[Serverless-Init] Improve Tags Performance by nhulston · Pull Request #41582 · DataDog/datadog-agent

nhulston · 2025-10-03T16:11:32Z

What does this PR do?

Serverless-init is a special build of the agent for Serverless containers like Google Cloud Run or Azure Container Apps.

Create a custom JSON encoder for serverless-init
Cache stringified tags since tags are constant in serverless-init. There is only one log source in serverless-init
This significantly improves CPU performance. In my tests, we eliminated ~7% CPU usage that was being wasted:

% go tool pprof ./saved-profiles/cpu-tagstostring-before.pb.gz 
Duration: 60.14s, Total samples = 8.25s (13.72%)
(pprof) top -cum TagsToString
Showing top 10 nodes out of 52
      flat  flat%   sum%        cum   cum%
         0     0%     0%      0.60s  7.27%  github.com/DataDog/datadog-agent/pkg/logs/message.(*MessageMetadata).TagsToString (inline)
         0     0%     0%      0.60s  7.27%  github.com/DataDog/datadog-agent/pkg/logs/message.(*Origin).TagsToString
         0     0%     0%      0.60s  7.27%  github.com/DataDog/datadog-agent/pkg/logs/processor.(*Processor).processMessage
         0     0%     0%      0.60s  7.27%  github.com/DataDog/datadog-agent/pkg/logs/processor.(*Processor).run
         0     0%     0%      0.60s  7.27%  github.com/DataDog/datadog-agent/pkg/logs/processor.(*jsonServerlessEncoder).Encode

% go tool pprof ./saved-profiles/cpu-tagstostring-after.pb.gz
Duration: 60.08s, Total samples = 7.93s (13.20%)
(pprof) top -cum TagsToString
Focus expression matched no samples

Flame graph before:

You can view the profiles yourself: before and after

Motivation

Improve serverless-init performance

https://datadoghq.atlassian.net/browse/SVLS-7657

Describe how you validated your changes

Via profiles and manually. I verified that tags still get added as expected on Google Cloud Run.

We also have e2e tests and long-running tests to detect regressions. We always run them before doing a release.

Additional Notes

gabedos

lgtm for updating environment detection from serverless to lambda

cit-pr-commenter · 2025-10-03T19:05:21Z

Regression Detector

Regression Detector Results

Metrics dashboard
Target profiles
Run ID: c6e707e0-68e8-47ac-b057-cecdf711952c

Baseline: 9010a7a
Comparison: dc2a7d4
Diff

Optimization Goals: ❌ Regression(s) detected

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
❌	docker_containers_memory	memory utilization	+5.94	[+5.54, +6.33]	1	Logs

Experiments ignored for regressions

Regressions in experiments with settings containing erratic: true are ignored.

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
➖	docker_containers_cpu	% cpu utilization	+0.21	[-0.78, +1.19]	1	Logs

Fine details of change detection per experiment

perf	experiment	goal	Δ mean %	Δ mean % CI	trials	links
❌	docker_containers_memory	memory utilization	+5.94	[+5.54, +6.33]	1	Logs
➖	otlp_ingest_logs	memory utilization	+0.88	[+0.76, +0.99]	1	Logs
➖	ddot_metrics	memory utilization	+0.67	[+0.51, +0.83]	1	Logs
➖	tcp_syslog_to_blackhole	ingress throughput	+0.51	[+0.44, +0.57]	1	Logs
➖	otlp_ingest_metrics	memory utilization	+0.30	[+0.18, +0.42]	1	Logs
➖	quality_gate_metrics_logs	memory utilization	+0.25	[+0.03, +0.46]	1	Logs bounds checks dashboard
➖	ddot_metrics_sum_cumulativetodelta_exporter	memory utilization	+0.23	[+0.04, +0.42]	1	Logs
➖	docker_containers_cpu	% cpu utilization	+0.21	[-0.78, +1.19]	1	Logs
➖	quality_gate_idle_all_features	memory utilization	+0.20	[+0.16, +0.24]	1	Logs bounds checks dashboard
➖	file_to_blackhole_500ms_latency	egress throughput	+0.07	[-0.53, +0.66]	1	Logs
➖	file_to_blackhole_1000ms_latency	egress throughput	+0.06	[-0.53, +0.65]	1	Logs
➖	uds_dogstatsd_to_api	ingress throughput	+0.01	[-0.22, +0.24]	1	Logs
➖	ddot_metrics_sum_delta	memory utilization	+0.00	[-0.16, +0.17]	1	Logs
➖	tcp_dd_logs_filter_exclude	ingress throughput	+0.00	[-0.01, +0.01]	1	Logs
➖	file_tree	memory utilization	-0.02	[-0.06, +0.02]	1	Logs
➖	file_to_blackhole_100ms_latency	egress throughput	-0.03	[-0.64, +0.59]	1	Logs
➖	quality_gate_logs	% cpu utilization	-0.03	[-2.80, +2.75]	1	Logs bounds checks dashboard
➖	file_to_blackhole_0ms_latency	egress throughput	-0.09	[-0.64, +0.47]	1	Logs
➖	quality_gate_idle	memory utilization	-0.23	[-0.27, -0.19]	1	Logs bounds checks dashboard
➖	ddot_logs	memory utilization	-0.30	[-0.35, -0.24]	1	Logs
➖	ddot_metrics_sum_cumulative	memory utilization	-0.39	[-0.51, -0.27]	1	Logs
➖	uds_dogstatsd_20mb_12k_contexts_20_senders	memory utilization	-0.53	[-0.58, -0.49]	1	Logs

