/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright 2011 Nexenta Systems, Inc. All rights reserved.
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2012, 2016 by Delphix. All rights reserved.
* Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
*/
#ifndef _ZIO_H
#define _ZIO_H
+#include <sys/zio_priority.h>
#include <sys/zfs_context.h>
#include <sys/spa.h>
#include <sys/txg.h>
ZIO_CHECKSUM_FLETCHER_4,
ZIO_CHECKSUM_SHA256,
ZIO_CHECKSUM_ZILOG2,
+ ZIO_CHECKSUM_NOPARITY,
+ ZIO_CHECKSUM_SHA512,
+ ZIO_CHECKSUM_SKEIN,
+ ZIO_CHECKSUM_EDONR,
ZIO_CHECKSUM_FUNCTIONS
};
+/*
+ * The number of "legacy" compression functions which can be set on individual
+ * objects.
+ */
+#define ZIO_CHECKSUM_LEGACY_FUNCTIONS ZIO_CHECKSUM_ZILOG2
+
#define ZIO_CHECKSUM_ON_VALUE ZIO_CHECKSUM_FLETCHER_4
#define ZIO_CHECKSUM_DEFAULT ZIO_CHECKSUM_ON
#define ZIO_DEDUPCHECKSUM ZIO_CHECKSUM_SHA256
#define ZIO_DEDUPDITTO_MIN 100
-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,
- ZIO_COMPRESS_LZ4,
- ZIO_COMPRESS_FUNCTIONS
-};
+/*
+ * The number of "legacy" compression functions which can be set on individual
+ * objects.
+ */
+#define ZIO_COMPRESS_LEGACY_FUNCTIONS ZIO_COMPRESS_LZ4
+
+/*
+ * The meaning of "compress = on" selected by the compression features enabled
+ * on a given pool.
+ */
+#define ZIO_COMPRESS_LEGACY_ON_VALUE ZIO_COMPRESS_LZJB
+#define ZIO_COMPRESS_LZ4_ON_VALUE ZIO_COMPRESS_LZ4
-#define ZIO_COMPRESS_ON_VALUE ZIO_COMPRESS_LZJB
-#define ZIO_COMPRESS_DEFAULT ZIO_COMPRESS_OFF
+#define ZIO_COMPRESS_DEFAULT ZIO_COMPRESS_OFF
#define BOOTFS_COMPRESS_VALID(compress) \
((compress) == ZIO_COMPRESS_LZJB || \
(compress) == ZIO_COMPRESS_LZ4 || \
- ((compress) == ZIO_COMPRESS_ON && \
- ZIO_COMPRESS_ON_VALUE == ZIO_COMPRESS_LZJB) || \
+ (compress) == ZIO_COMPRESS_ON || \
(compress) == ZIO_COMPRESS_OFF)
/*
* Default Linux timeout for a sd device.
