Aliaksandr Valialkin
76f4fd8a52
runtime: improve timers scalability on multi-CPU systems
...
Use per-P timers, so each P may work with its own timers.
This CL improves performance on multi-CPU systems
in the following cases:
- When serving high number of concurrent connections
with read/write deadlines set (for instance, highly loaded
net/http server).
- When using high number of concurrent timers. These timers
may be implicitly created via context.WithDeadline
or context.WithTimeout.
Production servers should usually set timeout on connections
and external requests in order to prevent from resource leakage.
See https://blog.cloudflare.com/the-complete-guide-to-golang-net-http-timeouts/
Below are relevant benchmark results for various GOMAXPROCS values
on linux/amd64:
context package:
name old time/op new time/op delta
WithTimeout/concurrency=40 4.92µs ± 0% 5.17µs ± 1% +5.07% (p=0.000 n=9+9)
WithTimeout/concurrency=4000 6.03µs ± 1% 6.49µs ± 0% +7.63% (p=0.000 n=8+10)
WithTimeout/concurrency=400000 8.58µs ± 7% 9.02µs ± 4% +5.02% (p=0.019 n=10+10)
name old time/op new time/op delta
WithTimeout/concurrency=40-2 3.70µs ± 1% 2.78µs ± 4% -24.90% (p=0.000 n=8+9)
WithTimeout/concurrency=4000-2 4.49µs ± 4% 3.67µs ± 5% -18.26% (p=0.000 n=10+10)
WithTimeout/concurrency=400000-2 6.16µs ±10% 5.15µs ±13% -16.30% (p=0.000 n=10+10)
name old time/op new time/op delta
WithTimeout/concurrency=40-4 3.58µs ± 1% 2.64µs ± 2% -26.13% (p=0.000 n=9+10)
WithTimeout/concurrency=4000-4 4.17µs ± 0% 3.32µs ± 1% -20.36% (p=0.000 n=10+10)
WithTimeout/concurrency=400000-4 5.57µs ± 9% 4.83µs ±10% -13.27% (p=0.001 n=10+10)
time package:
name old time/op new time/op delta
AfterFunc 6.15ms ± 3% 6.07ms ± 2% ~ (p=0.133 n=10+9)
AfterFunc-2 3.43ms ± 1% 3.56ms ± 1% +3.91% (p=0.000 n=10+9)
AfterFunc-4 5.04ms ± 2% 2.36ms ± 0% -53.20% (p=0.000 n=10+9)
After 6.54ms ± 2% 6.49ms ± 3% ~ (p=0.393 n=10+10)
After-2 3.68ms ± 1% 3.87ms ± 0% +5.14% (p=0.000 n=9+9)
After-4 6.66ms ± 1% 2.87ms ± 1% -56.89% (p=0.000 n=10+10)
Stop 698µs ± 2% 689µs ± 1% -1.26% (p=0.011 n=10+10)
Stop-2 729µs ± 2% 434µs ± 3% -40.49% (p=0.000 n=10+10)
Stop-4 837µs ± 3% 333µs ± 2% -60.20% (p=0.000 n=10+10)
SimultaneousAfterFunc 694µs ± 1% 692µs ± 7% ~ (p=0.481 n=10+10)
SimultaneousAfterFunc-2 714µs ± 3% 569µs ± 2% -20.33% (p=0.000 n=10+10)
SimultaneousAfterFunc-4 782µs ± 2% 386µs ± 2% -50.67% (p=0.000 n=10+10)
StartStop 267µs ± 3% 274µs ± 0% +2.64% (p=0.000 n=8+9)
StartStop-2 238µs ± 2% 140µs ± 3% -40.95% (p=0.000 n=10+8)
StartStop-4 320µs ± 1% 125µs ± 1% -61.02% (p=0.000 n=9+9)
Reset 75.0µs ± 1% 77.5µs ± 2% +3.38% (p=0.000 n=10+10)
Reset-2 150µs ± 2% 40µs ± 5% -73.09% (p=0.000 n=10+9)
Reset-4 226µs ± 1% 33µs ± 1% -85.42% (p=0.000 n=10+10)
Sleep 857µs ± 6% 878µs ± 9% ~ (p=0.079 n=10+9)
Sleep-2 617µs ± 4% 585µs ± 2% -5.21% (p=0.000 n=10+10)
Sleep-4 689µs ± 3% 465µs ± 4% -32.53% (p=0.000 n=10+10)
Ticker 55.9ms ± 2% 55.9ms ± 2% ~ (p=0.971 n=10+10)
Ticker-2 28.7ms ± 2% 28.1ms ± 1% -2.06% (p=0.000 n=10+10)
Ticker-4 14.6ms ± 0% 13.6ms ± 1% -6.80% (p=0.000 n=9+10)
Fixes #15133
Change-Id: I6f4b09d2db8c5bec93146db6501b44dbfe5c0ac4
Reviewed-on: https://go-review.googlesource.com/34784
Reviewed-by: Austin Clements <austin@google.com>
2017-09-12 16:52:23 +00:00
