zfs/include/sys/zio.h

575 lines
17 KiB
C
Raw Normal View History

2008-11-20 20:01:55 +00:00
/*
* 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.
2008-11-20 20:01:55 +00:00
*/
/*
* Copyright 2011 Nexenta Systems, Inc. All rights reserved.
*/
2008-11-20 20:01:55 +00:00
#ifndef _ZIO_H
#define _ZIO_H
#include <sys/zfs_context.h>
#include <sys/spa.h>
#include <sys/txg.h>
#include <sys/avl.h>
#include <sys/fs/zfs.h>
#include <sys/zio_impl.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* Embedded checksum
*/
#define ZEC_MAGIC 0x210da7ab10c7a11ULL
2008-11-20 20:01:55 +00:00
typedef struct zio_eck {
uint64_t zec_magic; /* for validation, endianness */
zio_cksum_t zec_cksum; /* 256-bit checksum */
} zio_eck_t;
2008-11-20 20:01:55 +00:00
/*
* Gang block headers are self-checksumming and contain an array
* of block pointers.
*/
#define SPA_GANGBLOCKSIZE SPA_MINBLOCKSIZE
#define SPA_GBH_NBLKPTRS ((SPA_GANGBLOCKSIZE - \
sizeof (zio_eck_t)) / sizeof (blkptr_t))
2008-11-20 20:01:55 +00:00
#define SPA_GBH_FILLER ((SPA_GANGBLOCKSIZE - \
sizeof (zio_eck_t) - \
2008-11-20 20:01:55 +00:00
(SPA_GBH_NBLKPTRS * sizeof (blkptr_t))) /\
sizeof (uint64_t))
typedef struct zio_gbh {
blkptr_t zg_blkptr[SPA_GBH_NBLKPTRS];
uint64_t zg_filler[SPA_GBH_FILLER];
zio_eck_t zg_tail;
2008-11-20 20:01:55 +00:00
} zio_gbh_phys_t;
enum zio_checksum {
ZIO_CHECKSUM_INHERIT = 0,
ZIO_CHECKSUM_ON,
ZIO_CHECKSUM_OFF,
ZIO_CHECKSUM_LABEL,
ZIO_CHECKSUM_GANG_HEADER,
ZIO_CHECKSUM_ZILOG,
ZIO_CHECKSUM_FLETCHER_2,
ZIO_CHECKSUM_FLETCHER_4,
ZIO_CHECKSUM_SHA256,
ZIO_CHECKSUM_ZILOG2,
2008-11-20 20:01:55 +00:00
ZIO_CHECKSUM_FUNCTIONS
};
2009-07-02 22:44:48 +00:00
#define ZIO_CHECKSUM_ON_VALUE ZIO_CHECKSUM_FLETCHER_4
2008-11-20 20:01:55 +00:00
#define ZIO_CHECKSUM_DEFAULT ZIO_CHECKSUM_ON
#define ZIO_CHECKSUM_MASK 0xffULL
#define ZIO_CHECKSUM_VERIFY (1 << 8)
#define ZIO_DEDUPCHECKSUM ZIO_CHECKSUM_SHA256
#define ZIO_DEDUPDITTO_MIN 100
2008-11-20 20:01:55 +00:00
enum zio_compress {
ZIO_COMPRESS_INHERIT = 0,
ZIO_COMPRESS_ON,
ZIO_COMPRESS_OFF,
ZIO_COMPRESS_LZJB,
ZIO_COMPRESS_EMPTY,
ZIO_COMPRESS_GZIP_1,
ZIO_COMPRESS_GZIP_2,
ZIO_COMPRESS_GZIP_3,
ZIO_COMPRESS_GZIP_4,
ZIO_COMPRESS_GZIP_5,
ZIO_COMPRESS_GZIP_6,
ZIO_COMPRESS_GZIP_7,
ZIO_COMPRESS_GZIP_8,
ZIO_COMPRESS_GZIP_9,
ZIO_COMPRESS_ZLE,
2008-11-20 20:01:55 +00:00
ZIO_COMPRESS_FUNCTIONS
};
#define ZIO_COMPRESS_ON_VALUE ZIO_COMPRESS_LZJB
#define ZIO_COMPRESS_DEFAULT ZIO_COMPRESS_OFF
#define BOOTFS_COMPRESS_VALID(compress) \
((compress) == ZIO_COMPRESS_LZJB || \
((compress) == ZIO_COMPRESS_ON && \
ZIO_COMPRESS_ON_VALUE == ZIO_COMPRESS_LZJB) || \
(compress) == ZIO_COMPRESS_OFF)
/*
* Default Linux timeout for a sd device.