*/
-#define ZIO_DELAY_MAX (30 * MILLISEC)
+#define ZIO_DELAY_MAX (30 * MILLISEC)
#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
-
-#define ZIO_PIPELINE_CONTINUE 0x100
-#define ZIO_PIPELINE_STOP 0x101
-
enum zio_flag {
/*
* Flags inherited by gang, ddt, and vdev children,
ZIO_FLAG_RESILVER = 1 << 3,
ZIO_FLAG_SCRUB = 1 << 4,
ZIO_FLAG_SCAN_THREAD = 1 << 5,
+ ZIO_FLAG_PHYSICAL = 1 << 6,
#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,
+ ZIO_FLAG_CANFAIL = 1 << 7, /* must be first for INHERIT */
+ ZIO_FLAG_SPECULATIVE = 1 << 8,
+ ZIO_FLAG_CONFIG_WRITER = 1 << 9,
+ ZIO_FLAG_DONT_RETRY = 1 << 10,
+ ZIO_FLAG_DONT_CACHE = 1 << 11,
+ ZIO_FLAG_NODATA = 1 << 12,
+ ZIO_FLAG_INDUCE_DAMAGE = 1 << 13,
+ ZIO_FLAG_IO_ALLOCATING = 1 << 14,
#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,
+ ZIO_FLAG_IO_RETRY = 1 << 15, /* must be first for INHERIT */
+ ZIO_FLAG_PROBE = 1 << 16,
+ ZIO_FLAG_TRYHARD = 1 << 17,
+ ZIO_FLAG_OPTIONAL = 1 << 18,
#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,
- ZIO_FLAG_GODFATHER = 1 << 24,
- ZIO_FLAG_FASTWRITE = 1 << 25
+ ZIO_FLAG_DONT_QUEUE = 1 << 19, /* must be first for INHERIT */
+ ZIO_FLAG_DONT_PROPAGATE = 1 << 20,
+ ZIO_FLAG_IO_BYPASS = 1 << 21,
+ ZIO_FLAG_IO_REWRITE = 1 << 22,
+ ZIO_FLAG_RAW = 1 << 23,
+ ZIO_FLAG_GANG_CHILD = 1 << 24,
+ ZIO_FLAG_DDT_CHILD = 1 << 25,
+ ZIO_FLAG_GODFATHER = 1 << 26,
+ ZIO_FLAG_NOPWRITE = 1 << 27,
+ ZIO_FLAG_REEXECUTED = 1 << 28,
+ ZIO_FLAG_DELEGATED = 1 << 29,
+ ZIO_FLAG_FASTWRITE = 1 << 30
};
#define ZIO_FLAG_MUSTSUCCEED 0
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];
+extern int zio_dva_throttle_enabled;
+extern const char *zio_type_name[ZIO_TYPES];
/*
* A bookmark is a four-tuple <objset, object, level, blkid> that uniquely
* 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>.
+ * dnode visit bookmarks are <objset, object id of dnode, -3, 0>.
*
* Note: this structure is called a bookmark because its original purpose
* was to remember where to resume a pool-wide traverse.
*
- * Note: this structure is passed between userland and the kernel.
- * Therefore it must not change size or alignment between 32/64 bit
- * compilation options.
+ * Note: this structure is passed between userland and the kernel, and is
+ * stored on disk (by virtue of being incorporated into other on-disk
+ * structures, e.g. dsl_scan_phys_t).
*/
-struct zbookmark {
+struct zbookmark_phys {
uint64_t zb_objset;
uint64_t zb_object;
int64_t zb_level;
uint64_t zb_blkid;
- char * zb_func;
};
#define SET_BOOKMARK(zb, objset, object, level, blkid) \
(zb)->zb_object = object; \
(zb)->zb_level = level; \
(zb)->zb_blkid = blkid; \
- (zb)->zb_func = FTAG; \
}
#define ZB_DESTROYED_OBJSET (-1ULL)
#define ZB_ZIL_OBJECT (0ULL)
#define ZB_ZIL_LEVEL (-2LL)
+#define ZB_DNODE_LEVEL (-3LL)
+#define ZB_DNODE_BLKID (0ULL)
+
#define ZB_IS_ZERO(zb) \
((zb)->zb_objset == 0 && (zb)->zb_object == 0 && \
(zb)->zb_level == 0 && (zb)->zb_blkid == 0)
dmu_object_type_t zp_type;
uint8_t zp_level;
uint8_t zp_copies;
- uint8_t zp_dedup;
- uint8_t zp_dedup_verify;
+ boolean_t zp_dedup;
+ boolean_t zp_dedup_verify;
+ boolean_t zp_nopwrite;
} zio_prop_t;
typedef struct zio_cksum_report zio_cksum_report_t;
struct zio_bad_cksum; /* defined in zio_checksum.h */
struct dnode_phys;
+struct abd;
struct zio_cksum_report {
struct zio_cksum_report *zcr_next;
} 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);
