pebble

type AbbreviatedKey = base.AbbreviatedKey

type ArchiveCleaner = base.ArchiveCleaner

type AttributeAndLen = base.AttributeAndLen

type BackingType int

type Batch struct {
	// contains filtered or unexported fields
}

type BatchCommitStats struct {
	// TotalDuration is the time spent in DB.{Apply,ApplyNoSyncWait} or
	// Batch.Commit, plus the time waiting in Batch.SyncWait. If there is a gap
	// between calling ApplyNoSyncWait and calling SyncWait, that gap could
	// include some duration in which real work was being done for the commit
	// and will not be included here. This missing time is considered acceptable
	// since the goal of these stats is to understand user-facing latency.
	//
	// TotalDuration includes time spent in various queues both inside Pebble
	// and outside Pebble (I/O queues, goroutine scheduler queue, mutex wait
	// etc.). For some of these queues (which we consider important) the wait
	// times are included below -- these expose low-level implementation detail
	// and are meant for expert diagnosis and subject to change. There may be
	// unaccounted time after subtracting those values from TotalDuration.
	TotalDuration time.Duration
	// SemaphoreWaitDuration is the wait time for semaphores in
	// commitPipeline.Commit.
	SemaphoreWaitDuration time.Duration
	// WALQueueWaitDuration is the wait time for allocating memory blocks in the
	// LogWriter (due to the LogWriter not writing fast enough). At the moment
	// this is duration is always zero because a single WAL will allow
	// allocating memory blocks up to the entire memtable size. In the future,
	// we may pipeline WALs and bound the WAL queued blocks separately, so this
	// field is preserved for that possibility.
	WALQueueWaitDuration time.Duration
	// MemTableWriteStallDuration is the wait caused by a write stall due to too
	// many memtables (due to not flushing fast enough).
	MemTableWriteStallDuration time.Duration
	// L0ReadAmpWriteStallDuration is the wait caused by a write stall due to
	// high read amplification in L0 (due to not compacting fast enough out of
	// L0).
	L0ReadAmpWriteStallDuration time.Duration
	// WALRotationDuration is the wait time for WAL rotation, which includes
	// syncing and closing the old WAL and creating (or reusing) a new one.
	WALRotationDuration time.Duration
	// CommitWaitDuration is the wait for publishing the seqnum plus the
	// duration for the WAL sync (if requested). The former should be tiny and
	// one can assume that this is all due to the WAL sync.
	CommitWaitDuration time.Duration
}

type BatchReader []byte

type BlockPropertyCollector = sstable.BlockPropertyCollector

type BlockPropertyFilter = base.BlockPropertyFilter

type BlockPropertyFilterMask interface {
	BlockPropertyFilter

	// SetSuffix configures the mask with the suffix of a range key. The filter
	// should return false from Intersects whenever it's provided with a
	// property encoding a block's minimum suffix that's greater (according to
	// Compare) than the provided suffix.
	SetSuffix(suffix []byte) error
}

type CPUWorkHandle interface {
	// Permitted indicates whether Pebble can use additional CPU resources.
	Permitted() bool
}

type CPUWorkPermissionGranter interface {
	// GetPermission returns a handle regardless of whether permission is granted
	// or not. In the latter case, the handle is only useful for recording
	// the CPU time actually spent on this calling goroutine.
	GetPermission(time.Duration) CPUWorkHandle
	// CPUWorkDone must be called regardless of whether CPUWorkHandle.Permitted
	// returns true or false.
	CPUWorkDone(CPUWorkHandle)
}

type Cache = cache.Cache

type CacheMetrics = cache.Metrics

type CheckLevelsStats struct {
	NumPoints     int64
	NumTombstones int
}

type CheckpointOption func(*checkpointOptions)

type CheckpointSpan struct {
	Start []byte
	End   []byte
}

type Cleaner = base.Cleaner

type CloneOptions struct {
	// IterOptions, if non-nil, define the iterator options to configure a
	// cloned iterator. If nil, the clone adopts the same IterOptions as the
	// iterator being cloned.
	IterOptions *IterOptions
	// RefreshBatchView may be set to true when cloning an Iterator over an
	// indexed batch. When false, the clone adopts the same (possibly stale)
	// view of the indexed batch as the cloned Iterator. When true, the clone is
	// constructed with a refreshed view of the batch, observing all of the
	// batch's mutations at the time of the Clone. If the cloned iterator was
	// not constructed to read over an indexed batch, RefreshVatchView has no
	// effect.
	RefreshBatchView bool
}

type CompactionInfo struct {
	// JobID is the ID of the compaction job.
	JobID int
	// Reason is the reason for the compaction.
	Reason string
	// Input contains the input tables for the compaction organized by level.
	Input []LevelInfo
	// Output contains the output tables generated by the compaction. The output
	// tables are empty for the compaction begin event.
	Output LevelInfo
	// Duration is the time spent compacting, including reading and writing
	// sstables.
	Duration time.Duration
	// TotalDuration is the total wall-time duration of the compaction,
	// including applying the compaction to the database. TotalDuration is
	// always ≥ Duration.
	TotalDuration time.Duration
	Done          bool
	Err           error

	SingleLevelOverlappingRatio float64
	MultiLevelOverlappingRatio  float64

	// Annotations specifies additional info to appear in a compaction's event log line
	Annotations compactionAnnotations
}

type Compare = base.Compare

type Comparer = base.Comparer

type Compression = sstable.Compression

type DB struct {
	// contains filtered or unexported fields
}

type DBDesc struct {
	// Exists is true if an existing database was found.
	Exists bool
	// FormatMajorVersion indicates the database's current format
	// version.
	FormatMajorVersion FormatMajorVersion
	// ManifestFilename is the filename of the current active manifest,
	// if the database exists.
	ManifestFilename string
}

type DeferredBatchOp struct {

	// Key and Value point to parts of the binary batch representation where
	// keys and values should be encoded/copied into. len(Key) and len(Value)
	// bytes must be copied into these slices respectively before calling
	// Finish(). Changing where these slices point to is not allowed.
	Key, Value []byte
	// contains filtered or unexported fields
}

type DeletableValueMerger = base.DeletableValueMerger

type DeleteCleaner = base.DeleteCleaner

type DiskSlowInfo = vfs.DiskSlowInfo

type DownloadSpan struct {
	StartKey []byte
	// EndKey is exclusive.
	EndKey []byte
}

type Equal = base.Equal

type EventListener struct {
	// BackgroundError is invoked whenever an error occurs during a background
	// operation such as flush or compaction.
	BackgroundError func(error)

	// CompactionBegin is invoked after the inputs to a compaction have been
	// determined, but before the compaction has produced any output.
	CompactionBegin func(CompactionInfo)

	// CompactionEnd is invoked after a compaction has completed and the result
	// has been installed.
	CompactionEnd func(CompactionInfo)

	// DiskSlow is invoked after a disk write operation on a file created with a
	// disk health checking vfs.FS (see vfs.DefaultWithDiskHealthChecks) is
	// observed to exceed the specified disk slowness threshold duration. DiskSlow
	// is called on a goroutine that is monitoring slowness/stuckness. The callee
	// MUST return without doing any IO, or blocking on anything (like a mutex)
	// that is waiting on IO. This is imperative in order to reliably monitor for
	// slowness, since if this goroutine gets stuck, the monitoring will stop
	// working.
	DiskSlow func(DiskSlowInfo)

	// FlushBegin is invoked after the inputs to a flush have been determined,
	// but before the flush has produced any output.
	FlushBegin func(FlushInfo)

	// FlushEnd is invoked after a flush has complated and the result has been
	// installed.
	FlushEnd func(FlushInfo)

	// FormatUpgrade is invoked after the database's FormatMajorVersion
	// is upgraded.
	FormatUpgrade func(FormatMajorVersion)