*/
#define ZIO_DELAY_MAX (30 * MILLISEC)
2008-11-20 20:01:55 +00:00
#define ZIO_FAILURE_MODE_WAIT 0
#define ZIO_FAILURE_MODE_CONTINUE 1
#define ZIO_FAILURE_MODE_PANIC 2
#define ZIO_PRIORITY_NOW (zio_priority_table[0])
#define ZIO_PRIORITY_SYNC_READ (zio_priority_table[1])
#define ZIO_PRIORITY_SYNC_WRITE (zio_priority_table[2])
#define ZIO_PRIORITY_LOG_WRITE (zio_priority_table[3])
#define ZIO_PRIORITY_CACHE_FILL (zio_priority_table[4])
#define ZIO_PRIORITY_AGG (zio_priority_table[5])
#define ZIO_PRIORITY_FREE (zio_priority_table[6])
#define ZIO_PRIORITY_ASYNC_WRITE (zio_priority_table[7])
#define ZIO_PRIORITY_ASYNC_READ (zio_priority_table[8])
#define ZIO_PRIORITY_RESILVER (zio_priority_table[9])
#define ZIO_PRIORITY_SCRUB (zio_priority_table[10])
#define ZIO_PRIORITY_DDT_PREFETCH (zio_priority_table[11])
#define ZIO_PRIORITY_TABLE_SIZE 12
2009-01-15 21:59:39 +00:00
2008-11-20 20:01:55 +00:00
#define ZIO_PIPELINE_CONTINUE 0x100
#define ZIO_PIPELINE_STOP 0x101
enum zio_flag {
/*
* Flags inherited by gang, ddt, and vdev children,
* and that must be equal for two zios to aggregate
*/
ZIO_FLAG_DONT_AGGREGATE = 1 << 0,
ZIO_FLAG_IO_REPAIR = 1 << 1,
ZIO_FLAG_SELF_HEAL = 1 << 2,
ZIO_FLAG_RESILVER = 1 << 3,
ZIO_FLAG_SCRUB = 1 << 4,
ZIO_FLAG_SCAN_THREAD = 1 << 5,
#define ZIO_FLAG_AGG_INHERIT (ZIO_FLAG_CANFAIL - 1)
/*
* Flags inherited by ddt, gang, and vdev children.
*/
ZIO_FLAG_CANFAIL = 1 << 6, /* must be first for INHERIT */
ZIO_FLAG_SPECULATIVE = 1 << 7,
ZIO_FLAG_CONFIG_WRITER = 1 << 8,
ZIO_FLAG_DONT_RETRY = 1 << 9,
ZIO_FLAG_DONT_CACHE = 1 << 10,
ZIO_FLAG_NODATA = 1 << 11,
ZIO_FLAG_INDUCE_DAMAGE = 1 << 12,
#define ZIO_FLAG_DDT_INHERIT (ZIO_FLAG_IO_RETRY - 1)
#define ZIO_FLAG_GANG_INHERIT (ZIO_FLAG_IO_RETRY - 1)
/*
* Flags inherited by vdev children.
*/
ZIO_FLAG_IO_RETRY = 1 << 13, /* must be first for INHERIT */
ZIO_FLAG_PROBE = 1 << 14,
ZIO_FLAG_TRYHARD = 1 << 15,
ZIO_FLAG_OPTIONAL = 1 << 16,
#define ZIO_FLAG_VDEV_INHERIT (ZIO_FLAG_DONT_QUEUE - 1)
/*
* Flags not inherited by any children.