+ zio_gang_node_t *gn, struct abd *data, uint64_t offset);
-typedef void zio_transform_func_t(zio_t *zio, void *data, uint64_t size);
+typedef void zio_transform_func_t(zio_t *zio, struct abd *data, uint64_t size);
typedef struct zio_transform {
- void *zt_orig_data;
+ struct abd *zt_orig_abd;
uint64_t zt_orig_size;
uint64_t zt_bufsize;
zio_transform_func_t *zt_transform;
#define ZIO_REEXECUTE_NOW 0x01
#define ZIO_REEXECUTE_SUSPEND 0x02
+typedef struct zio_alloc_list {
+ list_t zal_list;
+ uint64_t zal_size;
+} zio_alloc_list_t;
+
typedef struct zio_link {
zio_t *zl_parent;
zio_t *zl_child;
struct zio {
/* Core information about this I/O */
- zbookmark_t io_bookmark;
+ zbookmark_phys_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;
+ zio_priority_t io_priority;
uint8_t io_reexecute;
uint8_t io_state[ZIO_WAIT_TYPES];
uint64_t io_txg;
blkptr_t io_bp_copy;
list_t io_parent_list;
list_t io_child_list;
- zio_link_t *io_walk_link;
zio_t *io_logical;
zio_transform_t *io_transform_stack;
/* Callback info */
zio_done_func_t *io_ready;
+ zio_done_func_t *io_children_ready;
+ zio_done_func_t *io_physdone;
zio_done_func_t *io_done;
void *io_private;
int64_t io_prev_space_delta; /* DMU private */
blkptr_t io_bp_orig;
+ /* io_lsize != io_orig_size iff this is a raw write */
+ uint64_t io_lsize;
/* Data represented by this I/O */
- void *io_data;
- void *io_orig_data;
+ struct abd *io_abd;
+ struct abd *io_orig_abd;
uint64_t io_size;
uint64_t io_orig_size;
const zio_vsd_ops_t *io_vsd_ops;
uint64_t io_offset;
- uint64_t io_deadline; /* expires at timestamp + deadline */
hrtime_t io_timestamp; /* submitted at */
+ hrtime_t io_queued_timestamp;
+ hrtime_t io_target_timestamp;
hrtime_t io_delta; /* vdev queue service delta */
- uint64_t io_delay; /* vdev disk service delta (ticks) */
+ hrtime_t io_delay; /* Device access time (disk or */
+ /* file). */
+ avl_node_t io_queue_node;
avl_node_t io_offset_node;
- avl_node_t io_deadline_node;
- avl_tree_t *io_vdev_tree;
+ avl_node_t io_alloc_node;
+ zio_alloc_list_t io_alloc_list;
/* Internal pipeline state */
enum zio_flag io_flags;
enum zio_flag io_orig_flags;
enum zio_stage io_orig_stage;
enum zio_stage io_orig_pipeline;
+ enum zio_stage io_pipeline_trace;
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_phys_children;
uint64_t io_parent_count;
uint64_t *io_stall;
zio_t *io_gang_leader;
taskq_ent_t io_tqent;
};
+extern int zio_timestamp_compare(const void *, const void *);
+
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);
extern zio_t *zio_root(spa_t *spa,
zio_done_func_t *done, void *private, enum zio_flag flags);
-extern zio_t *zio_read(zio_t *pio, spa_t *spa, const blkptr_t *bp, void *data,
- uint64_t size, zio_done_func_t *done, void *private,
- int priority, enum zio_flag flags, const zbookmark_t *zb);
+extern zio_t *zio_read(zio_t *pio, spa_t *spa, const blkptr_t *bp,
+ struct abd *data, uint64_t lsize, zio_done_func_t *done, void *private,
+ zio_priority_t priority, enum zio_flag flags, const zbookmark_phys_t *zb);
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);
+ struct abd *data, uint64_t size, uint64_t psize, const zio_prop_t *zp,
+ zio_done_func_t *ready, zio_done_func_t *children_ready,
+ zio_done_func_t *physdone, zio_done_func_t *done,
+ void *private, zio_priority_t priority, enum zio_flag flags,
+ const zbookmark_phys_t *zb);
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);
