*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2012 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2018 by Delphix. All rights reserved.
+ * Copyright (c) 2017, Intel Corporation.
*/
#ifndef _SYS_VDEV_IMPL_H
#define _SYS_VDEV_IMPL_H
#include <sys/avl.h>
+#include <sys/bpobj.h>
#include <sys/dmu.h>
#include <sys/metaslab.h>
#include <sys/nvpair.h>
#include <sys/vdev.h>
#include <sys/dkio.h>
#include <sys/uberblock_impl.h>
+#include <sys/vdev_indirect_mapping.h>
+#include <sys/vdev_indirect_births.h>
+#include <sys/vdev_removal.h>
+#include <sys/zfs_ratelimit.h>
#ifdef __cplusplus
extern "C" {
* Forward declarations that lots of things need.
*/
typedef struct vdev_queue vdev_queue_t;
-typedef struct vdev_io vdev_io_t;
typedef struct vdev_cache vdev_cache_t;
typedef struct vdev_cache_entry vdev_cache_entry_t;
+struct abd;
+
+extern int zfs_vdev_queue_depth_pct;
+extern int zfs_vdev_def_queue_depth;
+extern uint32_t zfs_vdev_async_write_max_active;
/*
* Virtual device operations
uint64_t *ashift);
typedef void vdev_close_func_t(vdev_t *vd);
typedef uint64_t vdev_asize_func_t(vdev_t *vd, uint64_t psize);
-typedef int vdev_io_start_func_t(zio_t *zio);
+typedef void vdev_io_start_func_t(zio_t *zio);
typedef void vdev_io_done_func_t(zio_t *zio);
typedef void vdev_state_change_func_t(vdev_t *vd, int, int);
+typedef boolean_t vdev_need_resilver_func_t(vdev_t *vd, uint64_t, size_t);
typedef void vdev_hold_func_t(vdev_t *vd);
typedef void vdev_rele_func_t(vdev_t *vd);
+typedef void vdev_remap_cb_t(uint64_t inner_offset, vdev_t *vd,
+ uint64_t offset, uint64_t size, void *arg);
+typedef void vdev_remap_func_t(vdev_t *vd, uint64_t offset, uint64_t size,
+ vdev_remap_cb_t callback, void *arg);
+
typedef const struct vdev_ops {
vdev_open_func_t *vdev_op_open;
vdev_close_func_t *vdev_op_close;
vdev_io_start_func_t *vdev_op_io_start;
vdev_io_done_func_t *vdev_op_io_done;
vdev_state_change_func_t *vdev_op_state_change;
+ vdev_need_resilver_func_t *vdev_op_need_resilver;
vdev_hold_func_t *vdev_op_hold;
vdev_rele_func_t *vdev_op_rele;
+ vdev_remap_func_t *vdev_op_remap;
char vdev_op_type[16];
boolean_t vdev_op_leaf;
} vdev_ops_t;
* Virtual device properties
*/
struct vdev_cache_entry {
- char *ve_data;
+ struct abd *ve_abd;
uint64_t ve_offset;
- uint64_t ve_lastused;
+ clock_t ve_lastused;
avl_node_t ve_offset_node;
avl_node_t ve_lastused_node;
uint32_t ve_hits;
kmutex_t vc_lock;
};
+typedef struct vdev_queue_class {
+ uint32_t vqc_active;
+
+ /*
+ * Sorted by offset or timestamp, depending on if the queue is
+ * LBA-ordered vs FIFO.
+ */
+ avl_tree_t vqc_queued_tree;
+} vdev_queue_class_t;
+
struct vdev_queue {
- avl_tree_t vq_deadline_tree;
- avl_tree_t vq_read_tree;
- avl_tree_t vq_write_tree;
- avl_tree_t vq_pending_tree;
- hrtime_t vq_io_complete_ts;
+ vdev_t *vq_vdev;
+ vdev_queue_class_t vq_class[ZIO_PRIORITY_NUM_QUEUEABLE];
+ avl_tree_t vq_active_tree;
+ avl_tree_t vq_read_offset_tree;
+ avl_tree_t vq_write_offset_tree;
+ uint64_t vq_last_offset;
+ hrtime_t vq_io_complete_ts; /* time last i/o completed */
hrtime_t vq_io_delta_ts;
- list_t vq_io_list;
+ zio_t vq_io_search; /* used as local for stack reduction */
kmutex_t vq_lock;
};
-struct vdev_io {
- char vi_buffer[SPA_MAXBLOCKSIZE]; /* Must be first */
- list_node_t vi_node;
-};
+typedef enum vdev_alloc_bias {
+ VDEV_BIAS_NONE,
+ VDEV_BIAS_LOG, /* dedicated to ZIL data (SLOG) */
+ VDEV_BIAS_SPECIAL, /* dedicated to ddt, metadata, and small blks */
+ VDEV_BIAS_DEDUP /* dedicated to dedup metadata */
+} vdev_alloc_bias_t;
+
+
+/*
+ * On-disk indirect vdev state.
