[netperf-dev] netperf2 commit notice r593 - in trunk: . doc
raj at netperf.org
raj at netperf.org
Tue Jun 19 14:05:40 PDT 2012
Author: raj
Date: 2012-06-19 14:05:40 -0700 (Tue, 19 Jun 2012)
New Revision: 593
Modified:
trunk/Release_Notes
trunk/doc/netperf.html
trunk/doc/netperf.info
trunk/doc/netperf.pdf
trunk/doc/netperf.texi
trunk/doc/netperf.txt
Log:
more nits
Modified: trunk/Release_Notes
===================================================================
--- trunk/Release_Notes 2012-06-19 21:01:06 UTC (rev 592)
+++ trunk/Release_Notes 2012-06-19 21:05:40 UTC (rev 593)
@@ -1,4 +1,4 @@
-These are the Release Notes for post Revision 2.5.0 top-of-trunk netperf:
+These are the Release Notes for Revision 2.6.0 of netperf:
*) Initial pass at support for --enable-intervals (WANT_INTERVALS) for
Windows, courtesy of Jonathan Cook.
Modified: trunk/doc/netperf.html
===================================================================
--- trunk/doc/netperf.html 2012-06-19 21:01:06 UTC (rev 592)
+++ trunk/doc/netperf.html 2012-06-19 21:05:40 UTC (rev 593)
@@ -1,8 +1,8 @@
<html lang="en">
<head>
-<title>Care and Feeding of Netperf 2.5.X</title>
+<title>Care and Feeding of Netperf 2.6.X</title>
<meta http-equiv="Content-Type" content="text/html">
-<meta name="description" content="Care and Feeding of Netperf 2.5.X">
+<meta name="description" content="Care and Feeding of Netperf 2.6.X">
<meta name="generator" content="makeinfo 4.13">
<link title="Top" rel="top" href="#Top">
<link href="http://www.gnu.org/software/texinfo/" rel="generator-home" title="Texinfo Homepage">
@@ -10,7 +10,7 @@
This is Rick Jones' feeble attempt at a Texinfo-based manual for the
netperf benchmark.
-Copyright (C) 2005-2011 Hewlett-Packard Company
+Copyright (C) 2005-2012 Hewlett-Packard Company
Permission is granted to copy, distribute and/or modify this
document per the terms of the netperf source license, a copy of
@@ -31,7 +31,7 @@
--></style>
</head>
<body>
-<h1 class="settitle">Care and Feeding of Netperf 2.5.X</h1>
+<h1 class="settitle">Care and Feeding of Netperf 2.6.X</h1>
<div class="contents">
<h2>Table of Contents</h2>
<ul>
@@ -147,7 +147,7 @@
<p>This is Rick Jones' feeble attempt at a Texinfo-based manual for the
netperf benchmark.
- <p>Copyright © 2005-2011 Hewlett-Packard Company
+ <p>Copyright © 2005-2012 Hewlett-Packard Company
<blockquote>
Permission is granted to copy, distribute and/or modify this document
per the terms of the netperf source license, a copy of which can be
@@ -372,7 +372,7 @@
<a href="http://www.netperf.org/svn/netperf2/tags">tagged</a> for retrieval
via subversion. For example, there is a tag for the first version
corresponding to this version of the manual -
-<a href="http://www.netperf.org/svn/netperf2/tags/netperf-2.5.0">netperf 2.5.0</a>. Those wishing to be on the bleeding edge of netperf
+<a href="http://www.netperf.org/svn/netperf2/tags/netperf-2.6.0">netperf 2.6.0</a>. Those wishing to be on the bleeding edge of netperf
development can use subversion to grab the
<a href="http://www.netperf.org/svn/netperf2/trunk">top of trunk</a>. When
fixing bugs or making enhancements, patches against the top-of-trunk
@@ -433,7 +433,7 @@
command. As of this writing, the configure script will not include
those tests automagically.
