mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-27 19:39:35 +03:00
d4a72f2386
Currently, scrubs and resilvers can take an extremely long time to complete. This is largely due to the fact that zfs scans process pools in logical order, as determined by each block's bookmark. This makes sense from a simplicity perspective, but blocks in zfs are often scattered randomly across disks, particularly due to zfs's copy-on-write mechanisms. This patch improves performance by splitting scrubs and resilvers into a metadata scanning phase and an IO issuing phase. The metadata scan reads through the structure of the pool and gathers an in-memory queue of I/Os, sorted by size and offset on disk. The issuing phase will then issue the scrub I/Os as sequentially as possible, greatly improving performance. This patch also updates and cleans up some of the scan code which has not been updated in several years. Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Authored-by: Saso Kiselkov <saso.kiselkov@nexenta.com> Authored-by: Alek Pinchuk <apinchuk@datto.com> Authored-by: Tom Caputi <tcaputi@datto.com> Signed-off-by: Tom Caputi <tcaputi@datto.com> Closes #3625 Closes #6256
121 lines
4.3 KiB
C
121 lines
4.3 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 2009 Sun Microsystems, Inc. All rights reserved.
|
|
* Use is subject to license terms.
|
|
*/
|
|
|
|
/*
|
|
* Copyright (c) 2013, 2014 by Delphix. All rights reserved.
|
|
*/
|
|
|
|
#ifndef _SYS_RANGE_TREE_H
|
|
#define _SYS_RANGE_TREE_H
|
|
|
|
#include <sys/avl.h>
|
|
#include <sys/dmu.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define RANGE_TREE_HISTOGRAM_SIZE 64
|
|
|
|
typedef struct range_tree_ops range_tree_ops_t;
|
|
|
|
typedef struct range_tree {
|
|
avl_tree_t rt_root; /* offset-ordered segment AVL tree */
|
|
uint64_t rt_space; /* sum of all segments in the map */
|
|
uint64_t rt_gap; /* allowable inter-segment gap */
|
|
range_tree_ops_t *rt_ops;
|
|
|
|
/* rt_avl_compare should only be set if rt_arg is an AVL tree */
|
|
void *rt_arg;
|
|
int (*rt_avl_compare)(const void *, const void *);
|
|
|
|
|
|
/*
|
|
* The rt_histogram maintains a histogram of ranges. Each bucket,
|
|
* rt_histogram[i], contains the number of ranges whose size is:
|
|
* 2^i <= size of range in bytes < 2^(i+1)
|
|
*/
|
|
uint64_t rt_histogram[RANGE_TREE_HISTOGRAM_SIZE];
|
|
kmutex_t *rt_lock; /* pointer to lock that protects map */
|
|
} range_tree_t;
|
|
|
|
typedef struct range_seg {
|
|
avl_node_t rs_node; /* AVL node */
|
|
avl_node_t rs_pp_node; /* AVL picker-private node */
|
|
uint64_t rs_start; /* starting offset of this segment */
|
|
uint64_t rs_end; /* ending offset (non-inclusive) */
|
|
uint64_t rs_fill; /* actual fill if gap mode is on */
|
|
} range_seg_t;
|
|
|
|
struct range_tree_ops {
|
|
void (*rtop_create)(range_tree_t *rt, void *arg);
|
|
void (*rtop_destroy)(range_tree_t *rt, void *arg);
|
|
void (*rtop_add)(range_tree_t *rt, range_seg_t *rs, void *arg);
|
|
void (*rtop_remove)(range_tree_t *rt, range_seg_t *rs, void *arg);
|
|
void (*rtop_vacate)(range_tree_t *rt, void *arg);
|
|
};
|
|
|
|
typedef void range_tree_func_t(void *arg, uint64_t start, uint64_t size);
|
|
|
|
void range_tree_init(void);
|
|
void range_tree_fini(void);
|
|
range_tree_t *range_tree_create_impl(range_tree_ops_t *ops, void *arg,
|
|
int (*avl_compare) (const void *, const void *), kmutex_t *lp,
|
|
uint64_t gap);
|
|
range_tree_t *range_tree_create(range_tree_ops_t *ops, void *arg, kmutex_t *lp);
|
|
void range_tree_destroy(range_tree_t *rt);
|
|
boolean_t range_tree_contains(range_tree_t *rt, uint64_t start, uint64_t size);
|
|
range_seg_t *range_tree_find(range_tree_t *rt, uint64_t start, uint64_t size);
|
|
void range_tree_resize_segment(range_tree_t *rt, range_seg_t *rs,
|
|
uint64_t newstart, uint64_t newsize);
|
|
uint64_t range_tree_space(range_tree_t *rt);
|
|
void range_tree_verify(range_tree_t *rt, uint64_t start, uint64_t size);
|
|
void range_tree_swap(range_tree_t **rtsrc, range_tree_t **rtdst);
|
|
void range_tree_stat_verify(range_tree_t *rt);
|
|
void range_tree_set_lock(range_tree_t *rt, kmutex_t *lp);
|
|
|
|
void range_tree_add(void *arg, uint64_t start, uint64_t size);
|
|
void range_tree_remove(void *arg, uint64_t start, uint64_t size);
|
|
void range_tree_remove_fill(range_tree_t *rt, uint64_t start, uint64_t size);
|
|
void range_tree_adjust_fill(range_tree_t *rt, range_seg_t *rs, int64_t delta);
|
|
void range_tree_clear(range_tree_t *rt, uint64_t start, uint64_t size);
|
|
|
|
void range_tree_vacate(range_tree_t *rt, range_tree_func_t *func, void *arg);
|
|
void range_tree_walk(range_tree_t *rt, range_tree_func_t *func, void *arg);
|
|
range_seg_t *range_tree_first(range_tree_t *rt);
|
|
|
|
void rt_avl_create(range_tree_t *rt, void *arg);
|
|
void rt_avl_destroy(range_tree_t *rt, void *arg);
|
|
void rt_avl_add(range_tree_t *rt, range_seg_t *rs, void *arg);
|
|
void rt_avl_remove(range_tree_t *rt, range_seg_t *rs, void *arg);
|
|
void rt_avl_vacate(range_tree_t *rt, void *arg);
|
|
extern struct range_tree_ops rt_avl_ops;
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_RANGE_TREE_H */
|