1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
|
#![feature(test)]
extern crate futures;
extern crate futures_cpupool;
extern crate num_cpus;
extern crate test;
extern crate tokio_threadpool;
const NUM_SPAWN: usize = 10_000;
const NUM_YIELD: usize = 1_000;
const TASKS_PER_CPU: usize = 50;
mod threadpool {
use futures::{future, task, Async};
use num_cpus;
use std::sync::atomic::AtomicUsize;
use std::sync::atomic::Ordering::SeqCst;
use std::sync::{mpsc, Arc};
use test;
use tokio_threadpool::*;
#[bench]
fn spawn_many(b: &mut test::Bencher) {
let threadpool = ThreadPool::new();
let (tx, rx) = mpsc::sync_channel(10);
let rem = Arc::new(AtomicUsize::new(0));
b.iter(move || {
rem.store(super::NUM_SPAWN, SeqCst);
for _ in 0..super::NUM_SPAWN {
let tx = tx.clone();
let rem = rem.clone();
threadpool.spawn(future::lazy(move || {
if 1 == rem.fetch_sub(1, SeqCst) {
tx.send(()).unwrap();
}
Ok(())
}));
}
let _ = rx.recv().unwrap();
});
}
#[bench]
fn yield_many(b: &mut test::Bencher) {
let threadpool = ThreadPool::new();
let tasks = super::TASKS_PER_CPU * num_cpus::get();
let (tx, rx) = mpsc::sync_channel(tasks);
b.iter(move || {
for _ in 0..tasks {
let mut rem = super::NUM_YIELD;
let tx = tx.clone();
threadpool.spawn(future::poll_fn(move || {
rem -= 1;
if rem == 0 {
tx.send(()).unwrap();
Ok(Async::Ready(()))
} else {
// Notify the current task
task::current().notify();
// Not ready
Ok(Async::NotReady)
}
}));
}
for _ in 0..tasks {
let _ = rx.recv().unwrap();
}
});
}
}
// In this case, CPU pool completes the benchmark faster, but this is due to how
// CpuPool currently behaves, starving other futures. This completes the
// benchmark quickly but results in poor runtime characteristics for a thread
// pool.
//
// See rust-lang-nursery/futures-rs#617
//
mod cpupool {
use futures::future::{self, Executor};
use futures::{task, Async};
use futures_cpupool::*;
use num_cpus;
use std::sync::atomic::AtomicUsize;
use std::sync::atomic::Ordering::SeqCst;
use std::sync::{mpsc, Arc};
use test;
#[bench]
fn spawn_many(b: &mut test::Bencher) {
let pool = CpuPool::new(num_cpus::get());
let (tx, rx) = mpsc::sync_channel(10);
let rem = Arc::new(AtomicUsize::new(0));
b.iter(move || {
rem.store(super::NUM_SPAWN, SeqCst);
for _ in 0..super::NUM_SPAWN {
let tx = tx.clone();
let rem = rem.clone();
pool.execute(future::lazy(move || {
if 1 == rem.fetch_sub(1, SeqCst) {
tx.send(()).unwrap();
}
Ok(())
}))
.ok()
.unwrap();
}
let _ = rx.recv().unwrap();
});
}
#[bench]
fn yield_many(b: &mut test::Bencher) {
let pool = CpuPool::new(num_cpus::get());
let tasks = super::TASKS_PER_CPU * num_cpus::get();
let (tx, rx) = mpsc::sync_channel(tasks);
b.iter(move || {
for _ in 0..tasks {
let mut rem = super::NUM_YIELD;
let tx = tx.clone();
pool.execute(future::poll_fn(move || {
rem -= 1;
if rem == 0 {
tx.send(()).unwrap();
Ok(Async::Ready(()))
} else {
// Notify the current task
task::current().notify();
// Not ready
Ok(Async::NotReady)
}
}))
.ok()
.unwrap();
}
for _ in 0..tasks {
let _ = rx.recv().unwrap();
}
});
}
}
|
