[CWS] Use u64 image tag#51156
Conversation
|
@codex review |
|
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7fe2ec9260
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
Files inventory check summaryFile checks results against ancestor 120c1774: Results for datadog-agent_7.81.0~devel.git.84.7f125d1.pipeline.114501129-1_amd64.deb:No change detected |
Static quality checks✅ Please find below the results from static quality gates Successful checksInfo
|
Regression DetectorRegression Detector ResultsMetrics dashboard Baseline: b7c4f46 Optimization Goals: ✅ No significant changes detected
|
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ❌ | docker_containers_cpu | % cpu utilization | +5.39 | [+2.36, +8.43] | 1 | Logs |
Fine details of change detection per experiment
| perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
|---|---|---|---|---|---|---|
| ❌ | docker_containers_cpu | % cpu utilization | +5.39 | [+2.36, +8.43] | 1 | Logs |
| ➖ | quality_gate_metrics_logs | memory utilization | +2.74 | [+2.49, +3.00] | 1 | Logs bounds checks dashboard |
| ➖ | tcp_syslog_to_blackhole | ingress throughput | +0.78 | [+0.57, +0.99] | 1 | Logs |
| ➖ | otlp_ingest_logs | memory utilization | +0.52 | [+0.42, +0.61] | 1 | Logs |
| ➖ | quality_gate_idle | memory utilization | +0.47 | [+0.42, +0.52] | 1 | Logs bounds checks dashboard |
| ➖ | otlp_ingest_metrics | memory utilization | +0.40 | [+0.24, +0.56] | 1 | Logs |
| ➖ | ddot_metrics_sum_cumulativetodelta_exporter | memory utilization | +0.24 | [+0.00, +0.48] | 1 | Logs |
| ➖ | quality_gate_logs | % cpu utilization | +0.02 | [-0.97, +1.02] | 1 | Logs bounds checks dashboard |
| ➖ | file_to_blackhole_0ms_latency | egress throughput | +0.02 | [-0.47, +0.50] | 1 | Logs |
| ➖ | docker_containers_memory | memory utilization | +0.01 | [-0.09, +0.11] | 1 | Logs |
| ➖ | file_to_blackhole_100ms_latency | egress throughput | +0.00 | [-0.13, +0.13] | 1 | Logs |
| ➖ | file_to_blackhole_1000ms_latency | egress throughput | +0.00 | [-0.46, +0.46] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api | ingress throughput | -0.00 | [-0.20, +0.19] | 1 | Logs |
| ➖ | tcp_dd_logs_filter_exclude | ingress throughput | -0.00 | [-0.10, +0.10] | 1 | Logs |
| ➖ | uds_dogstatsd_to_api_v3 | ingress throughput | -0.01 | [-0.21, +0.19] | 1 | Logs |
| ➖ | ddot_metrics_sum_cumulative | memory utilization | -0.05 | [-0.21, +0.11] | 1 | Logs |
| ➖ | ddot_metrics | memory utilization | -0.07 | [-0.27, +0.13] | 1 | Logs |
| ➖ | file_to_blackhole_500ms_latency | egress throughput | -0.07 | [-0.47, +0.33] | 1 | Logs |
| ➖ | ddot_logs | memory utilization | -0.11 | [-0.18, -0.05] | 1 | Logs |
| ➖ | ddot_metrics_sum_delta | memory utilization | -0.12 | [-0.31, +0.07] | 1 | Logs |
| ➖ | uds_dogstatsd_20mb_12k_contexts_20_senders | memory utilization | -0.28 | [-0.32, -0.23] | 1 | Logs |
| ➖ | file_tree | memory utilization | -0.34 | [-0.39, -0.30] | 1 | Logs |
| ➖ | quality_gate_idle_all_features | memory utilization | -0.37 | [-0.43, -0.30] | 1 | Logs bounds checks dashboard |
Bounds Checks: ✅ Passed
| perf | experiment | bounds_check_name | replicates_passed | observed_value | links |
|---|---|---|---|---|---|
| ✅ | docker_containers_cpu | simple_check_run | 10/10 | 699 ≥ 26 | |
| ✅ | docker_containers_memory | memory_usage | 10/10 | 243.54MiB ≤ 370MiB | |
| ✅ | docker_containers_memory | simple_check_run | 10/10 | 725 ≥ 26 | |
| ✅ | file_to_blackhole_0ms_latency | memory_usage | 10/10 | 0.16GiB ≤ 1.20GiB | |
| ✅ | file_to_blackhole_0ms_latency | missed_bytes | 10/10 | 0B = 0B | |
| ✅ | file_to_blackhole_1000ms_latency | memory_usage | 10/10 | 0.20GiB ≤ 1.20GiB | |
| ✅ | file_to_blackhole_1000ms_latency | missed_bytes | 10/10 | 0B = 0B | |
| ✅ | file_to_blackhole_100ms_latency | memory_usage | 10/10 | 0.17GiB ≤ 1.20GiB | |
| ✅ | file_to_blackhole_100ms_latency | missed_bytes | 10/10 | 0B = 0B | |
| ✅ | file_to_blackhole_500ms_latency | memory_usage | 10/10 | 0.18GiB ≤ 1.20GiB | |
| ✅ | file_to_blackhole_500ms_latency | missed_bytes | 10/10 | 0B = 0B | |
| ✅ | quality_gate_idle | intake_connections | 10/10 | 3 ≤ 4 | bounds checks dashboard |
| ✅ | quality_gate_idle | memory_usage | 10/10 | 144.33MiB ≤ 147MiB | bounds checks dashboard |
| ✅ | quality_gate_idle | total_bytes_received | 10/10 | 740.47KiB ≤ 819.20KiB | bounds checks dashboard |
| ✅ | quality_gate_idle_all_features | intake_connections | 10/10 | 2 ≤ 4 | bounds checks dashboard |
| ✅ | quality_gate_idle_all_features | memory_usage | 10/10 | 424.29MiB ≤ 495MiB | bounds checks dashboard |
| ✅ | quality_gate_idle_all_features | total_bytes_received | 10/10 | 1.12MiB ≤ 1.25MiB | bounds checks dashboard |
| ✅ | quality_gate_logs | intake_connections | 10/10 | 4 ≤ 6 | bounds checks dashboard |
| ✅ | quality_gate_logs | memory_usage | 10/10 | 174.48MiB ≤ 195MiB | bounds checks dashboard |
| ✅ | quality_gate_logs | missed_bytes | 10/10 | 0B = 0B | bounds checks dashboard |
| ✅ | quality_gate_logs | total_bytes_received | 10/10 | 264.00MiB ≤ 292MiB | bounds checks dashboard |
| ✅ | quality_gate_metrics_logs | cpu_usage | 10/10 | 346.54 ≤ 2000 | bounds checks dashboard |
| ✅ | quality_gate_metrics_logs | intake_connections | 10/10 | 4 ≤ 6 | bounds checks dashboard |
| ✅ | quality_gate_metrics_logs | memory_usage | 10/10 | 390.77MiB ≤ 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 | 0.94GiB ≤ 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:
-
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 cpu_usage: 10/10 replicas passed. Gate passed.