Bounds Checks: ❌ Failed

perf	experiment	bounds_check_name	replicates_passed	links
✅	docker_containers_cpu	simple_check_run	10/10
❌	docker_containers_memory	memory_usage	9/10
✅	docker_containers_memory	simple_check_run	10/10
✅	file_to_blackhole_0ms_latency	lost_bytes	10/10
✅	file_to_blackhole_0ms_latency	memory_usage	10/10
✅	file_to_blackhole_1000ms_latency	memory_usage	10/10
✅	file_to_blackhole_100ms_latency	lost_bytes	10/10
✅	file_to_blackhole_100ms_latency	memory_usage	10/10
✅	file_to_blackhole_500ms_latency	lost_bytes	10/10
✅	file_to_blackhole_500ms_latency	memory_usage	10/10
✅	quality_gate_idle	intake_connections	10/10	bounds checks dashboard
✅	quality_gate_idle	memory_usage	10/10	bounds checks dashboard
✅	quality_gate_idle_all_features	intake_connections	10/10	bounds checks dashboard
✅	quality_gate_idle_all_features	memory_usage	10/10	bounds checks dashboard
✅	quality_gate_logs	intake_connections	10/10	bounds checks dashboard
✅	quality_gate_logs	lost_bytes	10/10	bounds checks dashboard
✅	quality_gate_logs	memory_usage	10/10	bounds checks dashboard
✅	quality_gate_metrics_logs	cpu_usage	10/10	bounds checks dashboard
✅	quality_gate_metrics_logs	intake_connections	10/10	bounds checks dashboard
✅	quality_gate_metrics_logs	lost_bytes	10/10	bounds checks dashboard
✅	quality_gate_metrics_logs	memory_usage	10/10	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:

Its estimated |Δ mean %| ≥ 5.00%, indicating the change is big enough to merit a closer look.
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.
Its configuration does not mark it "erratic".

CI Pass/Fail Decision

✅ Passed. All Quality Gates passed.

quality_gate_metrics_logs, bounds check memory_usage: 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 lost_bytes: 10/10 replicas passed. Gate passed.
quality_gate_metrics_logs, bounds check cpu_usage: 10/10 replicas passed. Gate passed.
quality_gate_logs, bounds check memory_usage: 10/10 replicas passed. Gate passed.
quality_gate_logs, bounds check lost_bytes: 10/10 replicas passed. Gate passed.
quality_gate_logs, bounds check intake_connections: 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 memory_usage: 10/10 replicas passed. Gate passed.
quality_gate_idle, bounds check intake_connections: 10/10 replicas passed. Gate passed.

agent-platform-auto-pr · 2025-10-03T19:17:40Z

Static quality checks

✅ Please find below the results from static quality gates
Comparison made with ancestor 9010a7a