- <p><a name="index-g_t_002d_002denable_002domni_002c-Configure-8"></a>Starting with version 2.5.0, netperf is migrating most of the
+ <p><a name="index-g_t_002d_002denable_002domni_002c-Configure-8"></a>Starting with version 2.5.0, netperf began migrating most of the
“classic” netperf tests found in <samp><span class="file">src/nettest_bsd.c</span></samp> to the
so-called “omni” tests (aka “two routines to run them all”) found
in <samp><span class="file">src/nettest_omni.c</span></samp>. This migration enables a number of new
@@ -450,7 +450,7 @@
omni tests will not be compiled-in and the classic tests will not be
migrated.
- <p>Starting with version 2.5.0, netperf will include the “burst mode”
+ <p>Starting with version 2.5.0, netperf includes the “burst mode”
functionality in a default compilation of the bits. If you encounter
problems with this, please first attempt to obtain help via
<a href="mailto:netperf-talk at netperf.org">netperf-talk at netperf.org</a> or
@@ -1319,7 +1319,7 @@
<p>In an <a href="#The-Omni-Tests">omni</a> test the verbosity setting is largely
ignored, save for when asking for the time histogram to be displayed.
-In version 2.5.0 there is no <a href="#Omni-Output-Selectors">output selector</a> for the histogram and so it remains displayed only when the
+In version 2.5.0 and later there is no <a href="#Omni-Output-Selectors">output selector</a> for the histogram and so it remains displayed only when the
verbosity level is set to 2.
<p><a name="index-g_t_002dV_002c-Global-43"></a><br><dt><code>-V</code><dd>This option displays the netperf version and then exits.
Modified: trunk/doc/netperf.info
===================================================================
--- trunk/doc/netperf.info 2012-06-19 21:01:06 UTC (rev 592)
+++ trunk/doc/netperf.info 2012-06-19 21:05:40 UTC (rev 593)
@@ -4,7 +4,7 @@
This is Rick Jones' feeble attempt at a Texinfo-based manual for the
netperf benchmark.
- Copyright (C) 2005-2011 Hewlett-Packard Company
+ Copyright (C) 2005-2012 Hewlett-Packard Company
Permission is granted to copy, distribute and/or modify this
document per the terms of the netperf source license, a copy of
@@ -20,7 +20,7 @@
This is Rick Jones' feeble attempt at a Texinfo-based manual for the
netperf benchmark.
- Copyright (C) 2005-2011 Hewlett-Packard Company
+ Copyright (C) 2005-2012 Hewlett-Packard Company
Permission is granted to copy, distribute and/or modify this
document per the terms of the netperf source license, a copy of
@@ -222,8 +222,8 @@
The bits corresponding to each discrete release of netperf are
tagged (http://www.netperf.org/svn/netperf2/tags) for retrieval via
subversion. For example, there is a tag for the first version
-corresponding to this version of the manual - netperf 2.5.0
-(http://www.netperf.org/svn/netperf2/tags/netperf-2.5.0). Those
+corresponding to this version of the manual - netperf 2.6.0
+(http://www.netperf.org/svn/netperf2/tags/netperf-2.6.0). Those
wishing to be on the bleeding edge of netperf development can use
subversion to grab the top of trunk
(http://www.netperf.org/svn/netperf2/trunk). When fixing bugs or
@@ -278,7 +278,7 @@
command. As of this writing, the configure script will not include
those tests automagically.
- Starting with version 2.5.0, netperf is migrating most of the
+ Starting with version 2.5.0, netperf began migrating most of the
"classic" netperf tests found in `src/nettest_bsd.c' to the so-called
"omni" tests (aka "two routines to run them all") found in
`src/nettest_omni.c'. This migration enables a number of new features
@@ -292,7 +292,7 @@
`--enable-omni=no' to the configure command and the omni tests will not
be compiled-in and the classic tests will not be migrated.
