mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-11-17 10:01:01 +03:00
53dce5acc6
If the zfs_remove_max_segment tunable is changed to be not a multiple of
the sector size, then the device removal code will malfunction and try
to create mappings that are smaller than one sector, leading to a panic.
On debug bits this assertion will fail in spa_vdev_copy_segment():
ASSERT3U(DVA_GET_ASIZE(&dst), ==, size);
On nondebug, the system panics with a stack like:
metaslab_free_concrete()
metaslab_free_impl()
metaslab_free_impl_cb()
vdev_indirect_remap()
free_from_removing_vdev()
metaslab_free_impl()
metaslab_free_dva()
metaslab_free()
Fortunately, the default for zfs_remove_max_segment is 1MB, so this
can't occur by default. We hit it during this test because
removal_remap.ksh changes zfs_remove_max_segment to 1KB. When testing on
4KB-sector disks, we hit the bug.
This change makes the zfs_remove_max_segment tunable more robust,
automatically rounding it up to a multiple of the sector size. We also
turn some key assertions into VERIFY's so that similar bugs would be
caught before they are encoded on disk (and thus avoid a
panic-reboot-loop).
Reviewed-by: Sean Eric Fagan <sef@ixsystems.com>
Reviewed-by: Pavel Zakharov <pavel.zakharov@delphix.com>
Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com>
Reviewed-by: Sebastien Roy <sebastien.roy@delphix.com>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Signed-off-by: Matthew Ahrens <mahrens@delphix.com>
External-issue: DLPX-61342
Closes #8893
97 lines
2.6 KiB
C
97 lines
2.6 KiB
C
/*
|
|
* CDDL HEADER START
|
|
*
|
|
* This file and its contents are supplied under the terms of the
|
|
* Common Development and Distribution License ("CDDL"), version 1.0.
|
|
* You may only use this file in accordance with the terms of version
|
|
* 1.0 of the CDDL.
|
|
*
|
|
* A full copy of the text of the CDDL should have accompanied this
|
|
* source. A copy of the CDDL is also available via the Internet at
|
|
* http://www.illumos.org/license/CDDL.
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
|
|
/*
|
|
* Copyright (c) 2014, 2019 by Delphix. All rights reserved.
|
|
*/
|
|
|
|
#ifndef _SYS_VDEV_REMOVAL_H
|
|
#define _SYS_VDEV_REMOVAL_H
|
|
|
|
#include <sys/spa.h>
|
|
#include <sys/bpobj.h>
|
|
#include <sys/vdev_indirect_mapping.h>
|
|
#include <sys/vdev_indirect_births.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
typedef struct spa_vdev_removal {
|
|
uint64_t svr_vdev_id;
|
|
uint64_t svr_max_offset_to_sync[TXG_SIZE];
|
|
/* Thread performing a vdev removal. */
|
|
kthread_t *svr_thread;
|
|
/* Segments left to copy from the current metaslab. */
|
|
range_tree_t *svr_allocd_segs;
|
|
kmutex_t svr_lock;
|
|
kcondvar_t svr_cv;
|
|
boolean_t svr_thread_exit;
|
|
|
|
/*
|
|
* New mappings to write out each txg.
|
|
*/
|
|
list_t svr_new_segments[TXG_SIZE];
|
|
|
|
/*
|
|
* Ranges that were freed while a mapping was in flight. This is
|
|
* a subset of the ranges covered by vdev_im_new_segments.
|
|
*/
|
|
range_tree_t *svr_frees[TXG_SIZE];
|
|
|
|
/*
|
|
* Number of bytes which we have finished our work for
|
|
* in each txg. This could be data copied (which will be part of
|
|
* the mappings in vdev_im_new_segments), or data freed before
|
|
* we got around to copying it.
|
|
*/
|
|
uint64_t svr_bytes_done[TXG_SIZE];
|
|
|
|
/* List of leaf zap objects to be unlinked */
|
|
nvlist_t *svr_zaplist;
|
|
} spa_vdev_removal_t;
|
|
|
|
typedef struct spa_condensing_indirect {
|
|
/*
|
|
* New mappings to write out each txg.
|
|
*/
|
|
list_t sci_new_mapping_entries[TXG_SIZE];
|
|
|
|
vdev_indirect_mapping_t *sci_new_mapping;
|
|
} spa_condensing_indirect_t;
|
|
|
|
extern int spa_remove_init(spa_t *);
|
|
extern void spa_restart_removal(spa_t *);
|
|
extern int spa_condense_init(spa_t *);
|
|
extern void spa_condense_fini(spa_t *);
|
|
extern void spa_start_indirect_condensing_thread(spa_t *);
|
|
extern void spa_vdev_condense_suspend(spa_t *);
|
|
extern int spa_vdev_remove(spa_t *, uint64_t, boolean_t);
|
|
extern void free_from_removing_vdev(vdev_t *, uint64_t, uint64_t);
|
|
extern int spa_removal_get_stats(spa_t *, pool_removal_stat_t *);
|
|
extern void svr_sync(spa_t *, dmu_tx_t *);
|
|
extern void spa_vdev_remove_suspend(spa_t *);
|
|
extern int spa_vdev_remove_cancel(spa_t *);
|
|
extern void spa_vdev_removal_destroy(spa_vdev_removal_t *);
|
|
extern uint64_t spa_remove_max_segment(spa_t *);
|
|
|
|
extern int vdev_removal_max_span;
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_VDEV_REMOVAL_H */
|