mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2025-02-05 06:43:31 +03:00
db2af93d72
By default, when multihost is enabled for a pool, the pool is suspended if (zfs_multihost_fail_intervals*zfs_multihost_interval) ms pass without a successful MMP write. This is the recommended configuration. The default value for zfs_multihost_fail_intervals has been 5, and the default value for zfs_multihost_interval has been 1000, so pool suspension occurred at 5 seconds. There have been multiple cases where a single misbehaving device in a pool triggered a SCSI reset, and all I/O paused for 5-6 seconds. This in turn caused MMP to suspend the pool. In the cases observed, the rest of the devices were healthy and the pool was otherwise correctly performing I/O. The reset was handled correctly by ZFS, and by suspending the pool MMP made replacing the device more difficult as well as forcing the host to be rebooted. Increase the default value of zfs_multihost_fail_intervals to 10, so that MMP tolerates up to 10 seconds of failed MMP writes before suspending the pool. Increase the default value of zfs_multihost_import_intervals to 20, to maintain the 2:1 safety factor. This results in a force import taking approximately 20 seconds when MMP is enabled, with default values. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Andreas Dilger <andreas.dilger@whamcloud.com> Reviewed-by: George Melikov <mail@gmelikov.ru> Signed-off-by: Olaf Faaland <faaland1@llnl.gov> Closes #7709 Closes #8495
69 lines
2.0 KiB
C
69 lines
2.0 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) 2017 by Lawrence Livermore National Security, LLC.
|
|
*/
|
|
|
|
#ifndef _SYS_MMP_H
|
|
#define _SYS_MMP_H
|
|
|
|
#include <sys/spa.h>
|
|
#include <sys/zfs_context.h>
|
|
#include <sys/uberblock_impl.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define MMP_MIN_INTERVAL 100 /* ms */
|
|
#define MMP_DEFAULT_INTERVAL 1000 /* ms */
|
|
#define MMP_DEFAULT_IMPORT_INTERVALS 20
|
|
#define MMP_DEFAULT_FAIL_INTERVALS 10
|
|
|
|
typedef struct mmp_thread {
|
|
kmutex_t mmp_thread_lock; /* protect thread mgmt fields */
|
|
kcondvar_t mmp_thread_cv;
|
|
kthread_t *mmp_thread;
|
|
uint8_t mmp_thread_exiting;
|
|
kmutex_t mmp_io_lock; /* protect below */
|
|
hrtime_t mmp_last_write; /* last successful MMP write */
|
|
uint64_t mmp_delay; /* decaying avg ns between MMP writes */
|
|
uberblock_t mmp_ub; /* last ub written by sync */
|
|
zio_t *mmp_zio_root; /* root of mmp write zios */
|
|
uint64_t mmp_kstat_id; /* unique id for next MMP write kstat */
|
|
int mmp_skip_error; /* reason for last skipped write */
|
|
vdev_t *mmp_last_leaf; /* last mmp write sent here */
|
|
uint64_t mmp_leaf_last_gen; /* last mmp write sent here */
|
|
} mmp_thread_t;
|
|
|
|
|
|
extern void mmp_init(struct spa *spa);
|
|
extern void mmp_fini(struct spa *spa);
|
|
extern void mmp_thread_start(struct spa *spa);
|
|
extern void mmp_thread_stop(struct spa *spa);
|
|
extern void mmp_update_uberblock(struct spa *spa, struct uberblock *ub);
|
|
extern void mmp_signal_all_threads(void);
|
|
|
|
/* Global tuning */
|
|
extern ulong_t zfs_multihost_interval;
|
|
extern uint_t zfs_multihost_fail_intervals;
|
|
extern uint_t zfs_multihost_import_intervals;
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_MMP_H */
|