[RFC PATCHv4 6/6] nvme-multipath: add debugfs attribute adaptive_stat
Nilay Shroff
nilay at linux.ibm.com
Tue Nov 4 02:45:21 PST 2025
This commit introduces a new debugfs attribute, "adaptive_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 adaptive I/O policy to aid in debugging and performance
analysis.
For per-path entries, "adaptive_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 adaptive I/O path selection
behavior and help diagnose imbalance or instability in multipath
performance.
Reviewed-by: Hannes Reinecke <hare at suse.de>
Signed-off-by: Nilay Shroff <nilay at linux.ibm.com>
---
drivers/nvme/host/debugfs.c | 113 ++++++++++++++++++++++++++++++++++++
1 file changed, 113 insertions(+)
diff --git a/drivers/nvme/host/debugfs.c b/drivers/nvme/host/debugfs.c
index e382fa411b13..28de4a8e2333 100644
--- a/drivers/nvme/host/debugfs.c
+++ b/drivers/nvme/host/debugfs.c
@@ -182,6 +182,115 @@ static ssize_t nvme_adp_weight_timeout_store(void *data,
WRITE_ONCE(head->adp_weight_timeout, res * NSEC_PER_SEC);
return count;
}
+
+static void *nvme_mpath_adp_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;
+
+ /* 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_adp_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_adp_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;
+
+ srcu_read_unlock(&head->srcu, srcu_idx);
+}
+
+static int nvme_mpath_adp_stat_show(struct seq_file *m, void *v)
+{
+ int i, cpu;
+ struct nvme_path_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->info, 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_adp_stat_seq_ops = {
+ .start = nvme_mpath_adp_stat_start,
+ .next = nvme_mpath_adp_stat_next,
+ .stop = nvme_mpath_adp_stat_stop,
+ .show = nvme_mpath_adp_stat_show
+};
+
+static void adp_stat_read_all(struct nvme_ns *ns, struct nvme_path_stat *batch)
+{
+ int i, cpu;
+ u32 ncpu[NVME_NUM_STAT_GROUPS] = {0};
+ struct nvme_path_stat *stat;
+
+ for_each_online_cpu(cpu) {
+ for (i = 0; i < NVME_NUM_STAT_GROUPS; i++) {
+ stat = &per_cpu_ptr(ns->info, 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_adp_stat_show(void *data, struct seq_file *m)
+{
+ int i;
+ struct nvme_path_stat stat[NVME_NUM_STAT_GROUPS] = {0};
+ struct nvme_ns *ns = (struct nvme_ns *)data;
+
+ adp_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[] = {
@@ -190,11 +299,15 @@ static const struct nvme_debugfs_attr nvme_mpath_debugfs_attrs[] = {
nvme_adp_ewma_shift_store},
{"adaptive_weight_timeout", 0600, nvme_adp_weight_timeout_show,
nvme_adp_weight_timeout_store},
+ {"adaptive_stat", 0400, .seq_ops = &nvme_mpath_adp_stat_seq_ops},
#endif
{},
};
static const struct nvme_debugfs_attr nvme_ns_debugfs_attrs[] = {
+#ifdef CONFIG_NVME_MULTIPATH
+ {"adaptive_stat", 0400, nvme_ns_adp_stat_show},
+#endif
{},
};
--
2.51.0
More information about the Linux-nvme
mailing list