nvme-multipath: implement "queue-depth" iopolicy

JIRA: https://issues.redhat.com/browse/RHEL-45230

Upstream Status: git://git.infradead.org/nvme.git branch "nvme-6.11"

The round-robin path selector is inefficient in cases where there is a
difference in latency between paths.  In the presence of one or more
high latency paths the round-robin selector continues to use the high
latency path equally. This results in a bias towards the highest latency
path and can cause a significant decrease in overall performance as IOs
pile on the highest latency path. This problem is acute with NVMe-oF
controllers.

The queue-depth path selector sends I/O down the path with the lowest
number of requests in its request queue. Paths with lower latency will
clear requests more quickly and have less requests queued compared to
higher latency paths. The goal of this path selector is to make more use
of lower latency paths which will bring down overall IO latency and
increase throughput and performance.

Signed-off-by: Thomas Song <tsong@purestorage.com>
[emilne: commandeered patch developed by Thomas Song @ Pure Storage]
Co-developed-by: Ewan D. Milne <emilne@redhat.com>
Signed-off-by: Ewan D. Milne <emilne@redhat.com>
Co-developed-by: John Meneghini <jmeneghi@redhat.com>
Signed-off-by: John Meneghini <jmeneghi@redhat.com>
Link: https://lore.kernel.org/linux-nvme/20240509202929.831680-1-jmeneghi@redhat.com/
Tested-by: Marco Patalano <mpatalan@redhat.com>
Tested-by: Jyoti Rani <jrani@purestorage.com>
Tested-by: John Meneghini <jmeneghi@redhat.com>
Reviewed-by: Randy Jennings <randyj@purestorage.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
(cherry picked from commit f227345)
Signed-off-by: John Meneghini <jmeneghi@redhat.com>

Author: johnmeneghini

drivers/nvme/host/core.c

@@ -110,7 +110,7 @@ struct workqueue_struct *nvme_delete_wq;
 EXPORT_SYMBOL_GPL(nvme_delete_wq);
 
 static LIST_HEAD(nvme_subsystems);
-static DEFINE_MUTEX(nvme_subsystems_lock);
+DEFINE_MUTEX(nvme_subsystems_lock);
 
 static DEFINE_IDA(nvme_instance_ida);
 static dev_t nvme_ctrl_base_chr_devt;

drivers/nvme/host/multipath.c

@@ -17,6 +17,7 @@ MODULE_PARM_DESC(multipath,
 static const char *nvme_iopolicy_names[] = {
 	[NVME_IOPOLICY_NUMA]	= "numa",
 	[NVME_IOPOLICY_RR]	= "round-robin",
+	[NVME_IOPOLICY_QD]      = "queue-depth",
 };
 
 static int iopolicy = NVME_IOPOLICY_NUMA;
@@ -29,6 +30,8 @@ static int nvme_set_iopolicy(const char *val, const struct kernel_param *kp)
 		iopolicy = NVME_IOPOLICY_NUMA;
 	else if (!strncmp(val, "round-robin", 11))
 		iopolicy = NVME_IOPOLICY_RR;
+	else if (!strncmp(val, "queue-depth", 11))
+		iopolicy = NVME_IOPOLICY_QD;
 	else
 		return -EINVAL;
 
@@ -43,7 +46,7 @@ static int nvme_get_iopolicy(char *buf, const struct kernel_param *kp)
 module_param_call(iopolicy, nvme_set_iopolicy, nvme_get_iopolicy,
 	&iopolicy, 0644);
 MODULE_PARM_DESC(iopolicy,
-	"Default multipath I/O policy; 'numa' (default) or 'round-robin'");
+	"Default multipath I/O policy; 'numa' (default), 'round-robin' or 'queue-depth'");
 
 void nvme_mpath_default_iopolicy(struct nvme_subsystem *subsys)
 {
@@ -133,6 +136,11 @@ void nvme_mpath_start_request(struct request *rq)
 	struct nvme_ns *ns = rq->q->queuedata;
 	struct gendisk *disk = ns->head->disk;
 
+	if (READ_ONCE(ns->head->subsys->iopolicy) == NVME_IOPOLICY_QD) {
+		atomic_inc(&ns->ctrl->nr_active);
+		nvme_req(rq)->flags |= NVME_MPATH_CNT_ACTIVE;
+	}
+
 	if (!blk_queue_io_stat(disk->queue) || blk_rq_is_passthrough(rq))
 		return;
 
@@ -146,6 +154,9 @@ void nvme_mpath_end_request(struct request *rq)
 {
 	struct nvme_ns *ns = rq->q->queuedata;
 
+	if (nvme_req(rq)->flags & NVME_MPATH_CNT_ACTIVE)
+		atomic_dec_if_positive(&ns->ctrl->nr_active);
+
 	if (!(nvme_req(rq)->flags & NVME_MPATH_IO_STATS))
 		return;
 	bdev_end_io_acct(ns->head->disk->part0, req_op(rq),
@@ -344,6 +355,42 @@ static struct nvme_ns *nvme_round_robin_path(struct nvme_ns_head *head)
 	return found;
 }
 
