statistics

Documentation

Index

• type Bucket
• type Column
  • func (c *Column) String() string
• type FMSketch
  • func NewFMSketch(maxSize int) *FMSketch
  • func (s *FMSketch) InsertValue(value types.Datum) error
  • func (s *FMSketch) NDV() int64
• type Handle
  • func NewHandle(ctx context.Context) *Handle
  • func (h *Handle) Clear()
  • func (h *Handle) DDLEventCh() chan *ddl.Event
  • func (h *Handle) DumpStatsDeltaToKV()
  • func (h *Handle) GetTableStats(tblID int64) *Table
  • func (h *Handle) HandleDDLEvent(t *ddl.Event) error
  • func (h *Handle) NewSessionStatsCollector() *SessionStatsCollector
  • func (h *Handle) Update(is infoschema.InfoSchema) error
  • func (h *Handle) UpdateTableStats(tables []*Table, deletedIDs []int64)
• type Histogram
  • func BuildColumn(ctx context.Context, numBuckets, id int64, ndv int64, count int64, ...) (*Histogram, error)
  • func BuildIndex(ctx context.Context, numBuckets, id int64, records ast.RecordSet) (int64, *Histogram, error)
  • func BuildPK(ctx context.Context, numBuckets, id int64, records ast.RecordSet) (int64, *Histogram, error)
  • func (hg *Histogram) SaveToStorage(ctx context.Context, tableID int64, count int64, isIndex int) error
• type Index
  • func (idx *Index) String() string
• type SessionStatsCollector
  • func (s *SessionStatsCollector) Delete()
  • func (s *SessionStatsCollector) Update(id int64, delta int64, count int64)
• type Table
  • func PseudoTable(tableID int64) *Table
  • func (t *Table) ColumnBetweenRowCount(sc *variable.StatementContext, a, b types.Datum, colInfo *model.ColumnInfo) (float64, error)
  • func (t *Table) ColumnEqualRowCount(sc *variable.StatementContext, value types.Datum, colInfo *model.ColumnInfo) (float64, error)
  • func (t *Table) ColumnGreaterRowCount(sc *variable.StatementContext, value types.Datum, colInfo *model.ColumnInfo) (float64, error)
  • func (t *Table) ColumnLessRowCount(sc *variable.StatementContext, value types.Datum, colInfo *model.ColumnInfo) (float64, error)
  • func (t *Table) GetRowCountByIndexRanges(sc *variable.StatementContext, idxID int64, indexRanges []*types.IndexRange, ...) (float64, error)
  • func (t *Table) GetRowCountByIntColumnRanges(sc *variable.StatementContext, colID int64, intRanges []types.IntColumnRange) (float64, error)
  • func (t *Table) String() string

Types

type Bucket

type Bucket struct {
	Count   int64
	Value   types.Datum
	Repeats int64
}

Bucket is an element of histogram.

A bucket count is the number of items stored in all previous buckets and the current bucket. bucket numbers are always in increasing order.

A bucket value is the greatest item value stored in the bucket.

Repeat is the number of repeats of the bucket value, it can be used to find popular values.

type Column

type Column struct {
	Histogram
}

Column represents a column histogram.

func (*Column) String

func (c *Column) String() string

type FMSketch

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

FMSketch is used to count the number of distinct elements in a set.

func NewFMSketch

func NewFMSketch(maxSize int) *FMSketch

NewFMSketch returns a new FM sketch.

func (*FMSketch) InsertValue

func (s *FMSketch) InsertValue(value types.Datum) error

InsertValue inserts a value into the FM sketch.

func (*FMSketch) NDV

func (s *FMSketch) NDV() int64

NDV returns the ndv of the sketch.

type Handle

type Handle struct {

	// LastVersion is the latest update version before last lease. Exported for test.
	LastVersion uint64
	// PrevLastVersion is the latest update version before two lease. Exported for test.
	// We need this because for two tables, the smaller version may write later than the one with larger version.
	// We can read the version with lastTwoVersion if the diff between commit time and version is less than one lease.
	// PrevLastVersion will be assigned by LastVersion every time Update is called.
	PrevLastVersion uint64
	// contains filtered or unexported fields
}

Handle can update stats info periodically.

func NewHandle

func NewHandle(ctx context.Context) *Handle

NewHandle creates a Handle for update stats.

func (*Handle) Clear

func (h *Handle) Clear()

Clear the statsCache, only for test.

func (*Handle) DDLEventCh

func (h *Handle) DDLEventCh() chan *ddl.Event

DDLEventCh returns ddl events channel in handle.

func (*Handle) DumpStatsDeltaToKV

func (h *Handle) DumpStatsDeltaToKV()

DumpStatsDeltaToKV sweeps the whole list and updates the global map. Then we dumps every table that held in map to KV.