- Starting with version 2.5.0, netperf will include the "burst mode"
+ Starting with version 2.5.0, netperf includes the "burst mode"
functionality in a default compilation of the bits. If you encounter
problems with this, please first attempt to obtain help via
<netperf-talk at netperf.org> or <netperf-feedback at netperf.org>. If that
@@ -1172,9 +1172,9 @@
In an *note omni: The Omni Tests. test the verbosity setting is
largely ignored, save for when asking for the time histogram to be
- displayed. In version 2.5.0 there is no *note output selector:
- Omni Output Selectors. for the histogram and so it remains
- displayed only when the verbosity level is set to 2.
+ displayed. In version 2.5.0 and later there is no *note output
+ selector: Omni Output Selectors. for the histogram and so it
+ remains displayed only when the verbosity level is set to 2.
`-V'
This option displays the netperf version and then exits.
@@ -4253,62 +4253,62 @@
Node: Installing Netperf5913
Node: Getting Netperf Bits7467
Node: Installing Netperf Bits9326
-Node: Verifying Installation17821
-Node: The Design of Netperf18525
-Node: CPU Utilization20121
-Node: CPU Utilization in a Virtual Guest28845
-Node: Global Command-line Options30432
-Node: Command-line Options Syntax30971
-Node: Global Options32367
-Node: Using Netperf to Measure Bulk Data Transfer56520
-Node: Issues in Bulk Transfer57193
-Node: Options common to TCP UDP and SCTP tests61454
-Node: TCP_STREAM67779
-Node: TCP_MAERTS71864
-Node: TCP_SENDFILE73101
-Node: UDP_STREAM75601
-Node: XTI_TCP_STREAM79037
-Node: XTI_UDP_STREAM79682
-Node: SCTP_STREAM80327
-Node: DLCO_STREAM81027
-Node: DLCL_STREAM83000
-Node: STREAM_STREAM83874
-Node: DG_STREAM84732
-Node: Using Netperf to Measure Request/Response85413
-Node: Issues in Request/Response87731
-Node: Options Common to TCP UDP and SCTP _RR tests90105
-Node: TCP_RR95129
-Node: TCP_CC97529
-Node: TCP_CRR99763
-Node: UDP_RR100825
-Node: XTI_TCP_RR103129
-Node: XTI_TCP_CC103712
-Node: XTI_TCP_CRR104217
-Node: XTI_UDP_RR104729
-Node: DLCL_RR105306
-Node: DLCO_RR105459
-Node: SCTP_RR105611
-Node: Using Netperf to Measure Aggregate Performance105747
-Node: Running Concurrent Netperf Tests106779
-Node: Issues in Running Concurrent Tests111420
-Node: Using --enable-burst113684
-Node: Using --enable-demo120583
-Node: Using Netperf to Measure Bidirectional Transfer126139
-Node: Bidirectional Transfer with Concurrent Tests127271
-Node: Bidirectional Transfer with TCP_RR129627
-Node: Implications of Concurrent Tests vs Burst Request/Response132011
-Node: The Omni Tests133825
-Node: Native Omni Tests134872
-Node: Migrated Tests140150
-Node: Omni Output Selection142255
-Node: Omni Output Selectors145238
-Node: Other Netperf Tests172946
-Node: CPU rate calibration173381
-Node: UUID Generation175749
-Node: Address Resolution176465
-Node: Enhancing Netperf178441
-Node: Netperf4179936
-Node: Concept Index180841
-Node: Option Index183167
+Node: Verifying Installation17820
+Node: The Design of Netperf18524
+Node: CPU Utilization20120
+Node: CPU Utilization in a Virtual Guest28844
+Node: Global Command-line Options30431
+Node: Command-line Options Syntax30970
+Node: Global Options32366
+Node: Using Netperf to Measure Bulk Data Transfer56529
+Node: Issues in Bulk Transfer57202
+Node: Options common to TCP UDP and SCTP tests61463
+Node: TCP_STREAM67788
+Node: TCP_MAERTS71873