*/
ZIO_FLAG_DONT_QUEUE = 1 << 17, /* must be first for INHERIT */
ZIO_FLAG_DONT_PROPAGATE = 1 << 18,
ZIO_FLAG_IO_BYPASS = 1 << 19,
ZIO_FLAG_IO_REWRITE = 1 << 20,
ZIO_FLAG_RAW = 1 << 21,
ZIO_FLAG_GANG_CHILD = 1 << 22,
ZIO_FLAG_DDT_CHILD = 1 << 23,
Add FASTWRITE algorithm for synchronous writes. Currently, ZIL blocks are spread over vdevs using hint block pointers managed by the ZIL commit code and passed to metaslab_alloc(). Spreading log blocks accross vdevs is important for performance: indeed, using mutliple disks in parallel decreases the ZIL commit latency, which is the main performance metric for synchronous writes. However, the current implementation suffers from the following issues: 1) It would be best if the ZIL module was not aware of such low-level details. They should be handled by the ZIO and metaslab modules; 2) Because the hint block pointer is managed per log, simultaneous commits from multiple logs might use the same vdevs at the same time, which is inefficient; 3) Because dmu_write() does not honor the block pointer hint, indirect writes are not spread. The naive solution of rotating the metaslab rotor each time a block is allocated for the ZIL or dmu_sync() doesn't work in practice because the first ZIL block to be written is actually allocated during the previous commit. Consequently, when metaslab_alloc() decides the vdev for this block, it will do so while a bunch of other allocations are happening at the same time (from dmu_sync() and other ZILs). This means the vdev for this block is chosen more or less at random. When the next commit happens, there is a high chance (especially when the number of blocks per commit is slightly less than the number of the disks) that one disk will have to write two blocks (with a potential seek) while other disks are sitting idle, which defeats spreading and increases the commit latency. This commit introduces a new concept in the metaslab allocator: fastwrites. Basically, each top-level vdev maintains a counter indicating the number of synchronous writes (from dmu_sync() and the ZIL) which have been allocated but not yet completed. When the metaslab is called with the FASTWRITE flag, it will choose the vdev with the least amount of pending synchronous writes. If there are multiple vdevs with the same value, the first matching vdev (starting from the rotor) is used. Once metaslab_alloc() has decided which vdev the block is allocated to, it updates the fastwrite counter for this vdev. The rationale goes like this: when an allocation is done with FASTWRITE, it "reserves" the vdev until the data is written. Until then, all future allocations will naturally avoid this vdev, even after a full rotation of the rotor. As a result, pending synchronous writes at a given point in time will be nicely spread over all vdevs. This contrasts with the previous algorithm, which is based on the implicit assumption that blocks are written instantaneously after they're allocated. metaslab_fastwrite_mark() and metaslab_fastwrite_unmark() are used to manually increase or decrease fastwrite counters, respectively. They should be used with caution, as there is no per-BP tracking of fastwrite information, so leaks and "double-unmarks" are possible. There is, however, an assert in the vdev teardown code which will fire if the fastwrite counters are not zero when the pool is exported or the vdev removed. Note that as stated above, marking is also done implictly by metaslab_alloc(). ZIO also got a new FASTWRITE flag; when it is used, ZIO will pass it to the metaslab when