Improve sort tests and benchmarks

Author: Stjepan Glavina

src/liballoc/benches/lib.rs

@@ -17,6 +17,7 @@
 #![feature(sort_unstable)]
 #![feature(test)]
 
+extern crate rand;
 extern crate test;
 
 mod btree;

src/liballoc/benches/slice.rs

@@ -8,9 +8,11 @@
 // option. This file may not be copied, modified, or distributed
 // except according to those terms.
 
-use std::{mem, ptr};
-use std::__rand::{Rng, thread_rng};
+use std::__rand::{thread_rng};
+use std::mem;
+use std::ptr;
 
+use rand::{Rng, SeedableRng, XorShiftRng};
 use test::{Bencher, black_box};
 
 #[bench]
@@ -191,17 +193,17 @@ fn gen_descending(len: usize) -> Vec<u64> {
 }
 
 fn gen_random(len: usize) -> Vec<u64> {
-    let mut rng = thread_rng();
+    let mut rng = XorShiftRng::from_seed([0, 1, 2, 3]);
     rng.gen_iter::<u64>().take(len).collect()
 }
 
 fn gen_random_bytes(len: usize) -> Vec<u8> {
-    let mut rng = thread_rng();
+    let mut rng = XorShiftRng::from_seed([0, 1, 2, 3]);
     rng.gen_iter::<u8>().take(len).collect()
 }
 
 fn gen_mostly_ascending(len: usize) -> Vec<u64> {
-    let mut rng = thread_rng();
+    let mut rng = XorShiftRng::from_seed([0, 1, 2, 3]);
     let mut v = gen_ascending(len);
     for _ in (0usize..).take_while(|x| x * x <= len) {
         let x = rng.gen::<usize>() % len;
@@ -212,7 +214,7 @@ fn gen_mostly_ascending(len: usize) -> Vec<u64> {
 }
 
 fn gen_mostly_descending(len: usize) -> Vec<u64> {
-    let mut rng = thread_rng();
+    let mut rng = XorShiftRng::from_seed([0, 1, 2, 3]);
     let mut v = gen_descending(len);
     for _ in (0usize..).take_while(|x| x * x <= len) {
         let x = rng.gen::<usize>() % len;
@@ -223,7 +225,7 @@ fn gen_mostly_descending(len: usize) -> Vec<u64> {
 }
 
 fn gen_strings(len: usize) -> Vec<String> {
-    let mut rng = thread_rng();
+    let mut rng = XorShiftRng::from_seed([0, 1, 2, 3]);
     let mut v = vec![];
     for _ in 0..len {
         let n = rng.gen::<usize>() % 20 + 1;
@@ -233,26 +235,40 @@ fn gen_strings(len: usize) -> Vec<String> {
 }
 
 fn gen_big_random(len: usize) -> Vec<[u64; 16]> {
-    let mut rng = thread_rng();
+    let mut rng = XorShiftRng::from_seed([0, 1, 2, 3]);
     rng.gen_iter().map(|x| [x; 16]).take(len).collect()
 }
 
 macro_rules! sort {
     ($f:ident, $name:ident, $gen:expr, $len:expr) => {
         #[bench]
         fn $name(b: &mut Bencher) {
-            b.iter(|| $gen($len).$f());
+            let v = $gen($len);
+            b.iter(|| v.clone().$f());
             b.bytes = $len * mem::size_of_val(&$gen(1)[0]) as u64;
         }
     }
 }
 
+macro_rules! sort_strings {
+    ($f:ident, $name:ident, $gen:expr, $len:expr) => {
+        #[bench]
+        fn $name(b: &mut Bencher) {
+            let v = $gen($len);
+            let v = v.iter().map(|s| &**s).collect::<Vec<&str>>();
+            b.iter(|| v.clone().$f());
+            b.bytes = $len * mem::size_of::<&str>() as u64;
+        }
+    }
+}
+
 macro_rules! sort_expensive {
     ($f:ident, $name:ident, $gen:expr, $len:expr) => {
         #[bench]
         fn $name(b: &mut Bencher) {
+            let v = $gen($len);
             b.iter(|| {
-                let mut v = $gen($len);
+                let mut v = v.clone();
                 let mut count = 0;
                 v.$f(|a: &u64, b: &u64| {
                     count += 1;
@@ -263,38 +279,38 @@ macro_rules! sort_expensive {
                 });
                 black_box(count);
             });
-            b.bytes = $len as u64 * mem::size_of::<u64>() as u64;
+            b.bytes = $len * mem::size_of_val(&$gen(1)[0]) as u64;
         }
     }
 }
 
 sort!(sort, sort_small_ascending, gen_ascending, 10);
 sort!(sort, sort_small_descending, gen_descending, 10);
 sort!(sort, sort_small_random, gen_random, 10);
-sort!(sort, sort_small_big_random, gen_big_random, 10);
+sort!(sort, sort_small_big, gen_big_random, 10);
 sort!(sort, sort_medium_random, gen_random, 100);
 sort!(sort, sort_large_ascending, gen_ascending, 10000);
 sort!(sort, sort_large_descending, gen_descending, 10000);
 sort!(sort, sort_large_mostly_ascending, gen_mostly_ascending, 10000);
 sort!(sort, sort_large_mostly_descending, gen_mostly_descending, 10000);
 sort!(sort, sort_large_random, gen_random, 10000);
-sort!(sort, sort_large_big_random, gen_big_random, 10000);
-sort!(sort, sort_large_strings, gen_strings, 10000);
-sort_expensive!(sort_by, sort_large_random_expensive, gen_random, 10000);
+sort!(sort, sort_large_big, gen_big_random, 10000);
+sort_strings!(sort, sort_large_strings, gen_strings, 10000);
+sort_expensive!(sort_by, sort_large_expensive, gen_random, 10000);
 
