All of lore.kernel.org
 help / color / mirror / Atom feed
From: Nilay Shroff <nilay@linux.ibm.com>
To: linux-nvme@lists.infradead.org
Cc: hare@suse.de, kbusch@kernel.org, hch@lst.de, sagi@grimberg.me,
	dwagner@suse.de, kanie@linux.alibaba.com, jmeneghi@redhat.com,
	randyj@purestorage.com, martin.petersen@oracle.com,
	john.g.garry@oracle.com, gjoyce@linux.ibm.com,
	Nilay Shroff <nilay@linux.ibm.com>
Subject: [PATCH v7 8/9] nvme-multipath: add debugfs attribute latency_stat
Date: Sun,  9 Aug 2026 15:38:03 +0530	[thread overview]
Message-ID: <20260809100825.2014133-9-nilay@linux.ibm.com> (raw)
In-Reply-To: <20260809100825.2014133-1-nilay@linux.ibm.com>

This commit introduces a new debugfs attribute, "latency_stat", under
both per-path and head debugfs directories (defined under /sys/kernel/
debug/block/). This attribute provides visibility into the internal
state of the latency I/O policy to aid in debugging and performance
analysis.

For per-path entries, "latency_stat" reports the corresponding path
statistics such as I/O weight, selection count, processed samples, and
ignored samples.

For head entries, it reports per-CPU statistics for each reachable path,
including I/O weight, path score, smoothed (EWMA) latency, selection
count, processed samples, and ignored samples.

These additions enhance observability of the I/O path selection behavior
and help diagnose imbalance or instability in multipath performance.

Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
---
 drivers/nvme/host/debugfs.c | 124 ++++++++++++++++++++++++++++++++++++
 1 file changed, 124 insertions(+)

diff --git a/drivers/nvme/host/debugfs.c b/drivers/nvme/host/debugfs.c
index 63b0ad5d105b..b4bc7c710050 100644
--- a/drivers/nvme/host/debugfs.c
+++ b/drivers/nvme/host/debugfs.c
@@ -181,6 +181,126 @@ static ssize_t nvme_latency_batch_timeout_store(void *data,
 	WRITE_ONCE(head->latency_batch_timeout, res * NSEC_PER_SEC);
 	return count;
 }
+
+static void *nvme_mpath_latency_stat_start(struct seq_file *m, loff_t *pos)
+{
+	struct nvme_ns *ns;
+	struct nvme_debugfs_ctx *ctx = m->private;
+	struct nvme_ns_head *head = ctx->data;
+
+	if (!head->disk)
+		return NULL;
+
+	/* Remember srcu index, so we can unlock later. */
+	ctx->srcu_idx = srcu_read_lock(&head->srcu);
+	ns = list_first_or_null_rcu(&head->list, struct nvme_ns, siblings);
+
+	while (*pos && ns) {
+		ns = list_next_or_null_rcu(&head->list, &ns->siblings,
+				struct nvme_ns, siblings);
+		(*pos)--;
+	}
+
+	return ns;
+}
+
+static void *nvme_mpath_latency_stat_next(struct seq_file *m, void *v,
+		loff_t *pos)
+{
+	struct nvme_ns *ns = v;
+	struct nvme_debugfs_ctx *ctx = m->private;
+	struct nvme_ns_head *head = ctx->data;
+
+	(*pos)++;
+
+	return list_next_or_null_rcu(&head->list, &ns->siblings,
+			struct nvme_ns, siblings);
+}
+
+static void nvme_mpath_latency_stat_stop(struct seq_file *m, void *v)
+{
+	struct nvme_debugfs_ctx *ctx = m->private;
+	struct nvme_ns_head *head = ctx->data;
+	int srcu_idx = ctx->srcu_idx;
+
+	if (!head->disk)
+		return;
+
+	srcu_read_unlock(&head->srcu, srcu_idx);
+}
+
+static int nvme_mpath_latency_stat_show(struct seq_file *m, void *v)
+{
+	int i, cpu;
+	struct nvme_path_lat_stat *stat;
+	struct nvme_ns *ns = v;
+
+	seq_printf(m, "%s:\n", ns->disk->disk_name);
+	for_each_online_cpu(cpu) {
+		seq_printf(m, "cpu %d : ", cpu);
+		for (i = 0; i < NVME_NUM_STAT_GROUPS; i++) {
+			stat = &per_cpu_ptr(ns->path_lat, cpu)[i].stat;
+			seq_printf(m, "%u %u %llu %llu %llu %llu %llu ",
+				stat->weight, stat->credit, stat->score,
+				stat->slat_ns, stat->sel,
+				stat->nr_samples, stat->nr_ignored);
+		}
+		seq_putc(m, '\n');
+	}
+	return 0;
+}
+
+static const struct seq_operations nvme_mpath_latency_stat_seq_ops = {
+	.start = nvme_mpath_latency_stat_start,
+	.next  = nvme_mpath_latency_stat_next,
+	.stop  = nvme_mpath_latency_stat_stop,
+	.show  = nvme_mpath_latency_stat_show
+};
+
+static void nvme_latency_stat_read_all(struct nvme_ns *ns,
+		struct nvme_path_lat_stat *batch)
+{
+	int i, cpu;
+	u32 ncpu[NVME_NUM_STAT_GROUPS] = {0};
+	struct nvme_path_lat_stat *stat;
+
+	for_each_online_cpu(cpu) {
+		for (i = 0; i < NVME_NUM_STAT_GROUPS; i++) {
+			stat = &per_cpu_ptr(ns->path_lat, cpu)[i].stat;
+			batch[i].sel += stat->sel;
+			batch[i].nr_samples += stat->nr_samples;
+			batch[i].nr_ignored += stat->nr_ignored;
+			batch[i].weight += stat->weight;
+			if (stat->weight)
+				ncpu[i]++;
+		}
+	}
+
+	for (i = 0; i < NVME_NUM_STAT_GROUPS; i++) {
+		if (!ncpu[i])
+			continue;
+		batch[i].weight = DIV_U64_ROUND_CLOSEST(batch[i].weight,
+				ncpu[i]);
+	}
+}
+
+static int nvme_ns_latency_stat_show(void *data, struct seq_file *m)
+{
+	int i;
+	struct nvme_path_lat_stat stat[NVME_NUM_STAT_GROUPS] = {0};
+	struct nvme_ns *ns = (struct nvme_ns *)data;
+
+	if (!ns->head->disk)
+		return 0;
+
+	nvme_latency_stat_read_all(ns, stat);
+	for (i = 0; i < NVME_NUM_STAT_GROUPS; i++) {
+		seq_printf(m, "%u %llu %llu %llu ",
+			stat[i].weight, stat[i].sel,
+			stat[i].nr_samples, stat[i].nr_ignored);
+	}
+	return 0;
+}
 #endif
 
