c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-22 02:27:36 +03:00
Code Issues Packages Projects Releases Wiki Activity

zed: Ensure spare activation after kernel-initiated device removal

Browse Source 
In addition to hotplug events, the kernel may also mark a failing vdev
as REMOVED. This was observed in a customer report and reproduced by
forcing the NVMe host driver to disable the device after a failed reset
due to command timeout. In such cases, the spare was not activated
because the device had already transitioned to a REMOVED state before
zed processed the event.
To address this, explicitly attempt hot spare activation when the
kernel marks a device as REMOVED.

Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Ameer Hamza <ahamza@ixsystems.com>
Closes #17187
This commit is contained in:
Ameer Hamza
2025-03-29 00:48:38 +05:00
committed by Tony Hutter
parent 76bd2ae5c8
commit ab455c7b80
5 changed files with 46 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
cmd/zed/agents/zfs_retire.c
+15 -4
View File
@@ -404,6 +404,7 @@ zfs_retire_recv(fmd_hdl_t *hdl, fmd_event_t *ep, nvlist_t *nvl,
(state == VDEV_STATE_REMOVED || state == VDEV_STATE_FAULTED))) {
const char *devtype;
char *devname;
boolean_t skip_removal = B_FALSE;
if (nvlist_lookup_string(nvl, FM_EREPORT_PAYLOAD_ZFS_VDEV_TYPE,
&devtype) == 0) {
@@ -441,18 +442,28 @@ zfs_retire_recv(fmd_hdl_t *hdl, fmd_event_t *ep, nvlist_t *nvl,
nvlist_lookup_uint64_array(vdev, ZPOOL_CONFIG_VDEV_STATS,
(uint64_t **)&vs, &c);
if (vs->vs_state == VDEV_STATE_OFFLINE)
return;
/*
* If state removed is requested for already removed vdev,
* its a loopback event from spa_async_remove(). Just
* ignore it.
*/
if ((vs->vs_state == VDEV_STATE_REMOVED && state ==
VDEV_STATE_REMOVED) || vs->vs_state == VDEV_STATE_OFFLINE)
return;
if ((vs->vs_state == VDEV_STATE_REMOVED &&
state == VDEV_STATE_REMOVED)) {
if (strcmp(class, "resource.fs.zfs.removed") == 0 &&
nvlist_exists(nvl, "by_kernel")) {
skip_removal = B_TRUE;
} else {
return;
}
}
/* Remove the vdev since device is unplugged */
int remove_status = 0;
if (l2arc || (strcmp(class, "resource.fs.zfs.removed") == 0)) {
if (!skip_removal && (l2arc ||
(strcmp(class, "resource.fs.zfs.removed") == 0))) {
remove_status = zpool_vdev_remove_wanted(zhp, devname);
fmd_hdl_debug(hdl, "zpool_vdev_remove_wanted '%s'"
", err:%d", devname, libzfs_errno(zhdl));