func (*Handle) GetTableStats

func (h *Handle) GetTableStats(tblID int64) *Table

GetTableStats retrieves the statistics table from cache, and the cache will be updated by a goroutine.

func (*Handle) HandleDDLEvent

func (h *Handle) HandleDDLEvent(t *ddl.Event) error

HandleDDLEvent begins to process a ddl task.

func (*Handle) NewSessionStatsCollector

func (h *Handle) NewSessionStatsCollector() *SessionStatsCollector

NewSessionStatsCollector allocates a stats collector for a session.

func (*Handle) Update

func (h *Handle) Update(is infoschema.InfoSchema) error

Update reads stats meta from store and updates the stats map.

func (*Handle) UpdateTableStats

func (h *Handle) UpdateTableStats(tables []*Table, deletedIDs []int64)

UpdateTableStats updates the statistics table cache using copy on write.

type Histogram

type Histogram struct {
	ID  int64 // Column ID.
	NDV int64 // Number of distinct values.
	// LastUpdateVersion is the version that this histogram updated last time.
	LastUpdateVersion uint64

	Buckets []Bucket
}

Histogram represents statistics for a column or index.

func BuildColumn

func BuildColumn(ctx context.Context, numBuckets, id int64, ndv int64, count int64, samples []types.Datum) (*Histogram, error)

BuildColumn builds histogram from samples for column.

func BuildIndex

func BuildIndex(ctx context.Context, numBuckets, id int64, records ast.RecordSet) (int64, *Histogram, error)

BuildIndex builds histogram for index.

func BuildPK

func BuildPK(ctx context.Context, numBuckets, id int64, records ast.RecordSet) (int64, *Histogram, error)

BuildPK builds histogram for pk.

func (*Histogram) SaveToStorage

func (hg *Histogram) SaveToStorage(ctx context.Context, tableID int64, count int64, isIndex int) error

SaveToStorage saves the histogram to storage.

type Index

type Index struct {
	Histogram
	NumColumns int
}

Index represents an index histogram.

func (*Index) String

func (idx *Index) String() string

type SessionStatsCollector

type SessionStatsCollector struct {
	sync.Mutex
	// contains filtered or unexported fields
}

SessionStatsCollector is a list item that holds the delta mapper. If you want to write or read mapper, you must lock it.

func (*SessionStatsCollector) Delete

func (s *SessionStatsCollector) Delete()

Delete only sets the deleted flag true, it will be deleted from list when DumpStatsDeltaToKV is called.

func (*SessionStatsCollector) Update

func (s *SessionStatsCollector) Update(id int64, delta int64, count int64)

Update will updates the delta and count for one table id.

type Table

type Table struct {
	TableID int64
	Columns map[int64]*Column
	Indices map[int64]*Index
	Count   int64 // Total row count in a table.
	Pseudo  bool
}

Table represents statistics for a table.

func PseudoTable

func PseudoTable(tableID int64) *Table

PseudoTable creates a pseudo table statistics when statistic can not be found in KV store.

func (*Table) ColumnBetweenRowCount

func (t *Table) ColumnBetweenRowCount(sc *variable.StatementContext, a, b types.Datum, colInfo *model.ColumnInfo) (float64, error)

ColumnBetweenRowCount estimates the row count where column greater or equal to a and less than b.

func (*Table) ColumnEqualRowCount

func (t *Table) ColumnEqualRowCount(sc *variable.StatementContext, value types.Datum, colInfo *model.ColumnInfo) (float64, error)

ColumnEqualRowCount estimates the row count where the column equals to value.

func (*Table) ColumnGreaterRowCount

func (t *Table) ColumnGreaterRowCount(sc *variable.StatementContext, value types.Datum, colInfo *model.ColumnInfo) (float64, error)

ColumnGreaterRowCount estimates the row count where the column greater than value.

func (*Table) ColumnLessRowCount

func (t *Table) ColumnLessRowCount(sc *variable.StatementContext, value types.Datum, colInfo *model.ColumnInfo) (float64, error)

ColumnLessRowCount estimates the row count where the column less than value.

func (*Table) GetRowCountByIndexRanges

func (t *Table) GetRowCountByIndexRanges(sc *variable.StatementContext, idxID int64, indexRanges []*types.IndexRange, inAndEQCnt int) (float64, error)

GetRowCountByIndexRanges estimates the row count by a slice of IndexRange.

func (*Table) GetRowCountByIntColumnRanges

func (t *Table) GetRowCountByIntColumnRanges(sc *variable.StatementContext, colID int64, intRanges []types.IntColumnRange) (float64, error)

GetRowCountByIntColumnRanges estimates the row count by a slice of IntColumnRange.

func (*Table) String

func (t *Table) String() string

String implements Stringer interface.