[RFC PATCHv5 5/7] nvme-multipath: add debugfs attribute adaptive_weight_timeout

[Nilay Shroff <nilay@linux.ibm.com>]

By default, the adaptive I/O policy accumulates latency samples over a
15-second window. When this window expires, the driver computes the
average latency and updates the smoothed (EWMA) latency value. The
path weight is then recalculated based on this data.

A 15-second window provides a good balance for most workloads, as it
helps smooth out transient latency spikes and produces a more stable
path weight profile. However, some workloads may benefit from faster
or slower adaptation to changing latency conditions.

This commit introduces a new debugfs attribute, adaptive_weight_timeout,
which allows users to configure the path weight calculation interval
based on their workload requirements.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 drivers/nvme/host/core.c      |  1 +
 drivers/nvme/host/debugfs.c   | 40 ++++++++++++++++++++++++++++++++++-
 drivers/nvme/host/multipath.c |  7 ++++--
 drivers/nvme/host/nvme.h      |  1 +
 4 files changed, 46 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 43b9b0d6cbdf..d3828c4812fc 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3915,6 +3915,7 @@ static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 	head->rotational = info->is_rotational;
 #ifdef CONFIG_NVME_MULTIPATH
 	head->adp_ewma_shift = NVME_DEFAULT_ADP_EWMA_SHIFT;
+	head->adp_weight_timeout = NVME_DEFAULT_ADP_WEIGHT_TIMEOUT;
 #endif
 	ratelimit_state_init(&head->rs_nuse, 5 * HZ, 1);
 	ratelimit_set_flags(&head->rs_nuse, RATELIMIT_MSG_ON_RELEASE);
diff --git a/drivers/nvme/host/debugfs.c b/drivers/nvme/host/debugfs.c
index e3c37041e8f2..e382fa411b13 100644
--- a/drivers/nvme/host/debugfs.c
+++ b/drivers/nvme/host/debugfs.c
@@ -146,12 +146,50 @@ static ssize_t nvme_adp_ewma_shift_store(void *data, const char __user *ubuf,
 	WRITE_ONCE(head->adp_ewma_shift, res);
 	return count;
 }
+
+static int nvme_adp_weight_timeout_show(void *data, struct seq_file *m)
+{
+	struct nvme_ns_head *head = data;
+
+	seq_printf(m, "%llu\n",
+		div_u64(READ_ONCE(head->adp_weight_timeout), NSEC_PER_SEC));
+	return 0;
+}
+
+static ssize_t nvme_adp_weight_timeout_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;
+
+	WRITE_ONCE(head->adp_weight_timeout, res * NSEC_PER_SEC);
+	return count;
+}
 #endif
 
 static const struct nvme_debugfs_attr nvme_mpath_debugfs_attrs[] = {
 #ifdef CONFIG_NVME_MULTIPATH
-		{"adaptive_ewma_shift", 0600, nvme_adp_ewma_shift_show,
+	{"adaptive_ewma_shift", 0600, nvme_adp_ewma_shift_show,
 			nvme_adp_ewma_shift_store},
+	{"adaptive_weight_timeout", 0600, nvme_adp_weight_timeout_show,
+			nvme_adp_weight_timeout_store},
 #endif
 	{},
 };
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index c7470cc8844e..e70a7d5cf036 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -362,8 +362,11 @@ static void nvme_mpath_add_sample(struct request *rq, struct nvme_ns *ns)
 	stat->batch_count++;
 	stat->nr_samples++;
 
-	if (now > stat->last_weight_ts &&
-	    (now - stat->last_weight_ts) >= NVME_DEFAULT_ADP_WEIGHT_TIMEOUT) {
+	if (now > stat->last_weight_ts) {
+		u64 timeout = READ_ONCE(head->adp_weight_timeout);
+
+		if ((now - stat->last_weight_ts) < timeout)
+			return;
 
 		stat->last_weight_ts = now;
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 97de45634f08..53d868cccbeb 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -546,6 +546,7 @@ struct nvme_ns_head {
 
 	struct nvme_ns * __percpu	*adp_path;
 	u32				adp_ewma_shift;
+	u64				adp_weight_timeout;
 
 #define NVME_NSHEAD_DISK_LIVE		0
 #define NVME_NSHEAD_QUEUE_IF_NO_PATH	1
-- 
2.51.0