Documentation ¶
Index ¶
- Constants
- func FMSketchToProto(s *FMSketch) *tipb.FMSketch
- func HistogramToProto(hg *Histogram) *tipb.Histogram
- func SampleCollectorToProto(c *SampleCollector) *tipb.SampleCollector
- type AnalyzeResult
- type Bucket
- type Column
- type FMSketch
- type Handle
- func (h *Handle) AnalyzeResultCh() chan *AnalyzeResult
- func (h *Handle) Clear()
- func (h *Handle) DDLEventCh() chan *ddl.Event
- func (h *Handle) DeleteTableStatsFromKV(id int64) error
- func (h *Handle) DumpStatsDeltaToKV()
- func (h *Handle) GetTableStats(tblID int64) *Table
- func (h *Handle) HandleAutoAnalyze(is infoschema.InfoSchema) error
- 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 HistogramFromProto(protoHg *tipb.Histogram) *Histogram
- func MergeHistograms(sc *variable.StatementContext, lh *Histogram, rh *Histogram, bucketSize int) (*Histogram, error)
- type Index
- type SampleBuilder
- type SampleCollector
- type SessionStatsCollector
- type SortedBuilder
- type 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) ColumnIsInvalid(colInfo *model.ColumnInfo) bool
- func (t *Table) ColumnLessRowCount(sc *variable.StatementContext, value types.Datum, colInfo *model.ColumnInfo) (float64, error)
- func (t *Table) GetRowCountByColumnRanges(sc *variable.StatementContext, colID int64, colRanges []*types.ColumnRange) (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) Selectivity(ctx context.Context, exprs []expression.Expression) (float64, error)
- func (t *Table) String() string
Constants ¶
const ( // StatsOwnerKey is the stats owner path that is saved to etcd. StatsOwnerKey = "/tidb/stats/owner" // StatsPrompt is the prompt for stats owner manager. StatsPrompt = "stats" )
Variables ¶
This section is empty.
Functions ¶
func FMSketchToProto ¶
func FMSketchToProto(s *FMSketch) *tipb.FMSketch
FMSketchToProto converts FMSketch to its protobuf representation.
func HistogramToProto ¶
func HistogramToProto(hg *Histogram) *tipb.Histogram
HistogramToProto converts Histogram to its protobuf representation. Note that when this is used, the lower/upper bound in the bucket must be BytesDatum.
func SampleCollectorToProto ¶
func SampleCollectorToProto(c *SampleCollector) *tipb.SampleCollector
SampleCollectorToProto converts SampleCollector to its protobuf representation.
Types ¶
type AnalyzeResult ¶
AnalyzeResult is used to represent analyze result.
type Bucket ¶
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 Info *model.ColumnInfo }
Column represents a column histogram.
type FMSketch ¶
type FMSketch struct {
// contains filtered or unexported fields
}
FMSketch is used to count the number of distinct elements in a set.
func FMSketchFromProto ¶
func FMSketchFromProto(protoSketch *tipb.FMSketch) *FMSketch
FMSketchFromProto converts FMSketch from its protobuf representation.
func (*FMSketch) InsertValue ¶
InsertValue inserts a value into the FM 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 Lease time.Duration // contains filtered or unexported fields }
Handle can update stats info periodically.
func (*Handle) AnalyzeResultCh ¶
func (h *Handle) AnalyzeResultCh() chan *AnalyzeResult
AnalyzeResultCh returns analyze result channel in handle.
func (*Handle) DDLEventCh ¶
DDLEventCh returns ddl events channel in handle.
func (*Handle) DeleteTableStatsFromKV ¶
DeleteTableStatsFromKV deletes table statistics from kv.
