Add Criterion benchmarks for parser (#7686)

This PR sets up [Criterion](https://github.com/bheisler/criterion.rs)
for benchmarking in the main `nu` crate, and adds some simple parser
benchmarks.

To run the benchmarks, just do `cargo bench` or `cargo bench -- <regex
matching benchmark names>` in the repo root:

```bash
〉cargo bench -- parse
...
     Running benches/parser_benchmark.rs (target/release/deps/parser_benchmark-75d224bac82d5b0b)
parse_default_env_file  time:   [221.17 µs 222.34 µs 223.61 µs]
Found 8 outliers among 100 measurements (8.00%)
  5 (5.00%) high mild
  3 (3.00%) high severe

parse_default_config_file
                        time:   [1.4935 ms 1.4993 ms 1.5059 ms]
Found 11 outliers among 100 measurements (11.00%)
  7 (7.00%) high mild
  4 (4.00%) high severe
```

Existing benchmarks from `nu-plugin` have been moved into the main `nu`
crate to keep all our benchmarks in one place.

Cargo.lock

@@ -80,6 +80,12 @@ dependencies = [
  "libc",
 ]
 
+[[package]]
+name = "anes"
+version = "0.1.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4b46cbb362ab8752921c97e041f5e366ee6297bd428a31275b9fcf1e380f7299"
+
 [[package]]
 name = "ansi-str"
 version = "0.5.0"
@@ -542,6 +548,33 @@ dependencies = [
  "phf_codegen 0.11.1",
 ]
 
+[[package]]
+name = "ciborium"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "b0c137568cc60b904a7724001b35ce2630fd00d5d84805fbb608ab89509d788f"
+dependencies = [
+ "ciborium-io",
+ "ciborium-ll",
+ "serde",
+]
+
+[[package]]
+name = "ciborium-io"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "346de753af073cc87b52b2083a506b38ac176a44cfb05497b622e27be899b369"
+
+[[package]]
+name = "ciborium-ll"
+version = "0.2.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "213030a2b5a4e0c0892b6652260cf6ccac84827b83a85a534e178e3906c4cf1b"
+dependencies = [
+ "ciborium-io",
+ "half",
+]
+
 [[package]]
 name = "clang-sys"
 version = "1.4.0"
@@ -555,13 +588,23 @@ dependencies = [
 
 [[package]]
 name = "clap"
-version = "2.34.0"
+version = "3.2.23"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a0610544180c38b88101fecf2dd634b174a62eef6946f84dfc6a7127512b381c"
+checksum = "71655c45cb9845d3270c9d6df84ebe72b4dad3c2ba3f7023ad47c144e4e473a5"
 dependencies = [
  "bitflags",
- "textwrap 0.11.0",
+ "clap_lex",
- "unicode-width",
+ "indexmap",
+ "textwrap 0.16.0",
+]
+
+[[package]]
+name = "clap_lex"
+version = "0.2.4"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2850f2f5a82cbf437dd5af4d49848fbdfc27c157c3d010345776f952765261c5"
+dependencies = [
+ "os_str_bytes",
 ]
 
 [[package]]
@@ -673,15 +716,16 @@ dependencies = [
 
 [[package]]
 name = "criterion"
-version = "0.3.6"
+version = "0.4.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b01d6de93b2b6c65e17c634a26653a29d107b3c98c607c765bf38d041531cd8f"
+checksum = "e7c76e09c1aae2bc52b3d2f29e13c6572553b30c4aa1b8a49fd70de6412654cb"
 dependencies = [
+ "anes",
  "atty",
  "cast",
+ "ciborium",
  "clap",
  "criterion-plot",
- "csv",
  "itertools",
  "lazy_static",
  "num-traits",
@@ -690,7 +734,6 @@ dependencies = [
  "rayon",
  "regex",
  "serde",
- "serde_cbor",
  "serde_derive",
  "serde_json",
  "tinytemplate",
@@ -699,9 +742,9 @@ dependencies = [
 
 [[package]]
 name = "criterion-plot"
-version = "0.4.5"
+version = "0.5.0"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2673cc8207403546f45f5fd319a974b1e6983ad1a3ee7e6041650013be041876"
+checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1"
 dependencies = [
  "cast",
  "itertools",
@@ -2486,6 +2529,7 @@ dependencies = [
  "assert_cmd",
  "atty",
  "chrono",
+ "criterion",
  "crossterm 0.24.0",
  "ctrlc",
  "hamcrest2",
@@ -2756,7 +2800,6 @@ name = "nu-plugin"
 version = "0.73.1"
 dependencies = [
  "bincode",
- "criterion",
  "nu-engine",
  "nu-protocol",
  "rmp",
@@ -3160,6 +3203,12 @@ dependencies = [
  "vcpkg",
 ]
 
+[[package]]
+name = "os_str_bytes"
+version = "6.4.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9b7820b9daea5457c9f21c69448905d723fbd21136ccf521748f23fd49e723ee"
+
 [[package]]
 name = "output_vt100"
 version = "0.1.3"
@@ -4432,16 +4481,6 @@ dependencies = [
  "serde_derive",
 ]
 