allocating (assuming ZIO does the allocation, which is only true in the case of dmu_sync). This flag will also trigger an unmark when zio_done() fires. A side-effect of the new algorithm is that when a ZIL stops being used, its last block can stay in the pending state (allocated but not yet written) for a long time, polluting the fastwrite counters. To avoid that, I've implemented a somewhat crude but working solution which unmarks these pending blocks in zil_sync(), thus guaranteeing that linguering fastwrites will get pruned at each sync event. The best performance improvements are observed with pools using a large number of top-level vdevs and heavy synchronous write workflows (especially indirect writes and concurrent writes from multiple ZILs). Real-life testing shows a 200% to 300% performance increase with indirect writes and various commit sizes. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Issue #1013
2012-06-27 13:20:20 +00:00
ZIO_FLAG_GODFATHER = 1 << 24,
ZIO_FLAG_FASTWRITE = 1 << 25
};
#define ZIO_FLAG_MUSTSUCCEED 0
#define ZIO_DDT_CHILD_FLAGS(zio) \
(((zio)->io_flags & ZIO_FLAG_DDT_INHERIT) | \
ZIO_FLAG_DDT_CHILD | ZIO_FLAG_CANFAIL)
#define ZIO_GANG_CHILD_FLAGS(zio) \
(((zio)->io_flags & ZIO_FLAG_GANG_INHERIT) | \
ZIO_FLAG_GANG_CHILD | ZIO_FLAG_CANFAIL)
#define ZIO_VDEV_CHILD_FLAGS(zio) \
(((zio)->io_flags & ZIO_FLAG_VDEV_INHERIT) | \
ZIO_FLAG_CANFAIL)
enum zio_child {
ZIO_CHILD_VDEV = 0,
ZIO_CHILD_GANG,
ZIO_CHILD_DDT,
ZIO_CHILD_LOGICAL,
ZIO_CHILD_TYPES
};
enum zio_wait_type {
ZIO_WAIT_READY = 0,
ZIO_WAIT_DONE,
ZIO_WAIT_TYPES
};
2008-11-20 20:01:55 +00:00
/*
* We'll take the unused errnos, 'EBADE' and 'EBADR' (from the Convergent
* graveyard) to indicate checksum errors and fragmentation.
*/
#define ECKSUM EBADE
#define EFRAGS EBADR
typedef void zio_done_func_t(zio_t *zio);
extern uint8_t zio_priority_table[ZIO_PRIORITY_TABLE_SIZE];
extern char *zio_type_name[ZIO_TYPES];
/*
* A bookmark is a four-tuple <objset, object, level, blkid> that uniquely
* identifies any block in the pool. By convention, the meta-objset (MOS)
* is objset 0, and the meta-dnode is object 0. This covers all blocks
* except root blocks and ZIL blocks, which are defined as follows:
2008-11-20 20:01:55 +00:00
*
* Root blocks (objset_phys_t) are object 0, level -1: <objset, 0, -1, 0>.
* ZIL blocks are bookmarked <objset, 0, -2, blkid == ZIL sequence number>.
* dmu_sync()ed ZIL data blocks are bookmarked <objset, object, -2, blkid>.
2008-11-20 20:01:55 +00:00
*
* Note: this structure is called a bookmark because its original purpose
* was to remember where to resume a pool-wide traverse.
2008-11-20 20:01:55 +00:00
*
* Note: this structure is passed between userland and the kernel.
* Therefore it must not change size or alignment between 32/64 bit
* compilation options.
*/
typedef struct zbookmark {
uint64_t zb_objset;
uint64_t zb_object;
int64_t zb_level;
uint64_t zb_blkid;
} zbookmark_t;
#define SET_BOOKMARK(zb, objset, object, level, blkid) \
{ \
(zb)->zb_objset = objset; \
(zb)->zb_object = object; \
(zb)->zb_level = level; \
(zb)->zb_blkid = blkid; \
}
#define ZB_DESTROYED_OBJSET (-1ULL)
#define ZB_ROOT_OBJECT (0ULL)
#define ZB_ROOT_LEVEL (-1LL)
#define ZB_ROOT_BLKID (0ULL)
#define ZB_ZIL_OBJECT (0ULL)
#define ZB_ZIL_LEVEL (-2LL)
typedef struct zio_prop {
enum zio_checksum zp_checksum;
enum zio_compress zp_compress;
dmu_object_type_t zp_type;
uint8_t zp_level;
uint8_t zp_copies;
uint8_t zp_dedup;
uint8_t zp_dedup_verify;
} zio_prop_t;
typedef struct zio_cksum_report zio_cksum_report_t;