 sort!(sort_unstable, sort_unstable_small_ascending, gen_ascending, 10);
 sort!(sort_unstable, sort_unstable_small_descending, gen_descending, 10);
 sort!(sort_unstable, sort_unstable_small_random, gen_random, 10);
-sort!(sort_unstable, sort_unstable_small_big_random, gen_big_random, 10);
+sort!(sort_unstable, sort_unstable_small_big, gen_big_random, 10);
 sort!(sort_unstable, sort_unstable_medium_random, gen_random, 100);
 sort!(sort_unstable, sort_unstable_large_ascending, gen_ascending, 10000);
 sort!(sort_unstable, sort_unstable_large_descending, gen_descending, 10000);
 sort!(sort_unstable, sort_unstable_large_mostly_ascending, gen_mostly_ascending, 10000);
 sort!(sort_unstable, sort_unstable_large_mostly_descending, gen_mostly_descending, 10000);
 sort!(sort_unstable, sort_unstable_large_random, gen_random, 10000);
-sort!(sort_unstable, sort_unstable_large_big_random, gen_big_random, 10000);
-sort!(sort_unstable, sort_unstable_large_strings, gen_strings, 10000);
-sort_expensive!(sort_unstable_by, sort_unstable_large_random_expensive, gen_random, 10000);
+sort!(sort_unstable, sort_unstable_large_big, gen_big_random, 10000);
+sort_strings!(sort_unstable, sort_unstable_large_strings, gen_strings, 10000);
+sort_expensive!(sort_unstable_by, sort_unstable_large_expensive, gen_random, 10000);
 
 macro_rules! reverse {
     ($name:ident, $ty:ty, $f:expr) => {

src/liballoc/slice.rs

@@ -1794,7 +1794,7 @@ unsafe fn merge<T, F>(v: &mut [T], mid: usize, buf: *mut T, is_less: &mut F)
 
     impl<T> Drop for MergeHole<T> {
         fn drop(&mut self) {
-            // `T` is not a zero-sized type, so it's okay to divide by it's size.
+            // `T` is not a zero-sized type, so it's okay to divide by its size.
             let len = (self.end as usize - self.start as usize) / mem::size_of::<T>();
             unsafe { ptr::copy_nonoverlapping(self.start, self.dest, len); }
         }
@@ -1908,7 +1908,7 @@ fn merge_sort<T, F>(v: &mut [T], mut is_less: F)
     // if `Some(r)` is returned, that means `runs[r]` and `runs[r + 1]` must be merged next. If the
     // algorithm should continue building a new run instead, `None` is returned.
     //
-    // TimSort is infamous for it's buggy implementations, as described here:
+    // TimSort is infamous for its buggy implementations, as described here:
     // http://envisage-project.eu/timsort-specification-and-verification/
     //
     // The gist of the story is: we must enforce the invariants on the top four runs on the stack.

src/liballoc/tests/slice.rs

@@ -396,18 +396,44 @@ fn test_sort() {
     let mut rng = thread_rng();
 
     for len in (2..25).chain(500..510) {
-        for _ in 0..100 {
-            let mut v: Vec<_> = rng.gen_iter::<i32>().take(len).collect();
-            let mut v1 = v.clone();
-
-            v.sort();
-            assert!(v.windows(2).all(|w| w[0] <= w[1]));
-
-            v1.sort_by(|a, b| a.cmp(b));
-            assert!(v1.windows(2).all(|w| w[0] <= w[1]));
-
-            v1.sort_by(|a, b| b.cmp(a));
-            assert!(v1.windows(2).all(|w| w[0] >= w[1]));
+        for &modulus in &[5, 10, 100, 1000] {
+            for _ in 0..10 {
+                let orig: Vec<_> = rng.gen_iter::<i32>()
+                    .map(|x| x % modulus)
+                    .take(len)
+                    .collect();
+
+                // Sort in default order.
+                let mut v = orig.clone();
+                v.sort();
+                assert!(v.windows(2).all(|w| w[0] <= w[1]));
+
+                // Sort in ascending order.
+                let mut v = orig.clone();
+                v.sort_by(|a, b| a.cmp(b));
+                assert!(v.windows(2).all(|w| w[0] <= w[1]));
+
+                // Sort in descending order.
+                let mut v = orig.clone();
+                v.sort_by(|a, b| b.cmp(a));
+                assert!(v.windows(2).all(|w| w[0] >= w[1]));
+
+                // Sort with many pre-sorted runs.
+                let mut v = orig.clone();
+                v.sort();
+                v.reverse();
+                for _ in 0..5 {
+                    let a = rng.gen::<usize>() % len;
+                    let b = rng.gen::<usize>() % len;
+                    if a < b {
+                        v[a..b].reverse();
+                    } else {
+                        v.swap(a, b);
+                    }
+                }
+                v.sort();
+                assert!(v.windows(2).all(|w| w[0] <= w[1]));
+            }
         }
     }