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

Force fault a vdev with 'zpool offline -f'

Browse Source 
This patch adds a '-f' option to 'zpool offline' to fault a vdev
instead of bringing it offline.  Unlike the OFFLINE state, the
FAULTED state will trigger the FMA code, allowing for things like
autoreplace and triggering the slot fault LED.  The -f faults
persist across imports, unless they were set with the temporary
(-t) flag.  Both persistent and temporary faults can be cleared
with zpool clear.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Tony Hutter <hutter2@llnl.gov>
Closes #6094
This commit is contained in:
Tony Hutter
2017-05-19 12:30:16 -07:00
committed by Brian Behlendorf
parent a32df59e18
commit 4a283c7f77
13 changed files with 266 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
module/zfs/spa_misc.c
+11 -3
View File
@@ -1181,13 +1181,21 @@ int
spa_vdev_state_exit(spa_t *spa, vdev_t *vd, int error)
{
boolean_t config_changed = B_FALSE;
vdev_t *vdev_top;
if (vd == NULL || vd == spa->spa_root_vdev) {
vdev_top = spa->spa_root_vdev;
} else {
vdev_top = vd->vdev_top;
}
if (vd != NULL || error == 0)
vdev_dtl_reassess(vd ? vd->vdev_top : spa->spa_root_vdev,
0, 0, B_FALSE);
vdev_dtl_reassess(vdev_top, 0, 0, B_FALSE);
if (vd != NULL) {
vdev_state_dirty(vd->vdev_top);
if (vd != spa->spa_root_vdev)
vdev_state_dirty(vdev_top);
config_changed = B_TRUE;
spa->spa_config_generation++;
}
module/zfs/vdev.c
+52 -6
View File
@@ -394,6 +394,8 @@ vdev_alloc(spa_t *spa, vdev_t **vdp, nvlist_t *nv, vdev_t *parent, uint_t id,
char *type;
uint64_t guid = 0, islog, nparity;
vdev_t *vd;
char *tmp = NULL;
int rc;
ASSERT(spa_config_held(spa, SCL_ALL, RW_WRITER) == SCL_ALL);
@@ -487,6 +489,19 @@ vdev_alloc(spa_t *spa, vdev_t **vdp, nvlist_t *nv, vdev_t *parent, uint_t id,
if (nvlist_lookup_string(nv, ZPOOL_CONFIG_PATH, &vd->vdev_path) == 0)
vd->vdev_path = spa_strdup(vd->vdev_path);
/*
* ZPOOL_CONFIG_AUX_STATE = "external" means we previously forced a
* fault on a vdev and want it to persist across imports (like with
* zpool offline -f).
*/
rc = nvlist_lookup_string(nv, ZPOOL_CONFIG_AUX_STATE, &tmp);
if (rc == 0 && tmp != NULL && strcmp(tmp, "external") == 0) {
vd->vdev_stat.vs_aux = VDEV_AUX_EXTERNAL;
vd->vdev_faulted = 1;
vd->vdev_label_aux = VDEV_AUX_EXTERNAL;
}
if (nvlist_lookup_string(nv, ZPOOL_CONFIG_DEVID, &vd->vdev_devid) == 0)
vd->vdev_devid = spa_strdup(vd->vdev_devid);
if (nvlist_lookup_string(nv, ZPOOL_CONFIG_PHYS_PATH,
@@ -591,12 +606,17 @@ vdev_alloc(spa_t *spa, vdev_t **vdp, nvlist_t *nv, vdev_t *parent, uint_t id,
&vd->vdev_resilver_txg);
/*
* When importing a pool, we want to ignore the persistent fault
* state, as the diagnosis made on another system may not be
* valid in the current context. Local vdevs will
* remain in the faulted state.
* In general, when importing a pool we want to ignore the
* persistent fault state, as the diagnosis made on another
* system may not be valid in the current context. The only
* exception is if we forced a vdev to a persistently faulted
* state with 'zpool offline -f'. The persistent fault will
* remain across imports until cleared.
*
* Local vdevs will remain in the faulted state.
*/
if (spa_load_state(spa) == SPA_LOAD_OPEN) {
if (spa_load_state(spa) == SPA_LOAD_OPEN ||
spa_load_state(spa) == SPA_LOAD_IMPORT) {
(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_FAULTED,
&vd->vdev_faulted);
(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_DEGRADED,
@@ -2478,6 +2498,32 @@ vdev_fault(spa_t *spa, uint64_t guid, vdev_aux_t aux)
tvd = vd->vdev_top;
/*
* If user did a 'zpool offline -f' then make the fault persist across
* reboots.
