seaweedfs/weed/filer/filechunks_read.go
Chris Lu d4566d4aaa
more solid weed mount (#4089)
* compare chunks by timestamp

* fix slab clearing error

* fix test compilation

* move oldest chunk to sealed, instead of by fullness

* lock on fh.entryViewCache

* remove verbose logs

* revert slat clearing

* less logs

* less logs

* track write and read by timestamp

* remove useless logic

* add entry lock on file handle release

* use mem chunk only, swap file chunk has problems

* comment out code that maybe used later

* add debug mode to compare data read and write

* more efficient readResolvedChunks with linked list

* small optimization

* fix test compilation

* minor fix on writer

* add SeparateGarbageChunks

* group chunks into sections

* turn off debug mode

* fix tests

* fix tests

* tmp enable swap file chunk

* Revert "tmp enable swap file chunk"

This reverts commit 985137ec47.

* simple refactoring

* simple refactoring

* do not re-use swap file chunk. Sealed chunks should not be re-used.

* comment out debugging facilities

* either mem chunk or swap file chunk is fine now

* remove orderedMutex  as *semaphore.Weighted

not found impactful

* optimize size calculation for changing large files

* optimize performance to avoid going through the long list of chunks

* still problems with swap file chunk

* rename

* tiny optimization

* swap file chunk save only successfully read data

* fix

* enable both mem and swap file chunk

* resolve chunks with range

* rename

* fix chunk interval list

* also change file handle chunk group when adding chunks

* pick in-active chunk with time-decayed counter

* fix compilation

* avoid nil with empty fh.entry

* refactoring

* rename

* rename

* refactor visible intervals to *list.List

* refactor chunkViews to *list.List

* add IntervalList for generic interval list

* change visible interval to use IntervalList in generics

* cahnge chunkViews to *IntervalList[*ChunkView]

* use NewFileChunkSection to create

* rename variables

* refactor

* fix renaming leftover

* renaming

* renaming

* add insert interval

* interval list adds lock

* incrementally add chunks to readers

Fixes:
1. set start and stop offset for the value object
2. clone the value object
3. use pointer instead of copy-by-value when passing to interval.Value
4. use insert interval since adding chunk could be out of order

* fix tests compilation

* fix tests compilation
2023-01-02 23:20:45 -08:00

123 lines
2.9 KiB
Go

package filer
import (
"container/list"
"github.com/seaweedfs/seaweedfs/weed/pb/filer_pb"
"golang.org/x/exp/slices"
)
func readResolvedChunks(chunks []*filer_pb.FileChunk, startOffset int64, stopOffset int64) (visibles *IntervalList[*VisibleInterval]) {
var points []*Point
for _, chunk := range chunks {
if chunk.IsChunkManifest {
println("This should not happen! A manifest chunk found:", chunk.GetFileIdString())
}
start, stop := max(chunk.Offset, startOffset), min(chunk.Offset+int64(chunk.Size), stopOffset)
if start >= stop {
continue
}
points = append(points, &Point{
x: chunk.Offset,
ts: chunk.ModifiedTsNs,
chunk: chunk,
isStart: true,
})
points = append(points, &Point{
x: chunk.Offset + int64(chunk.Size),
ts: chunk.ModifiedTsNs,
chunk: chunk,
isStart: false,
})
}
slices.SortFunc(points, func(a, b *Point) bool {
if a.x != b.x {
return a.x < b.x
}
if a.ts != b.ts {
return a.ts < b.ts
}
return !a.isStart
})
var prevX int64
queue := list.New() // points with higher ts are at the tail
visibles = NewIntervalList[*VisibleInterval]()
var prevPoint *Point
for _, point := range points {
if queue.Len() > 0 {
prevPoint = queue.Back().Value.(*Point)
} else {
prevPoint = nil
}
if point.isStart {
if prevPoint != nil {
if point.x != prevX && prevPoint.ts < point.ts {
addToVisibles(visibles, prevX, prevPoint, point)
prevX = point.x
}
}
// insert into queue
if prevPoint == nil || prevPoint.ts < point.ts {
queue.PushBack(point)
prevX = point.x
} else {
for e := queue.Front(); e != nil; e = e.Next() {
if e.Value.(*Point).ts > point.ts {
queue.InsertBefore(point, e)
break
}
}
}
} else {
isLast := true
for e := queue.Back(); e != nil; e = e.Prev() {
if e.Value.(*Point).ts == point.ts {
queue.Remove(e)
break
}
isLast = false
}
if isLast && prevPoint != nil {
addToVisibles(visibles, prevX, prevPoint, point)
prevX = point.x
}
}
}
return
}
func addToVisibles(visibles *IntervalList[*VisibleInterval], prevX int64, startPoint *Point, point *Point) {
if prevX < point.x {
chunk := startPoint.chunk
visible := &VisibleInterval{
start: prevX,
stop: point.x,
fileId: chunk.GetFileIdString(),
modifiedTsNs: chunk.ModifiedTsNs,
offsetInChunk: prevX - chunk.Offset,
chunkSize: chunk.Size,
cipherKey: chunk.CipherKey,
isGzipped: chunk.IsCompressed,
}
appendVisibleInterfal(visibles, visible)
}
}
func appendVisibleInterfal(visibles *IntervalList[*VisibleInterval], visible *VisibleInterval) {
visibles.AppendInterval(&Interval[*VisibleInterval]{
StartOffset: visible.start,
StopOffset: visible.stop,
TsNs: visible.modifiedTsNs,
Value: visible,
})
}
type Point struct {
x int64
ts int64
chunk *filer_pb.FileChunk
isStart bool
}