RDMA/core: Provide RDMA DIM support for ULPs
Added the interface in the infiniband driver that applies the rdma_dim adaptive moderation. There is now a special function for allocating an ib_cq that uses rdma_dim. Performance improvement (ConnectX-5 100GbE, x86) running FIO benchmark over NVMf between two equal end-hosts with 56 cores across a Mellanox switch using null_blk device: READS without DIM: blk size | BW | IOPS | 99th percentile latency | 99.99th latency 512B | 3.8GiB/s | 7.7M | 1401 usec | 2442 usec 4k | 7.0GiB/s | 1.8M | 4817 usec | 6587 usec 64k | 10.7GiB/s| 175k | 9896 usec | 10028 usec IO WRITES without DIM: blk size | BW | IOPS | 99th percentile latency | 99.99th latency 512B | 3.6GiB/s | 7.5M | 1434 usec | 2474 usec 4k | 6.3GiB/s | 1.6M | 938 usec | 1221 usec 64k | 10.7GiB/s| 175k | 8979 usec | 12780 usec IO READS with DIM: blk size | BW | IOPS | 99th percentile latency | 99.99th latency 512B | 4GiB/s | 8.2M | 816 usec | 889 usec 4k | 10.1GiB/s| 2.65M| 3359 usec | 5080 usec 64k | 10.7GiB/s| 175k | 9896 usec | 10028 usec IO WRITES with DIM: blk size | BW | IOPS | 99th percentile latency | 99.99th latency 512B | 3.9GiB/s | 8.1M | 799 usec | 922 usec 4k | 9.6GiB/s | 2.5M | 717 usec | 1004 usec 64k | 10.7GiB/s| 176k | 8586 usec | 12256 usec The rdma_dim algorithm was designed to measure the effectiveness of moderation on the flow in a general way and thus should be appropriate for all RDMA storage protocols. rdma_dim is configured to be the default option based on performance improvement seen after extensive tests. Signed-off-by: Yamin Friedman <yaminf@mellanox.com> Reviewed-by: Max Gurtovoy <maxg@mellanox.com> Reviewed-by: Sagi Grimberg <sagi@grimberg.me> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
This commit is contained in:

committed by
Jason Gunthorpe

parent
f4915455dc
commit
da6629793a
@@ -61,6 +61,7 @@
|
||||
#include <linux/cgroup_rdma.h>
|
||||
#include <linux/irqflags.h>
|
||||
#include <linux/preempt.h>
|
||||
#include <linux/dim.h>
|
||||
#include <uapi/rdma/ib_user_verbs.h>
|
||||
#include <rdma/rdma_counter.h>
|
||||
#include <rdma/restrack.h>
|
||||
@@ -1509,6 +1510,7 @@ struct ib_cq {
|
||||
struct work_struct work;
|
||||
};
|
||||
struct workqueue_struct *comp_wq;
|
||||
struct dim *dim;
|
||||
/*
|
||||
* Implementation details of the RDMA core, don't use in drivers:
|
||||
*/
|
||||
@@ -2576,6 +2578,8 @@ struct ib_device {
|
||||
u16 is_switch:1;
|
||||
/* Indicates kernel verbs support, should not be used in drivers */
|
||||
u16 kverbs_provider:1;
|
||||
/* CQ adaptive moderation (RDMA DIM) */
|
||||
u16 use_cq_dim:1;
|
||||
u8 node_type;
|
||||
u8 phys_port_cnt;
|
||||
struct ib_device_attr attrs;
|
||||
|
Reference in New Issue
Block a user