+ *
+ * An indirect vdev is described exclusively in the MOS config of a pool.
+ * The config for an indirect vdev includes several fields, which are
+ * accessed in memory by a vdev_indirect_config_t.
+ */
+typedef struct vdev_indirect_config {
+ /*
+ * Object (in MOS) which contains the indirect mapping. This object
+ * contains an array of vdev_indirect_mapping_entry_phys_t ordered by
+ * vimep_src. The bonus buffer for this object is a
+ * vdev_indirect_mapping_phys_t. This object is allocated when a vdev
+ * removal is initiated.
+ *
+ * Note that this object can be empty if none of the data on the vdev
+ * has been copied yet.
+ */
+ uint64_t vic_mapping_object;
+
+ /*
+ * Object (in MOS) which contains the birth times for the mapping
+ * entries. This object contains an array of
+ * vdev_indirect_birth_entry_phys_t sorted by vibe_offset. The bonus
+ * buffer for this object is a vdev_indirect_birth_phys_t. This object
+ * is allocated when a vdev removal is initiated.
+ *
+ * Note that this object can be empty if none of the vdev has yet been
+ * copied.
+ */
+ uint64_t vic_births_object;
+
+ /*
+ * This is the vdev ID which was removed previous to this vdev, or
+ * UINT64_MAX if there are no previously removed vdevs.
+ */
+ uint64_t vic_prev_indirect_vdev;
+} vdev_indirect_config_t;
/*
* Virtual device descriptor
vdev_t *vdev_parent; /* parent vdev */
vdev_t **vdev_child; /* array of children */
uint64_t vdev_children; /* number of children */
- space_map_t vdev_dtl[DTL_TYPES]; /* in-core dirty time logs */
vdev_stat_t vdev_stat; /* virtual device statistics */
+ vdev_stat_ex_t vdev_stat_ex; /* extended statistics */
boolean_t vdev_expanding; /* expand the vdev? */
boolean_t vdev_reopening; /* reopen in progress? */
+ boolean_t vdev_nonrot; /* true if solid state */
int vdev_open_error; /* error on last open */
kthread_t *vdev_open_thread; /* thread opening children */
uint64_t vdev_crtxg; /* txg when top-level was added */
txg_node_t vdev_txg_node; /* per-txg dirty vdev linkage */
boolean_t vdev_remove_wanted; /* async remove wanted? */
boolean_t vdev_probe_wanted; /* async probe wanted? */
- uint64_t vdev_removing; /* device is being removed? */
list_node_t vdev_config_dirty_node; /* config dirty list */
list_node_t vdev_state_dirty_node; /* state dirty list */
uint64_t vdev_deflate_ratio; /* deflation ratio (x512) */
uint64_t vdev_islog; /* is an intent log device */
- uint64_t vdev_ishole; /* is a hole in the namespace */
+ uint64_t vdev_removing; /* device is being removed? */
+ boolean_t vdev_ishole; /* is a hole in the namespace */
+ kmutex_t vdev_queue_lock; /* protects vdev_queue_depth */
+ uint64_t vdev_top_zap;
+ vdev_alloc_bias_t vdev_alloc_bias; /* metaslab allocation bias */
+
+ /* pool checkpoint related */
+ space_map_t *vdev_checkpoint_sm; /* contains reserved blocks */
+
+ /*
+ * Values stored in the config for an indirect or removing vdev.
+ */
+ vdev_indirect_config_t vdev_indirect_config;
+
+ /*
+ * The vdev_indirect_rwlock protects the vdev_indirect_mapping
+ * pointer from changing on indirect vdevs (when it is condensed).
+ * Note that removing (not yet indirect) vdevs have different
+ * access patterns (the mapping is not accessed from open context,
+ * e.g. from zio_read) and locking strategy (e.g. svr_lock).
+ */
+ krwlock_t vdev_indirect_rwlock;
+ vdev_indirect_mapping_t *vdev_indirect_mapping;
+ vdev_indirect_births_t *vdev_indirect_births;
+
+ /*
+ * In memory data structures used to manage the obsolete sm, for
+ * indirect or removing vdevs.
+ *
+ * The vdev_obsolete_segments is the in-core record of the segments
+ * that are no longer referenced anywhere in the pool (due to
+ * being freed or remapped and not referenced by any snapshots).
