mirrors/linux
2
0
Fork 0
mirror of https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git synced 2026-07-24 09:11:06 -04:00
Code Issues Packages Projects Releases Wiki Activity

nvme: export command error counters via sysfs

Browse Source 
When an NVMe command completes with an error status, the driver
logs the error to the kernel log. However, these messages may be
lost or overwritten over time since dmesg is a circular buffer.

Expose per-path and ctrl sysfs attribute command_error_count, under
diag attribute group to provide persistent visibility into error
occurrences. This allows users to observe the total number of commands
that have failed on a given path over time, which can be useful for
diagnosing path health and stability.

This attribute is both readable and writable thus allowing user to reset
these counters. These counters can also be consumed by observability
tools such as nvme-top to provide additional insight into NVMe error
behavior.

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 00:06:51 +05:30
committed by Keith Busch
parent 66ee95b3d4
commit 30ab37a128
3 changed files with 77 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
drivers/nvme/host/core.c
View File

@@ -438,11 +438,19 @@ static inline void nvme_end_req_zoned(struct request *req)
static inline void __nvme_end_req(struct request *req)
{
if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
struct nvme_ns *ns = req->q->queuedata;
struct nvme_request *nr = nvme_req(req);
if (unlikely(nr->status && !(req->rq_flags & RQF_QUIET))) {
if (blk_rq_is_passthrough(req))
nvme_log_err_passthru(req);
else
nvme_log_error(req);
if (ns)
atomic_long_inc(&ns->errors);
else
atomic_long_inc(&nr->ctrl->errors);
}
nvme_end_req_zoned(req);
nvme_trace_bio_complete(req);

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

@@ -415,6 +415,7 @@ struct nvme_ctrl {
unsigned long ka_last_check_time;
struct work_struct fw_act_work;
unsigned long events;
atomic_long_t errors;
#ifdef CONFIG_NVME_MULTIPATH
/* asymmetric namespace access: */
@@ -594,6 +595,7 @@ struct nvme_ns {
atomic_long_t failover;
#endif
atomic_long_t retries;
atomic_long_t errors;
struct list_head siblings;
struct kref kref;
struct nvme_ns_head *head;

66
drivers/nvme/host/sysfs.c
View File

@@ -6,6 +6,7 @@
*/
#include <linux/nvme-auth.h>
#include <linux/blkdev.h>
#include "nvme.h"
#include "fabrics.h"
@@ -369,8 +370,37 @@ static ssize_t command_retries_count_store(struct device *dev,
}
static DEVICE_ATTR_RW(command_retries_count);
static ssize_t nvme_io_errors_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
return sysfs_emit(buf, "%lu\n", atomic_long_read(&ns->errors));
}
static ssize_t nvme_io_errors_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
unsigned long errors;
int err;
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
err = kstrtoul(buf, 0, &errors);
if (err)
return -EINVAL;
atomic_long_set(&ns->errors, errors);
return count;
}
struct device_attribute dev_attr_io_errors =
__ATTR(command_error_count, 0644,
nvme_io_errors_show, nvme_io_errors_store);
static struct attribute *nvme_ns_diag_attrs[] = {
&dev_attr_command_retries_count.attr,
&dev_attr_io_errors.attr,
#ifdef CONFIG_NVME_MULTIPATH
&dev_attr_multipath_failover_count.attr,
#endif
@@ -386,6 +416,12 @@ 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_errors.attr) {
struct gendisk *disk = dev_to_disk(dev);
if (nvme_disk_is_ns_head(disk))
return 0;
}
#ifdef CONFIG_NVME_MULTIPATH
if (a == &dev_attr_multipath_failover_count.attr) {
if (nvme_disk_is_ns_head(dev_to_disk(dev)))
@@ -1076,7 +1112,37 @@ static const struct attribute_group nvme_tls_attrs_group = {
};
#endif
static ssize_t nvme_adm_errors_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
return sysfs_emit(buf, "%lu\n",
(unsigned long)atomic_long_read(&ctrl->errors));
}
static ssize_t nvme_adm_errors_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
unsigned long errors;
int err;
struct nvme_ctrl *ctrl = dev_get_drvdata(dev);
err = kstrtoul(buf, 0, &errors);
if (err)
return -EINVAL;
atomic_long_set(&ctrl->errors, errors);
return count;
}
struct device_attribute dev_attr_adm_errors =
__ATTR(command_error_count, 0644,
nvme_adm_errors_show, nvme_adm_errors_store);
static struct attribute *nvme_dev_diag_attrs[] = {
&dev_attr_adm_errors.attr,
NULL,
};