RDS: IB: split mr pool to improve 8K messages performance

8K message sizes are pretty important usecase for RDS current
workloads so we make provison to have 8K mrs available from the pool.
Based on number of SG's in the RDS message, we pick a pool to use.

Also to make sure that we don't under utlise mrs when say 8k messages
are dominating which could lead to 8k pull being exhausted, we fall-back
to 1m pool till 8k pool recovers for use.

This helps to at least push ~55 kB/s bidirectional data which
is a nice improvement.

Signed-off-by: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>

1 files changed, 33 insertions, 14 deletions

diff --git a/net/rds/ib.c b/net/rds/ib.c
index 883813a6cf44..a833ab7898fe 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -43,14 +43,14 @@
 #include "rds.h"
 #include "ib.h"
 
-static unsigned int fmr_pool_size = RDS_FMR_POOL_SIZE;
-unsigned int fmr_message_size = RDS_FMR_SIZE + 1; /* +1 allows for unaligned MRs */
+unsigned int rds_ib_fmr_1m_pool_size = RDS_FMR_1M_POOL_SIZE;
+unsigned int rds_ib_fmr_8k_pool_size = RDS_FMR_8K_POOL_SIZE;
 unsigned int rds_ib_retry_count = RDS_IB_DEFAULT_RETRY_COUNT;
 
-module_param(fmr_pool_size, int, 0444);
-MODULE_PARM_DESC(fmr_pool_size, " Max number of fmr per HCA");
-module_param(fmr_message_size, int, 0444);
-MODULE_PARM_DESC(fmr_message_size, " Max size of a RDMA transfer");
+module_param(rds_ib_fmr_1m_pool_size, int, 0444);
+MODULE_PARM_DESC(rds_ib_fmr_1m_pool_size, " Max number of 1M fmr per HCA");
+module_param(rds_ib_fmr_8k_pool_size, int, 0444);
+MODULE_PARM_DESC(rds_ib_fmr_8k_pool_size, " Max number of 8K fmr per HCA");
 module_param(rds_ib_retry_count, int, 0444);
 MODULE_PARM_DESC(rds_ib_retry_count, " Number of hw retries before reporting an error");
 
@@ -97,8 +97,10 @@ static void rds_ib_dev_free(struct work_struct *work)
 	struct rds_ib_device *rds_ibdev = container_of(work,
 					struct rds_ib_device, free_work);
 
-	if (rds_ibdev->mr_pool)
-		rds_ib_destroy_mr_pool(rds_ibdev->mr_pool);
+	if (rds_ibdev->mr_8k_pool)
+		rds_ib_destroy_mr_pool(rds_ibdev->mr_8k_pool);
+	if (rds_ibdev->mr_1m_pool)
+		rds_ib_destroy_mr_pool(rds_ibdev->mr_1m_pool);
 	if (rds_ibdev->pd)
 		ib_dealloc_pd(rds_ibdev->pd);
 
@@ -148,9 +150,13 @@ static void rds_ib_add_one(struct ib_device *device)
 	rds_ibdev->max_sge = min(dev_attr->max_sge, RDS_IB_MAX_SGE);
 
 	rds_ibdev->fmr_max_remaps = dev_attr->max_map_per_fmr?: 32;
-	rds_ibdev->max_fmrs = dev_attr->max_mr ?
-			min_t(unsigned int, dev_attr->max_mr, fmr_pool_size) :
-			fmr_pool_size;
+	rds_ibdev->max_1m_fmrs = dev_attr->max_mr ?
+		min_t(unsigned int, (dev_attr->max_mr / 2),
+		      rds_ib_fmr_1m_pool_size) : rds_ib_fmr_1m_pool_size;
+
+	rds_ibdev->max_8k_fmrs = dev_attr->max_mr ?
+		min_t(unsigned int, ((dev_attr->max_mr / 2) * RDS_MR_8K_SCALE),
+		      rds_ib_fmr_8k_pool_size) : rds_ib_fmr_8k_pool_size;
 
 	rds_ibdev->max_initiator_depth = dev_attr->max_qp_init_rd_atom;
 	rds_ibdev->max_responder_resources = dev_attr->max_qp_rd_atom;
@@ -162,12 +168,25 @@ static void rds_ib_add_one(struct ib_device *device)
 		goto put_dev;
 	}
 
-	rds_ibdev->mr_pool = rds_ib_create_mr_pool(rds_ibdev);
-	if (IS_ERR(rds_ibdev->mr_pool)) {
-		rds_ibdev->mr_pool = NULL;
+	rds_ibdev->mr_1m_pool =
+		rds_ib_create_mr_pool(rds_ibdev, RDS_IB_MR_1M_POOL);
+	if (IS_ERR(rds_ibdev->mr_1m_pool)) {
+		rds_ibdev->mr_1m_pool = NULL;
 		goto put_dev;
 	}
 
+	rds_ibdev->mr_8k_pool =
+		rds_ib_create_mr_pool(rds_ibdev, RDS_IB_MR_8K_POOL);
+	if (IS_ERR(rds_ibdev->mr_8k_pool)) {
+		rds_ibdev->mr_8k_pool = NULL;
+		goto put_dev;
+	}
+
+	rdsdebug("RDS/IB: max_mr = %d, max_wrs = %d, max_sge = %d, fmr_max_remaps = %d, max_1m_fmrs = %d, max_8k_fmrs = %d\n",
+		 dev_attr->max_fmr, rds_ibdev->max_wrs, rds_ibdev->max_sge,
+		 rds_ibdev->fmr_max_remaps, rds_ibdev->max_1m_fmrs,
+		 rds_ibdev->max_8k_fmrs);
+
 	INIT_LIST_HEAD(&rds_ibdev->ipaddr_list);
 	INIT_LIST_HEAD(&rds_ibdev->conn_list);