Successful checks

Info

	Quality gate	Delta	On disk size (MiB)	Delta	On wire size (MiB)
✅	agent_deb_amd64	$${+0.01}$$	$${701.25}$$ < $${703.13}$$	$${+0}$$	$${176.85}$$ < $${178.38}$$
✅	agent_deb_amd64_fips	$${+0.01}$$	$${695.74}$$ < $${697.61}$$	$${+0.02}$$	$${175.57}$$ < $${177.15}$$
✅	agent_heroku_amd64	$${+0}$$	$${339.26}$$ < $${341.62}$$	$${+0}$$	$${90.13}$$ < $${91.52}$$
✅	agent_msi	$${+0.02}$$	$${984.54}$$ < $${990.42}$$	$${-0}$$	$${149.83}$$ < $${152.42}$$
✅	agent_rpm_amd64	$${+0.01}$$	$${701.24}$$ < $${703.12}$$	$${-0.02}$$	$${180.1}$$ < $${180.53}$$
✅	agent_rpm_amd64_fips	$${+0.01}$$	$${695.73}$$ < $${697.6}$$	$${-0}$$	$${177.8}$$ < $${178.87}$$
✅	agent_rpm_arm64	$${+0.01}$$	$${685.41}$$ < $${689.82}$$	$${-0.01}$$	$${160.29}$$ < $${162.16}$$
✅	agent_rpm_arm64_fips	$${+0.01}$$	$${680.93}$$ < $${685.08}$$	$${+0}$$	$${159.24}$$ < $${161.11}$$
✅	agent_suse_amd64	$${+0.01}$$	$${701.24}$$ < $${703.12}$$	$${-0.02}$$	$${180.1}$$ < $${180.53}$$
✅	agent_suse_amd64_fips	$${+0.01}$$	$${695.73}$$ < $${697.6}$$	$${-0}$$	$${177.8}$$ < $${178.87}$$
✅	agent_suse_arm64	$${+0.01}$$	$${685.41}$$ < $${689.82}$$	$${-0.01}$$	$${160.29}$$ < $${162.16}$$
✅	agent_suse_arm64_fips	$${+0.01}$$	$${680.93}$$ < $${685.08}$$	$${+0}$$	$${159.24}$$ < $${161.11}$$
✅	docker_agent_amd64	$${+0.01}$$	$${772.68}$$ < $${774.54}$$	$${+0.01}$$	$${265.12}$$ < $${266.46}$$
✅	docker_agent_arm64	$${+0.01}$$	$${780.8}$$ < $${785.2}$$	$${+0.01}$$	$${250.9}$$ < $${252.92}$$
✅	docker_agent_jmx_amd64	$${+0.01}$$	$${963.55}$$ < $${965.41}$$	$${+0.02}$$	$${333.76}$$ < $${335.08}$$
✅	docker_agent_jmx_arm64	$${+0.01}$$	$${960.26}$$ < $${964.66}$$	$${-0.01}$$	$${315.51}$$ < $${317.54}$$
✅	docker_cluster_agent_amd64	$${+0}$$	$${212.81}$$ < $${213.74}$$	$${+0}$$	$${72.18}$$ < $${73.2}$$
✅	docker_cluster_agent_arm64	$${+0}$$	$${228.73}$$ < $${229.68}$$	$${-0}$$	$${68.46}$$ < $${69.48}$$
✅	docker_cws_instrumentation_amd64	$${+0}$$	$${7.06}$$ < $${7.12}$$	$${+0}$$	$${2.95}$$ < $${3.29}$$
✅	docker_cws_instrumentation_arm64	$${0}$$	$${6.69}$$ < $${6.92}$$	$${+0}$$	$${2.7}$$ < $${3.07}$$
✅	docker_dogstatsd_amd64	$${0}$$	$${38.36}$$ < $${39.3}$$	$${-0}$$	$${14.82}$$ < $${15.76}$$
✅	docker_dogstatsd_arm64	$${0}$$	$${37.06}$$ < $${37.94}$$	$${+0}$$	$${14.26}$$ < $${14.83}$$
✅	dogstatsd_deb_amd64	$${0}$$	$${29.58}$$ < $${30.53}$$	$${-0}$$	$${7.8}$$ < $${8.75}$$
✅	dogstatsd_deb_arm64	$${0}$$	$${28.17}$$ < $${29.12}$$	$${+0}$$	$${6.76}$$ < $${7.71}$$
✅	dogstatsd_rpm_amd64	$${0}$$	$${29.58}$$ < $${30.53}$$	$${+0}$$	$${7.81}$$ < $${8.77}$$
✅	dogstatsd_suse_amd64	$${0}$$	$${29.58}$$ < $${30.53}$$	$${+0}$$	$${7.81}$$ < $${8.77}$$
✅	iot_agent_deb_amd64	$${+0}$$	$${54.51}$$ < $${54.97}$$	$${-0}$$	$${13.62}$$ < $${14.45}$$
✅	iot_agent_deb_arm64	$${+0}$$	$${51.8}$$ < $${51.9}$$	$${-0}$$	$${11.75}$$ < $${12.63}$$
✅	iot_agent_deb_armhf	$${+0}$$	$${51.33}$$ < $${51.84}$$	$${-0}$$	$${11.82}$$ < $${12.74}$$
✅	iot_agent_rpm_amd64	$${+0}$$	$${54.51}$$ < $${54.97}$$	$${+0}$$	$${13.64}$$ < $${14.47}$$
✅	iot_agent_suse_amd64	$${+0}$$	$${54.51}$$ < $${54.97}$$	$${+0}$$	$${13.64}$$ < $${14.47}$$

nhulston · 2025-10-03T20:22:42Z

/merge

dd-devflow-routing-codex · 2025-10-03T20:22:46Z

View all feedbacks in Devflow UI.