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 ¶
GetTableStats retrieves the statistics table from cache, and the cache will be updated by a goroutine.
func (*Handle) HandleAutoAnalyze ¶
func (h *Handle) HandleAutoAnalyze(is infoschema.InfoSchema) error
HandleAutoAnalyze analyzes the newly created table or index.
func (*Handle) HandleDDLEvent ¶
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 ¶
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. NullCount int64 // Number of null 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, nullCount 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 HistogramFromProto ¶
func HistogramFromProto(protoHg *tipb.Histogram) *Histogram
HistogramFromProto converts Histogram from its protobuf representation. Note that we will set BytesDatum for the lower/upper bound in the bucket, the decode will be after all histograms merged.
func MergeHistograms ¶
func MergeHistograms(sc *variable.StatementContext, lh *Histogram, rh *Histogram, bucketSize int) (*Histogram, error)
MergeHistograms merges two histograms.
type SampleBuilder ¶
type SampleBuilder struct { Sc *variable.StatementContext RecordSet ast.RecordSet ColLen int // ColLen is the number of columns need to be sampled. PkID int64 // If primary key is handle, the PkID is the id of the primary key. If not exists, it is -1. MaxBucketSize int64 MaxSampleSize int64 MaxSketchSize int64 }
SampleBuilder is used to build samples for columns. Also, if primary key is handle, it will directly build histogram for it.
func (SampleBuilder) CollectSamplesAndEstimateNDVs ¶
func (s SampleBuilder) CollectSamplesAndEstimateNDVs() ([]*SampleCollector, *SortedBuilder, error)
CollectSamplesAndEstimateNDVs collects sample from the result set using Reservoir Sampling algorithm, and estimates NDVs using FM Sketch during the collecting process. It returns the sample collectors which contain total count, null count and distinct values count. It also returns the statistic builder for PK which contains the histogram. See https://en.wikipedia.org/wiki/Reservoir_sampling
type SampleCollector ¶
type SampleCollector struct { Samples []types.Datum NullCount int64 Count int64 MaxSampleSize int64 Sketch *FMSketch }
SampleCollector will collect Samples and calculate the count and ndv of an attribute.
func SampleCollectorFromProto ¶
func SampleCollectorFromProto(collector *tipb.SampleCollector) *SampleCollector
SampleCollectorFromProto converts SampleCollector from its protobuf representation.
func (*SampleCollector) MergeSampleCollector ¶
func (c *SampleCollector) MergeSampleCollector(rc *SampleCollector)
MergeSampleCollector merges two sample collectors.
type SessionStatsCollector ¶
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.
type SortedBuilder ¶
type SortedBuilder struct { Count int64 // contains filtered or unexported fields }
SortedBuilder is used to build histograms for PK and index.
func NewSortedBuilder ¶
func NewSortedBuilder(sc *variable.StatementContext, numBuckets, id int64) *SortedBuilder
NewSortedBuilder creates a new SortedBuilder.
func (*SortedBuilder) Hist ¶
func (b *SortedBuilder) Hist() *Histogram
Hist returns the histogram built by SortedBuilder.
type Table ¶
type Table struct { TableID int64 Columns map[int64]*Column Indices map[int64]*Index Count int64 // Total row count in a table. ModifyCount int64 // Total modify count in a table. Version uint64 Pseudo bool }
Table represents statistics for a table.
func PseudoTable ¶
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) ColumnIsInvalid ¶
func (t *Table) ColumnIsInvalid(colInfo *model.ColumnInfo) bool
ColumnIsInvalid checks if this column is invalid.
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) GetRowCountByColumnRanges ¶
func (t *Table) GetRowCountByColumnRanges(sc *variable.StatementContext, colID int64, colRanges []*types.ColumnRange) (float64, error)
GetRowCountByColumnRanges estimates the row count by a slice of ColumnRange.
func (*Table) GetRowCountByIndexRanges ¶
func (t *Table) GetRowCountByIndexRanges(sc *variable.StatementContext, idxID int64, indexRanges []*types.IndexRange) (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) Selectivity ¶
func (t *Table) Selectivity(ctx context.Context, exprs []expression.Expression) (float64, error)
Selectivity is a function calculate the selectivity of the expressions. The definition of selectivity is (row count after filter / row count before filter). And exprs must be CNF now, in other words, `exprs[0] and exprs[1] and ... and exprs[len - 1]` should be held when you call this. TODO: support expressions that the top layer is a DNF. Currently the time complexity is o(n^2).