nvme: generate uevent once a multipath namespace is operational again

When fast_io_fail_tmo is set I/O will be aborted while recovery is
still ongoing. This causes MD to set the namespace to failed, and
no futher I/O will be submitted to that namespace.

However, once the recovery succeeds and the namespace becomes
operational again the NVMe subsystem doesn't send a notification,
so MD cannot automatically reinstate operation and requires
manual interaction.

This patch will send a KOBJ_CHANGE uevent per multipathed namespace
once the underlying controller transitions to LIVE, allowing an automatic
MD reassembly with these udev rules:

/etc/udev/rules.d/65-md-auto-re-add.rules:
SUBSYSTEM!="block", GOTO="md_end"

ACTION!="change", GOTO="md_end"
ENV{ID_FS_TYPE}!="linux_raid_member", GOTO="md_end"
PROGRAM="/sbin/md_raid_auto_readd.sh $devnode"
LABEL="md_end"

/sbin/md_raid_auto_readd.sh:

MDADM=/sbin/mdadm
DEVNAME=$1

export $(${MDADM} --examine --export ${DEVNAME})

if [ -z "${MD_UUID}" ]; then
    exit 1
fi

UUID_LINK=$(readlink /dev/disk/by-id/md-uuid-${MD_UUID})
MD_DEVNAME=${UUID_LINK##*/}
export $(${MDADM} --detail --export /dev/${MD_DEVNAME})
if [ -z "${MD_METADATA}" ] ; then
    exit 1
fi
if [ $(cat /sys/block/${MD_DEVNAME}/md/degraded) != 1 ]; then
    echo "${MD_DEVNAME}: array not degraded, nothing to do"
    exit 0
fi
MD_STATE=$(cat /sys/block/${MD_DEVNAME}/md/array_state)
if [ ${MD_STATE} != "clean" ] ; then
    echo "${MD_DEVNAME}: array state ${MD_STATE}, cannot re-add"
    exit 1
fi
MD_VARNAME="MD_DEVICE_dev_${DEVNAME##*/}_ROLE"
if [ ${!MD_VARNAME} = "spare" ] ; then
    ${MDADM} --manage /dev/${MD_DEVNAME} --re-add ${DEVNAME}
fi

Changes to v2:
- Add udev rules example to description
Changes to v1:
- use disk_uevent() as suggested by hch

Signed-off-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
This commit is contained in:
Hannes Reinecke 2021-10-06 11:13:13 +02:00 committed by Christoph Hellwig
parent a9a7e30fd9
commit f6f09c15a7

View File

@ -105,8 +105,11 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
down_read(&ctrl->namespaces_rwsem);
list_for_each_entry(ns, &ctrl->namespaces, list) {
if (ns->head->disk)
kblockd_schedule_work(&ns->head->requeue_work);
if (!ns->head->disk)
continue;
kblockd_schedule_work(&ns->head->requeue_work);
if (ctrl->state == NVME_CTRL_LIVE)
disk_uevent(ns->head->disk, KOBJ_CHANGE);
}
up_read(&ctrl->namespaces_rwsem);
}