diff options
| author | Yamin Friedman <yaminf@mellanox.com> | 2019-10-07 16:59:32 +0300 |
|---|---|---|
| committer | Jason Gunthorpe <jgg@mellanox.com> | 2019-10-22 20:26:52 +0300 |
| commit | 00bd1439f464cfac3c60f6eabfe209b8a52e8194 (patch) | |
| tree | 8fd186b86ac484edee64b6f9d541e3d85a1a9a26 /include/rdma | |
| parent | 7d47433cf74f942a414171867d89c08640cfef45 (diff) | |
| download | linux-00bd1439f464cfac3c60f6eabfe209b8a52e8194.tar.xz | |
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>
Diffstat (limited to 'include/rdma')
| -rw-r--r-- | include/rdma/ib_verbs.h | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 6a47ba85c54c..a465fcae992b 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -445,6 +445,8 @@ struct ib_device_attr { struct ib_tm_caps tm_caps; struct ib_cq_caps cq_caps; u64 max_dm_size; + /* Max entries for sgl for optimized performance per READ */ + u32 max_sgl_rd; }; enum ib_mtu { |