	// ManifestCreated is invoked after a manifest has been created.
	ManifestCreated func(ManifestCreateInfo)

	// ManifestDeleted is invoked after a manifest has been deleted.
	ManifestDeleted func(ManifestDeleteInfo)

	// TableCreated is invoked when a table has been created.
	TableCreated func(TableCreateInfo)

	// TableDeleted is invoked after a table has been deleted.
	TableDeleted func(TableDeleteInfo)

	// TableIngested is invoked after an externally created table has been
	// ingested via a call to DB.Ingest().
	TableIngested func(TableIngestInfo)

	// TableStatsLoaded is invoked at most once, when the table stats
	// collector has loaded statistics for all tables that existed at Open.
	TableStatsLoaded func(TableStatsInfo)

	// TableValidated is invoked after validation runs on an sstable.
	TableValidated func(TableValidatedInfo)

	// WALCreated is invoked after a WAL has been created.
	WALCreated func(WALCreateInfo)

	// WALDeleted is invoked after a WAL has been deleted.
	WALDeleted func(WALDeleteInfo)

	// WriteStallBegin is invoked when writes are intentionally delayed.
	WriteStallBegin func(WriteStallBeginInfo)

	// WriteStallEnd is invoked when delayed writes are released.
	WriteStallEnd func()
}

type EventuallyFileOnlySnapshot struct {
	// contains filtered or unexported fields
}

type ExternalFile struct {
	// Locator is the shared.Locator that can be used with objProvider to
	// resolve a reference to this external sstable.
	Locator remote.Locator
	// ObjName is the unique name of this sstable on Locator.
	ObjName string
	// Size of the referenced proportion of the virtualized sstable. An estimate
	// is acceptable in lieu of the backing file size.
	Size uint64
	// SmallestUserKey and LargestUserKey are the [smallest,largest) user key
	// bounds of the sstable. Both these bounds are loose i.e. it's possible for
	// the sstable to not span the entirety of this range. However, multiple
	// ExternalFiles in one ingestion must all have non-overlapping
	// [smallest, largest) spans. Note that this Largest bound is exclusive.
	SmallestUserKey, LargestUserKey []byte
	// HasPointKey and HasRangeKey denote whether this file contains point keys
	// or range keys. If both structs are false, an error is returned during
	// ingestion.
	HasPointKey, HasRangeKey bool
}

type ExternalIterForwardOnly struct{}

type ExternalIterOption interface {
	// contains filtered or unexported methods
}

type FileNum = base.FileNum

type FilterMetrics = sstable.FilterMetrics

type FilterPolicy = base.FilterPolicy

type FilterType = base.FilterType

type FilterWriter = base.FilterWriter

type FlushInfo struct {
	// JobID is the ID of the flush job.
	JobID int
	// Reason is the reason for the flush.
	Reason string
	// Input contains the count of input memtables that were flushed.
	Input int
	// InputBytes contains the total in-memory size of the memtable(s) that were
	// flushed. This size includes skiplist indexing data structures.
	InputBytes uint64
	// Output contains the ouptut table generated by the flush. The output info
	// is empty for the flush begin event.
	Output []TableInfo
	// Duration is the time spent flushing. This duration includes writing and
	// syncing all of the flushed keys to sstables.
	Duration time.Duration
	// TotalDuration is the total wall-time duration of the flush, including
	// applying the flush to the database. TotalDuration is always ≥ Duration.
	TotalDuration time.Duration
	// Ingest is set to true if the flush is handling tables that were added to
	// the flushable queue via an ingestion operation.
	Ingest bool
	// IngestLevels are the output levels for each ingested table in the flush.
	// This field is only populated when Ingest is true.
	IngestLevels []int
	Done         bool
	Err          error
}

type FormatMajorVersion uint64

type IngestOperationStats struct {
	// Bytes is the total bytes in the ingested sstables.
	Bytes uint64
	// ApproxIngestedIntoL0Bytes is the approximate number of bytes ingested
	// into L0. This value is approximate when flushable ingests are active and
	// an ingest overlaps an entry in the flushable queue. Currently, this
	// approximation is very rough, only including tables that overlapped the
	// memtable. This estimate may be improved with #2112.
	ApproxIngestedIntoL0Bytes uint64
	// MemtableOverlappingFiles is the count of ingested sstables
	// that overlapped keys in the memtables.
	MemtableOverlappingFiles int
}

type InternalIteratorStats = base.InternalIteratorStats

type InternalKey = base.InternalKey

type InternalKeyKind = base.InternalKeyKind

type IterKeyType int8

type IterOptions struct {
	// LowerBound specifies the smallest key (inclusive) that the iterator will
	// return during iteration. If the iterator is seeked or iterated past this
	// boundary the iterator will return Valid()==false. Setting LowerBound
	// effectively truncates the key space visible to the iterator.
	LowerBound []byte
	// UpperBound specifies the largest key (exclusive) that the iterator will
	// return during iteration. If the iterator is seeked or iterated past this
	// boundary the iterator will return Valid()==false. Setting UpperBound
	// effectively truncates the key space visible to the iterator.
	UpperBound []byte
	// TableFilter can be used to filter the tables that are scanned during
	// iteration based on the user properties. Return true to scan the table and
	// false to skip scanning. This function must be thread-safe since the same
	// function can be used by multiple iterators, if the iterator is cloned.
	TableFilter func(userProps map[string]string) bool
	// SkipPoint may be used to skip over point keys that don't match an
	// arbitrary predicate during iteration. If set, the Iterator invokes
	// SkipPoint for keys encountered. If SkipPoint returns true, the iterator
	// will skip the key without yielding it to the iterator operation in
	// progress.
	//
	// SkipPoint must be a pure function and always return the same result when
	// provided the same arguments. The iterator may call SkipPoint multiple
	// times for the same user key.
	SkipPoint func(userKey []byte) bool
	// PointKeyFilters can be used to avoid scanning tables and blocks in tables
	// when iterating over point keys. This slice represents an intersection
	// across all filters, i.e., all filters must indicate that the block is
	// relevant.
	//
	// Performance note: When len(PointKeyFilters) > 0, the caller should ensure
	// that cap(PointKeyFilters) is at least len(PointKeyFilters)+1. This helps
	// avoid allocations in Pebble internal code that mutates the slice.
	PointKeyFilters []BlockPropertyFilter
	// RangeKeyFilters can be usefd to avoid scanning tables and blocks in tables
	// when iterating over range keys. The same requirements that apply to
	// PointKeyFilters apply here too.
	RangeKeyFilters []BlockPropertyFilter
	// KeyTypes configures which types of keys to iterate over: point keys,
	// range keys, or both.
	KeyTypes IterKeyType
	// RangeKeyMasking can be used to enable automatic masking of point keys by
	// range keys. Range key masking is only supported during combined range key
	// and point key iteration mode (IterKeyTypePointsAndRanges).
	RangeKeyMasking RangeKeyMasking

