github-mirror/linux
1
0
Fork 0
mirror of https://github.com/torvalds/linux.git synced 2026-07-27 09:36:22 +02:00
Code Issues Actions Packages Projects Releases Wiki Activity Graph

nvme: export command retry count via sysfs

Browse Source 
When Advanced Command Retry Enable (ACRE) is configured, a controller
may interrupt command execution and return a completion status
indicating command interrupted with the DNR bit cleared. In this case,
the driver retries the command based on the Command Retry Delay (CRD)
value provided in the completion status.

Currently, these command retries are handled entirely within the NVMe
driver and are not visible to userspace. As a result, there is no
observability into retry behavior, which can be a useful diagnostic
signal.

Expose a per-namespace sysfs attribute command_retries_count, under
diag attribute group to provide visibility into retry activity. This
information can help identify controller-side congestion under load
and enables comparison across paths in multipath setups (for example,
detecting cases where one path experiences significantly more retries
than another under identical workloads).

This exported metric is intended for diagnostics and monitoring tools
such as nvme-top, and does not change command retry behavior. A new
sysfs attribute named "command_retries_count" is added for this purpose.
This attribute is both readable as well as writable. So user could
reset this counter if needed.

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 00:06:49 +05:30 committed by Keith Busch
parent 37afebc79a
commit ab5af2903b
3 changed files with 38 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
drivers/nvme/host/core.c
View File

@ -323,6 +323,7 @@ static void nvme_retry_req(struct request *req)
{
unsigned long delay = 0;
u16 crd;
struct nvme_ns *ns = req->q->queuedata;
/* The mask and shift result must be <= 3 */
crd = (nvme_req(req)->status & NVME_STATUS_CRD) >> 11;
@ -330,6 +331,9 @@ static void nvme_retry_req(struct request *req)
delay = nvme_req(req)->ctrl->crdt[crd - 1] * 100;
nvme_req(req)->retries++;
if (ns)
atomic_long_inc(&ns->retries);
blk_mq_requeue_request(req, false);
blk_mq_delay_kick_requeue_list(req->q, delay);
}

1
drivers/nvme/host/nvme.h
View File

@ -592,6 +592,7 @@ struct nvme_ns {
enum nvme_ana_state ana_state;
u32 ana_grpid;
#endif
atomic_long_t retries;
struct list_head siblings;
struct kref kref;
struct nvme_ns_head *head;

33
drivers/nvme/host/sysfs.c
View File

@ -344,13 +344,46 @@ const struct attribute_group nvme_ns_mpath_attr_group = {
};
#endif
static ssize_t command_retries_count_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->retries));
}
static ssize_t command_retries_count_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
unsigned long retries;
int err;
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
err = kstrtoul(buf, 0, &retries);
if (err)
return -EINVAL;
atomic_long_set(&ns->retries, retries);
return count;
}
static DEVICE_ATTR_RW(command_retries_count);
static struct attribute *nvme_ns_diag_attrs[] = {
&dev_attr_command_retries_count.attr,
NULL,
};
static umode_t nvme_ns_diag_attrs_are_visible(struct kobject *kobj,
struct attribute *a, int n)
{
struct device *dev = container_of(kobj, struct device, kobj);
if (a == &dev_attr_command_retries_count.attr) {
if (nvme_disk_is_ns_head(dev_to_disk(dev)))
return 0;
}
return a->mode;
}