*/
if (aux == VDEV_AUX_EXTERNAL_PERSIST) {
/*
* There are two kinds of forced faults: temporary and
* persistent. Temporary faults go away at pool import, while
* persistent faults stay set. Both types of faults can be
* cleared with a zpool clear.
*
* We tell if a vdev is persistently faulted by looking at the
* ZPOOL_CONFIG_AUX_STATE nvpair. If it's set to "external" at
* import then it's a persistent fault. Otherwise, it's
* temporary. We get ZPOOL_CONFIG_AUX_STATE set to "external"
* by setting vd.vdev_stat.vs_aux to VDEV_AUX_EXTERNAL. This
* tells vdev_config_generate() (which gets run later) to set
* ZPOOL_CONFIG_AUX_STATE to "external" in the nvlist.
*/
vd->vdev_stat.vs_aux = VDEV_AUX_EXTERNAL;
vd->vdev_tmpoffline = B_FALSE;
aux = VDEV_AUX_EXTERNAL;
} else {
vd->vdev_tmpoffline = B_TRUE;
}
/*
* We don't directly use the aux state here, but if we do a
* vdev_reopen(), we need this value to be present to remember why we
@@ -2753,7 +2799,6 @@ vdev_clear(spa_t *spa, vdev_t *vd)
*/
if (vd->vdev_faulted || vd->vdev_degraded ||
!vdev_readable(vd) || !vdev_writeable(vd)) {
/*
* When reopening in response to a clear event, it may be due to
* a fmadm repair request. In this case, if the device is
@@ -2764,6 +2809,7 @@ vdev_clear(spa_t *spa, vdev_t *vd)
vd->vdev_faulted = vd->vdev_degraded = 0ULL;
vd->vdev_cant_read = B_FALSE;
vd->vdev_cant_write = B_FALSE;
vd->vdev_stat.vs_aux = 0;
vdev_reopen(vd == rvd ? rvd : vd->vdev_top);
module/zfs/vdev_label.c
+9 -1
View File
@@ -519,6 +519,7 @@ vdev_config_generate(spa_t *spa, vdev_t *vd, boolean_t getstats,
if (vd->vdev_ishole)
fnvlist_add_uint64(nv, ZPOOL_CONFIG_IS_HOLE, B_TRUE);
/* Set the reason why we're FAULTED/DEGRADED. */
switch (vd->vdev_stat.vs_aux) {
case VDEV_AUX_ERR_EXCEEDED:
aux = "err_exceeded";
@@ -529,8 +530,15 @@ vdev_config_generate(spa_t *spa, vdev_t *vd, boolean_t getstats,
break;
}
if (aux != NULL)
if (aux != NULL && !vd->vdev_tmpoffline) {
fnvlist_add_string(nv, ZPOOL_CONFIG_AUX_STATE, aux);
} else {
/*
* We're healthy - clear any previous AUX_STATE values.
*/
if (nvlist_exists(nv, ZPOOL_CONFIG_AUX_STATE))
nvlist_remove_all(nv, ZPOOL_CONFIG_AUX_STATE);
}
if (vd->vdev_splitting && vd->vdev_orig_guid != 0LL) {
fnvlist_add_uint64(nv, ZPOOL_CONFIG_ORIG_GUID,
module/zfs/zfs_ioctl.c
+4 -2
View File
@@ -156,6 +156,7 @@
#include <sys/spa.h>
#include <sys/spa_impl.h>
#include <sys/vdev.h>
#include <sys/vdev_impl.h>
#include <sys/priv_impl.h>
#include <sys/dmu.h>
#include <sys/dsl_dir.h>
@@ -1896,7 +1897,8 @@ zfs_ioc_vdev_set_state(zfs_cmd_t *zc)
case VDEV_STATE_FAULTED:
if (zc->zc_obj != VDEV_AUX_ERR_EXCEEDED &&
zc->zc_obj != VDEV_AUX_EXTERNAL)
zc->zc_obj != VDEV_AUX_EXTERNAL &&
zc->zc_obj != VDEV_AUX_EXTERNAL_PERSIST)
zc->zc_obj = VDEV_AUX_ERR_EXCEEDED;
error = vdev_fault(spa, zc->zc_guid, zc->zc_obj);
@@ -4919,7 +4921,7 @@ zfs_ioc_clear(zfs_cmd_t *zc)
vdev_clear(spa, vd);
(void) spa_vdev_state_exit(spa, NULL, 0);
(void) spa_vdev_state_exit(spa, spa->spa_root_vdev, 0);
/*
* Resume any suspended I/Os.