	// OnlyReadGuaranteedDurable is an advanced option that is only supported by
	// the Reader implemented by DB. When set to true, only the guaranteed to be
	// durable state is visible in the iterator.
	// - This definition is made under the assumption that the FS implementation
	//   is providing a durability guarantee when data is synced.
	// - The visible state represents a consistent point in the history of the
	//   DB.
	// - The implementation is free to choose a conservative definition of what
	//   is guaranteed durable. For simplicity, the current implementation
	//   ignores memtables. A more sophisticated implementation could track the
	//   highest seqnum that is synced to the WAL and published and use that as
	//   the visible seqnum for an iterator. Note that the latter approach is
	//   not strictly better than the former since we can have DBs that are (a)
	//   synced more rarely than memtable flushes, (b) have no WAL. (a) is
	//   likely to be true in a future CockroachDB context where the DB
	//   containing the state machine may be rarely synced.
	// NB: this current implementation relies on the fact that memtables are
	// flushed in seqnum order, and any ingested sstables that happen to have a
	// lower seqnum than a non-flushed memtable don't have any overlapping keys.
	// This is the fundamental level invariant used in other code too, like when
	// merging iterators.
	//
	// Semantically, using this option provides the caller a "snapshot" as of
	// the time the most recent memtable was flushed. An alternate interface
	// would be to add a NewSnapshot variant. Creating a snapshot is heavier
	// weight than creating an iterator, so we have opted to support this
	// iterator option.
	OnlyReadGuaranteedDurable bool
	// UseL6Filters allows the caller to opt into reading filter blocks for L6
	// sstables. Helpful if a lot of SeekPrefixGEs are expected in quick
	// succession, that are also likely to not yield a single key. Filter blocks in
	// L6 can be relatively large, often larger than data blocks, so the benefit of
	// loading them in the cache is minimized if the probability of the key
	// existing is not low or if we just expect a one-time Seek (where loading the
	// data block directly is better).
	UseL6Filters bool
	// contains filtered or unexported fields
}

type IterValidityState int8

type Iterator struct {
	// contains filtered or unexported fields
}

type IteratorLevel struct {
	Kind IteratorLevelKind
	// FlushableIndex indicates the position within the flushable queue of this level.
	// Only valid if kind == IteratorLevelFlushable.
	FlushableIndex int
	// The level within the LSM. Only valid if Kind == IteratorLevelLSM.
	Level int
	// Sublevel is only valid if Kind == IteratorLevelLSM and Level == 0.
	Sublevel int
}

type IteratorLevelKind int8

type IteratorMetrics struct {
	// The read amplification experienced by this iterator. This is the sum of
	// the memtables, the L0 sublevels and the non-empty Ln levels. Higher read
	// amplification generally results in slower reads, though allowing higher
	// read amplification can also result in faster writes.
	ReadAmp int
}

type IteratorStats struct {
	// ForwardSeekCount includes SeekGE, SeekPrefixGE, First.
	ForwardSeekCount [NumStatsKind]int
	// ReverseSeek includes SeekLT, Last.
	ReverseSeekCount [NumStatsKind]int
	// ForwardStepCount includes Next.
	ForwardStepCount [NumStatsKind]int
	// ReverseStepCount includes Prev.
	ReverseStepCount [NumStatsKind]int
	InternalStats    InternalIteratorStats
	RangeKeyStats    RangeKeyIteratorStats
}

type IteratorStatsKind int8

type KeyRange struct {
	Start, End []byte
}

type KeyStatistics struct {

	// SnapshotPinnedKeys represents obsolete keys that cannot be elided during
	// a compaction, because they are required by an open snapshot.
	SnapshotPinnedKeys int
	// SnapshotPinnedKeysBytes is the total number of bytes of all snapshot
	// pinned keys.
	SnapshotPinnedKeysBytes uint64
	// KindsCount is the count for each kind of key. It includes point keys,
	// range deletes and range keys.
	KindsCount [InternalKeyKindMax + 1]int
	// LatestKindsCount is the count for each kind of key when it is the latest
	// kind for a user key. It is only populated for point keys.
	LatestKindsCount [InternalKeyKindMax + 1]int
}

type LSMKeyStatistics struct {
	Accumulated KeyStatistics
	// Levels contains statistics only for point keys. Range deletions and range keys will
	// appear in Accumulated but not Levels.
	Levels [numLevels]KeyStatistics
	// BytesRead represents the logical, pre-compression size of keys and values read
	BytesRead uint64
}

type LazyFetcher = base.LazyFetcher

type LazyValue = base.LazyValue

type LevelInfo struct {
	Level  int
	Tables []TableInfo
	Score  float64
}

type LevelMetrics struct {
	// The number of sublevels within the level. The sublevel count corresponds
	// to the read amplification for the level. An empty level will have a
	// sublevel count of 0, implying no read amplification. Only L0 will have
	// a sublevel count other than 0 or 1.
	Sublevels int32
	// The total number of files in the level.
	NumFiles int64
	// The total number of virtual sstables in the level.
	NumVirtualFiles uint64
	// The total size in bytes of the files in the level.
	Size int64
	// The total size of the virtual sstables in the level.
	VirtualSize uint64
	// The level's compaction score. This is the compensatedScoreRatio in the
	// candidateLevelInfo.
	Score float64
	// The number of incoming bytes from other levels read during
	// compactions. This excludes bytes moved and bytes ingested. For L0 this is
	// the bytes written to the WAL.
	BytesIn uint64
	// The number of bytes ingested. The sibling metric for tables is
	// TablesIngested.
	BytesIngested uint64
	// The number of bytes moved into the level by a "move" compaction. The
	// sibling metric for tables is TablesMoved.
	BytesMoved uint64
	// The number of bytes read for compactions at the level. This includes bytes
	// read from other levels (BytesIn), as well as bytes read for the level.
	BytesRead uint64
	// The number of bytes written during compactions. The sibling
	// metric for tables is TablesCompacted. This metric may be summed
	// with BytesFlushed to compute the total bytes written for the level.
	BytesCompacted uint64
	// The number of bytes written during flushes. The sibling
	// metrics for tables is TablesFlushed. This metric is always
	// zero for all levels other than L0.
	BytesFlushed uint64
	// The number of sstables compacted to this level.
	TablesCompacted uint64
	// The number of sstables flushed to this level.
	TablesFlushed uint64
	// The number of sstables ingested into the level.
	TablesIngested uint64
	// The number of sstables moved to this level by a "move" compaction.
	TablesMoved uint64

	MultiLevel struct {
		// BytesInTop are the total bytes in a multilevel compaction coming from the top level.
		BytesInTop uint64

		// BytesIn, exclusively for multiLevel compactions.
		BytesIn uint64

		// BytesRead, exclusively for multilevel compactions.
		BytesRead uint64
	}

	// Additional contains misc additional metrics that are not always printed.
	Additional struct {
		// The sum of Properties.ValueBlocksSize for all the sstables in this
		// level. Printed by LevelMetrics.format iff there is at least one level
		// with a non-zero value.
		ValueBlocksSize uint64
		// Cumulative metrics about bytes written to data blocks and value blocks,
		// via compactions (except move compactions) or flushes. Not printed by
		// LevelMetrics.format, but are available to sophisticated clients.
		BytesWrittenDataBlocks  uint64
		BytesWrittenValueBlocks uint64
	}
}

type LevelOptions struct {
	// BlockRestartInterval is the number of keys between restart points
	// for delta encoding of keys.
	//
	// The default value is 16.
	BlockRestartInterval int

	// BlockSize is the target uncompressed size in bytes of each table block.
	//
	// The default value is 4096.
	BlockSize int

	// BlockSizeThreshold finishes a block if the block size is larger than the
	// specified percentage of the target block size and adding the next entry
	// would cause the block to be larger than the target block size.
	//
	// The default value is 90
	BlockSizeThreshold int

	// Compression defines the per-block compression to use.
	//
	// The default value (DefaultCompression) uses snappy compression.
	Compression Compression

	// FilterPolicy defines a filter algorithm (such as a Bloom filter) that can
	// reduce disk reads for Get calls.
	//
	// One such implementation is bloom.FilterPolicy(10) from the pebble/bloom
	// package.
	//
	// The default value means to use no filter.
	FilterPolicy FilterPolicy

	// FilterType defines whether an existing filter policy is applied at a
	// block-level or table-level. Block-level filters use less memory to create,
	// but are slower to access as a check for the key in the index must first be
	// performed to locate the filter block. A table-level filter will require
	// memory proportional to the number of keys in an sstable to create, but
	// avoids the index lookup when determining if a key is present. Table-level
	// filters should be preferred except under constrained memory situations.
	FilterType FilterType

