pkg/serializer/internal/metrics: replace Cols() with Range() in V3 sketch path to eliminate allocations

[AlexanderYastrebov]

What does this PR do?

Add Range method to sparseStore to allow callers iterate over k/n and
avoid allocations via Cols method.

Note: I also tried adding ColSeq (iter.Seq2) but it allocated two closures per bucket point
(the returned Seq2 and the yield closure), doubling alloc count to 889/op.

Range follows the sync.Map.Range callback convention — the closure is
stack-allocated by escape analysis since it doesn't outlive the call.

pkg: github.com/DataDog/datadog-agent/pkg/serializer/internal/metrics
cpu: Apple M4 Max
                                 │   HEAD~1    │                HEAD                │
                                 │   sec/op    │   sec/op     vs base               │
PayloadsBuilderV3/writeSketch-16   166.6µ ± 1%   152.5µ ± 1%  -8.47% (p=0.000 n=10)

                                 │    HEAD~1     │                 HEAD                 │
                                 │     B/op      │     B/op      vs base                │
PayloadsBuilderV3/writeSketch-16   189.80Ki ± 0%   47.20Ki ± 0%  -75.13% (p=0.000 n=10)

                                 │   HEAD~1   │               HEAD                │
                                 │ allocs/op  │ allocs/op   vs base               │
PayloadsBuilderV3/writeSketch-16   445.0 ± 0%   448.0 ± 0%  +0.67% (p=0.000 n=10)

Motivation

Learn this codebase area, reduce allocations.

Describe how you validated your changes

Added benchmark before the change, compared results before and after.

Additional Notes

• non-v3 path could also benefit from Range but it requires encoding packed values manually as molecule.ProtoStream expects value arrays. I can open another PR if that is interesting.
• I think v3 sketches are not fed via this codepath so the improvement benefit might be delayed until later.

[datadog-official]

✨ Fix all issues with BitsAI

⚠️ Warnings

🚦 3 Pipeline jobs failed

DataDog/datadog-agent | oracle: [21.3.0-xe]     

Label analysis | release-note-check     

Label analysis | skip-qa-check     

ℹ️ Info

🎯 Code Coverage (details)
• Patch Coverage: 78.57%
• Overall Coverage: 50.92% (-0.00%)

Useful? React with 👍 / 👎

_{This comment will be updated automatically if new data arrives.
🔗 Commit SHA: 53911db | Docs | Datadog PR Page | Give us feedback!}

[dd-octo-sts]

Files inventory check summary

File checks results against ancestor 8ac9cf30:

Results for datadog-agent_7.82.0~devel.git.180.53911db.pipeline.119995726-1_amd64.deb:

No change detected

[dd-octo-sts]

Static quality checks

✅ Please find below the results from static quality gates
Comparison made with ancestor 8ac9cf3
📊 Static Quality Gates Dashboard
🔗 SQG Job

Successful checks

Info

	Quality gate	Change	Size (prev → curr → max)
✅	agent_deb_amd64	+4.0 KiB (0.00% increase, -0.04% of buffer)	749.062 → 749.066 → 758.200
✅	agent_rpm_amd64	+4.0 KiB (0.00% increase, -0.04% of buffer)	749.046 → 749.050 → 758.170
✅	agent_rpm_arm64	+4.0 KiB (0.00% increase, -0.08% of buffer)	724.667 → 724.671 → 729.660
✅	agent_rpm_arm64_fips	+4.0 KiB (0.00% increase, -0.08% of buffer)	684.236 → 684.240 → 688.860
✅	agent_suse_amd64	+4.0 KiB (0.00% increase, -0.04% of buffer)	749.046 → 749.050 → 758.170
✅	agent_suse_arm64	+4.0 KiB (0.00% increase, -0.08% of buffer)	724.667 → 724.671 → 729.660
✅	agent_suse_arm64_fips	+4.0 KiB (0.00% increase, -0.08% of buffer)	684.236 → 684.240 → 688.860
✅	docker_agent_amd64	+4.0 KiB (0.00% increase, -0.08% of buffer)	808.801 → 808.804 → 813.790
✅	docker_agent_arm64	+3.99 KiB (0.00% increase, -0.07% of buffer)	809.402 → 809.406 → 815.030
✅	docker_agent_jmx_amd64	+4.0 KiB (0.00% increase, -0.08% of buffer)	999.698 → 999.702 → 1004.550
✅	docker_agent_jmx_arm64	+4.0 KiB (0.00% increase, -0.07% of buffer)	988.952 → 988.956 → 994.710
✅	docker_dogstatsd_arm64	-64.0 KiB (0.17% reduction, +6.17% of buffer)	37.257 → 37.194 → 38.270
✅	dogstatsd_deb_amd64	+4.0 KiB (0.01% increase, -0.28% of buffer)	29.741 → 29.744 → 31.150
✅	dogstatsd_rpm_amd64	+4.0 KiB (0.01% increase, -0.28% of buffer)	29.741 → 29.744 → 31.150
✅	dogstatsd_suse_amd64	+4.0 KiB (0.01% increase, -0.28% of buffer)	29.741 → 29.744 → 31.150
✅	iot_agent_deb_arm64	+4.0 KiB (0.01% increase, -0.27% of buffer)	42.292 → 42.296 → 43.720