+ * During a sync, segments are added to vdev_obsolete_segments
+ * via vdev_indirect_mark_obsolete(); at the end of each sync
+ * pass, this is appended to vdev_obsolete_sm via
+ * vdev_indirect_sync_obsolete(). The vdev_obsolete_lock
+ * protects against concurrent modifications of vdev_obsolete_segments
+ * from multiple zio threads.
+ */
+ kmutex_t vdev_obsolete_lock;
+ range_tree_t *vdev_obsolete_segments;
+ space_map_t *vdev_obsolete_sm;
+
+ /*
+ * The queue depth parameters determine how many async writes are
+ * still pending (i.e. allocated but not yet issued to disk) per
+ * top-level (vdev_async_write_queue_depth) and the maximum allowed
+ * (vdev_max_async_write_queue_depth). These values only apply to
+ * top-level vdevs.
+ */
+ uint64_t vdev_async_write_queue_depth;
+ uint64_t vdev_max_async_write_queue_depth;
+
+ /*
+ * Protects the vdev_scan_io_queue field itself as well as the
+ * structure's contents (when present).
+ */
+ kmutex_t vdev_scan_io_queue_lock;
+ struct dsl_scan_io_queue *vdev_scan_io_queue;
/*
* Leaf vdev state.
*/
- uint64_t vdev_psize; /* physical device capacity */
- space_map_obj_t vdev_dtl_smo; /* dirty time log space map obj */
+ range_tree_t *vdev_dtl[DTL_TYPES]; /* dirty time logs */
+ space_map_t *vdev_dtl_sm; /* dirty time log space map */
txg_node_t vdev_dtl_node; /* per-txg dirty DTL linkage */
+ uint64_t vdev_dtl_object; /* DTL object */
+ uint64_t vdev_psize; /* physical device capacity */
uint64_t vdev_wholedisk; /* true if this is a whole disk */
uint64_t vdev_offline; /* persistent offline state */
uint64_t vdev_faulted; /* persistent faulted state */
uint64_t vdev_degraded; /* persistent degraded state */
uint64_t vdev_removed; /* persistent removed state */
- uint64_t vdev_resilvering; /* persistent resilvering state */
+ uint64_t vdev_resilver_txg; /* persistent resilvering state */
uint64_t vdev_nparity; /* number of parity devices for raidz */
char *vdev_path; /* vdev path (if any) */
char *vdev_devid; /* vdev devid (if any) */
char *vdev_physpath; /* vdev device path (if any) */
+ char *vdev_enc_sysfs_path; /* enclosure sysfs path */
char *vdev_fru; /* physical FRU location */
uint64_t vdev_not_present; /* not present during import */
uint64_t vdev_unspare; /* unspare when resilvering done */
- hrtime_t vdev_last_try; /* last reopen time */
boolean_t vdev_nowritecache; /* true if flushwritecache failed */
boolean_t vdev_checkremove; /* temporary online test */
boolean_t vdev_forcefault; /* force online fault */
boolean_t vdev_splitting; /* split or repair in progress */
boolean_t vdev_delayed_close; /* delayed device close? */
- uint8_t vdev_tmpoffline; /* device taken offline temporarily? */
- uint8_t vdev_detached; /* device detached? */
- uint8_t vdev_cant_read; /* vdev is failing all reads */
- uint8_t vdev_cant_write; /* vdev is failing all writes */
- uint64_t vdev_isspare; /* was a hot spare */
- uint64_t vdev_isl2cache; /* was a l2cache device */
+ boolean_t vdev_tmpoffline; /* device taken offline temporarily? */
+ boolean_t vdev_detached; /* device detached? */
+ boolean_t vdev_cant_read; /* vdev is failing all reads */
+ boolean_t vdev_cant_write; /* vdev is failing all writes */
+ boolean_t vdev_isspare; /* was a hot spare */
+ boolean_t vdev_isl2cache; /* was a l2cache device */
+ boolean_t vdev_copy_uberblocks; /* post expand copy uberblocks */
+ boolean_t vdev_resilver_deferred; /* resilver deferred */
vdev_queue_t vdev_queue; /* I/O deadline schedule queue */
vdev_cache_t vdev_cache; /* physical block cache */
- spa_aux_vdev_t *vdev_aux; /* for l2cache vdevs */
+ spa_aux_vdev_t *vdev_aux; /* for l2cache and spares vdevs */
zio_t *vdev_probe_zio; /* root of current probe */
vdev_aux_t vdev_label_aux; /* on-disk aux state */
+ uint64_t vdev_leaf_zap;
+ hrtime_t vdev_mmp_pending; /* 0 if write finished */
+ uint64_t vdev_mmp_kstat_id; /* to find kstat entry */
+ uint64_t vdev_expansion_time; /* vdev's last expansion time */
/*
* For DTrace to work in userland (libzpool) context, these fields must
kmutex_t vdev_dtl_lock; /* vdev_dtl_{map,resilver} */
kmutex_t vdev_stat_lock; /* vdev_stat */
kmutex_t vdev_probe_lock; /* protects vdev_probe_zio */
+
+ /*
+ * We rate limit ZIO delay and ZIO checksum events, since they
+ * can flood ZED with tons of events when a drive is acting up.
