lz4-pyframe: add a benchmark

Summary:
This gives some sense about how fast it is.

Background: I was trying to get rid of python-lz4, by exposing this to Python.
However, I noticed it's 10x slower than python-lz4. Therefore I added some
benchmark here to test if it's the wrapper or the Rust lz4 code.

It does not seem to be this crate:

```
  # Pure Rust
  compress (100M)                77.170 ms
  decompress (~100M)             67.043 ms

  # python-lz4
  In [1]: import lz4, os
  In [2]: b=os.urandom(100000000);
  In [3]: %timeit lz4.compress(b)
  10 loops, best of 3: 87.4 ms per loop
```

Reviewed By: DurhamG

Differential Revision: D13516205

fbshipit-source-id: f55f94bbecc3b49667ed12174f7000b1aa29e7c4

lib/lz4-pyframe/Cargo.toml

@@ -9,4 +9,11 @@ failure = "0"
 lz4-sys = "1"
 
 [dev-dependencies]
+minibench = { path = "../minibench" }
 quickcheck = "0"
+rand_chacha = "0.1.0"
+rand_core = "0.3.0"
+
+[[bench]]
+name = "bench"
+harness = false

lib/lz4-pyframe/benches/bench.rs

@@ -0,0 +1,32 @@
+// Copyright 2018 Facebook, Inc.
+//
+// This software may be used and distributed according to the terms of the
+// GNU General Public License version 2 or any later version.
+
+extern crate lz4_pyframe;
+extern crate minibench;
+extern crate rand_chacha;
+extern crate rand_core;
+
+use lz4_pyframe::{compress, decompress};
+use minibench::{bench, elapsed};
+use rand_core::{RngCore, SeedableRng};
+
+fn main() {
+    let mut rng = rand_chacha::ChaChaRng::seed_from_u64(0);
+    let mut buf = vec![0u8; 100_000000];
+    rng.fill_bytes(&mut buf);
+    let compressed = compress(&buf).unwrap();
+
+    bench("compress (100M)", || {
+        elapsed(|| {
+            compress(&buf).unwrap();
+        })
+    });
+
+    bench("decompress (~100M)", || {
+        elapsed(|| {
+            decompress(&compressed).unwrap();
+        })
+    });
+}