16 successful checks with minimal change (< 2 KiB)

	Quality gate	Current Size
✅	agent_deb_amd64_fips	705.023 MiB
✅	agent_heroku_amd64	309.985 MiB
✅	agent_rpm_amd64_fips	705.006 MiB
✅	agent_suse_amd64_fips	705.006 MiB
✅	docker_cluster_agent_amd64	207.989 MiB
✅	docker_cluster_agent_arm64	221.189 MiB
✅	docker_cws_instrumentation_amd64	7.447 MiB
✅	docker_cws_instrumentation_arm64	6.877 MiB
✅	docker_dogstatsd_amd64	39.081 MiB
✅	docker_host_profiler_amd64	304.564 MiB
✅	docker_host_profiler_arm64	315.680 MiB
✅	dogstatsd_deb_arm64	27.800 MiB
✅	iot_agent_deb_amd64	45.566 MiB
✅	iot_agent_deb_armhf	43.077 MiB
✅	iot_agent_rpm_amd64	45.566 MiB
✅	iot_agent_suse_amd64	45.565 MiB

[cit-pr-commenter-54b7da]

Regression Detector

Regression Detector Results

Metrics dashboard
Target profiles
Run ID: 7939fb12-fa4e-43c8-b7ea-d861f51b387b

Baseline: 8ac9cf3
Comparison: 53911db
Diff

❌ Experiments with retried target crashes

This is a critical error. One or more replicates failed with a non-zero exit code. These replicates may have been retried. See Replicate Execution Details for more information.

• quality_gate_idle

Optimization Goals: ✅ No significant changes detected

Fine details of change detection per experiment

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
➖	quality_gate_idle_all_features	memory utilization	+0.01	[-0.03, +0.05]	1	Logs bounds checks dashboard
➖	quality_gate_logs	% cpu utilization	-0.42	[-1.49, +0.66]	1	Logs bounds checks dashboard
➖	quality_gate_idle	memory utilization	-0.44	[-0.49, -0.39]	1	Logs bounds checks dashboard
➖	quality_gate_metrics_logs	memory utilization	-1.96	[-2.22, -1.70]	1	Logs bounds checks dashboard

Bounds Checks: ✅ Passed

perf	experiment	bounds_check_name	replicates_passed	observed_value	links
✅	quality_gate_idle	intake_connections	10/10	3 ≤ 4	bounds checks dashboard
✅	quality_gate_idle	memory_usage	10/10	143.54MiB ≤ 154MiB	bounds checks dashboard
✅	quality_gate_idle	total_bytes_received	10/10	577.47KiB ≤ 819.20KiB	bounds checks dashboard
✅	quality_gate_idle_all_features	intake_connections	10/10	3 ≤ 4	bounds checks dashboard
✅	quality_gate_idle_all_features	memory_usage	10/10	484.54MiB ≤ 495MiB	bounds checks dashboard
✅	quality_gate_idle_all_features	total_bytes_received	10/10	0.90MiB ≤ 1.25MiB	bounds checks dashboard
✅	quality_gate_logs	intake_connections	10/10	3 ≤ 6	bounds checks dashboard
✅	quality_gate_logs	memory_usage	10/10	182.28MiB ≤ 195MiB	bounds checks dashboard
✅	quality_gate_logs	missed_bytes	10/10	0B = 0B	bounds checks dashboard
✅	quality_gate_logs	total_bytes_received	10/10	264.19MiB ≤ 292MiB	bounds checks dashboard
✅	quality_gate_metrics_logs	cpu_usage	10/10	338.91 ≤ 2000	bounds checks dashboard
✅	quality_gate_metrics_logs	intake_connections	10/10	3 ≤ 6	bounds checks dashboard
✅	quality_gate_metrics_logs	memory_usage	10/10	395.93MiB ≤ 430MiB	bounds checks dashboard
✅	quality_gate_metrics_logs	missed_bytes	10/10	0B = 0B	bounds checks dashboard
✅	quality_gate_metrics_logs	total_bytes_received	10/10	0.86GiB ≤ 1.04GiB	bounds checks dashboard

Explanation

Confidence level: 90.00%
Effect size tolerance: |Δ mean %| ≥ 5.00%

Performance changes are noted in the perf column of each table:

• ✅ = significantly better comparison variant performance
• ❌ = significantly worse comparison variant performance
• ➖ = no significant change in performance

A regression test is an A/B test of target performance in a repeatable rig, where "performance" is measured as "comparison variant minus baseline variant" for an optimization goal (e.g., ingress throughput). Due to intrinsic variability in measuring that goal, we can only estimate its mean value for each experiment; we report uncertainty in that value as a 90.00% confidence interval denoted "Δ mean % CI".