+static struct nvme_ns *nvme_queue_depth_path(struct nvme_ns_head *head)
+{
+	struct nvme_ns *best_opt = NULL, *best_nonopt = NULL, *ns;
+	unsigned int min_depth_opt = UINT_MAX, min_depth_nonopt = UINT_MAX;
+	unsigned int depth;
+
+	list_for_each_entry_rcu(ns, &head->list, siblings) {
+		if (nvme_path_is_disabled(ns))
+			continue;
+
+		depth = atomic_read(&ns->ctrl->nr_active);
+
+		switch (ns->ana_state) {
+		case NVME_ANA_OPTIMIZED:
+			if (depth < min_depth_opt) {
+				min_depth_opt = depth;
+				best_opt = ns;
+			}
+			break;
+		case NVME_ANA_NONOPTIMIZED:
+			if (depth < min_depth_nonopt) {
+				min_depth_nonopt = depth;
+				best_nonopt = ns;
+			}
+			break;
+		default:
+			break;
+		}
+
+		if (min_depth_opt == 0)
+			return best_opt;
+	}
+
+	return best_opt ? best_opt : best_nonopt;
+}
+
 static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
 {
 	return nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE &&
@@ -365,9 +412,14 @@ static struct nvme_ns *nvme_numa_path(struct nvme_ns_head *head)
 
 inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 {
-	if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR)
+	switch (READ_ONCE(head->subsys->iopolicy)) {
+	case NVME_IOPOLICY_QD:
+		return nvme_queue_depth_path(head);
+	case NVME_IOPOLICY_RR:
 		return nvme_round_robin_path(head);
-	return nvme_numa_path(head);
+	default:
+		return nvme_numa_path(head);
+	}
 }
 
 static bool nvme_available_path(struct nvme_ns_head *head)
@@ -816,6 +868,29 @@ static ssize_t nvme_subsys_iopolicy_show(struct device *dev,
 			  nvme_iopolicy_names[READ_ONCE(subsys->iopolicy)]);
 }
 
+static void nvme_subsys_iopolicy_update(struct nvme_subsystem *subsys,
+		int iopolicy)
+{
+	struct nvme_ctrl *ctrl;
+	int old_iopolicy = READ_ONCE(subsys->iopolicy);
+
+	if (old_iopolicy == iopolicy)
+		return;
+
+	WRITE_ONCE(subsys->iopolicy, iopolicy);
+
+	/* iopolicy changes clear the mpath by design */
+	mutex_lock(&nvme_subsystems_lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
+		nvme_mpath_clear_ctrl_paths(ctrl);
+	mutex_unlock(&nvme_subsystems_lock);
+
+	pr_notice("subsysnqn %s iopolicy changed from %s to %s\n",
+			subsys->subnqn,
+			nvme_iopolicy_names[old_iopolicy],
+			nvme_iopolicy_names[iopolicy]);
+}
+
 static ssize_t nvme_subsys_iopolicy_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
@@ -825,7 +900,7 @@ static ssize_t nvme_subsys_iopolicy_store(struct device *dev,
 
 	for (i = 0; i < ARRAY_SIZE(nvme_iopolicy_names); i++) {
 		if (sysfs_streq(buf, nvme_iopolicy_names[i])) {
-			WRITE_ONCE(subsys->iopolicy, i);
+			nvme_subsys_iopolicy_update(subsys, i);
 			return count;
 		}
 	}
@@ -935,6 +1010,9 @@ int nvme_mpath_init_identify(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
 	if (!ctrl->subsys || !(ctrl->subsys->cmic & NVME_CTRL_CMIC_ANA))
 		return 0;
 
+	/* initialize this in the identify path to cover controller resets */
+	atomic_set(&ctrl->nr_active, 0);
+
 	if (!ctrl->max_namespaces ||
 	    ctrl->max_namespaces > le32_to_cpu(id->nn)) {
 		dev_err(ctrl->device,

drivers/nvme/host/nvme.h

@@ -49,6 +49,7 @@ extern unsigned int admin_timeout;
 extern struct workqueue_struct *nvme_wq;
 extern struct workqueue_struct *nvme_reset_wq;
 extern struct workqueue_struct *nvme_delete_wq;
+extern struct mutex nvme_subsystems_lock;
 
 /*
  * List of workarounds for devices that required behavior not specified in
@@ -190,6 +191,7 @@ enum {
 	NVME_REQ_CANCELLED		= (1 << 0),
 	NVME_REQ_USERCMD		= (1 << 1),
 	NVME_MPATH_IO_STATS		= (1 << 2),
+	NVME_MPATH_CNT_ACTIVE		= (1 << 3),
 };
 
 static inline struct nvme_request *nvme_req(struct request *req)
@@ -356,6 +358,7 @@ struct nvme_ctrl {
 	size_t ana_log_size;
 	struct timer_list anatt_timer;
 	struct work_struct ana_work;
+	atomic_t nr_active;
 #endif
 
 #ifdef CONFIG_NVME_HOST_AUTH
@@ -404,6 +407,7 @@ static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
 enum nvme_iopolicy {
 	NVME_IOPOLICY_NUMA,
 	NVME_IOPOLICY_RR,
+	NVME_IOPOLICY_QD,
 };
 
 struct nvme_subsystem {