a72c5743fe
wild (https://github.com/davidlattimore/wild) is a Rust-native linker, typically 10-30% faster than mold on large release-LTO links. We have ~5 service binaries each doing release-LTO link, so the saving is meaningful: ~30-90 sec wall-time on a fresh compile. Approach (CI-only swap, zero local-dev impact): 1. Dockerfile.ci-builder-cpu installs wild 0.8.0 alongside mold (both linkers present; revert path is trivial). 2. .cargo/config.toml keeps `-fuse-ld=mold` as the file default so `cargo build` works locally without requiring wild on PATH. 3. compile-and-deploy-template.yaml's compile-services script does an in-place sed substitution `mold -> wild` immediately before `cargo build`, gated on `command -v wild` so a missing binary silently falls back to mold instead of failing the build. Why sed-in-script over RUSTFLAGS env var: RUSTFLAGS env var REPLACES the entire target.<triple>.rustflags array (per cargo docs precedence: env > target > build, mutually exclusive — they do NOT merge), which would silently drop our existing -Wl,-z,relro/--as-needed/target-cpu flags. Sed swap edits one token while preserving everything else. Validation: - python3 yaml.safe_load_all parses the template - cargo check --workspace --release --locked succeeds locally (still using mold per the unchanged config.toml default) - Dockerfile syntax visually verified; wild tarball URL confirmed live via curl https://api.github.com/repos/davidlattimore/wild/releases/latest Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
54 lines
1.9 KiB
TOML
54 lines
1.9 KiB
TOML
[env]
|
|
SQLX_OFFLINE = "false"
|
|
# GPU tests deadlock under parallel execution (shared CUDA context + 4GB RTX 3050).
|
|
# Single-threaded by default; CI overrides via RUST_TEST_THREADS in workflow.
|
|
RUST_TEST_THREADS = "1"
|
|
|
|
[cargo-new]
|
|
vcs = "none"
|
|
|
|
[net]
|
|
git-fetch-with-cli = true
|
|
|
|
[build]
|
|
# jobs: omitted → cargo uses all logical CPUs (scales to any machine)
|
|
# incremental: rely on per-profile defaults (false for release, true for dev/test).
|
|
# A workspace-wide override here forced incremental ON for --release too, which
|
|
# (a) bloats release artifacts with incremental metadata for no runtime benefit,
|
|
# (b) disables sccache caching for Rust (documented limitation).
|
|
pipelining = true
|
|
rustflags = [
|
|
"-D", "unsafe_op_in_unsafe_fn",
|
|
"-D", "clippy::undocumented_unsafe_blocks",
|
|
"-W", "rust_2024_idioms",
|
|
"-C", "force-frame-pointers=yes",
|
|
"-C", "relocation-model=pic",
|
|
]
|
|
|
|
[term]
|
|
verbose = false
|
|
progress.when = "auto"
|
|
|
|
[target.x86_64-unknown-linux-gnu]
|
|
linker = "clang"
|
|
rustflags = [
|
|
# mold is the default for local + CI. CI optionally swaps to `wild`
|
|
# via an in-script sed before `cargo build` (see compile-and-deploy
|
|
# WorkflowTemplate); both linkers are installed in
|
|
# Dockerfile.ci-builder-cpu. Keeping mold as the file default means
|
|
# local dev works out-of-the-box with the more widely packaged linker.
|
|
"-C", "link-arg=-fuse-ld=mold",
|
|
"-C", "link-arg=-Wl,-z,relro,-z,now",
|
|
"-C", "link-arg=-Wl,--as-needed",
|
|
# AVX2/FMA baseline — matches both Scaleway L4/H100 and most dev machines
|
|
"-C", "target-cpu=x86-64-v3",
|
|
"-C", "target-feature=+avx2,+fma,+bmi2",
|
|
# opt-level and codegen-units are set per-profile, NOT here.
|
|
# Setting them here would override ALL profiles (dev/test included),
|
|
# forcing full O3 + single-thread codegen on test builds.
|
|
]
|
|
|
|
|
|
# Profile definitions live in Cargo.toml — [profile.*] blocks in config.toml
|
|
# are silently ignored by Cargo. Do NOT add profiles here.
|