prometheus/promql/promqltest/testdata/histograms.test

# Two histograms with 4 buckets each (x_sum and x_count not included,
# only buckets). Lowest bucket for one histogram < 0, for the other >
# 0. They have the same name, just separated by label. Not useful in
# practice, but can happen (if clients change bucketing), and the
# server has to cope with it.

# Test histogram.
load 5m
	testhistogram_bucket{le="0.1", start="positive"}	0+5x10
	testhistogram_bucket{le=".2", start="positive"}		0+7x10
	testhistogram_bucket{le="1e0", start="positive"}	0+11x10
	testhistogram_bucket{le="+Inf", start="positive"}	0+12x10
	testhistogram_bucket{le="-.2", start="negative"}	0+1x10
	testhistogram_bucket{le="-0.1", start="negative"}	0+2x10
	testhistogram_bucket{le="0.3", start="negative"}	0+2x10
	testhistogram_bucket{le="+Inf", start="negative"}	0+3x10

# Another test histogram, where q(1/6), q(1/2), and q(5/6) are each in
# the middle of a bucket and should therefore be 1, 3, and 5,
# respectively.
load 5m
	testhistogram2_bucket{le="0"}	 0+0x10
	testhistogram2_bucket{le="2"}	 0+1x10
	testhistogram2_bucket{le="4"}    0+2x10
	testhistogram2_bucket{le="6"}	 0+3x10
	testhistogram2_bucket{le="+Inf"} 0+3x10

# Now a more realistic histogram per job and instance to test aggregation.
load 5m
	request_duration_seconds_bucket{job="job1", instance="ins1", le="0.1"}	0+1x10
	request_duration_seconds_bucket{job="job1", instance="ins1", le="0.2"}	0+3x10
	request_duration_seconds_bucket{job="job1", instance="ins1", le="+Inf"}	0+4x10
	request_duration_seconds_bucket{job="job1", instance="ins2", le="0.1"}	0+2x10
	request_duration_seconds_bucket{job="job1", instance="ins2", le="0.2"}	0+5x10
	request_duration_seconds_bucket{job="job1", instance="ins2", le="+Inf"}	0+6x10
	request_duration_seconds_bucket{job="job2", instance="ins1", le="0.1"}	0+3x10
	request_duration_seconds_bucket{job="job2", instance="ins1", le="0.2"}	0+4x10
	request_duration_seconds_bucket{job="job2", instance="ins1", le="+Inf"}	0+6x10
	request_duration_seconds_bucket{job="job2", instance="ins2", le="0.1"}	0+4x10
	request_duration_seconds_bucket{job="job2", instance="ins2", le="0.2"}	0+7x10
	request_duration_seconds_bucket{job="job2", instance="ins2", le="+Inf"}	0+9x10

# Different le representations in one histogram.
load 5m
	mixed_bucket{job="job1", instance="ins1", le="0.1"}	0+1x10
	mixed_bucket{job="job1", instance="ins1", le="0.2"}	0+1x10
	mixed_bucket{job="job1", instance="ins1", le="2e-1"}	0+1x10
	mixed_bucket{job="job1", instance="ins1", le="2.0e-1"}	0+1x10
	mixed_bucket{job="job1", instance="ins1", le="+Inf"}	0+4x10
	mixed_bucket{job="job1", instance="ins2", le="+inf"}	0+0x10
	mixed_bucket{job="job1", instance="ins2", le="+Inf"}	0+0x10

# Quantile too low.
eval instant at 50m histogram_quantile(-0.1, testhistogram_bucket)
	{start="positive"} -Inf
	{start="negative"} -Inf

# Quantile too high.
eval instant at 50m histogram_quantile(1.01, testhistogram_bucket)
	{start="positive"} +Inf
	{start="negative"} +Inf

# Quantile invalid.
eval instant at 50m histogram_quantile(NaN, testhistogram_bucket)
	{start="positive"} NaN
	{start="negative"} NaN

# Quantile value in lowest bucket, which is positive.
eval instant at 50m histogram_quantile(0, testhistogram_bucket{start="positive"})
	{start="positive"} 0

# Quantile value in lowest bucket, which is negative.
eval instant at 50m histogram_quantile(0, testhistogram_bucket{start="negative"})
	{start="negative"} -0.2

# Quantile value in highest bucket.
eval instant at 50m histogram_quantile(1, testhistogram_bucket)
	{start="positive"} 1
	{start="negative"} 0.3

# Finally some useful quantiles.
eval instant at 50m histogram_quantile(0.2, testhistogram_bucket)
	{start="positive"} 0.048
	{start="negative"} -0.2


eval instant at 50m histogram_quantile(0.5, testhistogram_bucket)
	{start="positive"} 0.15
	{start="negative"} -0.15

eval instant at 50m histogram_quantile(0.8, testhistogram_bucket)
	{start="positive"} 0.72
	{start="negative"} 0.3

# More realistic with rates.
eval instant at 50m histogram_quantile(0.2, rate(testhistogram_bucket[5m]))
	{start="positive"} 0.048
	{start="negative"} -0.2

eval instant at 50m histogram_quantile(0.5, rate(testhistogram_bucket[5m]))
	{start="positive"} 0.15
	{start="negative"} -0.15

eval instant at 50m histogram_quantile(0.8, rate(testhistogram_bucket[5m]))
	{start="positive"} 0.72
	{start="negative"} 0.3

# Want results exactly in the middle of the bucket.
eval instant at 7m histogram_quantile(1./6., testhistogram2_bucket)
	{} 1

eval instant at 7m histogram_quantile(0.5, testhistogram2_bucket)
	{} 3

eval instant at 7m histogram_quantile(5./6., testhistogram2_bucket)
	{} 5

eval instant at 47m histogram_quantile(1./6., rate(testhistogram2_bucket[15m]))
	{} 1

eval instant at 47m histogram_quantile(0.5, rate(testhistogram2_bucket[15m]))
	{} 3

eval instant at 47m histogram_quantile(5./6., rate(testhistogram2_bucket[15m]))
	{} 5