+ struct abd *data, uint64_t size, zio_done_func_t *done, void *private,
+ zio_priority_t priority, enum zio_flag flags, zbookmark_phys_t *zb);
-extern void zio_write_override(zio_t *zio, blkptr_t *bp, int copies);
+extern void zio_write_override(zio_t *zio, blkptr_t *bp, int copies,
+ boolean_t nopwrite);
extern void zio_free(spa_t *spa, uint64_t txg, const blkptr_t *bp);
zio_done_func_t *done, void *private, enum zio_flag flags);
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);
+ zio_done_func_t *done, void *private, enum zio_flag flags);
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,
- boolean_t labels);
+ uint64_t size, struct abd *data, int checksum,
+ zio_done_func_t *done, void *private, zio_priority_t priority,
+ enum zio_flag flags, 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,
- boolean_t labels);
+ uint64_t size, struct abd *data, int checksum,
+ zio_done_func_t *done, void *private, zio_priority_t priority,
+ enum zio_flag flags, 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 void zio_nowait(zio_t *zio);
extern void zio_execute(zio_t *zio);
extern void zio_interrupt(zio_t *zio);
+extern void zio_delay_init(zio_t *zio);
+extern void zio_delay_interrupt(zio_t *zio);
-extern zio_t *zio_walk_parents(zio_t *cio);
-extern zio_t *zio_walk_children(zio_t *pio);
+extern zio_t *zio_walk_parents(zio_t *cio, zio_link_t **);
+extern zio_t *zio_walk_children(zio_t *pio, zio_link_t **);
extern zio_t *zio_unique_parent(zio_t *cio);
extern void zio_add_child(zio_t *pio, zio_t *cio);
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);
+
+extern void zio_push_transform(zio_t *zio, struct abd *abd, uint64_t size,
+ uint64_t bufsize, zio_transform_func_t *transform);
+extern void zio_pop_transforms(zio_t *zio);
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);
+ uint64_t offset, struct abd *data, uint64_t size, int type,
+ zio_priority_t priority, enum zio_flag flags,
+ zio_done_func_t *done, void *private);
extern zio_t *zio_vdev_delegated_io(vdev_t *vd, uint64_t offset,
- void *data, uint64_t size, int type, int priority,
+ struct abd *data, uint64_t size, int type, zio_priority_t priority,
enum zio_flag flags, zio_done_func_t *done, void *private);
extern void zio_vdev_io_bypass(zio_t *zio);
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);
+extern enum zio_compress zio_compress_select(spa_t *spa,
+ enum zio_compress child, enum zio_compress parent);
extern void zio_suspend(spa_t *spa, zio_t *zio);
extern int zio_resume(spa_t *spa);
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);
-extern uint64_t zio_handle_io_delay(zio_t *zio);
+extern hrtime_t zio_handle_io_delay(zio_t *zio);
/*
* Checksum ereport functions
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 */
/* Called from spa_sync(), but primarily an injection handler */
extern void spa_handle_ignored_writes(spa_t *spa);
-/* zbookmark functions */
-boolean_t zbookmark_is_before(const struct dnode_phys *dnp,
- const zbookmark_t *zb1, const zbookmark_t *zb2);
+/* zbookmark_phys functions */
+boolean_t zbookmark_subtree_completed(const struct dnode_phys *dnp,
+ const zbookmark_phys_t *subtree_root, const zbookmark_phys_t *last_block);
+int zbookmark_compare(uint16_t dbss1, uint8_t ibs1, uint16_t dbss2,
+ uint8_t ibs2, const zbookmark_phys_t *zb1, const zbookmark_phys_t *zb2);
#ifdef __cplusplus
}
projects / mirror_zfs.git / blobdiff