typedef void zio_cksum_finish_f(zio_cksum_report_t *rep,
const void *good_data);
typedef void zio_cksum_free_f(void *cbdata, size_t size);
struct zio_bad_cksum; /* defined in zio_checksum.h */
struct zio_cksum_report {
struct zio_cksum_report *zcr_next;
nvlist_t *zcr_ereport;
nvlist_t *zcr_detector;
void *zcr_cbdata;
size_t zcr_cbinfo; /* passed to zcr_free() */
uint64_t zcr_align;
uint64_t zcr_length;
zio_cksum_finish_f *zcr_finish;
zio_cksum_free_f *zcr_free;
/* internal use only */
struct zio_bad_cksum *zcr_ckinfo; /* information from failure */
};
typedef void zio_vsd_cksum_report_f(zio_t *zio, zio_cksum_report_t *zcr,
void *arg);
zio_vsd_cksum_report_f zio_vsd_default_cksum_report;
typedef struct zio_vsd_ops {
zio_done_func_t *vsd_free;
zio_vsd_cksum_report_f *vsd_cksum_report;
} zio_vsd_ops_t;
typedef struct zio_gang_node {
zio_gbh_phys_t *gn_gbh;
struct zio_gang_node *gn_child[SPA_GBH_NBLKPTRS];
} zio_gang_node_t;
typedef zio_t *zio_gang_issue_func_t(zio_t *zio, blkptr_t *bp,
zio_gang_node_t *gn, void *data);
typedef void zio_transform_func_t(zio_t *zio, void *data, uint64_t size);
typedef struct zio_transform {
void *zt_orig_data;
uint64_t zt_orig_size;
uint64_t zt_bufsize;
zio_transform_func_t *zt_transform;
struct zio_transform *zt_next;
} zio_transform_t;
typedef int zio_pipe_stage_t(zio_t *zio);
/*
* The io_reexecute flags are distinct from io_flags because the child must
* be able to propagate them to the parent. The normal io_flags are local
* to the zio, not protected by any lock, and not modifiable by children;
* the reexecute flags are protected by io_lock, modifiable by children,
* and always propagated -- even when ZIO_FLAG_DONT_PROPAGATE is set.
*/
#define ZIO_REEXECUTE_NOW 0x01
#define ZIO_REEXECUTE_SUSPEND 0x02
2009-02-18 20:51:31 +00:00
typedef struct zio_link {
zio_t *zl_parent;
zio_t *zl_child;
list_node_t zl_parent_node;
list_node_t zl_child_node;
} zio_link_t;
2008-11-20 20:01:55 +00:00
struct zio {
/* Core information about this I/O */
zbookmark_t io_bookmark;
zio_prop_t io_prop;
zio_type_t io_type;
enum zio_child io_child_type;
int io_cmd;
uint8_t io_priority;
uint8_t io_reexecute;
2009-02-18 20:51:31 +00:00
uint8_t io_state[ZIO_WAIT_TYPES];
2008-11-20 20:01:55 +00:00
uint64_t io_txg;
spa_t *io_spa;
2008-11-20 20:01:55 +00:00
blkptr_t *io_bp;
blkptr_t *io_bp_override;
2008-11-20 20:01:55 +00:00
blkptr_t io_bp_copy;
2009-02-18 20:51:31 +00:00
list_t io_parent_list;
list_t io_child_list;
zio_link_t *io_walk_link;
2008-11-20 20:01:55 +00:00
zio_t *io_logical;
zio_transform_t *io_transform_stack;
2008-11-20 20:01:55 +00:00
/* Callback info */
zio_done_func_t *io_ready;
zio_done_func_t *io_done;
void *io_private;
int64_t io_prev_space_delta; /* DMU private */
2008-11-20 20:01:55 +00:00
blkptr_t io_bp_orig;
/* Data represented by this I/O */
void *io_data;
void *io_orig_data;
2008-11-20 20:01:55 +00:00
uint64_t io_size;
uint64_t io_orig_size;
2008-11-20 20:01:55 +00:00
/* Stuff for the vdev stack */
vdev_t *io_vd;
void *io_vsd;
const zio_vsd_ops_t *io_vsd_ops;
2008-11-20 20:01:55 +00:00
uint64_t io_offset;
uint64_t io_deadline;
avl_node_t io_offset_node;
avl_node_t io_deadline_node;
avl_tree_t *io_vdev_tree;
/* Internal pipeline state */
enum zio_flag io_flags;
enum zio_stage io_stage;
enum zio_stage io_pipeline;
enum zio_flag io_orig_flags;
enum zio_stage io_orig_stage;
enum zio_stage io_orig_pipeline;
uint64_t io_delay;
int io_error;
int io_child_error[ZIO_CHILD_TYPES];
uint64_t io_children[ZIO_CHILD_TYPES][ZIO_WAIT_TYPES];
uint64_t io_child_count;
uint64_t io_parent_count;
uint64_t *io_stall;
