[PATCH v8 07/10] nvme-multipath: add debugfs attribute latency_ewma_shift

[Nilay Shroff]

By default, the EWMA (Exponentially Weighted Moving Average) shift
value, used for storing latency samples for latency iopolicy, is set
to 3. The EWMA is calculated using the following formula:

ewma = (old * ((1 << ewma_shift) - 1) + new) >> ewma_shift;

The default value of 3 assigns ~87.5% weight to the existing EWMA value
and ~12.5% weight to the new latency sample. This provides a stable
average that smooths out short-term variations.

However, different workloads may require faster or slower adaptation to
changing conditions. This commit introduces a new debugfs attribute,
latency_ewma_shift, allowing users to tune the weighting factor.

For example:
   - latency_ewma_shift = 2 => 75% old, 25% new
   - latency_ewma_shift = 1 => 50% old, 50% new
   - latency_ewma_shift = 0 => 0% old, 100% new

Reviewed-by: Guixin Liu <kanie at linux.alibaba.com>
Reviewed-by: Hannes Reinecke <hare at suse.de>
Signed-off-by: Nilay Shroff <nilay at linux.ibm.com>
---
 drivers/nvme/host/debugfs.c   | 46 +++++++++++++++++++++++++++++++++++
 drivers/nvme/host/multipath.c |  9 ++++---
 drivers/nvme/host/nvme.h      |  1 +
 3 files changed, 52 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/host/debugfs.c b/drivers/nvme/host/debugfs.c
index 04f8250fe607..ca1a670bea78 100644
--- a/drivers/nvme/host/debugfs.c
+++ b/drivers/nvme/host/debugfs.c
@@ -108,8 +108,54 @@ static const struct file_operations nvme_debugfs_fops = {
 	.release = nvme_debugfs_release,
 };
 
+#ifdef CONFIG_NVME_MULTIPATH
+static int nvme_latency_ewma_shift_show(void *data, struct seq_file *m)
+{
+	struct nvme_ns_head *head = data;
+
+	seq_printf(m, "%u\n", READ_ONCE(head->latency_ewma_shift));
+	return 0;
+}
+
+static ssize_t nvme_latency_ewma_shift_store(void *data,
+		const char __user *ubuf, size_t count, loff_t *ppos)
+{
+	struct nvme_ns_head *head = data;
+	char kbuf[8];
+	u32 res;
+	int ret;
+	size_t len;
+	char *arg;
+
+	len = min(sizeof(kbuf) - 1, count);
+
+	if (copy_from_user(kbuf, ubuf, len))
+		return -EFAULT;
+
+	kbuf[len] = '\0';
+	arg = strstrip(kbuf);
+
+	ret = kstrtou32(arg, 0, &res);
+	if (ret)
+		return ret;
+
+	/*
+	 * Values greater than 8 are nonsensical, as they effectively assign
+	 * zero weight to new samples.
+	 */
+	if (res > 8)
+		return -EINVAL;
+
+	WRITE_ONCE(head->latency_ewma_shift, res);
+	return count;
+}
+#endif
 
 static const struct nvme_debugfs_attr nvme_mpath_debugfs_attrs[] = {
+#ifdef CONFIG_NVME_MULTIPATH
+	{"latency_ewma_shift", 0600, nvme_latency_ewma_shift_show,
+			nvme_latency_ewma_shift_store},
+#endif
 	{},
 };
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 8d5f1e42d10a..82a4f2326b79 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -293,10 +293,9 @@ static void nvme_mpath_weight_work(struct work_struct *weight_work)
  * For instance, with EWMA_SHIFT = 3, this assigns 7/8 (~87.5 %) weight to
  * the existing/old ewma and 1/8 (~12.5%) weight to the new sample.
  */
-static inline u64 calc_ewma_update(u64 old, u64 new)
+static inline u64 calc_ewma_update(u64 old, u64 new, u32 ewma_shift)
 {
-	return (old * ((1 << NVME_DEFAULT_LATENCY_EWMA_SHIFT) - 1)
-			+ new) >> NVME_DEFAULT_LATENCY_EWMA_SHIFT;
+	return (old * ((1 << ewma_shift) - 1) + new) >> ewma_shift;
 }
 
 static void nvme_mpath_add_sample(struct request *rq, struct nvme_ns *ns)
@@ -388,7 +387,8 @@ static void nvme_mpath_add_sample(struct request *rq, struct nvme_ns *ns)
 		if (unlikely(!stat->slat_ns))
 			WRITE_ONCE(stat->slat_ns, avg_lat_ns);
 		else {
-			slat_ns = calc_ewma_update(stat->slat_ns, avg_lat_ns);
+			slat_ns = calc_ewma_update(stat->slat_ns, avg_lat_ns,
+					READ_ONCE(head->latency_ewma_shift));
 			WRITE_ONCE(stat->slat_ns, slat_ns);
 		}
 
@@ -1170,6 +1170,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	INIT_WORK(&head->requeue_work, nvme_requeue_work);
 	INIT_WORK(&head->partition_scan_work, nvme_partition_scan_work);
 	INIT_DELAYED_WORK(&head->remove_work, nvme_remove_head_work);
+	head->latency_ewma_shift = NVME_DEFAULT_LATENCY_EWMA_SHIFT;
 
 	/*
 	 * If "multipath_always_on" is enabled, a multipath node is added
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 040307c6534a..55e4d1344e5e 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -626,6 +626,7 @@ struct nvme_ns_head {
 	atomic_long_t		io_requeue_no_usable_path_count;
 	atomic_long_t		io_fail_no_available_path_count;
 	struct nvme_ns * __percpu	*latency_path;
+	u32				latency_ewma_shift;
 
 #define NVME_NSHEAD_DISK_LIVE		0
 #define NVME_NSHEAD_QUEUE_IF_NO_PATH	1
-- 
2.53.0