- quality_gate_metrics_logs, bounds check total_bytes_received: 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 memory_usage: 10/10 replicas passed. Gate passed.
- quality_gate_metrics_logs, bounds check intake_connections: 10/10 replicas passed. Gate passed.
- quality_gate_logs, bounds check intake_connections: 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_logs, bounds check total_bytes_received: 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.
- quality_gate_idle_all_features, bounds check intake_connections: 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.
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 1afe91c6e3
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 7dc1890eee
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| tagID := tagToID(key.ImageTag) | ||
| if elem, ok := pn.GetSeenTimes(tagID); ok && elem.LastSeen.Before(before) { | ||
| pn.NodeBase.AppendImageTagID(tagID, time.Now()) |
There was a problem hiding this comment.
EvictUnusedNodes now refreshes protected process nodes by converting profileImageTag to an internal ID (tagToID) before checking Seen. If that tag string has not been inserted into the tree registry (for example when a node carries a valid non-zero tag ID but the registry entry is absent), tagToID returns 0 and the refresh path is skipped, so nodes that should be kept alive can still be evicted. This is a behavioral regression from the previous direct string-key lookup path in the same function.
Useful? React with 👍 / 👎.
|
@codex review |
|
Codex Review: Didn't find any major issues. Hooray! ℹ️ About Codex in GitHubCodex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback". |
|
@codex review |
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: b518fd4139
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| imageTagID := at.GetOrInsertImageTag(imageTag) | ||
|
|
||
| newEntry, err := at.insertEvent(event, false /* !dryRun */, insertMissingProcesses, imageTagID, generationType, resolvers) |
There was a problem hiding this comment.
Insert now allocates an image-tag ID before any of the early rejection paths in insertEvent run. When an event is dropped (for example invalid/untraced event types, invalid IMDS payloads, or missing/invalid process lineage), the tag slot remains in imageTagIDs even though no node references it. In environments with many transient image tags, this can cause unbounded registry growth and retain tags that were never actually learned by the tree.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
Good catch on the theoretical hole — fixed in the latest commit. Insert now checks whether the tag was freshly allocated, and if insertEvent returns an error before any node could reference it, the slot is freed immediately via removeImageTag.
That said, "unbounded registry growth" isn't realistic in practice: the imageTag argument to Insert is the workload's container image version (e.g. v1.2.3), not a per-event value. It's the same string across all events for a given profile. So a slot allocated on a failed first event would be reused on every subsequent event for the same tag — no accumulation. The growth is bounded by the number of distinct image versions seen by a tree, which is O(few) in any real deployment.
The fix closes the theoretical gap anyway.
| func (at *ActivityTree) CreateProcessNode(entry *model.ProcessCacheEntry, imageTag string, generationType NodeGenerationType, dryRun bool, resolvers *resolvers.EBPFResolvers) (*ProcessNode, bool, error) { | ||
| imageTagID := at.GetOrInsertImageTag(imageTag) | ||
| return at.createProcessNode(entry, imageTagID, generationType, dryRun, resolvers) |
There was a problem hiding this comment.
CreateProcessNode now calls GetOrInsertImageTag before any dry-run behavior is applied, so read-only probes can still mutate imageTagIDs (including when entry is nil). That changes tree state during what is expected to be a non-mutating path and can accumulate orphan tag IDs that never get attached to nodes.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
Fixed. CreateProcessNode now uses GetImageTagID (read-only) when dryRun is true, so read-only probes no longer mutate imageTagIDs. If the tag isn't registered yet, ID 0 is passed down — consistent with the null sentinel used everywhere else.
Worth noting: the only real-world caller today passes dryRun: false (profile.go), so this wasn't causing actual orphan tags in production. But the API contract was wrong regardless.
fixed registry leak remove println removed dead function
remove redundant comment
kovagsm
force-pushed
the
use_u64_image_tag_id
branch
from
b518fd4 to
8b77373
Compare
1 participant
What does this PR do?
Makes nodes use an u64 id representing the image tag to reduce the memory footprint.
Motivation
With Activity Profile v2, we create many more nodes in the activity tree and the memory footprint of using a map of string on each node becomes noticeable (on average ~ +15MiB heap).
Describe how you validated your changes
Additional Notes