From 3a1020526d1675148823bc32896d25789febda98 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alejandro=20Gonz=C3=A1lez?= <me@alegon.dev>
Date: Sun, 17 Sep 2023 14:33:45 +0200
Subject: [PATCH] perf: bring `musl` binaries performance in par with `glibc`
 ones

After profiling, I have confirmed that the cause of the relative
slowdown of `musl` binaries with respect to `glibc` was the usage of a
slower memory allocator in the `musl` case, which critically affects the
performance of Zopfli compression, especially on CPUs with lots of
physical threads.
---
 CHANGELOG.md                                  | 12 +++++++++++
 Cargo.lock                                    | 20 +++++++++++++++++++
 packages/packsquash_cli/Cargo.toml            |  9 +++++++++
 .../packsquash_cli/src/bin/packsquash/main.rs |  9 +++++++++
 4 files changed, 50 insertions(+)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index b5a702d65..a8b75402a 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -37,6 +37,18 @@ Versioning](https://semver.org/spec/v2.0.0.html).
     to their decentralized and free nature, the PackSquash project will most
     likely not pursue signing binaries with code signing certificates.
 
+#### Performance
+
+- The statically-linked PackSquash CLI Linux binaries now use the
+  [`mimalloc`](https://github.com/microsoft/mimalloc) memory allocator, instead
+  of the default `musl` C library allocator.
+  - This brings the performance of such binaries roughly in line with those
+    packaged for Debian, which dynamically link against `glibc`. Previously,
+    slowdowns of 5x or more could be expected, depending on the number of
+    threads used.
+  - Because they use statically-linked binaries, the PackSquash GitHub
+    Action and Docker container also saw performance improvements.
+
 #### Fixed
 
 - The UTF-8 BOM is no longer automatically stripped from properties files, as
diff --git a/Cargo.lock b/Cargo.lock
index b188ba2f4..e65fe4edc 100644
--- a/Cargo.lock
+++ b/Cargo.lock
@@ -1345,6 +1345,16 @@ version = "0.2.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "f7012b1bbb0719e1097c47611d3898568c546d597c2e74d66f6087edd5233ff4"
 
+[[package]]
+name = "libmimalloc-sys"
+version = "0.1.35"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "3979b5c37ece694f1f5e51e7ecc871fdb0f517ed04ee45f88d15d6d553cb9664"
+dependencies = [
+ "cc",
+ "libc",
+]
+
 [[package]]
 name = "libz-sys"
 version = "1.1.12"
@@ -1429,6 +1439,15 @@ dependencies = [
  "autocfg",
 ]
 
+[[package]]
+name = "mimalloc"
+version = "0.1.39"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "fa01922b5ea280a911e323e4d2fd24b7fe5cc4042e0d2cda3c40775cdc4bdc9c"
+dependencies = [
+ "libmimalloc-sys",
+]
+
 [[package]]
 name = "miniz_oxide"
 version = "0.7.1"
@@ -1688,6 +1707,7 @@ dependencies = [
  "env_logger",
  "getopts",
  "log",
+ "mimalloc",
  "packsquash",
  "serde_path_to_error",
  "tokio",
diff --git a/packages/packsquash_cli/Cargo.toml b/packages/packsquash_cli/Cargo.toml
index 854322149..f858069e3 100644
--- a/packages/packsquash_cli/Cargo.toml
+++ b/packages/packsquash_cli/Cargo.toml
@@ -26,6 +26,15 @@ env_logger = { version = "0.10.0", default-features = false, features = ["color"
 winapi = { version = "0.3.9", default-features = false, features = ["consoleapi"] }
 winapi-util = "0.1.5"
 
+[target.'cfg(all(target_os = "linux", target_env = "musl"))'.dependencies]
+# The mimalloc C malloc override feature is troublesome on macOS and Windows, but
+# luckily the Linux musl C library should support this well. See:
+# https://github.com/purpleprotocol/mimalloc_rust/issues/41
+# We are interested in overriding malloc because we depend on C libraries, and doing
+# so buys us a safety net against mismatching memory managed by different allocators,
+# in addition to keep binary sizes down
+mimalloc = { version = "0.1.39", default-features = false, features = ["override"] }
+
 [target.'cfg(windows)'.build-dependencies]
 winresource = "0.1.17"
 
diff --git a/packages/packsquash_cli/src/bin/packsquash/main.rs b/packages/packsquash_cli/src/bin/packsquash/main.rs
index 32e6aa814..03c5cda33 100644
--- a/packages/packsquash_cli/src/bin/packsquash/main.rs
+++ b/packages/packsquash_cli/src/bin/packsquash/main.rs
@@ -30,6 +30,15 @@ const LOG_TARGET: Target = Target::Stderr;
 /// A producer of the [`IsTerminal`] implementation that matches the [`LOG_TARGET`] constant.
 const LOG_TARGET_STREAM: fn() -> Stderr = io::stderr;
 
+/// Zopfli compression is pretty intensive on the memory allocator, and musl
+/// is known to use a simple but prone to extreme thread contention allocator.
+/// Replace its allocator with one whose performance is close to glibc so that
+/// the PackSquash CLI musl binaries have a similar performance to glibc
+/// binaries; otherwise, slowdowns of 5x or more are to be expected.
+#[cfg(all(target_os = "linux", target_env = "musl"))]
+#[global_allocator]
+static GLOBAL_ALLOCATOR: mimalloc::MiMalloc = mimalloc::MiMalloc;
+
 fn main() {
 	process::exit(run(TerminalTitleController::new()));
 }