mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2025-01-14 04:00:31 +03:00
3d31aad83e
Instead of choosing a leaf vdev quasi-randomly, by starting at the root
vdev and randomly choosing children, rotate over leaves to issue MMP
writes. This fixes an issue in a pool whose top-level vdevs have
different numbers of leaves.
The issue is that the frequency at which individual leaves are chosen
for MMP writes is based not on the total number of leaves but based on
how many siblings the leaves have.
For example, in a pool like this:
root-vdev
+------+---------------+
vdev1 vdev2
| |
| +------+-----+-----+----+
disk1 disk2 disk3 disk4 disk5 disk6
vdev1 and vdev2 will each be chosen 50% of the time. Every time vdev1
is chosen, disk1 will be chosen. However, every time vdev2 is chosen,
disk2 is chosen 20% of the time. As a result, disk1 will be sent 5x as
many MMP writes as disk2.
This may create wear issues in the case of SSDs. It also reduces the
effectiveness of MMP as it depends on the writes being evenly
distributed for the case where some devices fail or are partitioned.
The new code maintains a list of leaf vdevs in the pool. MMP records
the last leaf used for an MMP write in mmp->mmp_last_leaf. To choose
the next leaf, MMP starts at mmp->mmp_last_leaf and traverses the list,
continuing from the head if the tail is reached. It stops when a
suitable leaf is found or all leaves have been examined.
Added a test to verify MMP write distribution is even.
Reviewed-by: Tom Caputi <tcaputi@datto.com>
Reviewed-by: Kash Pande <kash@tripleback.net>
Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: loli10K <ezomori.nozomu@gmail.com>
Signed-off-by: Olaf Faaland <faaland1@llnl.gov>
Closes #7953
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 10
|
|
#define MMP_DEFAULT_FAIL_INTERVALS 5
|
|
|
|
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 */
|