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 multipath failover count via sysfs

Browse Source 
When an NVMe command completes with a path-specific error, the NVMe
driver may retry the command on an alternate controller or path if one
is available. These failover events indicate that I/O was redirected
away from the original path.

Currently, the number of times requests are failed over to another
available path is not visible to userspace. Exposing this information
can be useful for diagnosing path health and stability.

Export per-path sysfs attribute "multipath_failover_count" under diag
attribute group. This attribute is both readable and writable and thus
allowing user to reset the counter. This counter can be consumed by
monitoring tools such as nvme-top to help identify paths that
consistently trigger failovers under load.

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 00:06:50 +05:30 committed by Keith Busch
parent ab5af2903b
commit 66ee95b3d4
3 changed files with 38 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

27
drivers/nvme/host/multipath.c
View File

@ -152,6 +152,7 @@ void nvme_failover_req(struct request *req)
struct bio *bio;
nvme_mpath_clear_current_path(ns);
atomic_long_inc(&ns->failover);
/*
* If we got back an ANA error, we know the controller is alive but not
@ -1165,6 +1166,32 @@ static ssize_t delayed_removal_secs_store(struct device *dev,
DEVICE_ATTR_RW(delayed_removal_secs);
static ssize_t multipath_failover_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->failover));
}
static ssize_t multipath_failover_count_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t count)
{
unsigned long failover;
int ret;
struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
ret = kstrtoul(buf, 0, &failover);
if (ret)
return -EINVAL;
atomic_long_set(&ns->failover, failover);
return count;
}
DEVICE_ATTR_RW(multipath_failover_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

@ -591,6 +591,7 @@ struct nvme_ns {
#ifdef CONFIG_NVME_MULTIPATH
enum nvme_ana_state ana_state;
u32 ana_grpid;
atomic_long_t failover;
#endif
atomic_long_t retries;
struct list_head siblings;
@ -1065,6 +1066,7 @@ extern struct device_attribute dev_attr_ana_state;
extern struct device_attribute dev_attr_queue_depth;
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 subsys_attr_iopolicy;
static inline bool nvme_disk_is_ns_head(struct gendisk *disk)

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

@ -371,6 +371,9 @@ static DEVICE_ATTR_RW(command_retries_count);
static struct attribute *nvme_ns_diag_attrs[] = {
&dev_attr_command_retries_count.attr,
#ifdef CONFIG_NVME_MULTIPATH
&dev_attr_multipath_failover_count.attr,
#endif
NULL,
};
@ -383,7 +386,12 @@ static umode_t nvme_ns_diag_attrs_are_visible(struct kobject *kobj,
if (nvme_disk_is_ns_head(dev_to_disk(dev)))
return 0;
}
#ifdef CONFIG_NVME_MULTIPATH
if (a == &dev_attr_multipath_failover_count.attr) {
if (nvme_disk_is_ns_head(dev_to_disk(dev)))
return 0;
}
#endif
return a->mode;
}