[EBPF] Use Go internal ELF/DWARF library for complexity analysis

[gjulianm]

What does this PR do?

Uses the DWARF/ELF libraries to retrieve source maps for eBPF binaries instead of llvm-objdump

Motivation

For #26723, we need to run the verifier calculator on KMT VMs which do not have llvm-objdump installed.

Additional Notes

Possible Drawbacks / Trade-offs

Describe how to test/QA your changes

[pr-commenter]

Test changes on VM

Use this command from test-infra-definitions to manually test this PR changes on a VM:

inv create-vm --pipeline-id=37480531 --os-family=ubuntu

Note: This applies to commit fa97ac0

[brycekahle]

Did you ever evaluate if https://pkg.go.dev/github.com/go-delve/[email protected]/pkg/dwarf#section-directories would be a good fit for this changeset?

[gjulianm]

I didn't know about it, but looking at the code it seems it just does the base parsing of the DWARF data, not the linking between different entries and mapping the address to code.

[brycekahle]

This package seems to have a lot of that? https://pkg.go.dev/github.com/go-delve/[email protected]/pkg/dwarf/line

[gjulianm]

It has the part where it links program counters to lines, but the problem with the eBPF files is that they have multiple entry points per file, and thus multiple sequences of program counters starting at zero (that parser appears to assume program counters can only go up). It seem to be able to tell me to which symbol does each address belong to.

[pr-commenter]

Regression Detector

Regression Detector Results

Run ID: 787842bc-cc68-448d-88f9-087520b760c1 Metrics dashboard Target profiles

Baseline: fd2ef75
Comparison: fa97ac0

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

No significant changes in experiment optimization goals

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

There were no significant changes in experiment optimization goals at this confidence level and effect size tolerance.

Fine details of change detection per experiment

perf	experiment	goal	Δ mean %	Δ mean % CI	links
➖	tcp_syslog_to_blackhole	ingress throughput	+0.54	[-12.32, +13.40]	Logs
➖	otel_to_otel_logs	ingress throughput	+0.35	[-0.46, +1.16]	Logs
➖	uds_dogstatsd_to_api_cpu	% cpu utilization	+0.27	[-0.62, +1.17]	Logs
➖	uds_dogstatsd_to_api	ingress throughput	+0.00	[-0.00, +0.00]	Logs
➖	tcp_dd_logs_filter_exclude	ingress throughput	-0.00	[-0.01, +0.01]	Logs
➖	basic_py_check	% cpu utilization	-0.44	[-3.04, +2.15]	Logs
➖	idle	memory utilization	-0.52	[-0.55, -0.48]	Logs
➖	file_tree	memory utilization	-1.32	[-1.39, -1.26]	Logs
➖	pycheck_1000_100byte_tags	% cpu utilization	-4.03	[-8.71, +0.65]	Logs

Explanation

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".

[gjulianm]

/merge

[dd-devflow]

🚂 MergeQueue: pull request added to the queue

The median merge time in main is 25m.

Use /merge -c to cancel this operation!