# Aggregated histogram: Everything in one.
eval instant at 50m histogram_quantile(0.3, sum(rate(request_duration_seconds_bucket[5m])) by (le))
	{} 0.075

eval instant at 50m histogram_quantile(0.5, sum(rate(request_duration_seconds_bucket[5m])) by (le))
	{} 0.1277777777777778

# Aggregated histogram: Everything in one. Now with avg, which does not change anything.
eval instant at 50m histogram_quantile(0.3, avg(rate(request_duration_seconds_bucket[5m])) by (le))
	{} 0.075

eval instant at 50m histogram_quantile(0.5, avg(rate(request_duration_seconds_bucket[5m])) by (le))
	{} 0.12777777777777778

# Aggregated histogram: By instance.
eval instant at 50m histogram_quantile(0.3, sum(rate(request_duration_seconds_bucket[5m])) by (le, instance))
	{instance="ins1"} 0.075
	{instance="ins2"} 0.075

eval instant at 50m histogram_quantile(0.5, sum(rate(request_duration_seconds_bucket[5m])) by (le, instance))
	{instance="ins1"} 0.1333333333
	{instance="ins2"} 0.125

# Aggregated histogram: By job.
eval instant at 50m histogram_quantile(0.3, sum(rate(request_duration_seconds_bucket[5m])) by (le, job))
	{job="job1"} 0.1
	{job="job2"} 0.0642857142857143

eval instant at 50m histogram_quantile(0.5, sum(rate(request_duration_seconds_bucket[5m])) by (le, job))
	{job="job1"} 0.14
	{job="job2"} 0.1125

# Aggregated histogram: By job and instance.
eval instant at 50m histogram_quantile(0.3, sum(rate(request_duration_seconds_bucket[5m])) by (le, job, instance))
	{instance="ins1", job="job1"} 0.11
	{instance="ins2", job="job1"} 0.09
	{instance="ins1", job="job2"} 0.06
	{instance="ins2", job="job2"} 0.0675

eval instant at 50m histogram_quantile(0.5, sum(rate(request_duration_seconds_bucket[5m])) by (le, job, instance))
	{instance="ins1", job="job1"} 0.15
	{instance="ins2", job="job1"} 0.1333333333333333
	{instance="ins1", job="job2"} 0.1
	{instance="ins2", job="job2"} 0.1166666666666667

# The unaggregated histogram for comparison. Same result as the previous one.
eval instant at 50m histogram_quantile(0.3, rate(request_duration_seconds_bucket[5m]))
	{instance="ins1", job="job1"} 0.11
	{instance="ins2", job="job1"} 0.09
	{instance="ins1", job="job2"} 0.06
	{instance="ins2", job="job2"} 0.0675

eval instant at 50m histogram_quantile(0.5, rate(request_duration_seconds_bucket[5m]))
	{instance="ins1", job="job1"} 0.15
	{instance="ins2", job="job1"} 0.13333333333333333
	{instance="ins1", job="job2"} 0.1
	{instance="ins2", job="job2"} 0.11666666666666667

# A histogram with nonmonotonic bucket counts. This may happen when recording
# rule evaluation or federation races scrape ingestion, causing some buckets
# counts to be derived from fewer samples.

load 5m
    nonmonotonic_bucket{le="0.1"}   0+2x10
    nonmonotonic_bucket{le="1"}     0+1x10
    nonmonotonic_bucket{le="10"}    0+5x10
    nonmonotonic_bucket{le="100"}   0+4x10
    nonmonotonic_bucket{le="1000"}  0+9x10
    nonmonotonic_bucket{le="+Inf"}  0+8x10

# Nonmonotonic buckets
eval instant at 50m histogram_quantile(0.01, nonmonotonic_bucket)
    {} 0.0045

eval instant at 50m histogram_quantile(0.5, nonmonotonic_bucket)
    {} 8.5

eval instant at 50m histogram_quantile(0.99, nonmonotonic_bucket)
    {} 979.75

# Buckets with different representations of the same upper bound.
eval instant at 50m histogram_quantile(0.5, rate(mixed_bucket[5m]))
	{instance="ins1", job="job1"} 0.15
	{instance="ins2", job="job1"} NaN

eval instant at 50m histogram_quantile(0.75, rate(mixed_bucket[5m]))
	{instance="ins1", job="job1"} 0.2
	{instance="ins2", job="job1"} NaN

eval instant at 50m histogram_quantile(1, rate(mixed_bucket[5m]))
	{instance="ins1", job="job1"} 0.2
	{instance="ins2", job="job1"} NaN

load 5m
	empty_bucket{le="0.1", job="job1", instance="ins1"}    0x10
	empty_bucket{le="0.2", job="job1", instance="ins1"}    0x10
	empty_bucket{le="+Inf", job="job1", instance="ins1"}   0x10

eval instant at 50m histogram_quantile(0.2, rate(empty_bucket[5m]))
	{instance="ins1", job="job1"} NaN

# Load a duplicate histogram with a different name to test failure scenario on multiple histograms with the same label set
# https://github.com/prometheus/prometheus/issues/9910
load 5m
	request_duration_seconds2_bucket{job="job1", instance="ins1", le="0.1"}	0+1x10
	request_duration_seconds2_bucket{job="job1", instance="ins1", le="0.2"}	0+3x10
	request_duration_seconds2_bucket{job="job1", instance="ins1", le="+Inf"}	0+4x10

eval_fail instant at 50m histogram_quantile(0.99, {__name__=~"request_duration.*"})