----- Original Message ----- > From: "Bart Van Assche" <Bart.VanAssche@xxxxxxxxxxx> > To: loberman@xxxxxxxxxx > Cc: linux-rdma@xxxxxxxxxxxxxxx, dledford@xxxxxxxxxx > Sent: Friday, January 20, 2017 5:18:59 PM > Subject: Re: [PATCH v3 00/37] IB: Optimize DMA mapping > > On Fri, 2017-01-20 at 16:57 -0500, Laurence Oberman wrote: > > Hello Bart, if this the match to what you shared with me earlier I have > > tested the IB/SRP part of this series. > > > > This is the IB/RDMA/SRP stack, testing both ib_srp and ib_srpt. > > > > 1. Tested direct and buffered read I/O with 4MB I/O and smaller I/O sizes > > direct to mpath devices > > 2. Tested read and write I/O with 4MB and smaller I/O to XFS file systems. > > 3. Removed a SRP paths one by one and let then reconnect with no issues > > > > All my tests were SRP using connectX-4 (mlx5) at EDR (100G) > > > > For: Optimize DMA mapping tree, branch for next from latest copy on: > > https://github.com/bvanassche/linux > > Tested-by: Laurence Oberman <loberman@xxxxxxxxxx> > > Hello Laurence, > > The code I posted is identical to the code I asked you to test. Thanks for > the help with testing! > > I tested the following ULP and HBA drivers myself with this patch series: > ib_srp, ib_srpt, ib_mlx4 and rxe. > > Bart. OK, good, I guess I should add mlx5_ib to my list as its implied. Thanks !! so much for all this work you do in this space. Regards Laurence -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
