Merge pull request #2691 from benesch/linux-binsize

build: reduce linux release binary size by 87%

Author: benesch

.cargo/config

@@ -0,0 +1,8 @@
+[target."x86_64-unknown-linux-gnu"]
+# Compressing debug information can yield hundreds of megabytes of savings.
+# The Rust toolchain does not currently perform dead code elimination on
+# debug info.
+#
+# See: https://github.com/rust-lang/rust/issues/56068
+# See: https://reviews.llvm.org/D74169#1990180
+rustflags = ["-C", "link-arg=-Wl,--compress-debug-sections=zlib-gabi"]

.gitignore

@@ -11,7 +11,6 @@
 
 target
 miri-target
-/.cargo
 .mtrlz.log
 **/*.rs.bk
 .netlify

Cargo.toml

@@ -23,7 +23,13 @@ members = [
 ]
 
 [profile.release]
-debug = true
+# Emit only the line info tables, not full debug info, in release builds, to
+# substantially reduce the size of the debug info. Line info tables are enough
+# to correctly symbolicate a backtrace, but do not produce an ideal interactive
+# debugger experience. This seems to be the right tradeoff for release builds:
+# it's unlikely we're going to get interactive access to a debugger in
+# production installations, but we still want useful crash reports.
+debug = 1
 
 [patch.crates-io]
 # Waiting on a release with this commit:

bin/lint

@@ -60,6 +60,7 @@ copyright_files=$(grep -vE \
     -e '(^|/)\.gitmodules$' \
     -e '(^|/)go\.sum$' \
     -e '(^|/)Cargo\.toml$' \
+    -e '^\.cargo/config$' \
     -e '^Cargo\.lock$' \
     -e '^deny\.toml$' \
     -e '^netlify\.toml$' \

bin/xcompile

@@ -13,7 +13,7 @@
 
 set -euo pipefail
 
-root=$(dirname "$0")/..
+root=$(cd "$(dirname "$0")/.." && pwd)
 
 # shellcheck source=SCRIPTDIR/../misc/shlib/shlib.bash
 . "$root/misc/shlib/shlib.bash"
@@ -61,6 +61,7 @@ do_cargo() {
     export TARGET_CXX=$CXX
     export TARGET_CFLAGS=$CFLAGS
     export TARGET_CXXFLAGS=$CXXFLAGS
+    export CARGO_TARGET_X86_64_UNKNOWN_LINUX_GNU_LINKER=$CC
 
     cargo "$subcommand" --target=x86_64-unknown-linux-gnu "$@"
 }

misc/python/mzbuild.py

@@ -98,11 +98,15 @@ def xcargo_target_dir(root: Path) -> Path:
         return root / "target" / "x86_64-unknown-linux-gnu"
 
 
-def xstrip(root: Path) -> str:
+def xbinutil(tool: str) -> str:
     if sys.platform == "linux":
-        return "strip"
+        return tool
     else:
-        return "x86_64-unknown-linux-gnu-strip"
+        return f"x86_64-unknown-linux-gnu-{tool}"
+
+
+xobjcopy = xbinutil("objcopy")
+xstrip = xbinutil("strip")
 
 
 def docker_images() -> Set[str]:
@@ -157,13 +161,32 @@ def run(self, root: Path, path: Path) -> None:
             # down CI, since we're packaging these binaries up into Docker
             # images and shipping them around. A bit unfortunate, since it'd be
             # nice to have useful backtraces if the binary crashes.
-            runv([xstrip(root), path / self.bin])
+            runv([xstrip, path / self.bin])
+        else:
+            # Even if we've been asked not to strip the binary, remove the
+            # `.debug_pubnames` and `.debug_pubtypes` sections. These are just
+            # indexes that speed up launching a debugger against the binary,
+            # and we're happy to have slower debugger start up in exchange for
+            # smaller binaries. Plus the sections have been obsoleted by a
+            # `.debug_names` section in DWARF 5, and so debugger support for
+            # `.debug_pubnames`/`.debug_pubtypes` is minimal anyway.
+            # See: https://github.com/rust-lang/rust/issues/46034
+            runv(
+                [
+                    xobjcopy,
+                    "-R",
+                    ".debug_pubnames",
+                    "-R",
+                    ".debug_pubtypes",
+                    path / self.bin,
+                ]
+            )
 
     def depends(self, root: Path, path: Path) -> List[bytes]:
         # TODO(benesch): this should be much smarter about computing the Rust
         # files that actually contribute to this binary target.
         return super().depends(root, path) + git_ls_files(
-            root, "src/**", "Cargo.toml", "Cargo.lock"
+            root, "src/**", "Cargo.toml", "Cargo.lock", ".cargo"
         )
 
 
@@ -216,7 +239,7 @@ def run(self, root: Path, path: Path) -> None:
         with open(path / "tests" / "manifest", "w") as manifest:
             for (executable, slug, crate_path) in tests:
                 shutil.copy(executable, path / "tests" / slug)
-                runv([xstrip(root), path / "tests" / slug])
+                runv([xstrip, path / "tests" / slug])
                 manifest.write(f"{slug} {crate_path}\n")
         shutil.move(str(path / "testdrive"), path / "tests")
         shutil.copy(
@@ -229,7 +252,7 @@ def depends(self, root: Path, path: Path) -> List[bytes]:
         # TODO(benesch): this should be much smarter about computing the Rust
         # files that actually contribute to this binary target.
         return super().depends(root, path) + git_ls_files(
-            root, "src/**", "Cargo.toml", "Cargo.lock"
+            root, "src/**", "Cargo.toml", "Cargo.lock", ".cargo"
         )