	// IndexBlockSize is the target uncompressed size in bytes of each index
	// block. When the index block size is larger than this target, two-level
	// indexes are automatically enabled. Setting this option to a large value
	// (such as math.MaxInt32) disables the automatic creation of two-level
	// indexes.
	//
	// The default value is the value of BlockSize.
	IndexBlockSize int

	// The target file size for the level.
	TargetFileSize int64
}

type Lock struct {
	// contains filtered or unexported fields
}

type Logger = base.Logger

type LoggerAndTracer = base.LoggerAndTracer

type ManifestCreateInfo struct {
	// JobID is the ID of the job the caused the manifest to be created.
	JobID int
	Path  string
	// The file number of the new Manifest.
	FileNum FileNum
	Err     error
}

type ManifestDeleteInfo struct {
	// JobID is the ID of the job the caused the Manifest to be deleted.
	JobID   int
	Path    string
	FileNum FileNum
	Err     error
}

type Merge = base.Merge

type Merger = base.Merger

type Metrics struct {
	BlockCache CacheMetrics

	Compact struct {
		// The total number of compactions, and per-compaction type counts.
		Count             int64
		DefaultCount      int64
		DeleteOnlyCount   int64
		ElisionOnlyCount  int64
		MoveCount         int64
		ReadCount         int64
		RewriteCount      int64
		MultiLevelCount   int64
		CounterLevelCount int64
		// An estimate of the number of bytes that need to be compacted for the LSM
		// to reach a stable state.
		EstimatedDebt uint64
		// Number of bytes present in sstables being written by in-progress
		// compactions. This value will be zero if there are no in-progress
		// compactions.
		InProgressBytes int64
		// Number of compactions that are in-progress.
		NumInProgress int64
		// MarkedFiles is a count of files that are marked for
		// compaction. Such files are compacted in a rewrite compaction
		// when no other compactions are picked.
		MarkedFiles int
		// Duration records the cumulative duration of all compactions since the
		// database was opened.
		Duration time.Duration
	}

	Ingest struct {
		// The total number of ingestions
		Count uint64
	}

	Flush struct {
		// The total number of flushes.
		Count           int64
		WriteThroughput ThroughputMetric
		// Number of flushes that are in-progress. In the current implementation
		// this will always be zero or one.
		NumInProgress int64
		// AsIngestCount is a monotonically increasing counter of flush operations
		// handling ingested tables.
		AsIngestCount uint64
		// AsIngestCount is a monotonically increasing counter of tables ingested as
		// flushables.
		AsIngestTableCount uint64
		// AsIngestBytes is a monotonically increasing counter of the bytes flushed
		// for flushables that originated as ingestion operations.
		AsIngestBytes uint64
	}

	Filter FilterMetrics

	Levels [numLevels]LevelMetrics

	MemTable struct {
		// The number of bytes allocated by memtables and large (flushable)
		// batches.
		Size uint64
		// The count of memtables.
		Count int64
		// The number of bytes present in zombie memtables which are no longer
		// referenced by the current DB state. An unbounded number of memtables
		// may be zombie if they're still in use by an iterator. One additional
		// memtable may be zombie if it's no longer in use and waiting to be
		// recycled.
		ZombieSize uint64
		// The count of zombie memtables.
		ZombieCount int64
	}

	Keys struct {
		// The approximate count of internal range key set keys in the database.
		RangeKeySetsCount uint64
		// The approximate count of internal tombstones (DEL, SINGLEDEL and
		// RANGEDEL key kinds) within the database.
		TombstoneCount uint64
		// A cumulative total number of missized DELSIZED keys encountered by
		// compactions since the database was opened.
		MissizedTombstonesCount uint64
	}

	Snapshots struct {
		// The number of currently open snapshots.
		Count int
		// The sequence number of the earliest, currently open snapshot.
		EarliestSeqNum uint64
		// A running tally of keys written to sstables during flushes or
		// compactions that would've been elided if it weren't for open
		// snapshots.
		PinnedKeys uint64
		// A running cumulative sum of the size of keys and values written to
		// sstables during flushes or compactions that would've been elided if
		// it weren't for open snapshots.
		PinnedSize uint64
	}

	Table struct {
		// The number of bytes present in obsolete tables which are no longer
		// referenced by the current DB state or any open iterators.
		ObsoleteSize uint64
		// The count of obsolete tables.
		ObsoleteCount int64
		// The number of bytes present in zombie tables which are no longer
		// referenced by the current DB state but are still in use by an iterator.
		ZombieSize uint64
		// The count of zombie tables.
		ZombieCount int64
		// The count of the backing sstables.
		BackingTableCount uint64
		// The sum of the sizes of the all of the backing sstables.
		BackingTableSize uint64
	}

	TableCache CacheMetrics

	// Count of the number of open sstable iterators.
	TableIters int64
	// Uptime is the total time since this DB was opened.
	Uptime time.Duration

	WAL struct {
		// Number of live WAL files.
		Files int64
		// Number of obsolete WAL files.
		ObsoleteFiles int64
		// Physical size of the obsolete WAL files.
		ObsoletePhysicalSize uint64
		// Size of the live data in the WAL files. Note that with WAL file
		// recycling this is less than the actual on-disk size of the WAL files.
		Size uint64
		// Physical size of the WAL files on-disk. With WAL file recycling,
		// this is greater than the live data in WAL files.
		PhysicalSize uint64
		// Number of logical bytes written to the WAL.
		BytesIn uint64
		// Number of bytes written to the WAL.
		BytesWritten uint64
	}

	LogWriter struct {
		FsyncLatency prometheus.Histogram
		record.LogWriterMetrics
	}

	SecondaryCacheMetrics SecondaryCacheMetrics
	// contains filtered or unexported fields
}

type MultiLevelHeuristic interface {
	// contains filtered or unexported methods
}

type NoMultiLevel struct{}

type Options struct {
	// Sync sstables periodically in order to smooth out writes to disk. This
	// option does not provide any persistency guarantee, but is used to avoid
	// latency spikes if the OS automatically decides to write out a large chunk
	// of dirty filesystem buffers. This option only controls SSTable syncs; WAL
	// syncs are controlled by WALBytesPerSync.
	//
	// The default value is 512KB.
	BytesPerSync int

	// Cache is used to cache uncompressed blocks from sstables.
	//
	// The default cache size is 8 MB.
	Cache *cache.Cache

	// Cleaner cleans obsolete files.
	//
	// The default cleaner uses the DeleteCleaner.
	Cleaner Cleaner

	// Comparer defines a total ordering over the space of []byte keys: a 'less
	// than' relationship. The same comparison algorithm must be used for reads
	// and writes over the lifetime of the DB.
	//
	// The default value uses the same ordering as bytes.Compare.
	Comparer *Comparer

	// DebugCheck is invoked, if non-nil, whenever a new version is being
	// installed. Typically, this is set to pebble.DebugCheckLevels in tests
	// or tools only, to check invariants over all the data in the database.
	DebugCheck func(*DB) error

	// Disable the write-ahead log (WAL). Disabling the write-ahead log prohibits
	// crash recovery, but can improve performance if crash recovery is not
	// needed (e.g. when only temporary state is being stored in the database).
	//
	// TODO(peter): untested
	DisableWAL bool

	// ErrorIfExists causes an error on Open if the database already exists.
	// The error can be checked with errors.Is(err, ErrDBAlreadyExists).
	//
	// The default value is false.
	ErrorIfExists bool

	// ErrorIfNotExists causes an error on Open if the database does not already
	// exist. The error can be checked with errors.Is(err, ErrDBDoesNotExist).
	//
	// The default value is false which will cause a database to be created if it
	// does not already exist.
	ErrorIfNotExists bool