 static const struct nvme_debugfs_attr nvme_mpath_debugfs_attrs[] = {
@@ -189,11 +309,15 @@ static const struct nvme_debugfs_attr nvme_mpath_debugfs_attrs[] = {
 			nvme_latency_ewma_shift_store},
 	{"latency_batch_timeout", 0600, nvme_latency_batch_timeout_show,
 			nvme_latency_batch_timeout_store},
+	{"latency_stat", 0400, .seq_ops = &nvme_mpath_latency_stat_seq_ops},
 #endif
 	{},
 };
 
 static const struct nvme_debugfs_attr nvme_ns_debugfs_attrs[] = {
+#ifdef CONFIG_NVME_MULTIPATH
+	{"latency_stat", 0400, nvme_ns_latency_stat_show},
+#endif
 	{},
 };
 
-- 
2.53.0



  parent reply	other threads:[~2026-08-09 10:09 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-09 10:07 [PATCH v7 0/9] nvme-multipath: introduce latency I/O policy Nilay Shroff
2026-08-09 10:07 ` [PATCH v7 1/9] block: expose blk_stat_{enable,disable}_accounting() to drivers Nilay Shroff
2026-08-09 10:07 ` [PATCH v7 2/9] block: record I/O request start time for passthru request Nilay Shroff
2026-08-09 10:07 ` [PATCH v7 3/9] nvme-multipath: pass I/O type to nvme_find_path() Nilay Shroff
2026-08-09 10:07 ` [PATCH v7 4/9] nvme-multipath: add support for latency I/O policy Nilay Shroff
2026-08-09 10:08 ` [PATCH v7 5/9] nvme: add generic debugfs support Nilay Shroff
2026-08-09 10:08 ` [PATCH v7 6/9] nvme-multipath: add debugfs attribute latency_ewma_shift Nilay Shroff
2026-08-09 10:08 ` [PATCH v7 7/9] nvme-multipath: add debugfs attribute latency_batch_timeout Nilay Shroff
2026-08-09 10:08 ` Nilay Shroff [this message]
2026-08-09 10:08 ` [PATCH v7 9/9] nvme-multipath: add documentation for latency I/O policy Nilay Shroff

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260809100825.2014133-9-nilay@linux.ibm.com \
    --to=nilay@linux.ibm.com \
    --cc=dwagner@suse.de \
    --cc=gjoyce@linux.ibm.com \
    --cc=hare@suse.de \
    --cc=hch@lst.de \
    --cc=jmeneghi@redhat.com \
    --cc=john.g.garry@oracle.com \
    --cc=kanie@linux.alibaba.com \
    --cc=kbusch@kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=martin.petersen@oracle.com \
    --cc=randyj@purestorage.com \
    --cc=sagi@grimberg.me \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.