2009-07-02 22:44:48 +00:00
zio_t *io_gang_leader;
zio_gang_node_t *io_gang_tree;
void *io_executor;
2008-11-20 20:01:55 +00:00
void *io_waiter;
kmutex_t io_lock;
kcondvar_t io_cv;
/* FMA state */
zio_cksum_report_t *io_cksum_report;
2008-11-20 20:01:55 +00:00
uint64_t io_ena;
/* Taskq dispatching state */
taskq_ent_t io_tqent;
2008-11-20 20:01:55 +00:00
};
2009-02-18 20:51:31 +00:00
extern zio_t *zio_null(zio_t *pio, spa_t *spa, vdev_t *vd,
zio_done_func_t *done, void *private, enum zio_flag flags);
2008-11-20 20:01:55 +00:00
extern zio_t *zio_root(spa_t *spa,
zio_done_func_t *done, void *private, enum zio_flag flags);
2008-11-20 20:01:55 +00:00
extern zio_t *zio_read(zio_t *pio, spa_t *spa, const blkptr_t *bp, void *data,
2008-11-20 20:01:55 +00:00
uint64_t size, zio_done_func_t *done, void *private,
int priority, enum zio_flag flags, const zbookmark_t *zb);
2008-11-20 20:01:55 +00:00
extern zio_t *zio_write(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp,
void *data, uint64_t size, const zio_prop_t *zp,
zio_done_func_t *ready, zio_done_func_t *done, void *private,
int priority, enum zio_flag flags, const zbookmark_t *zb);
2008-11-20 20:01:55 +00:00
extern zio_t *zio_rewrite(zio_t *pio, spa_t *spa, uint64_t txg, blkptr_t *bp,
void *data, uint64_t size, zio_done_func_t *done, void *private,
int priority, enum zio_flag flags, zbookmark_t *zb);
extern void zio_write_override(zio_t *zio, blkptr_t *bp, int copies);
2008-11-20 20:01:55 +00:00
extern void zio_free(spa_t *spa, uint64_t txg, const blkptr_t *bp);
2008-11-20 20:01:55 +00:00
extern zio_t *zio_claim(zio_t *pio, spa_t *spa, uint64_t txg,
const blkptr_t *bp,
zio_done_func_t *done, void *private, enum zio_flag flags);
2008-11-20 20:01:55 +00:00
extern zio_t *zio_ioctl(zio_t *pio, spa_t *spa, vdev_t *vd, int cmd,
zio_done_func_t *done, void *private, int priority, enum zio_flag flags);
2008-11-20 20:01:55 +00:00
extern zio_t *zio_read_phys(zio_t *pio, vdev_t *vd, uint64_t offset,
uint64_t size, void *data, int checksum,
zio_done_func_t *done, void *private, int priority, enum zio_flag flags,
2008-11-20 20:01:55 +00:00
boolean_t labels);
extern zio_t *zio_write_phys(zio_t *pio, vdev_t *vd, uint64_t offset,
uint64_t size, void *data, int checksum,
zio_done_func_t *done, void *private, int priority, enum zio_flag flags,
2008-11-20 20:01:55 +00:00
boolean_t labels);
extern zio_t *zio_free_sync(zio_t *pio, spa_t *spa, uint64_t txg,
const blkptr_t *bp, enum zio_flag flags);
extern int zio_alloc_zil(spa_t *spa, uint64_t txg, blkptr_t *new_bp,
Add FASTWRITE algorithm for synchronous writes. Currently, ZIL blocks are spread over vdevs using hint block pointers managed by the ZIL commit code and passed to metaslab_alloc(). Spreading log blocks accross vdevs is important for performance: indeed, using mutliple disks in parallel decreases the ZIL commit latency, which is the main performance metric for synchronous writes. However, the current implementation suffers from the following issues: 1) It would be best if the ZIL module was not aware of such low-level details. They should be handled by the ZIO and metaslab modules; 2) Because the hint block pointer is managed per log, simultaneous commits from multiple logs might use the same vdevs at the same time, which is inefficient; 3) Because dmu_write() does not honor the block pointer hint, indirect writes are not spread. The naive solution of rotating the metaslab rotor each time a block is allocated for the ZIL or dmu_sync() doesn't work in practice because the first ZIL block to be written is actually