	// ErrorIfNotPristine causes an error on Open if the database already exists
	// and any operations have been performed on the database. The error can be
	// checked with errors.Is(err, ErrDBNotPristine).
	//
	// Note that a database that contained keys that were all subsequently deleted
	// may or may not trigger the error. Currently, we check if there are any live
	// SSTs or log records to replay.
	ErrorIfNotPristine bool

	// EventListener provides hooks to listening to significant DB events such as
	// flushes, compactions, and table deletion.
	EventListener *EventListener

	// Experimental contains experimental options which are off by default.
	// These options are temporary and will eventually either be deleted, moved
	// out of the experimental group, or made the non-adjustable default. These
	// options may change at any time, so do not rely on them.
	Experimental struct {
		// The threshold of L0 read-amplification at which compaction concurrency
		// is enabled (if CompactionDebtConcurrency was not already exceeded).
		// Every multiple of this value enables another concurrent
		// compaction up to MaxConcurrentCompactions.
		L0CompactionConcurrency int

		// CompactionDebtConcurrency controls the threshold of compaction debt
		// at which additional compaction concurrency slots are added. For every
		// multiple of this value in compaction debt bytes, an additional
		// concurrent compaction is added. This works "on top" of
		// L0CompactionConcurrency, so the higher of the count of compaction
		// concurrency slots as determined by the two options is chosen.
		CompactionDebtConcurrency uint64

		// IngestSplit, if it returns true, allows for ingest-time splitting of
		// existing sstables into two virtual sstables to allow ingestion sstables to
		// slot into a lower level than they otherwise would have.
		IngestSplit func() bool

		// ReadCompactionRate controls the frequency of read triggered
		// compactions by adjusting `AllowedSeeks` in manifest.FileMetadata:
		//
		// AllowedSeeks = FileSize / ReadCompactionRate
		//
		// From LevelDB:
		// “`
		// We arrange to automatically compact this file after
		// a certain number of seeks. Let's assume:
		//   (1) One seek costs 10ms
		//   (2) Writing or reading 1MB costs 10ms (100MB/s)
		//   (3) A compaction of 1MB does 25MB of IO:
		//         1MB read from this level
		//         10-12MB read from next level (boundaries may be misaligned)
		//         10-12MB written to next level
		// This implies that 25 seeks cost the same as the compaction
		// of 1MB of data.  I.e., one seek costs approximately the
		// same as the compaction of 40KB of data.  We are a little
		// conservative and allow approximately one seek for every 16KB
		// of data before triggering a compaction.
		// “`
		ReadCompactionRate int64

		// ReadSamplingMultiplier is a multiplier for the readSamplingPeriod in
		// iterator.maybeSampleRead() to control the frequency of read sampling
		// to trigger a read triggered compaction. A value of -1 prevents sampling
		// and disables read triggered compactions. The default is 1 << 4. which
		// gets multiplied with a constant of 1 << 16 to yield 1 << 20 (1MB).
		ReadSamplingMultiplier int64

		// TableCacheShards is the number of shards per table cache.
		// Reducing the value can reduce the number of idle goroutines per DB
		// instance which can be useful in scenarios with a lot of DB instances
		// and a large number of CPUs, but doing so can lead to higher contention
		// in the table cache and reduced performance.
		//
		// The default value is the number of logical CPUs, which can be
		// limited by runtime.GOMAXPROCS.
		TableCacheShards int

		// KeyValidationFunc is a function to validate a user key in an SSTable.
		//
		// Currently, this function is used to validate the smallest and largest
		// keys in an SSTable undergoing compaction. In this case, returning an
		// error from the validation function will result in a panic at runtime,
		// given that there is rarely any way of recovering from malformed keys
		// present in compacted files. By default, validation is not performed.
		//
		// Additional use-cases may be added in the future.
		//
		// NOTE: callers should take care to not mutate the key being validated.
		KeyValidationFunc func(userKey []byte) error

		// ValidateOnIngest schedules validation of sstables after they have
		// been ingested.
		//
		// By default, this value is false.
		ValidateOnIngest bool

		// LevelMultiplier configures the size multiplier used to determine the
		// desired size of each level of the LSM. Defaults to 10.
		LevelMultiplier int

		// MultiLevelCompactionHeuristic determines whether to add an additional
		// level to a conventional two level compaction. If nil, a multilevel
		// compaction will never get triggered.
		MultiLevelCompactionHeuristic MultiLevelHeuristic

		// MaxWriterConcurrency is used to indicate the maximum number of
		// compression workers the compression queue is allowed to use. If
		// MaxWriterConcurrency > 0, then the Writer will use parallelism, to
		// compress and write blocks to disk. Otherwise, the writer will
		// compress and write blocks to disk synchronously.
		MaxWriterConcurrency int

		// ForceWriterParallelism is used to force parallelism in the sstable
		// Writer for the metamorphic tests. Even with the MaxWriterConcurrency
		// option set, we only enable parallelism in the sstable Writer if there
		// is enough CPU available, and this option bypasses that.
		ForceWriterParallelism bool

		// CPUWorkPermissionGranter should be set if Pebble should be given the
		// ability to optionally schedule additional CPU. See the documentation
		// for CPUWorkPermissionGranter for more details.
		CPUWorkPermissionGranter CPUWorkPermissionGranter

		// EnableValueBlocks is used to decide whether to enable writing
		// TableFormatPebblev3 sstables. This setting is only respected by a
		// specific subset of format major versions: FormatSSTableValueBlocks,
		// FormatFlushableIngest and FormatPrePebblev1MarkedCompacted. In lower
		// format major versions, value blocks are never enabled. In higher
		// format major versions, value blocks are always enabled.
		EnableValueBlocks func() bool

		// ShortAttributeExtractor is used iff EnableValueBlocks() returns true
		// (else ignored). If non-nil, a ShortAttribute can be extracted from the
		// value and stored with the key, when the value is stored elsewhere.
		ShortAttributeExtractor ShortAttributeExtractor

		// RequiredInPlaceValueBound specifies an optional span of user key
		// prefixes that are not-MVCC, but have a suffix. For these the values
		// must be stored with the key, since the concept of "older versions" is
		// not defined. It is also useful for statically known exclusions to value
		// separation. In CockroachDB, this will be used for the lock table key
		// space that has non-empty suffixes, but those locks don't represent
		// actual MVCC versions (the suffix ordering is arbitrary). We will also
		// need to add support for dynamically configured exclusions (we want the
		// default to be to allow Pebble to decide whether to separate the value
		// or not, hence this is structured as exclusions), for example, for users
		// of CockroachDB to dynamically exclude certain tables.
		//
		// Any change in exclusion behavior takes effect only on future written
		// sstables, and does not start rewriting existing sstables.
		//
		// Even ignoring changes in this setting, exclusions are interpreted as a
		// guidance by Pebble, and not necessarily honored. Specifically, user
		// keys with multiple Pebble-versions *may* have the older versions stored
		// in value blocks.
		RequiredInPlaceValueBound UserKeyPrefixBound

		// DisableIngestAsFlushable disables lazy ingestion of sstables through
		// a WAL write and memtable rotation. Only effectual if the the format
		// major version is at least `FormatFlushableIngest`.
		DisableIngestAsFlushable func() bool

		// RemoteStorage enables use of remote storage (e.g. S3) for storing
		// sstables. Setting this option enables use of CreateOnShared option and
		// allows ingestion of external files.
		RemoteStorage remote.StorageFactory

		// If CreateOnShared is non-zero, new sstables are created on remote storage
		// (using CreateOnSharedLocator and with the appropriate
		// CreateOnSharedStrategy). These sstables can be shared between different
		// Pebble instances; the lifecycle of such objects is managed by the
		// remote.Storage constructed by options.RemoteStorage.
		//
		// Can only be used when RemoteStorage is set (and recognizes
		// CreateOnSharedLocator).
		CreateOnShared        remote.CreateOnSharedStrategy
		CreateOnSharedLocator remote.Locator

