mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-27 11:29:36 +03:00
f09fda5071
On systems with large amounts of storage and high fragmentation, a huge amount of space can be used by storing metaslab range trees. Since metaslabs are only unloaded during a txg sync, and only if they have been inactive for 8 txgs, it is possible to get into a state where all of the system's memory is consumed by range trees and metaslabs, and txgs cannot sync. While ZFS knows how to evict ARC data when needed, it has no such mechanism for range tree data. This can result in boot hangs for some system configurations. First, we add the ability to unload metaslabs outside of syncing context. Second, we store a multilist of all loaded metaslabs, sorted by their selection txg, so we can quickly identify the oldest metaslabs. We use a multilist to reduce lock contention during heavy write workloads. Finally, we add logic that will unload a metaslab when we're loading a new metaslab, if we're using more than a certain fraction of the available memory on range trees. Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: George Wilson <gwilson@delphix.com> Reviewed-by: Sebastien Roy <sebastien.roy@delphix.com> Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Paul Dagnelie <pcd@delphix.com> Closes #9128
145 lines
5.3 KiB
C
145 lines
5.3 KiB
C
/*
|
|
* 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 http://www.opensolaris.org/os/licensing.
|
|
* 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) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
|
|
* Copyright (c) 2011, 2018 by Delphix. All rights reserved.
|
|
* Copyright (c) 2017, Intel Corporation.
|
|
*/
|
|
|
|
#ifndef _SYS_METASLAB_H
|
|
#define _SYS_METASLAB_H
|
|
|
|
#include <sys/spa.h>
|
|
#include <sys/space_map.h>
|
|
#include <sys/txg.h>
|
|
#include <sys/zio.h>
|
|
#include <sys/avl.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
|
|
typedef struct metaslab_ops {
|
|
uint64_t (*msop_alloc)(metaslab_t *, uint64_t);
|
|
} metaslab_ops_t;
|
|
|
|
|
|
extern metaslab_ops_t *zfs_metaslab_ops;
|
|
|
|
int metaslab_init(metaslab_group_t *, uint64_t, uint64_t, uint64_t,
|
|
metaslab_t **);
|
|
void metaslab_fini(metaslab_t *);
|
|
|
|
void metaslab_set_unflushed_txg(metaslab_t *, uint64_t, dmu_tx_t *);
|
|
void metaslab_set_estimated_condensed_size(metaslab_t *, uint64_t, dmu_tx_t *);
|
|
uint64_t metaslab_unflushed_txg(metaslab_t *);
|
|
uint64_t metaslab_estimated_condensed_size(metaslab_t *);
|
|
int metaslab_sort_by_flushed(const void *, const void *);
|
|
uint64_t metaslab_unflushed_changes_memused(metaslab_t *);
|
|
|
|
int metaslab_load(metaslab_t *);
|
|
void metaslab_unload(metaslab_t *);
|
|
boolean_t metaslab_flush(metaslab_t *, dmu_tx_t *);
|
|
|
|
uint64_t metaslab_allocated_space(metaslab_t *);
|
|
|
|
void metaslab_sync(metaslab_t *, uint64_t);
|
|
void metaslab_sync_done(metaslab_t *, uint64_t);
|
|
void metaslab_sync_reassess(metaslab_group_t *);
|
|
uint64_t metaslab_largest_allocatable(metaslab_t *);
|
|
|
|
/*
|
|
* metaslab alloc flags
|
|
*/
|
|
#define METASLAB_HINTBP_FAVOR 0x0
|
|
#define METASLAB_HINTBP_AVOID 0x1
|
|
#define METASLAB_GANG_HEADER 0x2
|
|
#define METASLAB_GANG_CHILD 0x4
|
|
#define METASLAB_ASYNC_ALLOC 0x8
|
|