allocated during the previous commit. Consequently, when metaslab_alloc() decides the vdev for this block, it will do so while a bunch of other allocations are happening at the same time (from dmu_sync() and other ZILs). This means the vdev for this block is chosen more or less at random. When the next commit happens, there is a high chance (especially when the number of blocks per commit is slightly less than the number of the disks) that one disk will have to write two blocks (with a potential seek) while other disks are sitting idle, which defeats spreading and increases the commit latency. This commit introduces a new concept in the metaslab allocator: fastwrites. Basically, each top-level vdev maintains a counter indicating the number of synchronous writes (from dmu_sync() and the ZIL) which have been allocated but not yet completed. When the metaslab is called with the FASTWRITE flag, it will choose the vdev with the least amount of pending synchronous writes. If there are multiple vdevs with the same value, the first matching vdev (starting from the rotor) is used. Once metaslab_alloc() has decided which vdev the block is allocated to, it updates the fastwrite counter for this vdev. The rationale goes like this: when an allocation is done with FASTWRITE, it "reserves" the vdev until the data is written. Until then, all future allocations will naturally avoid this vdev, even after a full rotation of the rotor. As a result, pending synchronous writes at a given point in time will be nicely spread over all vdevs. This contrasts with the previous algorithm, which is based on the implicit assumption that blocks are written instantaneously after they're allocated. metaslab_fastwrite_mark() and metaslab_fastwrite_unmark() are used to manually increase or decrease fastwrite counters, respectively. They should be used with caution, as there is no per-BP tracking of fastwrite information, so leaks and "double-unmarks" are possible. There is, however, an assert in the vdev teardown code which will fire if the fastwrite counters are not zero when the pool is exported or the vdev removed. Note that as stated above, marking is also done implictly by metaslab_alloc(). ZIO also got a new FASTWRITE flag; when it is used, ZIO will pass it to the metaslab when allocating (assuming ZIO does the allocation, which is only true in the case of dmu_sync). This flag will also trigger an unmark when zio_done() fires. A side-effect of the new algorithm is that when a ZIL stops being used, its last block can stay in the pending state (allocated but not yet written) for a long time, polluting the fastwrite counters. To avoid that, I've implemented a somewhat crude but working solution which unmarks these pending blocks in zil_sync(), thus guaranteeing that linguering fastwrites will get pruned at each sync event. The best performance improvements are observed with pools using a large number of top-level vdevs and heavy synchronous write workflows (especially indirect writes and concurrent writes from multiple ZILs). Real-life testing shows a 200% to 300% performance increase with indirect writes and various commit sizes. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Issue #1013
2012-06-27 13:20:20 +00:00
uint64_t size, boolean_t use_slog);
extern void zio_free_zil(spa_t *spa, uint64_t txg, blkptr_t *bp);
2008-11-20 20:01:55 +00:00
extern void zio_flush(zio_t *zio, vdev_t *vd);
extern void zio_shrink(zio_t *zio, uint64_t size);
2008-11-20 20:01:55 +00:00
extern int zio_wait(zio_t *zio);
extern void zio_nowait(zio_t *zio);
