Troubleshooting Node profiler issue #33075
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Contributor
Preview links (active after the
|
janine-c
reviewed
Nov 27, 2025
Contributor
janine-c
left a comment
janine-c
left a comment
There was a problem hiding this comment.
Looks great, Reshmi, thank you for documenting these additional flags! I made some minor formatting suggestions to make the new content easier to copy and paste. Take a look and let me know what you think, or if there's anything I can clarify 🙂
| When the Datadog profiler is enabled, it periodically sends a small signal to collect profiling data. If the application is idle (waiting for I/O or timers), this signal briefly wakes the event loop to take a sample, even though there's no real work to do. As a result, ELU appears higher because the loop wakes up more often, but CPU usage stays low, and no latency or extra workload is introduced. | ||
| In a busy application, these same signals occur while the loop is already active, so the effect on ELU is negligible. | ||
|
|
||
| ## Disabling Advanced Profiling Features |
Contributor
There was a problem hiding this comment.
Suggested change
| ## Disabling Advanced Profiling Features | |
| ## Disable advanced profiling features |
|
|
||
| Advanced profiling capabilities in Datadog provide rich context—such as endpoint-level visibility, timeline correlations, and code hotspot linking—that significantly improve analysis quality. | ||
| Under normal circumstances, these should remain enabled. However, when diagnosing performance issues or overhead, temporarily disabling specific components can help isolate the source of additional load. | ||
| The goal is to narrow down which feature contributes to CPU, memory, or latency changes during profiling. |
Contributor
There was a problem hiding this comment.
Suggested change
| The goal is to narrow down which feature contributes to CPU, memory, or latency changes during profiling. | |
| You can do so to narrow down which feature contributes to CPU, memory, or latency changes during profiling. |
Comment on lines
+65
to
+75
| 1. Disable Code Hotspots | ||
|
|
||
| `DD_PROFILING_CODEHOTSPOTS_ENABLED=false` Disables trace-to-profile linking in Datadog UI. | ||
|
|
||
| 2. Disable Timeline View | ||
|
|
||
| `DD_PROFILING_TIMELINE_ENABLED=false` Disables timeline view in the Datadog UI. | ||
|
|
||
| 3. Disable Endpoint Collection | ||
|
|
||
| `DD_PROFILING_ENDPOINT_COLLECTION_ENABLED=false` Disables per-endpoint aggregation of profiling data, this prevents grouping samples by HTTP endpoints or routes |
Contributor
There was a problem hiding this comment.
Suggested change
| 1. Disable Code Hotspots | |
| `DD_PROFILING_CODEHOTSPOTS_ENABLED=false` Disables trace-to-profile linking in Datadog UI. | |
| 2. Disable Timeline View | |
| `DD_PROFILING_TIMELINE_ENABLED=false` Disables timeline view in the Datadog UI. | |
| 3. Disable Endpoint Collection | |
| `DD_PROFILING_ENDPOINT_COLLECTION_ENABLED=false` Disables per-endpoint aggregation of profiling data, this prevents grouping samples by HTTP endpoints or routes | |
| - **Disable code hotspots** | |
| Disable trace-to-profile linking in the Datadog UI: | |
| ``` | |
| DD_PROFILING_CODEHOTSPOTS_ENABLED=false | |
| ``` | |
| - **Disable timeline view** | |
| Disable timeline view in the Datadog UI: | |
| ``` | |
| DD_PROFILING_TIMELINE_ENABLED=false | |
| ``` | |
| - **Disable endpoint collection** | |
| Disable per-endpoint aggregation of profiling data, which groups samples by HTTP endpoints or routes: | |
| ``` | |
| DD_PROFILING_ENDPOINT_COLLECTION_ENABLED=false | |
| ``` |
Some minor formatting changes to create some indentation so it's easier to read, and make the code samples easier to see 🙂
|
|
||
| `DD_PROFILING_ENDPOINT_COLLECTION_ENABLED=false` Disables per-endpoint aggregation of profiling data, this prevents grouping samples by HTTP endpoints or routes | ||
|
|
||
| Once you identify that disabling a specific profiling feature reduces overhead, please report your findings so we can investigate further. You can contact [Datadog support][5] |
Contributor
There was a problem hiding this comment.
Suggested change
| Once you identify that disabling a specific profiling feature reduces overhead, please report your findings so we can investigate further. You can contact [Datadog support][5] | |
| After you identify that disabling a specific profiling feature reduces overhead, report your findings so Datadog can investigate further. You can do so by contacting [Datadog support][5]. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do? What is the motivation?
The flags for disabling advanced features are not fully documented in the Node.js troubleshooting sections, as most customers use the default profiler configuration. This information should be included to help customers fine-tune performance issues independently
Merge instructions
Merge readiness:
For Datadog employees:
Your branch name MUST follow the
<name>/<description>convention and include the forward slash (/). Without this format, your pull request will not pass CI, the GitLab pipeline will not run, and you won't get a branch preview. Getting a branch preview makes it easier for us to check any issues with your PR, such as broken links.If your branch doesn't follow this format, rename it or create a new branch and PR.
[6/5/2025] Merge queue has been disabled on the documentation repo. If you have write access to the repo, the PR has been reviewed by a Documentation team member, and all of the required checks have passed, you can use the Squash and Merge button to merge the PR. If you don't have write access, or you need help, reach out in the #documentation channel in Slack.
Additional notes