Minor instantiation benchmark updates (#3790)

This commit has a few minor updates and some improvements to the
instantiation benchmark harness:

* A `once_cell::unsync::Lazy` type is now used to guard creation of
  modules/engines/etc. This enables running singular benchmarks to be
  much faster since the benchmark no longer compiles all other
  benchmarks that are filtered out. Unfortunately I couldn't find a way
  in criterion to test whether a `BenchmarkId` is filtered out or not so
  we rely on the runtime laziness to initialize on the first run for
  benchmarks that do so.

* All files located in `benches/instantiation` are now loaded for
  benchmarking instead of a hardcoded list. This makes it a bit easier
  to throw files into the directory and have them benchmarked instead of
  having to recompile when working with new files.

* Finally a module deserialization benchmark was added to measure the
  time it takes to deserialize a precompiled module from disk (inspired
  by discussion on #3787)

While I was at it I also upped some limits to be able to instantiate
cfallin's `spidermonkey.wasm`.

Cargo.lock

@@ -3496,6 +3496,7 @@ dependencies = [
  "memchr",
  "more-asserts",
  "num_cpus",
+ "once_cell",
  "pretty_env_logger",
  "rayon",
  "rustix",

Cargo.toml

@@ -62,6 +62,7 @@ winapi = { version = "0.3.9", features = ['memoryapi'] }
 memchr = "2.4"
 async-trait = "0.1"
 wat = "1.0.41"
+once_cell = "1.9.0"
 
 [build-dependencies]
 anyhow = "1.0.19"

benches/instantiation.rs

@@ -1,6 +1,7 @@
 use anyhow::Result;
 use criterion::{criterion_group, criterion_main, BenchmarkId, Criterion};
-use std::path::{Path, PathBuf};
+use once_cell::unsync::Lazy;
+use std::path::Path;
 use std::process::Command;
 use std::sync::atomic::{AtomicBool, AtomicUsize, Ordering::SeqCst};
 use std::sync::Arc;
@@ -16,7 +17,6 @@ fn store(engine: &Engine) -> Store<WasiCtx> {
 fn instantiate(pre: &InstancePre<WasiCtx>, engine: &Engine) -> Result<()> {
     let mut store = store(engine);
     let _instance = pre.instantiate(&mut store)?;
-
     Ok(())
 }
 
@@ -34,27 +34,32 @@ fn bench_sequential(c: &mut Criterion, path: &Path) {
     let mut group = c.benchmark_group("sequential");
 
     for strategy in strategies() {
+        let id = BenchmarkId::new(
+            benchmark_name(&strategy),
+            path.file_name().unwrap().to_str().unwrap(),
+        );
+        let state = Lazy::new(|| {
             let mut config = Config::default();
             config.allocation_strategy(strategy.clone());
 
             let engine = Engine::new(&config).expect("failed to create engine");
-        let module = Module::from_file(&engine, path)
-            .unwrap_or_else(|e| panic!("failed to load benchmark `{}`: {:?}", path.display(), e));
+            let module = Module::from_file(&engine, path).unwrap_or_else(|e| {
+                panic!("failed to load benchmark `{}`: {:?}", path.display(), e)
+            });
             let mut linker = Linker::new(&engine);
             wasmtime_wasi::add_to_linker(&mut linker, |cx| cx).unwrap();
             let pre = linker
                 .instantiate_pre(&mut store(&engine), &module)
                 .expect("failed to pre-instantiate");
+            (engine, pre)
+        });
 
