mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2026-03-11 04:46:18 +03:00
f8457fbdc4
vdev_rebuild() is always called with spa_config_lock held in
RW_WRITER mode. However, when it tries to call dmu_tx_assign()
the latter may hang on dmu_tx_wait() waiting for available txg.
But that available txg may not happen because txg_sync takes
spa_config_lock in order to process the current txg. So we have
a deadlock case here:
- dmu_tx_assign() waits for txg holding spa_config_lock;
- txg_sync waits for spa_config_lock not progressing with txg.
Here are the stacks:
__schedule+0x24e/0x590
schedule+0x69/0x110
cv_wait_common+0xf8/0x130 [spl]
__cv_wait+0x15/0x20 [spl]
dmu_tx_wait+0x8e/0x1e0 [zfs]
dmu_tx_assign+0x49/0x80 [zfs]
vdev_rebuild_initiate+0x39/0xc0 [zfs]
vdev_rebuild+0x84/0x90 [zfs]
spa_vdev_attach+0x305/0x680 [zfs]
zfs_ioc_vdev_attach+0xc7/0xe0 [zfs]
cv_wait_common+0xf8/0x130 [spl]
__cv_wait+0x15/0x20 [spl]
spa_config_enter+0xf9/0x120 [zfs]
spa_sync+0x6d/0x5b0 [zfs]
txg_sync_thread+0x266/0x2f0 [zfs]
The solution is to pass txg returned by spa_vdev_enter(spa)
at the top of spa_vdev_attach() to vdev_rebuild() and call
dmu_tx_create_assigned(txg) which doesn't wait for txg.
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Akash B <akash-b@hpe.com>
Reviewed-by: Alek Pinchuk <apinchuk@axcient.com>
Signed-off-by: Andriy Tkachuk <andriy.tkachuk@seagate.com>
Closes #18210
Closes #18258
105 lines
3.5 KiB
C
105 lines
3.5 KiB
C
// SPDX-License-Identifier: CDDL-1.0
|
|
/*
|
|
* CDDL HEADER START
|
|
*
|
|
* The contents of this file are subject to the terms of the
|
|
* Common Development and Distribution License (the "License").
|
|
* You may not use this file except in compliance with the License.
|
|
*
|
|
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
|
|
* or https://opensource.org/licenses/CDDL-1.0.
|
|
* See the License for the specific language governing permissions
|
|
* and limitations under the License.
|
|
*
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
/*
|
|
* Copyright (c) 2018, Intel Corporation.
|
|
* Copyright (c) 2020 by Lawrence Livermore National Security, LLC.
|
|
*/
|
|
|
|
#ifndef _SYS_VDEV_REBUILD_H
|
|
#define _SYS_VDEV_REBUILD_H
|
|
|
|
#include <sys/spa.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
/*
|
|
* Number of entries in the physical vdev_rebuild_phys structure. This
|
|
* state is stored per top-level as VDEV_ZAP_TOP_VDEV_REBUILD_PHYS.
|
|
*/
|
|
#define REBUILD_PHYS_ENTRIES 12
|
|
|
|
/*
|
|
* On-disk rebuild configuration and state. When adding new fields they
|
|
* must be added to the end of the structure.
|
|
*/
|
|
typedef struct vdev_rebuild_phys {
|
|
uint64_t vrp_rebuild_state; /* vdev_rebuild_state_t */
|
|
uint64_t vrp_last_offset; /* last rebuilt offset */
|
|
uint64_t vrp_min_txg; /* minimum missing txg */
|
|
uint64_t vrp_max_txg; /* maximum missing txg */
|
|
uint64_t vrp_start_time; /* start time */
|
|
uint64_t vrp_end_time; /* end time */
|
|
uint64_t vrp_scan_time_ms; /* total run time in ms */
|
|
uint64_t vrp_bytes_scanned; /* alloc bytes scanned */
|
|
uint64_t vrp_bytes_issued; /* read bytes rebuilt */
|
|
uint64_t vrp_bytes_rebuilt; /* rebuilt bytes */
|
|
uint64_t vrp_bytes_est; /* total bytes to scan */
|
|
uint64_t vrp_errors; /* errors during rebuild */
|
|
} vdev_rebuild_phys_t;
|
|
|
|
/*
|
|
* The vdev_rebuild_t describes the current state and how a top-level vdev
|
|
* should be rebuilt. The core elements are the top-vdev, the metaslab being
|
|
* rebuilt, range tree containing the allocated extents and the on-disk state.
|
|
*/
|
|
typedef struct vdev_rebuild {
|
|
vdev_t *vr_top_vdev; /* top-level vdev to rebuild */
|
|
metaslab_t *vr_scan_msp; /* scanning disabled metaslab */
|
|
/* scan ranges (in metaslab) */
|
|
zfs_range_tree_t *vr_scan_tree;
|
|
kmutex_t vr_io_lock; /* inflight IO lock */
|
|
kcondvar_t vr_io_cv; /* inflight IO cv */
|
|
|
|
/* In-core state and progress */
|
|
uint64_t vr_scan_offset[TXG_SIZE];
|
|
uint64_t vr_prev_scan_time_ms; /* any previous scan time */
|
|
uint64_t vr_bytes_inflight_max; /* maximum bytes inflight */
|
|
uint64_t vr_bytes_inflight; /* current bytes inflight */
|
|
|
|
/* Per-rebuild pass statistics for calculating bandwidth */
|
|
uint64_t vr_pass_start_time;
|
|
uint64_t vr_pass_bytes_scanned;
|
|
uint64_t vr_pass_bytes_issued;
|
|
uint64_t vr_pass_bytes_skipped;
|
|
|
|
/* On-disk state updated by vdev_rebuild_zap_update_sync() */
|
|
vdev_rebuild_phys_t vr_rebuild_phys;
|
|
} vdev_rebuild_t;
|
|
|
|
boolean_t vdev_rebuild_active(vdev_t *);
|
|
|
|
int vdev_rebuild_load(vdev_t *);
|
|
void vdev_rebuild(vdev_t *, uint64_t);
|
|
void vdev_rebuild_stop_wait(vdev_t *);
|
|
void vdev_rebuild_stop_all(spa_t *);
|
|
void vdev_rebuild_restart(spa_t *);
|
|
void vdev_rebuild_clear_sync(void *, dmu_tx_t *);
|
|
int vdev_rebuild_get_stats(vdev_t *, vdev_rebuild_stat_t *);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_VDEV_REBUILD_H */
|