From b3ee33eb8e2f529eb10340a0c4f04919a890d0c7 Mon Sep 17 00:00:00 2001
From: Ze'ev Klapow <zklapow@gmail.com>
Date: Mon, 27 Mar 2023 20:54:19 -0400
Subject: [PATCH] fix le buckets when adjacent vmrange is empty (#4021)

There is a bug here where if you have a single bucket like:

foo{vmrange="4.084e+02...4.642e+02"} 2 123

The expected output is three le encoded buckets like:

foo{le="4.084e+02"} 0 123
foo{le="4.642e+02"} 2 123
foo{le="+Inf"} 2 123

This correctly encodes the start and end of the vmrange.
If however, the input contains the previous bucket, and that bucket is
empty then you only get the end le and +Inf out currently, i.e:

foo{vmrange="7.743e+05...8.799e+05"} 5 123
foo{vmrange="6.813e+05...7.743e+05"} 0 123

results in:

foo{le="8.799e+05"} 5 123
foo{le="+Inf"} 5 123

This causes issues when you go to compute a quantile because this means
that the assumed lower bound of the buckets is 0 and this we interpolate
between 0->end rather than the vmrange start->end as expected.
---
 app/vmselect/promql/transform.go      | 19 ++++++++++++++++++-
 app/vmselect/promql/transform_test.go |  9 +++++++++
 2 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/app/vmselect/promql/transform.go b/app/vmselect/promql/transform.go
index 16c6cda2b..bcebe46dd 100644
--- a/app/vmselect/promql/transform.go
+++ b/app/vmselect/promql/transform.go
@@ -548,14 +548,25 @@ func vmrangeBucketsToLE(tss []*timeseries) []*timeseries {
 		sort.Slice(xss, func(i, j int) bool { return xss[i].end < xss[j].end })
 		xssNew := make([]x, 0, len(xss)+2)
 		var xsPrev x
+		hasNonEmpty := false
 		uniqTs := make(map[string]*timeseries, len(xss))
 		for _, xs := range xss {
 			ts := xs.ts
 			if isZeroTS(ts) {
-				// Skip time series with zeros. They are substituted by xssNew below.
 				xsPrev = xs
+
+				if uniqTs[xs.endStr] == nil {
+					uniqTs[xs.endStr] = xs.ts
+					xssNew = append(xssNew, x{
+						endStr: xs.endStr,
+						end:    xs.end,
+						ts:     copyTS(ts, xs.endStr),
+					})
+				}
 				continue
 			}
+
+			hasNonEmpty = true
 			if xs.start != xsPrev.end && uniqTs[xs.startStr] == nil {
 				uniqTs[xs.startStr] = xs.ts
 				xssNew = append(xssNew, x{
@@ -575,6 +586,12 @@ func vmrangeBucketsToLE(tss []*timeseries) []*timeseries {
 			}
 			xsPrev = xs
 		}
+
+		if !hasNonEmpty {
+			xssNew = []x{}
+			continue
+		}
+
 		if !math.IsInf(xsPrev.end, 1) && !isZeroTS(xsPrev.ts) {
 			xssNew = append(xssNew, x{
 				endStr: "+Inf",
diff --git a/app/vmselect/promql/transform_test.go b/app/vmselect/promql/transform_test.go
index 5c5d7e414..6b9b8c476 100644
--- a/app/vmselect/promql/transform_test.go
+++ b/app/vmselect/promql/transform_test.go
@@ -78,6 +78,15 @@ foo{le="+Inf"} 1.23 456`,
 foo{le="+Inf"} 5.3 0`,
 	)
 
+	// Adjacent empty vmrange bucket
+	f(
+		`foo{vmrange="7.743e+05...8.799e+05"} 5 123
+foo{vmrange="6.813e+05...7.743e+05"} 0 123`,
+		`foo{le="7.743e+05"} 0 123
+foo{le="8.799e+05"} 5 123
+foo{le="+Inf"} 5 123`,
+	)
+
 	// Multiple non-empty vmrange buckets
 	f(
 		`foo{vmrange="4.084e+02...4.642e+02"} 2 123