github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-07-27 17:47:41 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

nvme: export I/O failure count when no path is available via sysfs

Browse Source 
When I/O is submitted to the NVMe namespace head and no available path
can handle the request, the driver fails the I/O immediately. Currently,
such failures are only reported via kernel log messages, which may be
lost over time since dmesg is a circular buffer.

Add a new ns-head sysfs counter io_fail_no_available_path_count, under
diag attribute group to expose the number of I/Os that failed due to the
absence of an available path. This provides persistent visibility into
path-related I/O failures and can help users diagnose the cause of I/O
errors. This counter is also writable and so user may reset its value,
if needed.

This counter can also be consumed by monitoring tools such as nvme-top.

Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
This commit is contained in:
Nilay Shroff 2026-05-17 00:06:53 +05:30 committed by Keith Busch
parent 76b5e1591e
commit a8e434cb03
3 changed files with 37 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
drivers/nvme/host/multipath.c
View File

@ -543,6 +543,7 @@ static void nvme_ns_head_submit_bio(struct bio *bio)
dev_warn_ratelimited(dev, "no available path - failing I/O\n");
bio_io_error(bio);
atomic_long_inc(&head->io_fail_no_available_path_count);
}
srcu_read_unlock(&head->srcu, srcu_idx);
@ -1222,6 +1223,35 @@ static ssize_t io_requeue_no_usable_path_count_store(struct device *dev,
DEVICE_ATTR_RW(io_requeue_no_usable_path_count);
static ssize_t io_fail_no_available_path_count_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct gendisk *disk = dev_to_disk(dev);
struct nvme_ns_head *head = disk->private_data;
return sysfs_emit(buf, "%lu\n",
atomic_long_read(&head->io_fail_no_available_path_count));
}
static ssize_t io_fail_no_available_path_count_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
int err;
unsigned long fail_cnt;
struct gendisk *disk = dev_to_disk(dev);
struct nvme_ns_head *head = disk->private_data;
err = kstrtoul(buf, 0, &fail_cnt);
if (err)
return -EINVAL;
atomic_long_set(&head->io_fail_no_available_path_count, fail_cnt);
return count;
}
DEVICE_ATTR_RW(io_fail_no_available_path_count);
static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl,
struct nvme_ana_group_desc *desc, void *data)
{

2
drivers/nvme/host/nvme.h
View File

@ -567,6 +567,7 @@ struct nvme_ns_head {
struct delayed_work remove_work;
unsigned int delayed_removal_secs;
atomic_long_t io_requeue_no_usable_path_count;
atomic_long_t io_fail_no_available_path_count;
#define NVME_NSHEAD_DISK_LIVE 0
#define NVME_NSHEAD_QUEUE_IF_NO_PATH 1
struct nvme_ns __rcu *current_path[];
@ -1071,6 +1072,7 @@ extern struct device_attribute dev_attr_numa_nodes;
extern struct device_attribute dev_attr_delayed_removal_secs;
extern struct device_attribute dev_attr_multipath_failover_count;
extern struct device_attribute dev_attr_io_requeue_no_usable_path_count;
extern struct device_attribute dev_attr_io_fail_no_available_path_count;
extern struct device_attribute subsys_attr_iopolicy;
static inline bool nvme_disk_is_ns_head(struct gendisk *disk)

5
drivers/nvme/host/sysfs.c
View File

@ -404,6 +404,7 @@ static struct attribute *nvme_ns_diag_attrs[] = {
#ifdef CONFIG_NVME_MULTIPATH
&dev_attr_multipath_failover_count.attr,
&dev_attr_io_requeue_no_usable_path_count.attr,
&dev_attr_io_fail_no_available_path_count.attr,
#endif
NULL,
};
@ -432,6 +433,10 @@ static umode_t nvme_ns_diag_attrs_are_visible(struct kobject *kobj,
if (!nvme_disk_is_ns_head(dev_to_disk(dev)))
return 0;
}
if (a == &dev_attr_io_fail_no_available_path_count.attr) {
if (!nvme_disk_is_ns_head(dev_to_disk(dev)))
return 0;
}
#endif
return a->mode;
}