-[[package]]
-name = "serde_cbor"
-version = "0.11.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "2bef2ebfde456fb76bbcf9f59315333decc4fda0b2b44b420243c11e0f5ec1f5"
-dependencies = [
- "half",
- "serde",
-]
-
 [[package]]
 name = "serde_derive"
 version = "1.0.145"
@@ -4959,15 +4998,6 @@ version = "0.2.4"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "507e9898683b6c43a9aa55b64259b721b52ba226e0f3779137e50ad114a4c90b"
 
-[[package]]
-name = "textwrap"
-version = "0.11.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d326610f408c7a4eb6f51c37c330e496b08506c9457c9d34287ecc38809fb060"
-dependencies = [
- "unicode-width",
-]
-
 [[package]]
 name = "textwrap"
 version = "0.15.1"
@@ -4979,6 +5009,12 @@ dependencies = [
  "unicode-width",
 ]
 
+[[package]]
+name = "textwrap"
+version = "0.16.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "222a222a5bfe1bba4a77b45ec488a741b3cb8872e5e499451fd7d0129c9c7c3d"
+
 [[package]]
 name = "thin-slice"
 version = "0.1.1"

Cargo.toml

@@ -83,6 +83,7 @@ atty = "0.2"
 nu-test-support = { path="./crates/nu-test-support", version = "0.73.1"  }
 tempfile = "3.2.0"
 assert_cmd = "2.0.2"
+criterion = "0.4"
 pretty_assertions = "1.0.0"
 serial_test = "0.8.0"
 hamcrest2 = "0.3.0"
@@ -140,3 +141,14 @@ path = "src/main.rs"
 # changing versions in each sub-crate of the workspace is tedious
 [patch.crates-io]
 # reedline = { git = "https://github.com/nushell/reedline.git", branch = "main" }
+
+# Criterion benchmarking setup
+# Run all benchmarks with `cargo bench`
+# Run individual benchmarks like `cargo bench -- <regex>` e.g. `cargo bench -- parse`
+[[bench]]
+name = "parser_benchmark"
+harness = false
+
+[[bench]]
+name = "encoder_benchmark"
+harness = false

benches/README.md

@@ -0,0 +1,7 @@
+# Criterion benchmarks
+
+These are benchmarks using [Criterion](https://github.com/bheisler/criterion.rs), a microbenchmarking tool for Rust.
+
+Run all benchmarks with `cargo bench`
+
+Or run individual benchmarks like `cargo bench -- <regex>` e.g. `cargo bench -- parse`

benches/parser_benchmark.rs

@@ -0,0 +1,34 @@
+use criterion::{criterion_group, criterion_main, BatchSize, Criterion};
+use nu_parser::parse;
+use nu_protocol::{Span, Value};
+use nu_utils::{get_default_config, get_default_env};
+
+fn criterion_benchmark(c: &mut Criterion) {
+    let mut engine_state = nu_command::create_default_context();
+    // parsing config.nu breaks without PWD set
+    engine_state.add_env_var(
+        "PWD".into(),
+        Value::string("/some/dir".to_string(), Span::test_data()),
+    );
+
+    let default_env = get_default_env().as_bytes();
+    c.bench_function("parse_default_env_file", |b| {
+        b.iter_batched(
+            || nu_protocol::engine::StateWorkingSet::new(&engine_state),
+            |mut working_set| parse(&mut working_set, None, default_env, false, &[]),
+            BatchSize::SmallInput,
+        )
+    });
+
+    let default_config = get_default_config().as_bytes();
+    c.bench_function("parse_default_config_file", |b| {
+        b.iter_batched(
+            || nu_protocol::engine::StateWorkingSet::new(&engine_state),
+            |mut working_set| parse(&mut working_set, None, default_config, false, &[]),
+            BatchSize::SmallInput,
+        )
+    });
+}
+
+criterion_group!(benches, criterion_benchmark);
+criterion_main!(benches);

crates/nu-plugin/Cargo.toml

@@ -15,10 +15,3 @@ serde = { version = "1.0.143" }
 serde_json = { version = "1.0"}
 rmp = "0.8.11"
 rmp-serde = "1.1.0"
-
-[dev-dependencies]
-criterion = "0.3"
-
-[[bench]]
-name = "encoder_benchmark"
-harness = false

crates/nu-plugin/README.md

@@ -1,6 +0,0 @@
-# nu-plugin
-
-## Benchmark
-Here is a simple benchmark for different protocol for encoding/decoding nushell table, with different rows and columns.  You can simply run `cargo bench` to run benchmark.
-
-The relative html report is in `target/criterion/report/index.html`.

crates/nu-utils/src/locale.rs

@@ -1,6 +1,5 @@
 use num_format::Locale;
 
-#[cfg(debug_assertions)]
 pub const LOCALE_OVERRIDE_ENV_VAR: &str = "NU_TEST_LOCALE_OVERRIDE";
 
 pub fn get_system_locale() -> Locale {