From dc7bddfa59e7428e1edea0844d6d25d4efbdb675 Mon Sep 17 00:00:00 2001
From: Ben Ye <benye@amazon.com>
Date: Wed, 7 Jun 2023 13:55:02 -0700
Subject: [PATCH] add approximate series size to index stats

Signed-off-by: Ben Ye <benye@amazon.com>
---
 pkg/block/index.go | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/pkg/block/index.go b/pkg/block/index.go
index 0aa7a74a75..44d13d1c11 100644
--- a/pkg/block/index.go
+++ b/pkg/block/index.go
@@ -85,6 +85,10 @@ type HealthStats struct {
 	ChunkAvgSize int64
 	ChunkMaxSize int64
 
+	SeriesMinSize int64
+	SeriesAvgSize int64
+	SeriesMaxSize int64
+
 	SingleSampleSeries int64
 	SingleSampleChunks int64
 
@@ -231,6 +235,7 @@ func GatherIndexHealthStats(logger log.Logger, fn string, minTime, maxTime int64
 		seriesChunks                                = newMinMaxSumInt64()
 		chunkDuration                               = newMinMaxSumInt64()
 		chunkSize                                   = newMinMaxSumInt64()
+		seriesSize                                  = newMinMaxSumInt64()
 	)
 
 	lnames, err := r.LabelNames()
@@ -245,11 +250,25 @@ func GatherIndexHealthStats(logger log.Logger, fn string, minTime, maxTime int64
 	}
 	stats.MetricLabelValuesCount = int64(len(lvals))
 
+	// As of version two all series entries are 16 byte padded. All references
+	// we get have to account for that to get the correct offset.
+	offsetMultiplier := 1
+	version := r.Version()
+	if version >= 2 {
+		offsetMultiplier = 16
+	}
+
 	// Per series.
+	var prevId storage.SeriesRef
 	for p.Next() {
 		lastLset = append(lastLset[:0], lset...)
 
 		id := p.At()
+		if prevId != 0 {
+			// Approximate size.
+			seriesSize.Add(int64(id-prevId) * int64(offsetMultiplier))
+		}
+		prevId = id
 		stats.TotalSeries++
 
 		if err := r.Series(id, &builder, &chks); err != nil {
@@ -362,6 +381,10 @@ func GatherIndexHealthStats(logger log.Logger, fn string, minTime, maxTime int64
 	stats.ChunkAvgSize = chunkSize.Avg()
 	stats.ChunkMinSize = chunkSize.min
 
+	stats.SeriesMaxSize = seriesSize.max
+	stats.SeriesAvgSize = seriesSize.Avg()
+	stats.SeriesMinSize = seriesSize.min
+
 	stats.ChunkMaxDuration = time.Duration(chunkDuration.max) * time.Millisecond
 	stats.ChunkAvgDuration = time.Duration(chunkDuration.Avg()) * time.Millisecond
 	stats.ChunkMinDuration = time.Duration(chunkDuration.min) * time.Millisecond