Age | Commit message (Collapse) | Author |
|
Change-Id: I804a05a5e7ded06239a355eb967ccb4235cae3d3
|
|
am: b9f9572cbe
Change-Id: I301f6c7d1ffd8cf7ac044bbf761e7f40567c4c4d
|
|
am: 4e57a4fc40
Change-Id: I43498c96f633d33d2473a644dcfee851405c71d2
|
|
am: b1cae5175e
Change-Id: Ic83af55a13c5a6f9ef2c6a1574a50d30415c683b
|
|
Bug: http://b/123261826
Test: build
Change-Id: Iccc3cd1f1475e33956d92a497d9c4306d53c3983
|
|
87ad254d23 am: dbad721648
am: 1d4b6646ff
Change-Id: I22b7d2bb86fabdbee42b1c3fccd8b2846e0b5f49
|
|
am: dbad721648
Change-Id: I07c47c266a9481c9aba306b5b368b5a63f8cb30e
|
|
am: 87ad254d23
Change-Id: I11f777fc60973fe03d1f6a23d422995f1aabca7d
|
|
Also adds NOTICE, METADATA, MODULE_LICENSE_*
Test: NA (not build yet)
Change-Id: Ia08a651fdecc5e540c2cad218a128099c7322280
|
|
|
|
|
|
iperf reported "impossible" CPU usage percentages in JSON output:
"cpu_utilization_percent": {
"host_total": 70907445.679701567,
"host_user": 1303335.9336584355,
"host_system": 69604109.746043131,
"remote_total": 13580675.258652203,
"remote_user": 540984.0827233647,
"remote_system": 13039620.331720918
},
Regression introduced in commit cde81d7 ("Add initial portable time
abstraction"), where "timediff" was accidentally changed from
microseconds to seconds:
- timediff = ((temp.tv_sec * 1000000.0 + temp.tv_usec) -
- (last.tv_sec * 1000000.0 + last.tv_usec));
+ iperf_time_diff(&now, &last, &temp_time);
+ timediff = iperf_time_in_secs(&temp_time);
|
|
`listen()` (#827)
This commit applies the same changes made by b481169 (#693), to the
TCP and SCTP server sockets.
|
|
Adds the `--bidir` flag to support simultaneous two-way tests.
Submitted by @LikHait. Fixes #201.
|
|
From author's notes (@ben-foxmore):
The current usage of gettimeofday causes issues for us when performing
tests shortly after restarting a system. In our setup, this occurs
often as we restart the system before each test to ensure reliable
results. We already maintain our own version of iperf for some subtle
changes, but this change feels like it might be useful to upstream.
(It's also a reasonable size change, so we'd prefer not maintain it
with each new version of iperf.)
It uses clock_gettime on systems that have it available, and falls
back to gettimeofday when it's not. These two options use different
structures for storing time - clock_gettime uses timespec, and
gettimeofday uses timeval. To provide abstraction to which one is
available, a separate iperf_time struct is defined to store time.
timespec has nanosecond accuracy, while timeval only has microseconds.
For the purposes of iperf, I don't think nanosecond accuracy is
neccesary, so iperf_time only uses microseconds, throwing away any
additional accuracy. Currently I have used the MONOTONIC clock, as I
think we only need a consistent time interval measure.
|
|
|
|
accelleran-iperf_time
|
|
(#776)
Fixes #599.
|
|
(#795)
Also fix some stupid looking code and update a copyright.
Fixes #790.
|
|
Fixes #791.
|
|
To reproduce, run the server as "iperf3 --server --verbose" and
run a client as "iperf3 --client localhost -reverse --parallel 2".
Fixes #778.
Based on https://github.com/Aquantia/iperf/commit/f1778271d2c6bed1dae09dccd33251
1b263f6871
|
|
* Fixed implementation of function set_test-reverse().
* Correct/improve some other checks
|
|
|
|
Also includes a test program.
|
|
Fixes #764.
|
|
Follow-on to #749, suggested by @artem-nefedov.
|
|
|
|
of iperf3_profile binary (#763)
Fixes #749.
|
|
* Add pacing timer, bytes and blocks functions to libiperf.
* Explicitly cast to uint64_t to match return type.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Debugging and/or verbose output can get in the way of producing
valid/parsable JSON.
Inspired by #737.
|
|
|
|
There are lots of mixed tabs and spaces, most of them look OK if tabs are 8
characters wide, but this bit seems to have been written by someone whose editor
thinks they're 4 characters wide, so it looks all messed up.
|
|
While here, get rid of an empty section for 3.5.
|
|
Fixes #727.
|
|
|
|
Towards #600.
|
|
|
|
|
|
Follow-up commit to #712 / #713.
|
|
Fixes #712. A subsequent commit will add some information to the libiperf manual page.
|
|
Also fix some RST formatting and add some text on FreeBSD TCP
congestion control algorithms.
Fixes #410.
|