-
Notifications
You must be signed in to change notification settings - Fork 1.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
sharedlibraries: rework ebpf prog concurrency #31745
Conversation
[Fast Unit Tests Report] On pipeline 50330944 (CI Visibility). The following jobs did not run any unit tests: Jobs:
If you modified Go files and expected unit tests to run in these jobs, please double check the job logs. If you think tests should have been executed reach out to #agent-devx-help |
Test changes on VMUse this command from test-infra-definitions to manually test this PR changes on a VM: inv aws.create-vm --pipeline-id=50330944 --os-family=ubuntu Note: This applies to commit 4f73a30 |
Regression DetectorRegression Detector ResultsMetrics dashboard Baseline: a79d704 Optimization Goals: ✅ Improvement(s) detected
|
perf | experiment | goal | Δ mean % | Δ mean % CI | trials | links |
---|---|---|---|---|---|---|
➖ | tcp_syslog_to_blackhole | ingress throughput | +2.07 | [+2.01, +2.13] | 1 | Logs |
➖ | otel_to_otel_logs | ingress throughput | +1.32 | [+0.63, +2.01] | 1 | Logs |
➖ | file_tree | memory utilization | +0.34 | [+0.20, +0.48] | 1 | Logs |
➖ | uds_dogstatsd_to_api_cpu | % cpu utilization | +0.06 | [-0.67, +0.79] | 1 | Logs |
➖ | quality_gate_idle | memory utilization | +0.04 | [-0.00, +0.09] | 1 | Logs bounds checks dashboard |
➖ | tcp_dd_logs_filter_exclude | ingress throughput | +0.00 | [-0.01, +0.01] | 1 | Logs |
➖ | file_to_blackhole_100ms_latency | egress throughput | -0.03 | [-0.69, +0.63] | 1 | Logs |
➖ | uds_dogstatsd_to_api | ingress throughput | -0.03 | [-0.13, +0.07] | 1 | Logs |
➖ | file_to_blackhole_0ms_latency | egress throughput | -0.03 | [-0.89, +0.82] | 1 | Logs |
➖ | file_to_blackhole_1000ms_latency_linear_load | egress throughput | -0.07 | [-0.53, +0.39] | 1 | Logs |
➖ | file_to_blackhole_300ms_latency | egress throughput | -0.17 | [-0.80, +0.46] | 1 | Logs |
➖ | file_to_blackhole_500ms_latency | egress throughput | -0.36 | [-1.13, +0.42] | 1 | Logs |
➖ | file_to_blackhole_1000ms_latency | egress throughput | -0.51 | [-1.29, +0.27] | 1 | Logs |
➖ | quality_gate_idle_all_features | memory utilization | -0.56 | [-0.66, -0.45] | 1 | Logs bounds checks dashboard |
➖ | quality_gate_logs | % cpu utilization | -1.57 | [-4.46, +1.31] | 1 | Logs |
➖ | basic_py_check | % cpu utilization | -2.13 | [-5.90, +1.64] | 1 | Logs |
✅ | pycheck_lots_of_tags | % cpu utilization | -7.76 | [-11.11, -4.41] | 1 | Logs |
Bounds Checks: ❌ Failed
perf | experiment | bounds_check_name | replicates_passed | links |
---|---|---|---|---|
❌ | file_to_blackhole_0ms_latency | lost_bytes | 9/10 | |
❌ | file_to_blackhole_100ms_latency | lost_bytes | 9/10 | |
✅ | file_to_blackhole_0ms_latency | memory_usage | 10/10 | |
✅ | file_to_blackhole_1000ms_latency | memory_usage | 10/10 | |
✅ | file_to_blackhole_1000ms_latency_linear_load | memory_usage | 10/10 | |
✅ | file_to_blackhole_100ms_latency | memory_usage | 10/10 | |
✅ | file_to_blackhole_300ms_latency | lost_bytes | 10/10 | |
✅ | file_to_blackhole_300ms_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 | memory_usage | 10/10 | bounds checks dashboard |
✅ | quality_gate_idle_all_features | memory_usage | 10/10 | bounds checks dashboard |
✅ | quality_gate_logs | lost_bytes | 10/10 | |
✅ | quality_gate_logs | memory_usage | 10/10 |
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_idle, bounds check memory_usage: 10/10 replicas passed. Gate passed.
- quality_gate_idle_all_features, bounds check memory_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.
Preliminary change to replace the sync.Once with a mutex, to better handle access to the EBPF program singleton
No need to use atomic operations, as we're protected with a mutex
fcf9687
to
1579436
Compare
/merge |
Devflow running:
|
What does this PR do?
Replaces the old method for initialization and teardown for the EBPFProgram struct.
Instead of
sync.Once
andatomic.Int32
to support concurrency, we simply use a mutex.Motivation
The current code is hacky and seems complicated.
Trying to simplify the readability of the code and avoid edge cases.
Describe how you validated your changes
Possible Drawbacks / Trade-offs
Additional Notes
negligible (if any) performance impact, as we have about 3-4 instances that use it, and the initialization/termination runs once per handler.