nvmet: use xarray for ctrl ns storing

This patch replaces the ctrl->namespaces tracking from linked list to
xarray and improves the performance when accessing one namespce :-

XArray vs Default:-

IOPS and BW (more the better) increase BW (~1.8%):-
---------------------------------------------------

 XArray :-
  read:  IOPS=160k,  BW=626MiB/s  (656MB/s)(18.3GiB/30001msec)
  read:  IOPS=160k,  BW=626MiB/s  (656MB/s)(18.3GiB/30001msec)
  read:  IOPS=162k,  BW=631MiB/s  (662MB/s)(18.5GiB/30001msec)

 Default:-
  read:  IOPS=156k,  BW=609MiB/s  (639MB/s)(17.8GiB/30001msec)
  read:  IOPS=157k,  BW=613MiB/s  (643MB/s)(17.0GiB/30001msec)
  read:  IOPS=160k,  BW=626MiB/s  (656MB/s)(18.3GiB/30001msec)

Submission latency (less the better) decrease (~8.3%):-
-------------------------------------------------------

 XArray:-
  slat  (usec):  min=7,  max=8386,  avg=11.19,  stdev=5.96
  slat  (usec):  min=7,  max=441,   avg=11.09,  stdev=4.48
  slat  (usec):  min=7,  max=1088,  avg=11.21,  stdev=4.54

 Default :-
  slat  (usec):  min=8,   max=2826.5k,  avg=23.96,  stdev=3911.50
  slat  (usec):  min=8,   max=503,      avg=12.52,  stdev=5.07
  slat  (usec):  min=8,   max=2384,     avg=12.50,  stdev=5.28

CPU Usage (less the better) decrease (~5.2%):-
----------------------------------------------

 XArray:-
  cpu  :  usr=1.84%,  sys=18.61%,  ctx=949471,  majf=0,  minf=250
  cpu  :  usr=1.83%,  sys=18.41%,  ctx=950262,  majf=0,  minf=237
  cpu  :  usr=1.82%,  sys=18.82%,  ctx=957224,  majf=0,  minf=234

 Default:-
  cpu  :  usr=1.70%,  sys=19.21%,  ctx=858196,  majf=0,  minf=251
  cpu  :  usr=1.82%,  sys=19.98%,  ctx=929720,  majf=0,  minf=227
  cpu  :  usr=1.83%,  sys=20.33%,  ctx=947208,  majf=0,  minf=235.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>

1 files changed, 6 insertions, 11 deletions

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 95bb3bc4e335..55918fcef80b 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -113,11 +113,10 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
 	u64 data_units_read = 0, data_units_written = 0;
 	struct nvmet_ns *ns;
 	struct nvmet_ctrl *ctrl;
+	unsigned long idx;
 
 	ctrl = req->sq->ctrl;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) {
+	xa_for_each(&ctrl->subsys->namespaces, idx, ns) {
 		/* we don't have the right data for file backed ns */
 		if (!ns->bdev)
 			continue;
@@ -127,9 +126,7 @@ static u16 nvmet_get_smart_log_all(struct nvmet_req *req,
 		host_writes += part_stat_read(ns->bdev->bd_part, ios[WRITE]);
 		data_units_written += DIV_ROUND_UP(
 			part_stat_read(ns->bdev->bd_part, sectors[WRITE]), 1000);
-
 	}
-	rcu_read_unlock();
 
 	put_unaligned_le64(host_reads, &slog->host_reads[0]);
 	put_unaligned_le64(data_units_read, &slog->data_units_read[0]);
@@ -230,14 +227,13 @@ static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 	struct nvmet_ns *ns;
+	unsigned long idx;
 	u32 count = 0;
 
 	if (!(req->cmd->get_log_page.lsp & NVME_ANA_LOG_RGO)) {
-		rcu_read_lock();
-		list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link)
+		xa_for_each(&ctrl->subsys->namespaces, idx, ns)
 			if (ns->anagrpid == grpid)
 				desc->nsids[count++] = cpu_to_le32(ns->nsid);
-		rcu_read_unlock();
 	}
 
 	desc->grpid = cpu_to_le32(grpid);
@@ -556,6 +552,7 @@ static void nvmet_execute_identify_nslist(struct nvmet_req *req)
 	static const int buf_size = NVME_IDENTIFY_DATA_SIZE;
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
 	struct nvmet_ns *ns;
+	unsigned long idx;
 	u32 min_nsid = le32_to_cpu(req->cmd->identify.nsid);
 	__le32 *list;
 	u16 status = 0;
@@ -567,15 +564,13 @@ static void nvmet_execute_identify_nslist(struct nvmet_req *req)
 		goto out;
 	}
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link) {
+	xa_for_each(&ctrl->subsys->namespaces, idx, ns) {
 		if (ns->nsid <= min_nsid)
 			continue;
 		list[i++] = cpu_to_le32(ns->nsid);
 		if (i == buf_size / sizeof(__le32))
 			break;
 	}
-	rcu_read_unlock();
 
 	status = nvmet_copy_to_sgl(req, 0, list, buf_size);