#define METASLAB_DONT_THROTTLE 0x10
|
|
#define METASLAB_MUST_RESERVE 0x20
|
|
#define METASLAB_FASTWRITE 0x40
|
|
|
|
int metaslab_alloc(spa_t *, metaslab_class_t *, uint64_t,
|
|
blkptr_t *, int, uint64_t, blkptr_t *, int, zio_alloc_list_t *, zio_t *,
|
|
int);
|
|
int metaslab_alloc_dva(spa_t *, metaslab_class_t *, uint64_t,
|
|
dva_t *, int, dva_t *, uint64_t, int, zio_alloc_list_t *, int);
|
|
void metaslab_free(spa_t *, const blkptr_t *, uint64_t, boolean_t);
|
|
void metaslab_free_concrete(vdev_t *, uint64_t, uint64_t, boolean_t);
|
|
void metaslab_free_dva(spa_t *, const dva_t *, boolean_t);
|
|
void metaslab_free_impl_cb(uint64_t, vdev_t *, uint64_t, uint64_t, void *);
|
|
void metaslab_unalloc_dva(spa_t *, const dva_t *, uint64_t);
|
|
int metaslab_claim(spa_t *, const blkptr_t *, uint64_t);
|
|
int metaslab_claim_impl(vdev_t *, uint64_t, uint64_t, uint64_t);
|
|
void metaslab_check_free(spa_t *, const blkptr_t *);
|
|
void metaslab_fastwrite_mark(spa_t *, const blkptr_t *);
|
|
void metaslab_fastwrite_unmark(spa_t *, const blkptr_t *);
|
|
|
|
void metaslab_alloc_trace_init(void);
|
|
void metaslab_alloc_trace_fini(void);
|
|
void metaslab_trace_init(zio_alloc_list_t *);
|
|
void metaslab_trace_fini(zio_alloc_list_t *);
|
|
|
|
metaslab_class_t *metaslab_class_create(spa_t *, metaslab_ops_t *);
|
|
void metaslab_class_destroy(metaslab_class_t *);
|
|
int metaslab_class_validate(metaslab_class_t *);
|
|
void metaslab_class_histogram_verify(metaslab_class_t *);
|
|
uint64_t metaslab_class_fragmentation(metaslab_class_t *);
|
|
uint64_t metaslab_class_expandable_space(metaslab_class_t *);
|
|
boolean_t metaslab_class_throttle_reserve(metaslab_class_t *, int, int,
|
|
zio_t *, int);
|
|
void metaslab_class_throttle_unreserve(metaslab_class_t *, int, int, zio_t *);
|
|
void metaslab_class_evict_old(metaslab_class_t *, uint64_t);
|
|
uint64_t metaslab_class_get_alloc(metaslab_class_t *);
|
|
uint64_t metaslab_class_get_space(metaslab_class_t *);
|
|
uint64_t metaslab_class_get_dspace(metaslab_class_t *);
|
|
uint64_t metaslab_class_get_deferred(metaslab_class_t *);
|
|
|
|
void metaslab_space_update(vdev_t *, metaslab_class_t *,
|
|
int64_t, int64_t, int64_t);
|
|
|
|
metaslab_group_t *metaslab_group_create(metaslab_class_t *, vdev_t *, int);
|
|
void metaslab_group_destroy(metaslab_group_t *);
|
|
void metaslab_group_activate(metaslab_group_t *);
|
|
void metaslab_group_passivate(metaslab_group_t *);
|
|
boolean_t metaslab_group_initialized(metaslab_group_t *);
|
|
uint64_t metaslab_group_get_space(metaslab_group_t *);
|
|
void metaslab_group_histogram_verify(metaslab_group_t *);
|
|
uint64_t metaslab_group_fragmentation(metaslab_group_t *);
|
|
void metaslab_group_histogram_remove(metaslab_group_t *, metaslab_t *);
|
|
void metaslab_group_alloc_decrement(spa_t *, uint64_t, void *, int, int,
|
|
boolean_t);
|
|
void metaslab_group_alloc_verify(spa_t *, const blkptr_t *, void *, int);
|
|
void metaslab_recalculate_weight_and_sort(metaslab_t *);
|
|
void metaslab_disable(metaslab_t *);
|
|
void metaslab_enable(metaslab_t *, boolean_t, boolean_t);
|
|
void metaslab_set_selected_txg(metaslab_t *, uint64_t);
|
|
|
|
extern int metaslab_debug_load;
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_METASLAB_H */
|