From b9469de41051c3cd88da06361b638aabf00a96d1 Mon Sep 17 00:00:00 2001
From: Aliaksandr Valialkin <valyala@gmail.com>
Date: Fri, 2 Apr 2021 23:55:54 +0300
Subject: [PATCH] app/vmselect/promql: add ability to set label value
 additionally to label name for the remaining sum of time series returned from
 `topk_*` and `bottomk_*` functions in the form: `topk_min(N, m,
 "label=value")`

---
 app/vmselect/promql/aggr.go      | 8 +++++++-
 app/vmselect/promql/exec_test.go | 4 ++--
 docs/MetricsQL.md                | 2 +-
 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/app/vmselect/promql/aggr.go b/app/vmselect/promql/aggr.go
index 5d6a71bf9..46ebc4323 100644
--- a/app/vmselect/promql/aggr.go
+++ b/app/vmselect/promql/aggr.go
@@ -693,8 +693,14 @@ func getRemainingSumTimeseries(tss []*timeseries, modifier *metricsql.ModifierEx
 	var dst timeseries
 	dst.CopyFromShallowTimestamps(tss[0])
 	removeGroupTags(&dst.MetricName, modifier)
+	tagValue := remainingSumTagName
+	n := strings.IndexByte(remainingSumTagName, '=')
+	if n >= 0 {
+		tagValue = remainingSumTagName[n+1:]
+		remainingSumTagName = remainingSumTagName[:n]
+	}
 	dst.MetricName.RemoveTag(remainingSumTagName)
-	dst.MetricName.AddTag(remainingSumTagName, remainingSumTagName)
+	dst.MetricName.AddTag(remainingSumTagName, tagValue)
 	for i, k := range ks {
 		kn := getIntK(k, len(tss))
 		var sum float64
diff --git a/app/vmselect/promql/exec_test.go b/app/vmselect/promql/exec_test.go
index fea34e448..d6d22735e 100644
--- a/app/vmselect/promql/exec_test.go
+++ b/app/vmselect/promql/exec_test.go
@@ -4823,7 +4823,7 @@ func TestExecSuccess(t *testing.T) {
 	})
 	t.Run(`topk_max(1, remaining_sum)`, func(t *testing.T) {
 		t.Parallel()
-		q := `sort_desc(topk_max(1, label_set(10, "foo", "bar") or label_set(time()/150, "baz", "sss"), "remaining_sum"))`
+		q := `sort_desc(topk_max(1, label_set(10, "foo", "bar") or label_set(time()/150, "baz", "sss"), "remaining_sum=foo"))`
 		r1 := netstorage.Result{
 			MetricName: metricNameExpected,
 			Values:     []float64{nan, nan, nan, 10.666666666666666, 12, 13.333333333333334},
@@ -4841,7 +4841,7 @@ func TestExecSuccess(t *testing.T) {
 		r2.MetricName.Tags = []storage.Tag{
 			{
 				Key:   []byte("remaining_sum"),
-				Value: []byte("remaining_sum"),
+				Value: []byte("foo"),
 			},
 		}
 		resultExpected := []netstorage.Result{r1, r2}
diff --git a/docs/MetricsQL.md b/docs/MetricsQL.md
index b67cb4d3c..53be6f107 100644
--- a/docs/MetricsQL.md
+++ b/docs/MetricsQL.md
@@ -121,7 +121,7 @@ This functionality can be tried at [an editable Grafana dashboard](http://play-g
    - `bottomk_avg(k, q)` - returns bottom K time series with the min averages on the given time range
    - `bottomk_median(k, q)` - returns bottom K time series with the min medians on the given time range.
 
-  All the `topk_*` and `bottomk_*` functions accept optional third argument - label name for the sum of the remaining time series outside top K or bottom K time series. For example, `topk_max(3, process_resident_memory_bytes, "remaining_sum")` would return up to 3 time series with the maximum value for `process_resident_memory_bytes` plus fourth time series with the sum of the remaining time series if any. The fourth time series will contain `remaining_sum="remaining_sum"` additional label.
+  All the `topk_*` and `bottomk_*` functions accept optional third argument - label to add to the sum of the remaining time series outside top K or bottom K time series. For example, `topk_max(3, sum(process_resident_memory_bytes) by (job), "job=other")` would return up to 3 time series with the maximum value for `sum(process_resident_memory_bytes) by (job)` plus fourth time series with the sum of the remaining time series if any. The fourth time series will contain `job="other"` label.
 - `share_le_over_time(m[d], le)` - returns share (in the range 0..1) of values in `m` over `d`, which are smaller or equal to `le`. Useful for calculating SLI and SLO.
   Example: `share_le_over_time(memory_usage_bytes[24h], 100*1024*1024)` returns the share of time series values for the last 24 hours when memory usage was below or equal to 100MB.
 - `share_gt_over_time(m[d], gt)` - returns share (in the range 0..1) of values in `m` over `d`, which are bigger than `gt`. Useful for calculating SLI and SLO.