1
1
Граф коммитов

793 Коммитов

Автор SHA1 Сообщение Дата
Bruce A. Mah
01fb3e6dcf
Regen. 2016-12-12 15:41:35 -08:00
Bruce A. Mah
29183ec341 iperf's master branch isn't 3.1, so don't generate that version string.
Signed-off-by: Bruce A. Mah <bmah@es.net>
2016-12-12 15:40:31 -08:00
Bruce A. Mah
a094d9feef Separate out application-level and fair-queueing-based pacing (#488)
* First try to fix pacing issues.  Code compiles, lightly run-tested.

Make --bandwidth only control application-level pacing, refecting
behavior of iperf 3.1.2 and earlier.

Add a new --fq-rate that controls only FQ-based per-socket pacing.
A given test can use application-level pacing, FQ pacing, both,
or neither.

Deprecate the --no-fq-socket-pacing option; specifying this generates
a warning and is equivalent to --fq-rate=0.

Towards issue #467 and related to issue #325.

* Move --fq-rate in the help text to be just below --b, tweak wording.

* Sigh.  One more tweak on help text.

Some day I probably need to review and rewrite the whole thing.

Still working towards #467.
2016-12-12 13:47:53 -08:00
Bruce A. Mah
7d2d5c41dd
Revert "Fix a bug in FQ pacing, where application pacing wasn't completely disabled."
This reverts commit 1fa41308fe.

This doesn't really do what we want.  Start over.
2016-12-08 15:25:06 -08:00
Bruce A. Mah
5307eae461
Revert "Reduce the default UDP send size to 1452 to avoid IP fragmentation"
This reverts commit f1e62c8d48.

Right idea, but it turns out to be a pretty high-impact change.
Need to rethink this, maybe with a more intelligent implementation
that checks the interface (or path?) MTU.
2016-12-08 15:23:51 -08:00
Bruce A. Mah
f1e62c8d48
Reduce the default UDP send size to 1452 to avoid IP fragmentation
with default parameters.

A UDP payload of 1452, plus an 8-byte UDP header, plus a 40-byte IPv6
header, results in a 1500 byte IP packet.  The IPv4 header is smaller
at 20 bytes.
2016-12-05 14:00:15 -08:00
Bruce A. Mah
1fa41308fe
Fix a bug in FQ pacing, where application pacing wasn't completely disabled.
It was therefore possible to have multiple levels of pacing happening,
which resulted in very nicely smoothed traffic, but wasn't really
the original design.

Do pacing correctly in iperf_check_throttle() and remove a hack in
iperf_send() where we were explicitly checking for the type of
pacing, but didn't really need to.

It turns out that with UDP and only-FQ pacing, iperf3 sends and throws
packets on the floor as fast as it can.  This isn't really desirable,
and probably not what was wanted in a test anyway, so if we're not
doing TCP tests, force the use of application-level pacing.
2016-12-05 10:37:56 -08:00
Bruce A. Mah
55598a072f
Fix socket buffer size checks. Clearly this wasn't tested well.
On Linux it's possible to set the socket buffer to one size but
(correctly it seems) get back some larger size up to 2x what you
asked for (see tcp(7)).

While here, make related debugging output more useful.

