12013508bf
Running clang-format
2015-07-24 15:35:11 -07:00
85e4151bca
manual merge
2015-07-24 15:17:22 -07:00
278247faa9
Starting a second earlier
2015-07-24 14:34:53 -07:00
ec617ae6e5
Getting rid of unused fields in config
2015-07-23 11:21:12 -07:00
d6786f75cb
Getting rid of unused fields in Worker
2015-07-23 11:01:09 -07:00
584f5f3734
Do not allow -r > -t
2015-07-23 10:37:51 -07:00
a04c67bcd6
Getting rid of print statements
2015-07-23 10:30:55 -07:00
8325c6ccdf
setting request number correctly:
2015-07-23 10:20:18 -07:00
30235f8809
Assigning clients to workers proportional to rate
2015-07-23 09:37:44 -07:00
65df3c63bf
Adding new rate and connection allocation to threads
2015-07-22 16:41:58 -07:00
916e27489f
rate now working
2015-07-21 16:53:46 -07:00
650e463a49
First try with something working, still need to clean and test
2015-07-21 11:28:12 -07:00
52152ad96d
Can make h2load, but running into recursive loop problem
2015-07-21 11:06:33 -07:00
921e393dcd
src: Use <PATH> instead of <FILE> in usage text
2015-07-20 23:50:05 +09:00
fa7a74cfa8
h2load: Use std::string::size instead of strlen
2015-07-19 18:37:41 +09:00
b37716ab6a
h2load: Workaround with clang-3.4
2015-07-19 18:35:14 +09:00
5dc060c1a2
src: Use C++11 value-initialization, instead of memset-ing 0
2015-07-19 17:55:37 +09:00
cce64e6728
h2load: Call second_timeout_cb manually so that we don't waste first 1 second
2015-07-19 17:31:35 +09:00
006ac7b1b0
h2load: Fix HTML formatting
2015-07-19 17:27:38 +09:00
d326e28c92
running clang-format
2015-07-17 14:10:40 -07:00
c1c177addc
Changing warning to mention #reqs rather than test time
2015-07-17 14:10:21 -07:00
eeba12144c
Refactored seconds setting and worker space reservation
2015-07-16 11:02:01 -07:00
ce00c50720
Changing comparison from double to ssize_t
2015-07-16 10:51:41 -07:00
7d2ea42c38
Fixing spelling mistake in num-conns description
2015-07-16 10:43:50 -07:00
e0d7ce439d
Fixing style for Config field initializer list
2015-07-16 10:35:03 -07:00
ccfe7f8548
Reordering Config field initializer list
2015-07-16 10:33:44 -07:00
5892385e5c
[EDGE-879] run clang-format and make sure style is good
2015-07-15 09:51:33 -07:00
d6551de8d4
[EDGE-877] [h2load] apply changes to new version of h2load
2015-07-14 23:41:29 +00:00
6b53f7ee19
[EDGE-879] run clang-format and make sure style is good
2015-07-14 11:16:37 -07:00
2482dd7f77
Adding -r and -C options to h2load
2015-07-13 11:28:15 -07:00
237f742100
h2load: Add --ciphers option
2015-07-08 23:14:41 +09:00
197493afd4
nghttpx: Add log variables related to SSL/TLS connection
...
This commit add following 3 log variables to SSL/TLS connection:
$ssl_cipher, $ssl_protocol, $ssl_session_id. If no information is
available for them, '-' is produced for each.
2015-06-28 16:44:34 +09:00
301df2a856
src: Disable SSL_OP_DONT_INSERT_EMPTY_FRAGMENTS
2015-06-22 23:26:45 +09:00
39f89f4a60
src: Use user-defined literals for k, m, and g.
2015-06-21 14:32:47 +09:00
69119f47c4
src: Support compile with LibreSSL
2015-06-17 18:24:51 +09:00
2952706b53
Fix scan-build error
2015-06-10 00:29:03 +09:00
9b0ccdef34
h2load: Code cleanup
2015-06-10 00:28:27 +09:00
791660ef8d
Fix up OpenSSL initialization
...
Use the example presented at
http://en.wikibooks.org/wiki/OpenSSL/Initialization
2015-05-23 00:23:38 +09:00
28adb2dad3
h2load: Fix bug that NPN fails if ALPN is enabled
2015-05-22 00:48:32 +09:00
38cfc5c47c
Check more headers and funcs
2015-05-13 23:29:20 +09:00
2f2a7ace81
Fix corresponding upstream source reported in previous commits accordingly
2015-05-12 23:24:18 +09:00
cc46d363c5
h2load: Refactor statistics hanlding to scale more upcoming new metrics
2015-05-04 22:36:21 +09:00
b4e8bea4b5
clang-format
2015-05-03 16:47:32 +09:00
555d5abac9
Merge branch 'finer_stats' of https://github.com/ericcarlschwartz/nghttp2 into ericcarlschwartz-finer_stats
2015-05-03 16:37:02 +09:00
4bba4bf66c
update h2load to give connect time and ttfb stats
...
finer statistics for h2load: update per comments from tatsuhiro-t
finer stats for h2load: fixed formatting
2015-05-01 10:30:09 -07:00
b41835f19b
h2load: Effectively disable flow control by setting large window size
...
Previously h2load used default flow control window as described in
HTTP/2 and SPDY specification. The window size is 64KiB, which is a
bit small, and cannot utilize full server performance when response
size is not too small. Basically, we do this kind of benchmarking
test to measure server's throughput, and optimal performance. Smaller
window certainly degrades performance even in local testing because
server is so fast that it has to wait for WINDOW_UPDATE from h2load.
To make default behaviour suitable for peak performance test, we
decided to disable flow control in h2load by setting large enough
window size.
Most users used h2load without -w or -W options, so they were
implicitly throttled by flow control and the result was affected by
that negatively. Now flow control is disabled by default, the result
may improve depending on the implementations.
2015-04-27 21:23:01 +09:00
e9cdb9c896
h2load: Remove unused fields in Client class
2015-03-28 20:17:30 +09:00
c4804ee50b
h2load: Remove Client::noop
2015-03-28 20:14:12 +09:00
95cb284e27
h2load: Rename Client::on_connect as connection_made
2015-03-28 20:13:37 +09:00
6f58434d89
nghttpx, h2load: Perform write whenever read succeeds
2015-03-28 19:13:14 +09:00
Nora Shoemaker
Tatsuhiro Tsujikawa
Nora Shoemaker
es