extern void zio_execute(zio_t *zio);
extern void zio_interrupt(zio_t *zio);
2009-02-18 20:51:31 +00:00
extern zio_t *zio_walk_parents(zio_t *cio);
extern zio_t *zio_walk_children(zio_t *pio);
extern zio_t *zio_unique_parent(zio_t *cio);
extern void zio_add_child(zio_t *pio, zio_t *cio);
2008-11-20 20:01:55 +00:00
extern void *zio_buf_alloc(size_t size);
extern void zio_buf_free(void *buf, size_t size);
extern void *zio_data_buf_alloc(size_t size);
extern void zio_data_buf_free(void *buf, size_t size);
extern void *zio_vdev_alloc(void);
extern void zio_vdev_free(void *buf);
2008-11-20 20:01:55 +00:00
extern void zio_resubmit_stage_async(void *);
extern zio_t *zio_vdev_child_io(zio_t *zio, blkptr_t *bp, vdev_t *vd,
uint64_t offset, void *data, uint64_t size, int type, int priority,
enum zio_flag flags, zio_done_func_t *done, void *private);
2008-11-20 20:01:55 +00:00
extern zio_t *zio_vdev_delegated_io(vdev_t *vd, uint64_t offset,
void *data, uint64_t size, int type, int priority,
enum zio_flag flags, zio_done_func_t *done, void *private);
2008-11-20 20:01:55 +00:00
extern void zio_vdev_io_bypass(zio_t *zio);
extern void zio_vdev_io_reissue(zio_t *zio);
extern void zio_vdev_io_redone(zio_t *zio);
extern void zio_checksum_verified(zio_t *zio);
extern int zio_worst_error(int e1, int e2);
2008-11-20 20:01:55 +00:00
extern enum zio_checksum zio_checksum_select(enum zio_checksum child,
enum zio_checksum parent);
extern enum zio_checksum zio_checksum_dedup_select(spa_t *spa,
enum zio_checksum child, enum zio_checksum parent);
extern enum zio_compress zio_compress_select(enum zio_compress child,
enum zio_compress parent);
2008-11-20 20:01:55 +00:00
extern void zio_suspend(spa_t *spa, zio_t *zio);
2009-07-02 22:44:48 +00:00
extern int zio_resume(spa_t *spa);
extern void zio_resume_wait(spa_t *spa);
2008-11-20 20:01:55 +00:00
/*
* Initial setup and teardown.
*/
extern void zio_init(void);
extern void zio_fini(void);
/*
* Fault injection
*/
struct zinject_record;
extern uint32_t zio_injection_enabled;
extern int zio_inject_fault(char *name, int flags, int *id,
struct zinject_record *record);
extern int zio_inject_list_next(int *id, char *name, size_t buflen,
struct zinject_record *record);
extern int zio_clear_fault(int id);
extern void zio_handle_panic_injection(spa_t *spa, char *tag, uint64_t type);
2008-11-20 20:01:55 +00:00
extern int zio_handle_fault_injection(zio_t *zio, int error);
2009-07-02 22:44:48 +00:00
extern int zio_handle_device_injection(vdev_t *vd, zio_t *zio, int error);
extern int zio_handle_label_injection(zio_t *zio, int error);
extern void zio_handle_ignored_writes(zio_t *zio);
/*
* Checksum ereport functions
*/
extern void zfs_ereport_start_checksum(spa_t *spa, vdev_t *vd, struct zio *zio,
uint64_t offset, uint64_t length, void *arg, struct zio_bad_cksum *info);
extern void zfs_ereport_finish_checksum(zio_cksum_report_t *report,
const void *good_data, const void *bad_data, boolean_t drop_if_identical);
extern void zfs_ereport_send_interim_checksum(zio_cksum_report_t *report);
extern void zfs_ereport_free_checksum(zio_cksum_report_t *report);
/* If we have the good data in hand, this function can be used */
extern void zfs_ereport_post_checksum(spa_t *spa, vdev_t *vd,
struct zio *zio, uint64_t offset, uint64_t length,
const void *good_data, const void *bad_data, struct zio_bad_cksum *info);
/* Called from spa_sync(), but primarily an injection handler */
extern void spa_handle_ignored_writes(spa_t *spa);
2008-11-20 20:01:55 +00:00
#ifdef __cplusplus
}
#endif
#endif /* _ZIO_H */