2025-10-03 20:22:46 UTC ℹ️ Start processing command /merge

2025-10-03 20:22:54 UTC ℹ️ MergeQueue: waiting for PR to be ready

This merge request is not mergeable yet, because of pending checks/missing approvals. It will be added to the queue as soon as checks pass and/or get approvals.
Note: if you pushed new commits since the last approval, you may need additional approval.
You can remove it from the waiting list with /remove command.

2025-10-03 22:18:11 UTC ℹ️ MergeQueue: merge request added to the queue

The expected merge time in main is approximately 47m (p90).

2025-10-03 22:49:40 UTC ℹ️ MergeQueue: This merge request was merged

OliviaShoup

thanks for the update @nhulston!

nhulston added 5 commits October 3, 2025 11:01

(feat): create custom json processor for serverless-init

4c6953c

(chore): rename IsServerless() to IsLambda()

46b6596

(feat): enable custom JSON encoder for serverless-init

efa8fa9

(feat): cache stringified tags

f475bdc

changelog

bc8aac3

github-actions Bot added medium review PR review might take time team/agent-log-pipelines labels Oct 3, 2025

add todo comment

e8cf17e

nhulston added the qa/done QA done before merge and regressions are covered by tests label Oct 3, 2025

nhulston marked this pull request as ready for review October 3, 2025 16:31

nhulston requested review from a team as code owners October 3, 2025 16:31

nhulston requested a review from s-alad October 3, 2025 16:31

Run dda inv tidy

dc2a7d4

gabedos approved these changes Oct 3, 2025

View reviewed changes

s-alad approved these changes Oct 3, 2025

View reviewed changes

nina9753 approved these changes Oct 3, 2025

View reviewed changes

gh123man approved these changes Oct 3, 2025

View reviewed changes

OliviaShoup approved these changes Oct 3, 2025

View reviewed changes

dd-mergequeue Bot merged commit 0046c01 into main Oct 3, 2025
269 checks passed

dd-mergequeue Bot deleted the nicholas.hulston/serverless-init-improve-tags-performance branch October 3, 2025 22:49

github-actions Bot added this to the 7.73.0 milestone Oct 3, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[Serverless-Init] Improve Tags Performance#41582

[Serverless-Init] Improve Tags Performance#41582
dd-mergequeue[bot] merged 7 commits into
mainfrom
nicholas.hulston/serverless-init-improve-tags-performance

nhulston commented Oct 3, 2025 •

edited

Loading

Uh oh!

gabedos left a comment

Uh oh!

cit-pr-commenter Bot commented Oct 3, 2025

Experiments ignored for regressions

Fine details of change detection per experiment

Explanation

Uh oh!

agent-platform-auto-pr Bot commented Oct 3, 2025

Info

Uh oh!

nhulston commented Oct 3, 2025

Uh oh!

dd-devflow-routing-codex Bot commented Oct 3, 2025 •

edited

Loading

Uh oh!

OliviaShoup left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

6 participants

Uh oh!

Conversation

nhulston commented Oct 3, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What does this PR do?

Motivation

Describe how you validated your changes

Additional Notes

Uh oh!

gabedos left a comment

Choose a reason for hiding this comment

Uh oh!

cit-pr-commenter Bot commented Oct 3, 2025

Regression Detector

Regression Detector Results

Optimization Goals: ❌ Regression(s) detected

Experiments ignored for regressions

Fine details of change detection per experiment

Bounds Checks: ❌ Failed

Explanation

CI Pass/Fail Decision

Uh oh!

agent-platform-auto-pr Bot commented Oct 3, 2025

Static quality checks

Info

Uh oh!

nhulston commented Oct 3, 2025

Uh oh!

dd-devflow-routing-codex Bot commented Oct 3, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

OliviaShoup left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

6 participants

nhulston commented Oct 3, 2025 •

edited

Loading

dd-devflow-routing-codex Bot commented Oct 3, 2025 •

edited

Loading