Repository navigation
Perf regression: bun-isolated/rescan wall +21% (cc938aa6..17793173; #1279 candidate) #1606
Description
[agent] Bench: confirmed weekly regression in bun-isolated/rescan (and a smaller one in bun-isolated/hosted / bun/hosted).
Base cc938aa6 (main, 2026-10-09) → head 657fce2b (main, 2026-10-15). Same machine, interleaved pairs. Daily A/B (e76cb9b3 → 657fce2b) is flat, so this is drift that is already on main.
| scenario | pairs | base wall | head wall | Δ wall [95% CI] | Δ CPU | Δ peak RSS | requests | verdict |
|---|---|---|---|---|---|---|---|---|
bun-isolated/rescan (round 1) |
15+10 | 177.3 ms | 212.2 ms | +22.9% [+12.7, +30.4] | +16.0% | +3.9% | 127 | regression |
bun-isolated/rescan (confirm) |
25+15 | 205.0 ms | 244.7 ms | +21.3% [+12.7, +32.7] | +12.1% | +5.8% | 127 | regression |
bun-isolated/hosted (confirm) |
25+15 | 243.6 ms | 281.1 ms | +15.6% [+8.4, +22.9] | +14.0% | +8.0% | 127 | regression |
bun/hosted (confirm) |
25+15 | 212.9 ms | 234.5 ms | +12.9% [+9.7, +16.5] | +7.0% | +4.3% | 127 | regression |
Request counts are unchanged. The 2026-10-12 daily run already saw bun-isolated/rescan +15% (f3c6313a..17793173); a large bun speedup earlier in that week hid it in the previous weekly windows.
Bisect (3 builds over the 151 commits cc938aa6..17793173, bun-isolated/rescan, 15 pairs each vs cc938aa6):
| build | Δ wall |
|---|---|
1438b1a7 (#1356) |
+5.8% [-0.5, +16.2] ≈ |
a43cf327 (#1332) |
+12.4% [+6.5, +23.2] |
eca5d247 (#1330) |
+11.5% [+2.1, +20.6] |
657fce2b (today) |
+21.3% |
So about half lands in 1438b1a7..a43cf327 (19 commits). The most plausible one there is dcdc1043 (#1279, "remove obsolete vendoring machinery and duplicate crate code"), with 4c800ac5 (#1370) as the other candidate that touches shared npm code. The rest lands after eca5d247, in eca5d247..17793173. Not narrowed further: the bisect budget is spent.
Repro
export CARGO_PROFILE_PERF_INHERITS=release CARGO_PROFILE_PERF_LTO=thin CARGO_PROFILE_PERF_STRIP=none
git worktree add /tmp/base cc938aa6 && (cd /tmp/base && CARGO_TARGET_DIR=/tmp/tb cargo build --locked --profile perf -p socket-patch-cli)
cargo build --locked --profile perf -p socket-patch-cli -p socket-patch-bench
target/perf/socket-patch-bench compare --base /tmp/tb/perf/socket-patch --head target/perf/socket-patch -f '^bun-isolated/' -f '^bun/hosted$' --runs 25Runner: 4 vCPU, Intel(R) Xeon(R) Processor @ 2.80GHz (cloud sandbox). A/A on the same runner was clean (npm/hosted -3.9%, pip/hosted -3.1%, cargo/hosted +5.1%, all ≈).
Progress log: #575
Generated by Claude Code
Activity
mikolalysenko commentedon Oct 16, 2026
[agent] Triaged as
priority:p1(Bun, npm family; perf regression). Not a duplicate of #1607 (yarn berry): the bisect candidates differ (#1279 / #1370 here vs #1321 / #1323 / #1397 there), so no shared root cause is confirmed. No open PR addresses it. Ranked below the open correctness bugs in this tier.Generated by Claude Code