For each experiment, we decide whether a change in performance is a "regression" -- a change worth investigating further -- if all of the following criteria are true:

1. Its estimated |Δ mean %| ≥ 5.00%, indicating the change is big enough to merit a closer look.

2. Its 90.00% confidence interval "Δ mean % CI" does not contain zero, indicating that if our statistical model is accurate, there is at least a 90.00% chance there is a difference in performance between baseline and comparison variants.

3. Its configuration does not mark it "erratic".

Replicate Execution Details

We run multiple replicates for each experiment/variant. However, we allow replicates to be automatically retried if there are any failures, up to 8 times, at which point the replicate is marked dead and we are unable to run analysis for the entire experiment. We call each of these attempts at running replicates a replicate execution. This section lists all replicate executions that failed due to the target crashing or being oom killed.

Note: In the below tables we bucket failures by experiment, variant, and failure type. For each of these buckets we list out the replicate indexes that failed with an annotation signifying how many times said replicate failed with the given failure mode. In the below example the baseline variant of the experiment named experiment_with_failures had two replicates that failed by oom kills. Replicate 0, which failed 8 executions, and replicate 1 which failed 6 executions, all with the same failure mode.

Experiment	Variant	Replicates	Failure	Logs	Debug Dashboard
experiment_with_failures	baseline	0 (x8) 1 (x6)	Oom killed		Debug Dashboard

The debug dashboard links will take you to a debugging dashboard specifically designed to investigate replicate execution failures.

❌ Retried Normal Replicate Execution Failures (non-profiling)

Experiment	Variant	Replicates	Failure	Debug Dashboard
quality_gate_idle	baseline	0	Oom killed	Debug Dashboard
quality_gate_idle	comparison	5	Oom killed	Debug Dashboard

❌ Retried Profiling Replicate Execution Failures (ddprof)

Note: Profiling replicas may still be executing. See the debug dashboard for up to date status.

Experiment	Variant	Replicates	Failure	Debug Dashboard
quality_gate_idle	baseline	10	Oom killed	Debug Dashboard
quality_gate_idle_all_features	baseline	10	Oom killed	Debug Dashboard
quality_gate_idle_all_features	comparison	10	Oom killed	Debug Dashboard
quality_gate_logs	comparison	10	Oom killed	Debug Dashboard
quality_gate_metrics_logs	baseline	10	Oom killed	Debug Dashboard
quality_gate_metrics_logs	comparison	10	Oom killed	Debug Dashboard

CI Pass/Fail Decision

✅ Passed. All Quality Gates passed.

• quality_gate_metrics_logs, bounds check total_bytes_received: 10/10 replicas passed. Gate passed.
• quality_gate_metrics_logs, bounds check intake_connections: 10/10 replicas passed. Gate passed.
• quality_gate_metrics_logs, bounds check missed_bytes: 10/10 replicas passed. Gate passed.
• quality_gate_metrics_logs, bounds check cpu_usage: 10/10 replicas passed. Gate passed.
• quality_gate_metrics_logs, bounds check memory_usage: 10/10 replicas passed. Gate passed.
• quality_gate_logs, bounds check intake_connections: 10/10 replicas passed. Gate passed.
• quality_gate_logs, bounds check total_bytes_received: 10/10 replicas passed. Gate passed.
• quality_gate_logs, bounds check memory_usage: 10/10 replicas passed. Gate passed.
• quality_gate_logs, bounds check missed_bytes: 10/10 replicas passed. Gate passed.
• quality_gate_idle_all_features, bounds check total_bytes_received: 10/10 replicas passed. Gate passed.
• quality_gate_idle_all_features, bounds check memory_usage: 10/10 replicas passed. Gate passed.
• quality_gate_idle_all_features, bounds check intake_connections: 10/10 replicas passed. Gate passed.
• quality_gate_idle, bounds check total_bytes_received: 10/10 replicas passed. Gate passed.
• quality_gate_idle, bounds check memory_usage: 10/10 replicas passed. Gate passed.
• quality_gate_idle, bounds check intake_connections: 10/10 replicas passed. Gate passed.

[RiantZ]

It seems it is still used, but perhaps shall be deprecated?

[AlexanderYastrebov]

It is used for non-v3 codepath.

[RiantZ]

Yes, it is used, but shall it be used for new code?

[RiantZ]

We are iterating here s.k and accessing к s.n[i]
If len(s.n) < len(s.k) will it lead to panic? or such case is impossible?

[AlexanderYastrebov]

k and n are the same size by construction, e.g. clients iterate them in lockstep when they are obtained via existing Cols method.

[RiantZ]

My comment was driven by the fact that the relationship between the sizes of the two arrays is not immediately obvious. In the future, if this code is reused or modified, it could be confusing.

[RiantZ]

Approved with few small comments