Fixes (again) #356.
2016-12-01 11:53:37 -08:00
Bruce A. Mah
a621cc263f
Improve debug output for application and fair-queue-based pacing. 2016-11-30 07:13:28 -08:00
Bruce A. Mah
d2202ee3be
After setting socket buffer sizes, verify they were set correctly.
Do this for both TCP and UDP, but not SCTP (which strangely doesn't
support --window, that's probably a bug).  Fixes #356.
2016-11-23 11:05:47 -08:00
Bruce A. Mah
c4a56a3c49
Improvements to systemd service file as per #430.
Submitted by @rpodgorny.
2016-11-18 13:45:06 -08:00
Sascha Spreitzer
b56d154cda Add systemd service file (#340)
To be modified by some code changes in #430.
2016-11-18 13:43:48 -08:00
Bruce A. Mah
902b195edd
D'oh. Fix bad formatting in dev.rst. 2016-11-10 14:28:14 -08:00
Bruce A. Mah
71d02d51df
Update supported development platforms. 2016-11-10 14:24:49 -08:00
Bruce A. Mah
c2b34b4d22
Add notes on generating new manpage rendering for online docs. 2016-11-10 14:23:42 -08:00
Bruce A. Mah
f0f3e52f24
Update manpage in online docs to reflect 3.1-STABLE sometime after 3.1.4.
Fixes #440.
2016-11-10 14:06:13 -08:00
Bruce A. Mah
6aff679e96
Fix executable name and date in the manpage heading. 2016-11-10 13:49:44 -08:00
Bruce A. Mah
bdbb9a1cab
Update docs for iperf-3.1.4. 2016-10-31 13:54:30 -07:00
Nevo Hed
ad2a706fd1 Replace iprintf w/ iperf_printf (cygwin conflict) (#468)
This does not seek to address all cygwin portability issues
just this specific compile-time conflict

See also #280 and #295.
See https://github.com/esnet/iperf/issues/280
2016-10-17 13:25:07 -07:00
Bruce A. Mah
d99a69f92b
Fix a buffer overflow in upstream cJSON.
This is DaveGamble/cJSON#30, and fixes issue #466.
2016-10-05 13:59:40 -07:00
Bruce A. Mah
1a756a949e Only print congestion control algorithm for a TCP test.
Properly (I think) label the two TCP instsances as "sender"
and "receiver".
2016-09-22 15:27:24 -07:00
Bruce A. Mah
7d413a5015 Fix build on FreeBSD. 2016-09-22 14:52:57 -07:00
Bruce A. Mah
7eeaa1cb07 First try at issue #461.
First, realize that we've been setting the congestion control (CC)
algorithm unnecessarily; rather than doing it for all listening or
connecting sockets, do it just for those sockets that are being used
for TCP test streams.

Record the CC algorithm in use (this handles the case where a CC algorithm
hasn't been specified), and have the client and server exchange this
information.

Report the CC algorithms that were used (note that it's theoretically
possible for the two ends of the test to be using different algorithms,
if no algorithm was explicitly specified and the two end hosts have
different defaults, or if one side allows setting the CC algorithm and
the other doesn't).

Committing to a branch to make it easier to test this code on a
wider combination of systems.
2016-09-22 13:34:52 -07:00
Bruce A. Mah
353615b772
Fix divide-by-zero problem that can occur with a zero-length interval
(this can happen at the end of a test under certain circumstances).
Fixes #388, alternate solution from pull request in #389.
2016-09-21 13:22:54 -07:00
Bruce A. Mah
55b4eb143e
Fix whitespace errors in .travis.yml. 2016-09-21 11:44:20 -07:00
g-coder
508b98e91a Created .travis.yml for build automation (#424)
This enhancement will automatic check and test the changes done. It will improve the testing capability of component as build can be tested at every pull request before commit.

To enable this feature , you will have to login in https://travis-ci.org/. using github account 
and enable the travis feature for the iperf library.

Many other github projects use this feature. Hope it will help iperf too.
2016-09-21 11:40:14 -07:00
Bruce A. Mah
03340fe595
Prevent a double-close on the server side in some cases.
Alternate solution to a problem pointed out by @g-coder in pull request #429.
2016-09-21 11:25:18 -07:00
woody77
93c498d417 Change pacing timer from 100ms to 1ms to smoothen out microbusts as much as possible (#460) 2016-09-21 10:31:48 -07:00
woody77
14caac895c Properly setting the no_fq_socket_pacing option when support for it is not compiled in. (#459) 2016-09-21 10:21:59 -07:00
Bruce A. Mah
099244ec68
Update documentation site for 3.1.3 and 3.0.12.
Also provide pointer to recently-released security advisory.
2016-06-08 12:32:35 -07:00
Bruce A. Mah
701ba3ed59
Regen. 2016-06-03 09:26:26 -07:00
Bruce A. Mah
b7ab2b4b25
Make the server more tolerant of most types of errors encountered
during tests.

