lukechilds/node - node - Gitea: Git with a cup of tea

Commit Graph

Author	SHA1	Message	Date
Ben Noordhuis	fda2b319dc	http: save roundtrips, convert buffers to strings This commit adds an optimization to the HTTP client that makes it possible to: * Pack the headers and the first chunk of the request body into a single write(). * Pack the chunk header and the chunk itself into a single write(). Because only one write() system call is issued instead of several, the chances of data ending up in a single TCP packet are phenomenally higher: the benchmark with `type=buf size=32` jumps from 50 req/s to 7,500 req/s, a 150-fold increase. This commit removes the check from `e4b716ef` that pushes binary encoded strings into the slow path. The commit log mentions that: We were assuming that any string can be concatenated safely to CRLF. However, for hex, base64, or binary encoded writes, this is not the case, and results in sending the incorrect response. For hex and base64 strings that's certainly true but binary strings are 'das Ding an sich': string.length is the same before and after decoding. Fixes #5528.	12 years ago
isaacs	201baa273b	benchmark: hash stream	12 years ago
Ben Noordhuis	05bd6b7bcd	bench: add child process read perf benchmark	12 years ago
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.	12 years ago
Ben Noordhuis	3dac421393	bench: add dgram send/recv benchmark	12 years ago
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	12 years ago
isaacs	e7b8bad3d9	bench: Do math on numbers in compare.js, not strings	12 years ago
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!	12 years ago
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	12 years ago
isaacs	88befa6021	bench: Make http easier to profile Do not run the http/simple.js server in a child process. Fix #4831	12 years ago
isaacs	053e02ef8e	benchmark: Fix alignment issues on --html compare output	12 years ago
isaacs	bd4d585b7a	bench: Add bench-crypto	12 years ago
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.	12 years ago
isaacs	2ed56e5235	bench: Consistency in benchmark filenames	12 years ago
isaacs	06fbcca6bb	bench: Remove _bench_timer (no loner used)	12 years ago
isaacs	ef08f0fbb1	bench: Use wrk for http benchmarking Remove ab, since it's no longer used.	12 years ago
isaacs	035aa6b4ce	bench: Show % change rather than % difference	12 years ago
isaacs	087c437961	bench: Add --html to compare script	12 years ago
isaacs	7658f4c29c	bench: Fail gracefully if function_call binding fails	12 years ago
isaacs	7d51745827	bench: Remove old run script	12 years ago
isaacs	0a406869df	bench: Replace tls-fragmentation with tls/throughput	12 years ago
isaacs	bafc51c0f9	bench: Move tls-connect into benchmark/tls Also, make it work properly with current node.	12 years ago
isaacs	8c719f7c71	bench: Make io.c output easier to read	12 years ago
isaacs	8a3f52170e	bench: Remove io.js Better covered by the other benchmark/fs scripts.	12 years ago
isaacs	2a64edb025	bench: Add fs write stream throughput	12 years ago
isaacs	1fc6f99340	bench: Add read-stream throughput	12 years ago
isaacs	6d116be7cf	bench: Move fs-readfile.js to fs/readfile.js	12 years ago
isaacs	844b33205c	bench: Move v8_bench into misc	12 years ago
isaacs	2a2942bd7f	bench: Move string_creation into misc	12 years ago
isaacs	fef35fc4f1	bench: Remove settimeout (Covered by misc/timeout.js)	12 years ago
isaacs	3761be3d99	bench: Move timers to misc/timers	12 years ago
isaacs	7e5cd08061	bench: move next-tick to misc/next-tick-breadth	12 years ago
isaacs	f7a4ccb409	bench: Move nexttick-2 to misc/next-tick-depth x	12 years ago
isaacs	44be55fc4e	bench: Move process_loop to misc/spawn-echo	12 years ago
isaacs	4e1bcdcab9	bench: Add function_call to bench-misc	12 years ago
isaacs	e87ed91fac	bench: Arrays	12 years ago
isaacs	3f67a48dd4	bench: Add buffers/dataview_set	12 years ago
isaacs	56b22956ad	bench: Remove unused 'fast_buffer2' benchmarks	12 years ago
isaacs	048f7fd37c	bench: Merge fast_buffer_creation and buffer_creation	12 years ago
isaacs	55aa2571a0	bench: Buffer read/write benchmarks	12 years ago
isaacs	419607e8eb	bench: Buffer creation	12 years ago
isaacs	cc38528acf	bench: buffer-base64-encode	12 years ago
isaacs	921c3c2097	bench: misc/startup.js	12 years ago
isaacs	3b16657e77	bench: misc/url	12 years ago
isaacs	536ce44689	bench: http benchmarks Also: make http_simple less chatty	12 years ago
isaacs	d5d04a51d6	bench: Remove client_latency No one actually knows what this is supposed to be doing, anyway. It's not a good benchmark.	12 years ago
isaacs	051c1317f9	bench: Remove throughput (covered by benchmark/net)	12 years ago
isaacs	e82f97401f	bench: net benchmarks using common script	12 years ago
isaacs	baea73ccda	bench: Move net-pipe into benchmark/net	12 years ago
isaacs	aa2edd4b89	bench: A compare script for analyzing benchmarks	12 years ago

1 2 3 4

174 Commits (231092d236de590a7448ed4257e121f308875326)