Searched hist:"00 bd1439" (Results 1 – 2 of 2) sorted by relevance
/openbmc/linux/drivers/infiniband/core/ |
H A D | rw.c | 00bd1439 Mon Oct 07 08:59:32 CDT 2019 Yamin Friedman <yaminf@mellanox.com> RDMA/rw: Support threshold for registration vs scattering to local pages
If there are more scatter entries than the recommended limit provided by the ib device, UMR registration is used. This will provide optimal performance when performing large RDMA READs over devices that advertise the threshold capability.
With ConnectX-5 running NVMeoF RDMA with FIO single QP 128KB writes: Without use of cap: 70Gb/sec With use of cap: 84Gb/sec
Link: https://lore.kernel.org/r/20191007135933.12483-3-leon@kernel.org Signed-off-by: Yamin Friedman <yaminf@mellanox.com> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com> 00bd1439 Mon Oct 07 08:59:32 CDT 2019 Yamin Friedman <yaminf@mellanox.com> RDMA/rw: Support threshold for registration vs scattering to local pages If there are more scatter entries than the recommended limit provided by the ib device, UMR registration is used. This will provide optimal performance when performing large RDMA READs over devices that advertise the threshold capability. With ConnectX-5 running NVMeoF RDMA with FIO single QP 128KB writes: Without use of cap: 70Gb/sec With use of cap: 84Gb/sec Link: https://lore.kernel.org/r/20191007135933.12483-3-leon@kernel.org Signed-off-by: Yamin Friedman <yaminf@mellanox.com> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|
/openbmc/linux/include/rdma/ |
H A D | ib_verbs.h | 00bd1439 Mon Oct 07 08:59:32 CDT 2019 Yamin Friedman <yaminf@mellanox.com> RDMA/rw: Support threshold for registration vs scattering to local pages
If there are more scatter entries than the recommended limit provided by the ib device, UMR registration is used. This will provide optimal performance when performing large RDMA READs over devices that advertise the threshold capability.
With ConnectX-5 running NVMeoF RDMA with FIO single QP 128KB writes: Without use of cap: 70Gb/sec With use of cap: 84Gb/sec
Link: https://lore.kernel.org/r/20191007135933.12483-3-leon@kernel.org Signed-off-by: Yamin Friedman <yaminf@mellanox.com> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com> 00bd1439 Mon Oct 07 08:59:32 CDT 2019 Yamin Friedman <yaminf@mellanox.com> RDMA/rw: Support threshold for registration vs scattering to local pages If there are more scatter entries than the recommended limit provided by the ib device, UMR registration is used. This will provide optimal performance when performing large RDMA READs over devices that advertise the threshold capability. With ConnectX-5 running NVMeoF RDMA with FIO single QP 128KB writes: Without use of cap: 70Gb/sec With use of cap: 84Gb/sec Link: https://lore.kernel.org/r/20191007135933.12483-3-leon@kernel.org Signed-off-by: Yamin Friedman <yaminf@mellanox.com> Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Reviewed-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
|