We used to exit if 5 consecutive errors were encountered.  Instead,
only exit if certain types of fatal errors happen.
2016-06-03 09:26:05 -07:00
Bruce A. Mah
4dcb275b5b
Make error handling on the control channel more robust. 2016-06-03 09:25:14 -07:00
Bruce A. Mah
ed94082be2
Fix a buffer overflow / heap corruption issue that could occur if a
malformed JSON string was passed on the control channel.  This issue,
present in the cJSON library, was already fixed upstream, so was
addressed here in iperf3 by importing a newer version of cJSON (plus
local ESnet modifications).

Discovered and reported by Dave McDaniel, Cisco Talos.

Based on a patch by @dopheide-esnet, with input from @DaveGamble.

Cross-references:  TALOS-CAN-0164, ESNET-SECADV-2016-0001,
CVE-2016-4303
2016-06-03 09:23:59 -07:00
Bruce A. Mah
a5f5765c8c
Regen. 2016-05-26 09:49:16 -07:00
Bruce A. Mah
9915746a8b
Squashed commit of the following:
commit 2dc03630a736be2ae9f64823aabb5776e7074c2a
Merge: 61e325c 0da552c
Author: Bruce A. Mah <bmah@es.net>
Date:   Thu May 26 09:40:58 2016 -0700

    Merge branch 'master' into issue-325

commit 61e325c5d0a4e7a9823221ce507db0f478fc98b5
Merge: 227992f ccbcee6
Author: Bruce A. Mah <bmah@es.net>
Date:   Thu May 26 11:09:54 2016 -0400

    Merge branch 'issue-325' of github.com:esnet/iperf into issue-325

    Conflicts:
    	src/iperf3.1

commit 227992f366e7f4895b6762011576ba22a42a752e
Author: Bruce A. Mah <bmah@es.net>
Date:   Thu May 26 11:07:01 2016 -0400

    Don't set SO_MAX_PACING_RATE if the rate is 0.  Also tweak some help text.

    Towards #325, in response to feedback from @bltierney.

commit ccbcee6366d50ec632fc00eb11fde8a886f8febe
Author: Bruce A. Mah <bmah@es.net>
Date:   Tue May 24 09:19:41 2016 -0700

    Fix manpage formatting for consistency.

commit 90ac5a9ce09bd746ca5f943a8226ab864da3ebf8
Author: Bruce A. Mah <bmah@es.net>
Date:   Tue May 24 12:14:16 2016 -0400

    Add some documentation for fair-queueing per-socket pacing.

    For #325.

commit 5571059870f7aefefb574816de70b6406848888f
Author: Bruce A. Mah <bmah@es.net>
Date:   Tue May 24 11:55:44 2016 -0400

    Change the fair-queueing socket pacing logic in response to feedback.

    By default, on platforms where per-socket pacing is available, it
    will be used.  If not available, iperf3 will fall back to application-
    level pacing.

    The --no-fq-socket-pacing option can be used to forcibly disable
    fair-queueing per-socket pacing.  (The earlier --socket-pacing option
    has been removed.)

    Tested on CentOS 7, more testing on other platforms is required to
    be sure it didn't break the old application-level pacing behavior.

    For #325.

commit 3e3f506fe9f375a5771c9e3ddfe8677c1a7146e7
Merge: 50a379e 3b23112
Author: Bruce A. Mah <bmah@es.net>
Date:   Tue May 24 09:54:39 2016 -0400

    Merge branch 'master' into issue-325

commit 50a379eddfa89d1313d2aeeb62a6fbc82f00ea17
Author: Bruce A. Mah <bmah@es.net>
Date:   Sat Apr 16 02:55:42 2016 -0400

    Regen.

commit 200d3fe3917b3d298bdf52a0bde32c47cf2727b0
Author: Bruce A. Mah <bmah@es.net>
Date:   Sat Apr 16 02:41:32 2016 -0400

    Checkpoint for initial work on #325 to add socket pacing.

