You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 911336e
Browse filesBrowse the repository at this point in the historyBrowse files
The reporter's `Duration` line covers the tests only. The coverage post-processing runs after it, so the runner sets `DEBUG=vitest:coverage` and records the provider's `Generate coverage total time` line next to the wall clock. `ast-v8-to-istanbul`, the converter under `@vitest/coverage-v8`, is part of the v8 measurement; the runner prints its version, and the result file records it in `meta.astV8ToIstanbul`.
94
+
The reporter's `Duration` line covers the tests only, so the tables report the whole-process wall clock. The runner also sets `DEBUG=vitest:coverage` and stores the provider's `Generate coverage total time` in the result file (`generate`), together with the `ast-v8-to-istanbul` version under `@vitest/coverage-v8` (`meta.astV8ToIstanbul`).
95
95
96
96
## Results: vitest 4.1.10 vs 5.0.0
97
97
@@ -273,119 +273,21 @@ A long-running DOM suite: 80 jsdom test files through 2 workers, each file holdi
273
273
274
274
## Coverage: vitest 4.1.10 vs 5.0.0
275
275
276
-
Same machine and protocol as above, `pnpm bench:coverage`, median of 3 reps (design-system and long-haul: 5 reps). 4.1.10 is the pinned install with `@vitest/coverage-v8` 4.1.10 on `ast-v8-to-istanbul` 1.0.4. 5.0.0 is the local build (5.0.0-rc.2 plus 41 commits, `130f79b8b`) with its own `@vitest/coverage-v8` on `ast-v8-to-istanbul` 1.0.5. Each app runs on its fastest warm row from the tables above, with the default coverage options: only files loaded by the tests are covered, and the `text`, `html`, `clover`, and `json` reports are written.
276
+
Whole-process wall clock of `vitest run` on the bold row of each app above, median of 3 reps (design-system and long-haul: 5 reps), without coverage and with each provider. Same machine and protocol as above. 4.1.10 is the pinned install with `@vitest/coverage-v8` 4.1.10 on `ast-v8-to-istanbul` 1.0.4. 5.0.0 is the local build (5.0.0-rc.2 plus 41 commits, `130f79b8b`) with its own `@vitest/coverage-v8` on `ast-v8-to-istanbul` 1.0.5. Default coverage options: only files loaded by the tests are covered, and the `text`, `html`, `clover`, and `json` reports are written. To regenerate: `pnpm bench:coverage --label vitest-4.1.10-coverage`, then `pnpm bench:coverage --label vitest-5.0-coverage` with the linked build, then `node scripts/render-coverage.mjs results/vitest-4.1.10-coverage.json results/vitest-5.0-coverage.json`.
277
277
278
-
Columns: `wall`is the whole-process wall clock of `vitest run`. `overhead` is the wall minus the wall of the `none` row, so it includes collection, conversion, and the report files. `generate` is the provider's own `Generate coverage total time` from `DEBUG=vitest:coverage`: the conversion of the raw coverage into istanbul maps, without the report files. Values under about 50ms are inside the noise of one run.
279
-
280
-
### micro-utils
281
-
282
-
pool threads, env node, isolate false, fsModuleCache false, warm.
0 commit comments