-        group.bench_function(
-            BenchmarkId::new(
-                benchmark_name(&strategy),
-                path.file_name().unwrap().to_str().unwrap(),
-            ),
-            |b| {
-                b.iter(|| instantiate(&pre, &engine).expect("failed to instantiate module"));
-            },
-        );
+        group.bench_function(id, |b| {
+            let (engine, pre) = &*state;
+            b.iter(|| {
+                instantiate(&pre, &engine).expect("failed to instantiate module");
+            });
+        });
     }
 
     group.finish();
@@ -64,11 +69,13 @@ fn bench_parallel(c: &mut Criterion, path: &Path) {
     let mut group = c.benchmark_group("parallel");
 
     for strategy in strategies() {
+        let state = Lazy::new(|| {
             let mut config = Config::default();
             config.allocation_strategy(strategy.clone());
 
             let engine = Engine::new(&config).expect("failed to create engine");
-        let module = Module::from_file(&engine, path).expect("failed to load WASI example module");
+            let module =
+                Module::from_file(&engine, path).expect("failed to load WASI example module");
             let mut linker = Linker::new(&engine);
             wasmtime_wasi::add_to_linker(&mut linker, |cx| cx).unwrap();
             let pre = Arc::new(
@@ -76,19 +83,19 @@ fn bench_parallel(c: &mut Criterion, path: &Path) {
                     .instantiate_pre(&mut store(&engine), &module)
                     .expect("failed to pre-instantiate"),
             );
+            (engine, pre)
+        });
 
         for threads in 1..=num_cpus::get_physical() {
-            group.bench_function(
-                BenchmarkId::new(
-                    benchmark_name(&strategy),
-                    format!(
-                        "{}: with {} background thread{}",
+            let name = format!(
+                "{}: with {} thread{}",
                 path.file_name().unwrap().to_str().unwrap(),
                 threads,
                 if threads == 1 { "" } else { "s" }
-                    ),
-                ),
-                |b| {
+            );
+            let id = BenchmarkId::new(benchmark_name(&strategy), name);
+            group.bench_function(id, |b| {
+                let (engine, pre) = &*state;
                 // Spin up N-1 threads doing background instantiations to
                 // simulate concurrent instantiations.
                 let done = Arc::new(AtomicBool::new(false));
@@ -129,14 +136,34 @@ fn bench_parallel(c: &mut Criterion, path: &Path) {
                 for t in workers {
                     t.join().unwrap();
                 }
-                },
-            );
+            });
         }
     }
 
     group.finish();
 }
 
+fn bench_deserialize_module(c: &mut Criterion, path: &Path) {
+    let mut group = c.benchmark_group("deserialize");
+
+    let name = path.file_name().unwrap().to_str().unwrap();
+    let tmpfile = tempfile::NamedTempFile::new().unwrap();
+    let state = Lazy::new(|| {
+        let engine = Engine::default();
+        let module = Module::from_file(&engine, path).expect("failed to load WASI example module");
+        std::fs::write(tmpfile.path(), module.serialize().unwrap()).unwrap();
+        (engine, tmpfile.path())
+    });
+    group.bench_function(BenchmarkId::new("deserialize", name), |b| {
+        let (engine, path) = &*state;
+        b.iter(|| unsafe {
+            Module::deserialize_file(&engine, path).unwrap();
+        });
+    });
+
+    group.finish();
+}
+
 fn build_wasi_example() {
     println!("Building WASI example module...");
     if !Command::new("cargo")
@@ -166,19 +193,12 @@ fn build_wasi_example() {
 
 fn bench_instantiation(c: &mut Criterion) {
     build_wasi_example();
-    let modules = &[
-        "empty.wat",
-        "small_memory.wat",
-        "data_segments.wat",
-        "wasi.wasm",
-    ];
-    for module in modules {
-        let mut path = PathBuf::new();
-        path.push("benches");
-        path.push("instantiation");
-        path.push(module);
+
+    for file in std::fs::read_dir("benches/instantiation").unwrap() {
+        let path = file.unwrap().path();
         bench_sequential(c, &path);
         bench_parallel(c, &path);
+        bench_deserialize_module(c, &path);
     }
 }
 
@@ -190,8 +210,9 @@ fn strategies() -> impl Iterator<Item = InstanceAllocationStrategy> {
         InstanceAllocationStrategy::Pooling {
             strategy: Default::default(),
             module_limits: ModuleLimits {
-                functions: 20_000,
+                functions: 40_000,
                 memory_pages: 1_000,
+                types: 200,
                 ..ModuleLimits::default()
             },
             instance_limits: InstanceLimits::default(),