    This works only on Linux and depends on the availability of
    the SO_MAX_PACING_RATE socket option and the fq queue discipline.
    Use --socket-pacing to use SO_MAX_PACING_RATE instead of the
    default iperf3 user-level rate limiting; in either case, the
    --bandwidth parameter controls the desired rate.

    Lightly tested with both --tcp and --udp, normal and --reverse.
    Real testing requires analysis of packet timestamps between
    multiple hosts.
2016-05-26 09:47:48 -07:00
g-coder
0da552c390 Safe programming practice. Added va_end. (#425)
In file iperf_util.c:
Function 'va_start' is called at line:327. But, 'va_end' is not called before returning from function 'iperf_json_printf()' at line:352 and line:355. 
The va_end performs cleanup for the argp object initialized by a call to va_start. If va_end is not called before a function that calls va_start returns, the behavior is undefined.

Applied Fix: added va_end before returning from the function.
2016-05-26 09:06:16 -07:00
g-coder
8fcfc2479f DEREF_AFTER_NULL in src/iperf_error.c (#423)
DEREF_AFTER_NULL: pointer ‘test’ at line:77 is passed as an argument to function iperf_delete_pidfile(), in which it is dereferenced at iperf_api.c:2832.
Pointer ‘test’ can be NULL and dereferencing a NULL pointer causes seg-fault.

Applied Fix: pointer ‘test’ is checked for NULL before passing it to function iperf_delete_pidfile().
2016-05-26 08:47:29 -07:00
Joe McEachern
3b2311263a Add fix for #412 (#414)
* Add fix for #412
This prevents negative loss counters with UDP when omit is used

* Track the original start time and bytes omitted. This allows the
throttle function to work after the omit timer fires. This is
a fix for issue #419.

* Remove changes to switch the bandwidth to received instead of sent bandwidth

* Roll back bandwidth sent vs received changes
2016-05-20 11:40:18 -07:00
Bruce A. Mah
f88486443c
Fix build on FreeBSD 11-CURRENT, as described in issue #413.
This caused by a combination of the iperf3 build somehow using
the system queue.h on FreeBSD 11 (possibly only on this platform)
and TAILQ_END not being defined in the system queue.h.

Expanding the TAILQ_END macro to NULL seems to solve the problem.

Submitted by:	@rbgarga
2016-05-20 10:05:24 -07:00
Monte Goode
897687ac0f Mods to summed output after meeting. 2016-04-18 12:22:59 -07:00
Monte Goode
8d94dc289d Add the row header to the --sum output. 2016-04-11 14:18:53 -07:00
Monte Goode
471aa5f133 New summing format. Still need row header from brian. 2016-04-11 12:18:21 -07:00
Monte Goode
2d3eb211f6 Quick linting pass and get the CR chars out of there so it'll actually run from a shell. :) 2016-04-11 10:07:04 -07:00
Bruce A. Mah
4fbdab392c Merge pull request #377 from quasoft/forceflush
Add option `--forceflush` to force flushing of output at the end of each interval
2016-03-25 10:44:20 -07:00
QuaSoft
08a2de459b Add command line option --forceflush to allow user to request flushing of output at the end of each interval.
Fixes #299
2016-03-06 16:47:02 +02:00
Bruce A. Mah
fab327943f
Update Web site for iperf-3.1.2. 2016-02-01 16:34:01 -08:00
Bruce A. Mah
cb25dfe687
Update copyright dates in a couple of places. 2016-02-01 14:01:54 -08:00
Bruce A. Mah
670c18584b
Get rid of nan values when there were no packets in a UDP interval.
This was causing some headaches for code trying to parse JSON.
Also revise a prior partial fix that hard-coded 100% loss for the
case of zero packets.

Partially fixes #278.

Merge candidate for 3.0 and 3.1 bugfix branches.
2016-01-28 16:04:33 -08:00
Brian Tierney
3cf50d9856 added additional project 2016-01-03 08:16:52 -08:00