+ */
+ zfs_ratelimit_t vdev_delay_rl;
+ zfs_ratelimit_t vdev_checksum_rl;
};
#define VDEV_RAIDZ_MAXPARITY 3
#define VDEV_PHYS_SIZE (112 << 10)
#define VDEV_UBERBLOCK_RING (128 << 10)
+/*
+ * MMP blocks occupy the last MMP_BLOCKS_PER_LABEL slots in the uberblock
+ * ring when MMP is enabled.
+ */
+#define MMP_BLOCKS_PER_LABEL 1
+
+/* The largest uberblock we support is 8k. */
+#define MAX_UBERBLOCK_SHIFT (13)
#define VDEV_UBERBLOCK_SHIFT(vd) \
- MAX((vd)->vdev_top->vdev_ashift, UBERBLOCK_SHIFT)
+ MIN(MAX((vd)->vdev_top->vdev_ashift, UBERBLOCK_SHIFT), \
+ MAX_UBERBLOCK_SHIFT)
#define VDEV_UBERBLOCK_COUNT(vd) \
(VDEV_UBERBLOCK_RING >> VDEV_UBERBLOCK_SHIFT(vd))
#define VDEV_UBERBLOCK_OFFSET(vd, n) \
#define VDD_METASLAB 0x01
#define VDD_DTL 0x02
+/* Offset of embedded boot loader region on each label */
+#define VDEV_BOOT_OFFSET (2 * sizeof (vdev_label_t))
/*
- * Size and offset of embedded boot loader region on each label.
+ * Size of embedded boot loader region on each label.
* The total size of the first two labels plus the boot area is 4MB.
*/
-#define VDEV_BOOT_OFFSET (2 * sizeof (vdev_label_t))
-#define VDEV_BOOT_SIZE (7ULL << 19) /* 3.5M */
+#define VDEV_BOOT_SIZE (7ULL << 19) /* 3.5M */
/*
* Size of label regions at the start and end of each leaf device.
/*
* vdev sync load and sync
*/
-extern void vdev_load_log_state(vdev_t *nvd, vdev_t *ovd);
extern boolean_t vdev_log_state_valid(vdev_t *vd);
-extern void vdev_load(vdev_t *vd);
+extern int vdev_load(vdev_t *vd);
+extern int vdev_dtl_load(vdev_t *vd);
extern void vdev_sync(vdev_t *vd, uint64_t txg);
extern void vdev_sync_done(vdev_t *vd, uint64_t txg);
extern void vdev_dirty(vdev_t *vd, int flags, void *arg, uint64_t txg);
+extern void vdev_dirty_leaves(vdev_t *vd, int flags, uint64_t txg);
/*
* Available vdev types.
extern vdev_ops_t vdev_missing_ops;
extern vdev_ops_t vdev_hole_ops;
extern vdev_ops_t vdev_spare_ops;
+extern vdev_ops_t vdev_indirect_ops;
/*
* Common size functions
extern void vdev_set_min_asize(vdev_t *vd);
/*
- * zdb uses this tunable, so it must be declared here to make lint happy.
+ * Global variables
*/
+extern int vdev_standard_sm_blksz;
+/* zdb uses this tunable, so it must be declared here to make lint happy. */
extern int zfs_vdev_cache_size;
+/*
+ * Functions from vdev_indirect.c
+ */
+extern void vdev_indirect_sync_obsolete(vdev_t *vd, dmu_tx_t *tx);
+extern boolean_t vdev_indirect_should_condense(vdev_t *vd);
+extern void spa_condense_indirect_start_sync(vdev_t *vd, dmu_tx_t *tx);
+extern int vdev_obsolete_sm_object(vdev_t *vd, uint64_t *sm_obj);
+extern int vdev_obsolete_counts_are_precise(vdev_t *vd, boolean_t *are_precise);
+
+/*
+ * Other miscellaneous functions
+ */
+int vdev_checkpoint_sm_object(vdev_t *vd, uint64_t *sm_obj);
+
#ifdef __cplusplus
}
#endif