		// CacheSizeBytesBytes is the size of the on-disk block cache for objects
		// on shared storage in bytes. If it is 0, no cache is used.
		SecondaryCacheSizeBytes int64

		// IneffectualPointDeleteCallback is called in compactions/flushes if any
		// single delete is being elided without deleting a point set/merge.
		IneffectualSingleDeleteCallback func(userKey []byte)

		// SingleDeleteInvariantViolationCallback is called in compactions/flushes if any
		// single delete has consumed a Set/Merge, and there is another immediately older
		// Set/SetWithDelete/Merge. The user of Pebble has violated the invariant under
		// which SingleDelete can be used correctly.
		//
		// Consider the sequence SingleDelete#3, Set#2, Set#1. There are three
		// ways some of these keys can first meet in a compaction.
		//
		// - All 3 keys in the same compaction: this callback will detect the
		//   violation.
		//
		// - SingleDelete#3, Set#2 meet in a compaction first: Both keys will
		//   disappear. The violation will not be detected, and the DB will have
		//   Set#1 which is likely incorrect (from the user's perspective).
		//
		// - Set#2, Set#1 meet in a compaction first: The output will be Set#2,
		//   which will later be consumed by SingleDelete#3. The violation will
		//   not be detected and the DB will be correct.
		SingleDeleteInvariantViolationCallback func(userKey []byte)
	}

	// Filters is a map from filter policy name to filter policy. It is used for
	// debugging tools which may be used on multiple databases configured with
	// different filter policies. It is not necessary to populate this filters
	// map during normal usage of a DB.
	Filters map[string]FilterPolicy

	// FlushDelayDeleteRange configures how long the database should wait before
	// forcing a flush of a memtable that contains a range deletion. Disk space
	// cannot be reclaimed until the range deletion is flushed. No automatic
	// flush occurs if zero.
	FlushDelayDeleteRange time.Duration

	// FlushDelayRangeKey configures how long the database should wait before
	// forcing a flush of a memtable that contains a range key. Range keys in
	// the memtable prevent lazy combined iteration, so it's desirable to flush
	// range keys promptly. No automatic flush occurs if zero.
	FlushDelayRangeKey time.Duration

	// FlushSplitBytes denotes the target number of bytes per sublevel in
	// each flush split interval (i.e. range between two flush split keys)
	// in L0 sstables. When set to zero, only a single sstable is generated
	// by each flush. When set to a non-zero value, flushes are split at
	// points to meet L0's TargetFileSize, any grandparent-related overlap
	// options, and at boundary keys of L0 flush split intervals (which are
	// targeted to contain around FlushSplitBytes bytes in each sublevel
	// between pairs of boundary keys). Splitting sstables during flush
	// allows increased compaction flexibility and concurrency when those
	// tables are compacted to lower levels.
	FlushSplitBytes int64

	// FormatMajorVersion sets the format of on-disk files. It is
	// recommended to set the format major version to an explicit
	// version, as the default may change over time.
	//
	// At Open if the existing database is formatted using a later
	// format major version that is known to this version of Pebble,
	// Pebble will continue to use the later format major version. If
	// the existing database's version is unknown, the caller may use
	// FormatMostCompatible and will be able to open the database
	// regardless of its actual version.
	//
	// If the existing database is formatted using a format major
	// version earlier than the one specified, Open will automatically
	// ratchet the database to the specified format major version.
	FormatMajorVersion FormatMajorVersion

	// FS provides the interface for persistent file storage.
	//
	// The default value uses the underlying operating system's file system.
	FS vfs.FS

	// Lock, if set, must be a database lock acquired through LockDirectory for
	// the same directory passed to Open. If provided, Open will skip locking
	// the directory. Closing the database will not release the lock, and it's
	// the responsibility of the caller to release the lock after closing the
	// database.
	//
	// Open will enforce that the Lock passed locks the same directory passed to
	// Open. Concurrent calls to Open using the same Lock are detected and
	// prohibited.
	Lock *Lock

	// The count of L0 files necessary to trigger an L0 compaction.
	L0CompactionFileThreshold int

	// The amount of L0 read-amplification necessary to trigger an L0 compaction.
	L0CompactionThreshold int

	// Hard limit on L0 read-amplification, computed as the number of L0
	// sublevels. Writes are stopped when this threshold is reached.
	L0StopWritesThreshold int

	// The maximum number of bytes for LBase. The base level is the level which
	// L0 is compacted into. The base level is determined dynamically based on
	// the existing data in the LSM. The maximum number of bytes for other levels
	// is computed dynamically based on the base level's maximum size. When the
	// maximum number of bytes for a level is exceeded, compaction is requested.
	LBaseMaxBytes int64

	// Per-level options. Options for at least one level must be specified. The
	// options for the last level are used for all subsequent levels.
	Levels []LevelOptions

	// Logger used to write log messages.
	//
	// The default logger uses the Go standard library log package.
	Logger Logger
	// LoggerAndTracer is used for writing log messages and traces.
	LoggerAndTracer LoggerAndTracer

	// MaxManifestFileSize is the maximum size the MANIFEST file is allowed to
	// become. When the MANIFEST exceeds this size it is rolled over and a new
	// MANIFEST is created.
	MaxManifestFileSize int64

	// MaxOpenFiles is a soft limit on the number of open files that can be
	// used by the DB.
	//
	// The default value is 1000.
	MaxOpenFiles int

	// The size of a MemTable in steady state. The actual MemTable size starts at
	// min(256KB, MemTableSize) and doubles for each subsequent MemTable up to
	// MemTableSize. This reduces the memory pressure caused by MemTables for
	// short lived (test) DB instances. Note that more than one MemTable can be
	// in existence since flushing a MemTable involves creating a new one and
	// writing the contents of the old one in the
	// background. MemTableStopWritesThreshold places a hard limit on the size of
	// the queued MemTables.
	//
	// The default value is 4MB.
	MemTableSize uint64

	// Hard limit on the number of queued of MemTables. Writes are stopped when
	// the sum of the queued memtable sizes exceeds:
	//   MemTableStopWritesThreshold * MemTableSize.
	//
	// This value should be at least 2 or writes will stop whenever a MemTable is
	// being flushed.
	//
	// The default value is 2.
	MemTableStopWritesThreshold int

	// Merger defines the associative merge operation to use for merging values
	// written with {Batch,DB}.Merge.
	//
	// The default merger concatenates values.
	Merger *Merger

	// MaxConcurrentCompactions specifies the maximum number of concurrent
	// compactions. The default is 1. Concurrent compactions are performed
	// - when L0 read-amplification passes the L0CompactionConcurrency threshold
	// - for automatic background compactions
	// - when a manual compaction for a level is split and parallelized
	// MaxConcurrentCompactions must be greater than 0.
	MaxConcurrentCompactions func() int

	// DisableAutomaticCompactions dictates whether automatic compactions are
	// scheduled or not. The default is false (enabled). This option is only used
	// externally when running a manual compaction, and internally for tests.
	DisableAutomaticCompactions bool

	// NoSyncOnClose decides whether the Pebble instance will enforce a
	// close-time synchronization (e.g., fdatasync() or sync_file_range())
	// on files it writes to. Setting this to true removes the guarantee for a
	// sync on close. Some implementations can still issue a non-blocking sync.
	NoSyncOnClose bool

	// NumPrevManifest is the number of non-current or older manifests which
	// we want to keep around for debugging purposes. By default, we're going
	// to keep one older manifest.
	NumPrevManifest int

	// ReadOnly indicates that the DB should be opened in read-only mode. Writes
	// to the DB will return an error, background compactions are disabled, and
	// the flush that normally occurs after replaying the WAL at startup is
	// disabled.
	ReadOnly bool

