c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-22 10:37:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

Too many vdev probe errors should suspend pool

Browse Source 
Similar to what we saw in #16569, we need to consider that a
replacing vdev should not be considered as fully contributing
to the redundancy of a raidz vdev even though current IO has
enough redundancy.

When a failed vdev_probe() is faulting a disk, it now checks
if that disk is required, and if so it suspends the pool until
the admin can return the missing disks.

Sponsored-by: Klara, Inc.
Sponsored-by: Wasabi Technology, Inc.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Alexander Motin <mav@FreeBSD.org>
Reviewed-by: Allan Jude <allan@klarasystems.com>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Don Brady <don.brady@klarasystems.com>
Closes #16864
This commit is contained in:
Don Brady
2025-01-04 11:28:33 -07:00
committed by GitHub
parent 50cbb14641
commit 939e0237c5
4 changed files with 176 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/spa.c
+19 -6
View File
@@ -8948,16 +8948,26 @@ spa_async_remove(spa_t *spa, vdev_t *vd)
}
static void
spa_async_fault_vdev(spa_t *spa, vdev_t *vd)
spa_async_fault_vdev(vdev_t *vd, boolean_t *suspend)
{
if (vd->vdev_fault_wanted) {
vdev_state_t newstate = VDEV_STATE_FAULTED;
vd->vdev_fault_wanted = B_FALSE;
vdev_set_state(vd, B_TRUE, VDEV_STATE_FAULTED,
VDEV_AUX_ERR_EXCEEDED);
}
/*
* If this device has the only valid copy of the data, then
* back off and simply mark the vdev as degraded instead.
*/
if (!vd->vdev_top->vdev_islog && vd->vdev_aux == NULL &&
vdev_dtl_required(vd)) {
newstate = VDEV_STATE_DEGRADED;
/* A required disk is missing so suspend the pool */
*suspend = B_TRUE;
}
vdev_set_state(vd, B_TRUE, newstate, VDEV_AUX_ERR_EXCEEDED);
}
for (int c = 0; c < vd->vdev_children; c++)
spa_async_fault_vdev(spa, vd->vdev_child[c]);
spa_async_fault_vdev(vd->vdev_child[c], suspend);
}
static void
@@ -9049,8 +9059,11 @@ spa_async_thread(void *arg)
*/
if (tasks & SPA_ASYNC_FAULT_VDEV) {
spa_vdev_state_enter(spa, SCL_NONE);
spa_async_fault_vdev(spa, spa->spa_root_vdev);
boolean_t suspend = B_FALSE;
spa_async_fault_vdev(spa->spa_root_vdev, &suspend);
(void) spa_vdev_state_exit(spa, NULL, 0);
if (suspend)
zio_suspend(spa, NULL, ZIO_SUSPEND_IOERR);
}
/*