > > > - Increased extensibility > > > > > > > > > > Tal Gilboa (6): > > > > > linux/dim: Move logic to dim.h > > > > > linux/dim: Remove "net" prefix from internal DIM members > > > > > linux/dim: Rename externally exposed macros > > > > > linux/dim: Rename net_dim_sample() to > > > > > net_dim_update_sample() > > > > > linux/dim: Rename externally used net_dim members > > > > > linux/dim: Move implementation to .c files > > > > > > > > > > Yamin Friedman (3): > > > > > linux/dim: Add completions count to dim_sample > > > > > linux/dim: Implement rdma_dim > > > > > RDMA/core: Provide RDMA DIM support for ULPs > > > > Saeed, > > > > > > > > No, for the RDMA patches. > > > > We need to see usage of those APIs before merging. > > > > > > I've asked Yamin to prepare patches for NVMeoF initiator and target > > > for > > > review, so I guess he has it on his plate (this is how he tested > > > it..). > > > > > > It might cause conflict with NVMe/blk branch maintained by Sagi, > > > Christoph > > > and Jens. > > > > It looks like nvme could pull this series + the RDMA patches into the > > nvme tree via PR? I'm not familiar with how that tree works. > > > > But we need to get the patches posted right away.. > > > > What do you suggest here ? > I think the netdev community also deserve to see the rdma patches, at > least with an external link, I can drop the last patch (or two ) ? but > i need an external rdma link for people who are going to review this > series. Yes, all the patches need to be posted. We should have a 'double branch' where you send the linux/dim & net stuff to net and then we add the RDMA stuff on top and send to nvme & rdma with the ULP patches Assuming nvme takes pull requests. But the whole thing should be posted as a single series on the list to get acks before the PRs are generated. Similar to how we've run the mlx5 shared branch Jason