Ben Noordhuis
05bd6b7bcd
bench: add child process read perf benchmark
2013-03-25 13:16:07 +01:00
Trevor Norris
31314b6978
bench: compare binaries equal times
...
The benchmark compare would drop the last run of the binary pairs. So
when they were only run once an error would arise because no data was
generated for the second binary.
2013-03-20 20:25:48 +01:00
Ben Noordhuis
3dac421393
bench: add dgram send/recv benchmark
2013-03-20 17:16:30 +01:00
isaacs
d62cf59dc1
http: Don't hot-path end() for large buffers
...
The benefits of the hot-path optimization below start to fall off when
the buffer size gets up near 128KB, because the cost of the copy is more
than the cost of the extra write() call. Switch to the write/end method
at that point.
Heuristics and magic numbers are awful, but slow http responses are
worse.
Fix #4975
2013-03-14 08:04:59 -07:00
isaacs
e7b8bad3d9
bench: Do math on numbers in compare.js, not strings
2013-03-07 11:56:53 -08:00
isaacs
db5d58e842
bench: Use environ to run compares more than once
...
This will run the benchmarks the number of times specified by NODE_BENCH_RUNS,
to attempt to reduce variability.
If the number of runs is high enough, it'll also throw out the top and bottom
quartiles, since that's where the outliers will be.
It's not very fancy statistics-fu, but it's better than nothing.
Also, linted this file. It had tabs in it. TABS!
2013-03-06 12:33:05 -08:00
isaacs
e4383c0170
bench: Add flag to be silent in runner
...
This is helpful in tracking down bailouts and deopts in Stream classes,
without triggering one from the string write in console.log
2013-03-05 14:23:01 -08:00
isaacs
88befa6021
bench: Make http easier to profile
...
Do not run the http/simple.js server in a child process.
Fix #4831
2013-02-25 17:47:28 -08:00
isaacs
053e02ef8e
benchmark: Fix alignment issues on --html compare output
2013-02-20 09:17:29 -08:00
isaacs
bd4d585b7a
bench: Add bench-crypto
2013-02-19 17:16:55 -08:00
isaacs
4b80f217cd
bench: Simplify duration arguments to benchmarks
...
For throughput benchmarks, run with just 5s durations rather than 1s and 3s.
For startup benchmark, run with just a single 1s duration, since it's very
consistent anyway.
2013-02-19 17:16:55 -08:00
isaacs
2ed56e5235
bench: Consistency in benchmark filenames
2013-02-19 17:16:55 -08:00
isaacs
06fbcca6bb
bench: Remove _bench_timer (no loner used)
2013-02-19 17:16:55 -08:00
isaacs
ef08f0fbb1
bench: Use wrk for http benchmarking
...
Remove ab, since it's no longer used.
2013-02-19 17:16:29 -08:00
isaacs
035aa6b4ce
bench: Show % change rather than % difference
2013-02-19 14:14:39 -08:00
isaacs
087c437961
bench: Add --html to compare script
2013-02-19 14:14:38 -08:00
isaacs
7658f4c29c
bench: Fail gracefully if function_call binding fails
2013-02-19 14:14:38 -08:00
isaacs
7d51745827
bench: Remove old run script
2013-02-19 14:14:37 -08:00
isaacs
0a406869df
bench: Replace tls-fragmentation with tls/throughput
2013-02-19 14:14:37 -08:00
isaacs
bafc51c0f9
bench: Move tls-connect into benchmark/tls
...
Also, make it work properly with current node.
2013-02-19 14:14:37 -08:00
isaacs
8c719f7c71
bench: Make io.c output easier to read
2013-02-19 14:14:37 -08:00
isaacs
8a3f52170e
bench: Remove io.js
...
Better covered by the other benchmark/fs scripts.
2013-02-19 14:14:36 -08:00
isaacs
2a64edb025
bench: Add fs write stream throughput
2013-02-19 14:14:36 -08:00
isaacs
1fc6f99340
bench: Add read-stream throughput
2013-02-19 14:14:36 -08:00
isaacs
6d116be7cf
bench: Move fs-readfile.js to fs/readfile.js
2013-02-19 14:14:35 -08:00
isaacs
844b33205c
bench: Move v8_bench into misc
2013-02-19 14:14:35 -08:00
isaacs
2a2942bd7f
bench: Move string_creation into misc
2013-02-19 14:14:35 -08:00
isaacs
fef35fc4f1
bench: Remove settimeout (Covered by misc/timeout.js)
2013-02-19 14:14:35 -08:00
isaacs
3761be3d99
bench: Move timers to misc/timers
2013-02-19 14:14:34 -08:00
isaacs
7e5cd08061
bench: move next-tick to misc/next-tick-breadth
2013-02-19 14:14:34 -08:00
isaacs
f7a4ccb409
bench: Move nexttick-2 to misc/next-tick-depth
...
x
2013-02-19 14:14:34 -08:00
isaacs
44be55fc4e
bench: Move process_loop to misc/spawn-echo
2013-02-19 14:14:34 -08:00
isaacs
4e1bcdcab9
bench: Add function_call to bench-misc
2013-02-19 14:14:33 -08:00
isaacs
e87ed91fac
bench: Arrays
2013-02-19 14:14:33 -08:00
isaacs
3f67a48dd4
bench: Add buffers/dataview_set
2013-02-19 14:14:33 -08:00
isaacs
56b22956ad
bench: Remove unused 'fast_buffer2' benchmarks
2013-02-19 14:14:33 -08:00
isaacs
048f7fd37c
bench: Merge fast_buffer_creation and buffer_creation
2013-02-19 14:14:32 -08:00
isaacs
55aa2571a0
bench: Buffer read/write benchmarks
2013-02-19 14:14:32 -08:00
isaacs
419607e8eb
bench: Buffer creation
2013-02-19 14:14:32 -08:00
isaacs
cc38528acf
bench: buffer-base64-encode
2013-02-19 14:14:32 -08:00
isaacs
921c3c2097
bench: misc/startup.js
2013-02-19 14:14:31 -08:00
isaacs
3b16657e77
bench: misc/url
2013-02-19 14:14:31 -08:00
isaacs
536ce44689
bench: http benchmarks
...
Also: make http_simple less chatty
2013-02-19 14:14:31 -08:00
isaacs
d5d04a51d6
bench: Remove client_latency
...
No one actually knows what this is supposed to be doing,
anyway. It's not a good benchmark.
2013-02-19 14:14:31 -08:00
isaacs
051c1317f9
bench: Remove throughput (covered by benchmark/net)
2013-02-19 14:14:30 -08:00
isaacs
e82f97401f
bench: net benchmarks using common script
2013-02-19 14:14:30 -08:00
isaacs
baea73ccda
bench: Move net-pipe into benchmark/net
2013-02-19 14:14:30 -08:00
isaacs
aa2edd4b89
bench: A compare script for analyzing benchmarks
2013-02-19 14:14:30 -08:00
isaacs
37077de83d
bench: add runner
2013-02-19 14:14:29 -08:00
isaacs
dd069a2539
bench: Add ab() method to common for http testing
2013-02-19 14:14:29 -08:00
