Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

statistics: reduce memory usage when to MergePartTopN2GlobalTopN (#45718) #45971

Merged
merged 3 commits into from
Aug 11, 2023
Merged

statistics: reduce memory usage when to MergePartTopN2GlobalTopN (#45718) #45971

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
03d70d9
statistics: reduce memory usage when to MergePartTopN2GlobalTopN
hawkingrei Aug 7, 2023
fbb8b0e
statistics: reduce memory usage when to MergePartTopN2GlobalTopN
hawkingrei Aug 7, 2023
6f0c16e
update
hawkingrei Aug 8, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 1 addition & 15 deletions statistics/cmsketch.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -799,10 +799,7 @@ func MergePartTopN2GlobalTopN(loc *time.Location, version int, topNs []*TopN, n
if checkEmptyTopNs(topNs) {
return nil, nil, hists, nil
}

partNum := len(topNs)
removeVals := make([][]TopNMeta, partNum)

// Different TopN structures may hold the same value, we have to merge them.
counter := make(map[hack.MutableString]float64)
// datumMap is used to store the mapping from the string type to datum type.
Expand Down Expand Up @@ -864,22 +861,11 @@ func MergePartTopN2GlobalTopN(loc *time.Location, version int, topNs []*TopN, n
if count != 0 {
counter[encodedVal] += count
// Remove the value corresponding to encodedVal from the histogram.
removeVals[j] = append(removeVals[j], TopNMeta{Encoded: datum.GetBytes(), Count: uint64(count)})
hists[j].BinarySearchRemoveVal(TopNMeta{Encoded: datum.GetBytes(), Count: uint64(count)})
}
}
}
}
// Remove the value from the Hists.
for i := 0; i < partNum; i++ {
if len(removeVals[i]) > 0 {
tmp := removeVals[i]
slices.SortFunc(tmp, func(i, j TopNMeta) bool {
cmpResult := bytes.Compare(i.Encoded, j.Encoded)
return cmpResult < 0
})
hists[i].RemoveVals(tmp)
}
}
numTop := len(counter)
if numTop == 0 {
return nil, nil, hists, nil
Expand Down
29 changes: 29 additions & 0 deletions statistics/histogram.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -281,6 +281,35 @@ func (hg *Histogram) BucketToString(bktID, idxCols int) string {
return fmt.Sprintf("num: %d lower_bound: %s upper_bound: %s repeats: %d ndv: %d", hg.bucketCount(bktID), lowerVal, upperVal, hg.Buckets[bktID].Repeat, hg.Buckets[bktID].NDV)
}

// BinarySearchRemoveVal removes the value from the TopN using binary search.
func (hg *Histogram) BinarySearchRemoveVal(valCntPairs TopNMeta) {
lowIdx, highIdx := 0, hg.Len()-1
for lowIdx <= highIdx {
midIdx := (lowIdx + highIdx) / 2
cmpResult := bytes.Compare(hg.Bounds.Column(0).GetRaw(midIdx*2), valCntPairs.Encoded)
if cmpResult > 0 {
lowIdx = midIdx + 1
continue
}
cmpResult = bytes.Compare(hg.Bounds.Column(0).GetRaw(midIdx*2+1), valCntPairs.Encoded)
if cmpResult < 0 {
highIdx = midIdx - 1
continue
}
if hg.Buckets[midIdx].NDV > 0 {
hg.Buckets[midIdx].NDV--
}
if cmpResult == 0 {
hg.Buckets[midIdx].Repeat = 0
}
hg.Buckets[midIdx].Count -= int64(valCntPairs.Count)
if hg.Buckets[midIdx].Count < 0 {
hg.Buckets[midIdx].Count = 0
}
break
}
}

// RemoveVals remove the given values from the histogram.
// This function contains an **ASSUMPTION**: valCntPairs is sorted in ascending order.
func (hg *Histogram) RemoveVals(valCntPairs []TopNMeta) {
Expand Down