Add a latency-based I/O policy for multipathing. It uses the blk-nodelat
latency tracker to provide latencies for each node, and schedules
I/O on the path with the least latency for the submitting node.
Signed-off-by: Hannes Reinecke <hare@xxxxxxxxxx>
---
drivers/nvme/host/multipath.c | 57 ++++++++++++++++++++++++++++++-----
drivers/nvme/host/nvme.h | 1 +
2 files changed, 51 insertions(+), 7 deletions(-)
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 5397fb428b24..18e7fe45c2c1 100644
--- a/drivers/nvme/host/multipath.c
+++ b/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_LAT] = "latency",
};
static int iopolicy = NVME_IOPOLICY_NUMA;
@@ -29,6 +30,10 @@ 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;
+#ifdef CONFIG_BLK_NODE_LATENCY
+ else if (!strncmp(val, "latency", 7))
+ iopolicy = NVME_IOPOLICY_LAT;
+#endif
else
return -EINVAL;
@@ -40,6 +45,28 @@ static int nvme_get_iopolicy(char *buf, const struct kernel_param *kp)
return sprintf(buf, "%s\n", nvme_iopolicy_names[iopolicy]);
}
+static int nvme_activate_iopolicy(struct nvme_subsystem *subsys, int iopolicy)
+{
+ struct nvme_ns_head *h;
+ struct nvme_ns *ns;
+ bool enable = iopolicy == NVME_IOPOLICY_LAT;
+ int ret = 0;
+
+ mutex_lock(&subsys->lock);
+ list_for_each_entry(h, &subsys->nsheads, entry) {
+ list_for_each_entry_rcu(ns, &h->list, siblings) {
+ if (enable) {
+ ret = blk_nlat_enable(ns->disk);
+ if (ret)
+ break;
+ } else
+ blk_nlat_disable(ns->disk);
+ }
+ }
+ mutex_unlock(&subsys->lock);
+ return ret;
+}
+
module_param_call(iopolicy, nvme_set_iopolicy, nvme_get_iopolicy,
&iopolicy, 0644);
MODULE_PARM_DESC(iopolicy,
@@ -242,13 +269,16 @@ static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head, int node)
{
int found_distance = INT_MAX, fallback_distance = INT_MAX, distance;
struct nvme_ns *found = NULL, *fallback = NULL, *ns;
+ int iopolicy = READ_ONCE(head->subsys->iopolicy);
list_for_each_entry_rcu(ns, &head->list, siblings) {
if (nvme_path_is_disabled(ns))
continue;
- if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_NUMA)
+ if (iopolicy == NVME_IOPOLICY_NUMA)
distance = node_distance(node, ns->ctrl->numa_node);
+ else if (iopolicy == NVME_IOPOLICY_LAT)
+ distance = blk_nlat_latency(ns->disk, node);
else
distance = LOCAL_DISTANCE;
@@ -339,15 +369,17 @@ static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
{
int node = numa_node_id();
+ int iopolicy = READ_ONCE(head->subsys->iopolicy);
struct nvme_ns *ns;
ns = srcu_dereference(head->current_path[node], &head->srcu);
if (unlikely(!ns))
return __nvme_find_path(head, node);
- if (READ_ONCE(head->subsys->iopolicy) == NVME_IOPOLICY_RR)
+ if (iopolicy == NVME_IOPOLICY_RR)
return nvme_round_robin_path(head, node, ns);
- if (unlikely(!nvme_path_is_optimized(ns)))
+ if (iopolicy == NVME_IOPOLICY_LAT ||
+ unlikely(!nvme_path_is_optimized(ns)))
return __nvme_find_path(head, node);
return ns;
}
@@ -803,15 +835,18 @@ static ssize_t nvme_subsys_iopolicy_store(struct device *dev,
{
struct nvme_subsystem *subsys =
container_of(dev, struct nvme_subsystem, dev);
- int i;
+ int i, ret;
for (i = 0; i < ARRAY_SIZE(nvme_iopolicy_names); i++) {
if (sysfs_streq(buf, nvme_iopolicy_names[i])) {
- WRITE_ONCE(subsys->iopolicy, i);
- return count;
+ ret = nvme_activate_iopolicy(subsys, i);
+ if (!ret) {
+ WRITE_ONCE(subsys->iopolicy, i);
+ return count;
+ }
+ return ret;
}
}
-
return -EINVAL;
}
SUBSYS_ATTR_RW(iopolicy, S_IRUGO | S_IWUSR,
@@ -847,6 +882,14 @@ static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl,
void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid)
{
+ if (!blk_nlat_init(ns->disk) &&
+ READ_ONCE(ns->head->subsys->iopolicy) == NVME_IOPOLICY_LAT) {
+ int ret = blk_nlat_enable(ns->disk);
+ if (unlikely(ret))
+ pr_warn("%s: Failed to enable latency tracking, error %d\n",
+ ns->disk->disk_name, ret);
+ }
+
if (nvme_ctrl_use_ana(ns->ctrl)) {
struct nvme_ana_group_desc desc = {
.grpid = anagrpid,
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 27397f8404d6..b07afb1aa5bb 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -402,6 +402,7 @@ static inline enum nvme_ctrl_state nvme_ctrl_state(struct nvme_ctrl *ctrl)
enum nvme_iopolicy {
NVME_IOPOLICY_NUMA,
NVME_IOPOLICY_RR,
+ NVME_IOPOLICY_LAT,
};
struct nvme_subsystem {
--
2.35.3