+Node: TCP_SENDFILE73110
+Node: UDP_STREAM75610
+Node: XTI_TCP_STREAM79046
+Node: XTI_UDP_STREAM79691
+Node: SCTP_STREAM80336
+Node: DLCO_STREAM81036
+Node: DLCL_STREAM83009
+Node: STREAM_STREAM83883
+Node: DG_STREAM84741
+Node: Using Netperf to Measure Request/Response85422
+Node: Issues in Request/Response87740
+Node: Options Common to TCP UDP and SCTP _RR tests90114
+Node: TCP_RR95138
+Node: TCP_CC97538
+Node: TCP_CRR99772
+Node: UDP_RR100834
+Node: XTI_TCP_RR103138
+Node: XTI_TCP_CC103721
+Node: XTI_TCP_CRR104226
+Node: XTI_UDP_RR104738
+Node: DLCL_RR105315
+Node: DLCO_RR105468
+Node: SCTP_RR105620
+Node: Using Netperf to Measure Aggregate Performance105756
+Node: Running Concurrent Netperf Tests106788
+Node: Issues in Running Concurrent Tests111429
+Node: Using --enable-burst113693
+Node: Using --enable-demo120592
+Node: Using Netperf to Measure Bidirectional Transfer126148
+Node: Bidirectional Transfer with Concurrent Tests127280
+Node: Bidirectional Transfer with TCP_RR129636
+Node: Implications of Concurrent Tests vs Burst Request/Response132020
+Node: The Omni Tests133834
+Node: Native Omni Tests134881
+Node: Migrated Tests140159
+Node: Omni Output Selection142264
+Node: Omni Output Selectors145247
+Node: Other Netperf Tests172955
+Node: CPU rate calibration173390
+Node: UUID Generation175758
+Node: Address Resolution176474
+Node: Enhancing Netperf178450
+Node: Netperf4179945
+Node: Concept Index180850
+Node: Option Index183176
End Tag Table
Modified: trunk/doc/netperf.pdf
===================================================================
(Binary files differ)
Modified: trunk/doc/netperf.texi
===================================================================
(Binary files differ)
Modified: trunk/doc/netperf.txt
===================================================================
--- trunk/doc/netperf.txt 2012-06-19 21:01:06 UTC (rev 592)
+++ trunk/doc/netperf.txt 2012-06-19 21:05:40 UTC (rev 593)
@@ -45,7 +45,8 @@
7 Using Netperf to Measure Aggregate Performance
7.1 Running Concurrent Netperf Tests
7.1.1 Issues in Running Concurrent Tests
- 7.2 Using -enable-burst
+ 7.2 Using - -enable-burst
+ 7.3 Using - -enable-demo
8 Using Netperf to Measure Bidirectional Transfer
8.1 Bidirectional Transfer with Concurrent Tests
8.2 Bidirectional Transfer with TCP_RR
@@ -71,7 +72,7 @@
This is Rick Jones' feeble attempt at a Texinfo-based manual for the
netperf benchmark.
- Copyright (C) 2005-2011 Hewlett-Packard Company
+ Copyright (C) 2005-2012 Hewlett-Packard Company
Permission is granted to copy, distribute and/or modify this
document per the terms of the netperf source license, a copy of
@@ -232,8 +233,8 @@
The bits corresponding to each discrete release of netperf are
tagged (http://www.netperf.org/svn/netperf2/tags) for retrieval via
subversion. For example, there is a tag for the first version
-corresponding to this version of the manual - netperf 2.5.0
-(http://www.netperf.org/svn/netperf2/tags/netperf-2.5.0). Those
+corresponding to this version of the manual - netperf 2.6.0
+(http://www.netperf.org/svn/netperf2/tags/netperf-2.6.0). Those
wishing to be on the bleeding edge of netperf development can use
subversion to grab the top of trunk
(http://www.netperf.org/svn/netperf2/trunk). When fixing bugs or
@@ -285,7 +286,7 @@
command. As of this writing, the configure script will not include
those tests automagically.