	// TableCache is an initialized TableCache which should be set as an
	// option if the DB needs to be initialized with a pre-existing table cache.
	// If TableCache is nil, then a table cache which is unique to the DB instance
	// is created. TableCache can be shared between db instances by setting it here.
	// The TableCache set here must use the same underlying cache as Options.Cache
	// and pebble will panic otherwise.
	TableCache *TableCache

	// TablePropertyCollectors is a list of TablePropertyCollector creation
	// functions. A new TablePropertyCollector is created for each sstable built
	// and lives for the lifetime of the table.
	TablePropertyCollectors []func() TablePropertyCollector

	// BlockPropertyCollectors is a list of BlockPropertyCollector creation
	// functions. A new BlockPropertyCollector is created for each sstable
	// built and lives for the lifetime of writing that table.
	BlockPropertyCollectors []func() BlockPropertyCollector

	// WALBytesPerSync sets the number of bytes to write to a WAL before calling
	// Sync on it in the background. Just like with BytesPerSync above, this
	// helps smooth out disk write latencies, and avoids cases where the OS
	// writes a lot of buffered data to disk at once. However, this is less
	// necessary with WALs, as many write operations already pass in
	// Sync = true.
	//
	// The default value is 0, i.e. no background syncing. This matches the
	// default behaviour in RocksDB.
	WALBytesPerSync int

	// WALDir specifies the directory to store write-ahead logs (WALs) in. If
	// empty (the default), WALs will be stored in the same directory as sstables
	// (i.e. the directory passed to pebble.Open).
	WALDir string

	// WALMinSyncInterval is the minimum duration between syncs of the WAL. If
	// WAL syncs are requested faster than this interval, they will be
	// artificially delayed. Introducing a small artificial delay (500us) between
	// WAL syncs can allow more operations to arrive and reduce IO operations
	// while having a minimal impact on throughput. This option is supplied as a
	// closure in order to allow the value to be changed dynamically. The default
	// value is 0.
	//
	// TODO(peter): rather than a closure, should there be another mechanism for
	// changing options dynamically?
	WALMinSyncInterval func() time.Duration

	// TargetByteDeletionRate is the rate (in bytes per second) at which sstable file
	// deletions are limited to (under normal circumstances).
	//
	// Deletion pacing is used to slow down deletions when compactions finish up
	// or readers close and newly-obsolete files need cleaning up. Deleting lots
	// of files at once can cause disk latency to go up on some SSDs, which this
	// functionality guards against.
	//
	// This value is only a best-effort target; the effective rate can be
	// higher if deletions are falling behind or disk space is running low.
	//
	// Setting this to 0 disables deletion pacing, which is also the default.
	TargetByteDeletionRate int
	// contains filtered or unexported fields
}

type ParseHooks struct {
	NewCache        func(size int64) *Cache
	NewCleaner      func(name string) (Cleaner, error)
	NewComparer     func(name string) (*Comparer, error)
	NewFilterPolicy func(name string) (FilterPolicy, error)
	NewMerger       func(name string) (*Merger, error)
	SkipUnknown     func(name, value string) bool
}

type RangeKeyData struct {
	Suffix []byte
	Value  []byte
}

type RangeKeyIteratorStats struct {
	// Count records the number of range keys encountered during
	// iteration. Range keys may be counted multiple times if the iterator
	// leaves a range key's bounds and then returns.
	Count int
	// ContainedPoints records the number of point keys encountered within the
	// bounds of a range key. Note that this includes point keys with suffixes
	// that sort both above and below the covering range key's suffix.
	ContainedPoints int
	// SkippedPoints records the count of the subset of ContainedPoints point
	// keys that were skipped during iteration due to range-key masking. It does
	// not include point keys that were never loaded because a
	// RangeKeyMasking.Filter excluded the entire containing block.
	SkippedPoints int
}

type RangeKeyMasking struct {
	// Suffix configures which range keys may mask point keys. Only range keys
	// that are defined at suffixes greater than or equal to Suffix will mask
	// point keys.
	Suffix []byte
	// Filter is an optional field that may be used to improve performance of
	// range-key masking through a block-property filter defined over key
	// suffixes. If non-nil, Filter is called by Pebble to construct a
	// block-property filter mask at iterator creation. The filter is used to
	// skip whole point-key blocks containing point keys with suffixes greater
	// than a covering range-key's suffix.
	//
	// To use this functionality, the caller must create and configure (through
	// Options.BlockPropertyCollectors) a block-property collector that records
	// the maxmimum suffix contained within a block. The caller then must write
	// and provide a BlockPropertyFilterMask implementation on that same
	// property. See the BlockPropertyFilterMask type for more information.
	Filter func() BlockPropertyFilterMask
}

type Reader interface {
	// Get gets the value for the given key. It returns ErrNotFound if the DB
	// does not contain the key.
	//
	// The caller should not modify the contents of the returned slice, but it is
	// safe to modify the contents of the argument after Get returns. The
	// returned slice will remain valid until the returned Closer is closed. On
	// success, the caller MUST call closer.Close() or a memory leak will occur.
	Get(key []byte) (value []byte, closer io.Closer, err error)

	// NewIter returns an iterator that is unpositioned (Iterator.Valid() will
	// return false). The iterator can be positioned via a call to SeekGE,
	// SeekLT, First or Last.
	NewIter(o *IterOptions) (*Iterator, error)

	// Close closes the Reader. It may or may not close any underlying io.Reader
	// or io.Writer, depending on how the DB was created.
	//
	// It is not safe to close a DB until all outstanding iterators are closed.
	// It is valid to call Close multiple times. Other methods should not be
	// called after the DB has been closed.
	Close() error
}

type SSTableInfo struct {
	manifest.TableInfo
	// Virtual indicates whether the sstable is virtual.
	Virtual bool
	// BackingSSTNum is the file number associated with backing sstable which
	// backs the sstable associated with this SSTableInfo. If Virtual is false,
	// then BackingSSTNum == FileNum.
	BackingSSTNum base.FileNum
	// BackingType is the type of storage backing this sstable.
	BackingType BackingType
	// Locator is the remote.Locator backing this sstable, if the backing type is
	// not BackingTypeLocal.
	Locator remote.Locator

	// Properties is the sstable properties of this table. If Virtual is true,
	// then the Properties are associated with the backing sst.
	Properties *sstable.Properties
}

type SSTablesOption func(*sstablesOptions)

type ScanStatisticsOptions struct {
	// LimitBytesPerSecond indicates the number of bytes that are able to be read
	// per second using ScanInternal.
	// A value of 0 indicates that there is no limit set.
	LimitBytesPerSecond int64
}

type SecondaryCacheMetrics = sharedcache.Metrics

type Separator = base.Separator

type SharedSSTMeta struct {
	// Backing is the shared object underlying this SST. Can be attached to an
	// objstorage.Provider.
	Backing objstorage.RemoteObjectBackingHandle

	// Smallest and Largest internal keys for the overall bounds. The kind and
	// SeqNum of these will reflect what is physically present on the source Pebble
	// instance's view of the sstable; it's up to the ingesting instance to set the
	// sequence number in the trailer to match the read-time sequence numbers
	// reserved for the level this SST is being ingested into. The Kind is expected
	// to remain unchanged by the ingesting instance.
	//
	// Note that these bounds could be narrower than the bounds of the underlying
	// sstable; ScanInternal is expected to truncate sstable bounds to the user key
	// bounds passed into that method.
	Smallest, Largest InternalKey

	// SmallestRangeKey and LargestRangeKey are internal keys that denote the
	// range key bounds of this sstable. Must lie within [Smallest, Largest].
	SmallestRangeKey, LargestRangeKey InternalKey

	// SmallestPointKey and LargestPointKey are internal keys that denote the
	// point key bounds of this sstable. Must lie within [Smallest, Largest].
	SmallestPointKey, LargestPointKey InternalKey

