exec

Documentation

Index

• func Compact(ctx context.Context, pool *lake.Pool, branchName string, ...) (ksuid.KSUID, error)
• func NewCommitMetaPlanner(ctx context.Context, zctx *zed.Context, r *lake.Root, ...) (from.Planner, error)
• func NewLakeMetaPlanner(ctx context.Context, zctx *zed.Context, r *lake.Root, meta string, ...) (from.Planner, error)
• func NewPlanner(ctx context.Context, zctx *zed.Context, p *lake.Pool, commit ksuid.KSUID, ...) (from.Planner, error)
• func NewPlannerByID(ctx context.Context, zctx *zed.Context, r *lake.Root, ...) (from.Planner, error)
• func NewPoolMetaPlanner(ctx context.Context, zctx *zed.Context, r *lake.Root, poolID ksuid.KSUID, ...) (from.Planner, error)
• func PartitionObjects(objects []*data.Object, o order.Which) []meta.Partition
• func ScanIndexes(ctx context.Context, snap commits.View, span extent.Span, o order.Which, ...) error
• func ScanPartitions(ctx context.Context, snap commits.View, span extent.Span, o order.Which, ...) error
• func ScanSpan(ctx context.Context, snap commits.View, span extent.Span, o order.Which, ...) error
• func ScanSpanInOrder(ctx context.Context, snap commits.View, span extent.Span, o order.Which, ...) error
• type BranchStats
  • func GetBranchStats(ctx context.Context, b *lake.Branch, snap commits.View) (info BranchStats, err error)
• type Planner
  • func NewSortedPlanner(ctx context.Context, zctx *zed.Context, pool *lake.Pool, snap commits.View, ...) (*Planner, error)
  • func (p *Planner) Progress() zbuf.Progress
  • func (p *Planner) PullScanWork() (meta.Partition, error)
  • func (p *Planner) PullWork() (zbuf.Puller, error)
• type PoolStats
  • func GetPoolStats(ctx context.Context, p *lake.Pool, snap commits.View) (info PoolStats, err error)

Functions

func Compact

func Compact(ctx context.Context, pool *lake.Pool, branchName string, objectIDs []ksuid.KSUID, author, message, meta string) (ksuid.KSUID, error)

func NewCommitMetaPlanner

func NewCommitMetaPlanner(ctx context.Context, zctx *zed.Context, r *lake.Root, poolID, commit ksuid.KSUID, meta string, span extent.Span, filter zbuf.Filter) (from.Planner, error)

func NewLakeMetaPlanner

func NewLakeMetaPlanner(ctx context.Context, zctx *zed.Context, r *lake.Root, meta string, filter zbuf.Filter) (from.Planner, error)

func NewPlanner

func NewPlanner(ctx context.Context, zctx *zed.Context, p *lake.Pool, commit ksuid.KSUID, span extent.Span, filter zbuf.Filter) (from.Planner, error)

func NewPlannerByID

func NewPlannerByID(ctx context.Context, zctx *zed.Context, r *lake.Root, poolID, commit ksuid.KSUID, span extent.Span, filter zbuf.Filter) (from.Planner, error)

func NewPoolMetaPlanner

func NewPoolMetaPlanner(ctx context.Context, zctx *zed.Context, r *lake.Root, poolID ksuid.KSUID, meta string, filter zbuf.Filter) (from.Planner, error)

func PartitionObjects

func PartitionObjects(objects []*data.Object, o order.Which) []meta.Partition

PartitionObjects takes a sorted set of data objects with possibly overlapping key ranges and returns an ordered list of Ranges such that none of the Ranges overlap with one another. This is the straightforward computational geometry problem of merging overlapping intervals, e.g., https://www.geeksforgeeks.org/merging-intervals/

XXX this algorithm doesn't quite do what we want because it continues to merge *anything* that overlaps. It's easy to fix though. Issue #2538

func ScanIndexes

func ScanIndexes(ctx context.Context, snap commits.View, span extent.Span, o order.Which, ch chan<- *index.Object) error

func ScanPartitions

func ScanPartitions(ctx context.Context, snap commits.View, span extent.Span, o order.Which, ch chan<- meta.Partition) error

ScanPartitions partitions all the data objects in snap overlapping span into non-overlapping partitions, sorts them by pool key and order, and sends them to ch.

func ScanSpan

func ScanSpan(ctx context.Context, snap commits.View, span extent.Span, o order.Which, ch chan<- data.Object) error

func ScanSpanInOrder

func ScanSpanInOrder(ctx context.Context, snap commits.View, span extent.Span, o order.Which, ch chan<- data.Object) error

Types

type BranchStats

type BranchStats struct {
	Size int64 `zed:"size"`
	// XXX (nibs) - This shouldn't be a span because keys don't have to be time.
	Span *nano.Span `zed:"span"`
}

func GetBranchStats

func GetBranchStats(ctx context.Context, b *lake.Branch, snap commits.View) (info BranchStats, err error)

type Planner

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

func NewSortedPlanner

func NewSortedPlanner(ctx context.Context, zctx *zed.Context, pool *lake.Pool, snap commits.View, span extent.Span, filter zbuf.Filter) (*Planner, error)

func (*Planner) Progress

func (p *Planner) Progress() zbuf.Progress

func (*Planner) PullScanWork

func (p *Planner) PullScanWork() (meta.Partition, error)

PullScanWork returns the next span in the schedule. This is useful for a worker proc that pulls spans from teh scheduler, sends them to a remote worker, and streams the results into the runtime DAG.

func (*Planner) PullWork

func (p *Planner) PullWork() (zbuf.Puller, error)

type PoolStats

type PoolStats struct {
	Size int64 `zed:"size"`
	// XXX (nibs) - This shouldn't be a span because keys don't have to be time.
	Span *nano.Span `zed:"span"`
}

XXX for backward compat keep this for now, and return branchstats for pool/main

func GetPoolStats

func GetPoolStats(ctx context.Context, p *lake.Pool, snap commits.View) (info PoolStats, err error)