	// Level denotes the level at which this file was present at read time.
	// For files visited by ScanInternal, this value will only be 5 or 6.
	Level uint8

	// Size contains an estimate of the size of this sstable.
	Size uint64
	// contains filtered or unexported fields
}

type ShortAttribute = base.ShortAttribute

type ShortAttributeExtractor = base.ShortAttributeExtractor

type Snapshot struct {
	// contains filtered or unexported fields
}

type Split = base.Split

type Successor = base.Successor

type TableCache struct {
	// contains filtered or unexported fields
}

type TableCreateInfo struct {
	JobID int
	// Reason is the reason for the table creation: "compacting", "flushing", or
	// "ingesting".
	Reason  string
	Path    string
	FileNum FileNum
}

type TableDeleteInfo struct {
	JobID   int
	Path    string
	FileNum FileNum
	Err     error
}

type TableInfo = manifest.TableInfo

type TableIngestInfo struct {
	// JobID is the ID of the job the caused the table to be ingested.
	JobID  int
	Tables []struct {
		TableInfo
		Level int
	}
	// GlobalSeqNum is the sequence number that was assigned to all entries in
	// the ingested table.
	GlobalSeqNum uint64

	Err error
	// contains filtered or unexported fields
}

type TablePropertyCollector = sstable.TablePropertyCollector

type TableStatsInfo struct {
	// JobID is the ID of the job that finished loading the initial tables'
	// stats.
	JobID int
}

type TableValidatedInfo struct {
	JobID int
	Meta  *fileMetadata
}

type ThroughputMetric = base.ThroughputMetric

type UserKeyPrefixBound = sstable.UserKeyPrefixBound

type ValueMerger = base.ValueMerger

type WALCreateInfo struct {
	// JobID is the ID of the job the caused the WAL to be created.
	JobID int
	Path  string
	// The file number of the new WAL.
	FileNum FileNum
	// The file number of a previous WAL which was recycled to create this
	// one. Zero if recycling did not take place.
	RecycledFileNum FileNum
	Err             error
}

type WALDeleteInfo struct {
	// JobID is the ID of the job the caused the WAL to be deleted.
	JobID   int
	Path    string
	FileNum FileNum
	Err     error
}

type WriteAmpHeuristic struct {
	// addPropensity is a constant that affects the propensity to conduct multilevel
	// compactions. If positive, a multilevel compaction may get picked even if
	// the single level compaction has lower write amp, and vice versa.
	AddPropensity float64

	// AllowL0 if true, allow l0 to be involved in a ML compaction.
	AllowL0 bool
}

type WriteOptions struct {
	// Sync is whether to sync writes through the OS buffer cache and down onto
	// the actual disk, if applicable. Setting Sync is required for durability of
	// individual write operations but can result in slower writes.
	//
	// If false, and the process or machine crashes, then a recent write may be
	// lost. This is due to the recently written data being buffered inside the
	// process running Pebble. This differs from the semantics of a write system
	// call in which the data is buffered in the OS buffer cache and would thus
	// survive a process crash.
	//
	// The default value is true.
	Sync bool
}

type WriteStallBeginInfo struct {
	Reason string
}

type Writer interface {
	// Apply the operations contained in the batch to the DB.
	//
	// It is safe to modify the contents of the arguments after Apply returns.
	Apply(batch *Batch, o *WriteOptions) error

	// Delete deletes the value for the given key. Deletes are blind all will
	// succeed even if the given key does not exist.
	//
	// It is safe to modify the contents of the arguments after Delete returns.
	Delete(key []byte, o *WriteOptions) error

	// DeleteSized behaves identically to Delete, but takes an additional
	// argument indicating the size of the value being deleted. DeleteSized
	// should be preferred when the caller has the expectation that there exists
	// a single internal KV pair for the key (eg, the key has not been
	// overwritten recently), and the caller knows the size of its value.
	//
	// DeleteSized will record the value size within the tombstone and use it to
	// inform compaction-picking heuristics which strive to reduce space
	// amplification in the LSM. This "calling your shot" mechanic allows the
	// storage engine to more accurately estimate and reduce space
	// amplification.
	//
	// It is safe to modify the contents of the arguments after DeleteSized
	// returns.
	DeleteSized(key []byte, valueSize uint32, _ *WriteOptions) error

	// SingleDelete is similar to Delete in that it deletes the value for the given key. Like Delete,
	// it is a blind operation that will succeed even if the given key does not exist.
	//
	// WARNING: Undefined (non-deterministic) behavior will result if a key is overwritten and
	// then deleted using SingleDelete. The record may appear deleted immediately, but be
	// resurrected at a later time after compactions have been performed. Or the record may
	// be deleted permanently. A Delete operation lays down a "tombstone" which shadows all
	// previous versions of a key. The SingleDelete operation is akin to "anti-matter" and will
	// only delete the most recently written version for a key. These different semantics allow
	// the DB to avoid propagating a SingleDelete operation during a compaction as soon as the
	// corresponding Set operation is encountered. These semantics require extreme care to handle
	// properly. Only use if you have a workload where the performance gain is critical and you
	// can guarantee that a record is written once and then deleted once.
	//
	// SingleDelete is internally transformed into a Delete if the most recent record for a key is either
	// a Merge or Delete record.
	//
	// It is safe to modify the contents of the arguments after SingleDelete returns.
	SingleDelete(key []byte, o *WriteOptions) error

	// DeleteRange deletes all of the point keys (and values) in the range
	// [start,end) (inclusive on start, exclusive on end). DeleteRange does NOT
	// delete overlapping range keys (eg, keys set via RangeKeySet).
	//
	// It is safe to modify the contents of the arguments after DeleteRange
	// returns.
	DeleteRange(start, end []byte, o *WriteOptions) error

	// LogData adds the specified to the batch. The data will be written to the
	// WAL, but not added to memtables or sstables. Log data is never indexed,
	// which makes it useful for testing WAL performance.
	//
	// It is safe to modify the contents of the argument after LogData returns.
	LogData(data []byte, opts *WriteOptions) error

	// Merge merges the value for the given key. The details of the merge are
	// dependent upon the configured merge operation.
	//
	// It is safe to modify the contents of the arguments after Merge returns.
	Merge(key, value []byte, o *WriteOptions) error

	// Set sets the value for the given key. It overwrites any previous value
	// for that key; a DB is not a multi-map.
	//
	// It is safe to modify the contents of the arguments after Set returns.
	Set(key, value []byte, o *WriteOptions) error

	// RangeKeySet sets a range key mapping the key range [start, end) at the MVCC
	// timestamp suffix to value. The suffix is optional. If any portion of the key
	// range [start, end) is already set by a range key with the same suffix value,
	// RangeKeySet overrides it.
	//
	// It is safe to modify the contents of the arguments after RangeKeySet returns.
	RangeKeySet(start, end, suffix, value []byte, opts *WriteOptions) error

	// RangeKeyUnset removes a range key mapping the key range [start, end) at the
	// MVCC timestamp suffix. The suffix may be omitted to remove an unsuffixed
	// range key. RangeKeyUnset only removes portions of range keys that fall within
	// the [start, end) key span, and only range keys with suffixes that exactly
	// match the unset suffix.
	//
	// It is safe to modify the contents of the arguments after RangeKeyUnset
	// returns.
	RangeKeyUnset(start, end, suffix []byte, opts *WriteOptions) error

	// RangeKeyDelete deletes all of the range keys in the range [start,end)
	// (inclusive on start, exclusive on end). It does not delete point keys (for
	// that use DeleteRange). RangeKeyDelete removes all range keys within the
	// bounds, including those with or without suffixes.
	//
	// It is safe to modify the contents of the arguments after RangeKeyDelete
	// returns.
	RangeKeyDelete(start, end []byte, opts *WriteOptions) error
}