- Starting with version 2.5.0, netperf is migrating most of the
+ Starting with version 2.5.0, netperf began migrating most of the
"classic" netperf tests found in `src/nettest_bsd.c' to the so-called
"omni" tests (aka "two routines to run them all") found in
`src/nettest_omni.c'. This migration enables a number of new features
@@ -299,7 +300,7 @@
`--enable-omni=no' to the configure command and the omni tests will not
be compiled-in and the classic tests will not be migrated.
- Starting with version 2.5.0, netperf will include the "burst mode"
+ Starting with version 2.5.0, netperf includes the "burst mode"
functionality in a default compilation of the bits. If you encounter
problems with this, please first attempt to obtain help via
<netperf-talk at netperf.org> or <netperf-feedback at netperf.org>. If that
@@ -1145,9 +1146,9 @@
In an *note omni: The Omni Tests. test the verbosity setting is
largely ignored, save for when asking for the time histogram to be
- displayed. In version 2.5.0 there is no *note output selector:
- Omni Output Selectors. for the histogram and so it remains
- displayed only when the verbosity level is set to 2.
+ displayed. In version 2.5.0 and later there is no *note output
+ selector: Omni Output Selectors. for the histogram and so it
+ remains displayed only when the verbosity level is set to 2.
`-V'
This option displays the netperf version and then exits.
@@ -1377,7 +1378,7 @@
units to be 2^30 (GB), 2^20 (MB) or 2^10 (KB) respectively. A
suffix of "g," "m" or "k" will specify units of 10^9, 10^6 or 10^3
bytes respectively. For example:
- `-s 128K'
+ `-S 128K'
Will request the remote send and receive socket buffer sizes to be
128KB or 131072 bytes.
@@ -1907,7 +1908,7 @@
units to be 2^30 (GB), 2^20 (MB) or 2^10 (KB) respectively. A
suffix of "g," "m" or "k" will specify units of 10^9, 10^6 or 10^3
bytes respectively. For example:
- `-s 128K'
+ `-S 128K'
Will request the remote (netserver) send and receive socket buffer
sizes to be 128KB or 131072 bytes.
@@ -2144,10 +2145,11 @@
netperf4 is ready for prime time, one can make use of the heuristics
and procedures mentioned here for the 85% solution.
- Basically, there are two ways to measure aggregate performance with
-netperf. The first is to run multiple, concurrent netperf tests and
-can be applied to any of the netperf tests. The second is to configure
-netperf with `--enable-burst' and is applicable to the TCP_RR test.
+ There are a few ways to measure aggregate performance with netperf.
+The first is to run multiple, concurrent netperf tests and can be
+applied to any of the netperf tests. The second is to configure
+netperf with `--enable-burst' and is applicable to the TCP_RR test. The
+third is a variation on the first.
7.1 Running Concurrent Netperf Tests
====================================
@@ -2179,7 +2181,16 @@
87380 16384 16384 10.03 233.96
We can take the sum of the results and be reasonably confident that
-the aggregate performance was 940 Mbits/s.
+the aggregate performance was 940 Mbits/s. This method does not need
+to be limited to one system speaking to one other system. It can be
+extended to one system talking to N other systems. It could be as
+simple as:
+ for host in 'foo bar baz bing'
+ do
+ netperf -t TCP_STREAM -H $hosts -i 10 -P 0 &
+ done
+ A more complicated/sophisticated example can be found in
+`doc/examples/runemomniagg2.sh' where.
If you see warnings about netperf not achieving the confidence
intervals, the best thing to do is to increase the number of iterations
@@ -2233,9 +2244,9 @@
You will notice that the tests completed in an order other than they
were started from the shell. This underscores why there is a threat of
-skew error and why netperf4 is the preferred tool for aggregate tests.
-Even if you see the Netperf Contributing Editor acting to the
-contrary!-)
+skew error and why netperf4 will eventually be the preferred tool for
+aggregate tests. Even if you see the Netperf Contributing Editor
+acting to the contrary!-)
7.1.1 Issues in Running Concurrent Tests
----------------------------------------
@@ -2263,9 +2274,21 @@
be wrong. One has to compute service demands for concurrent tests by
hand
-7.2 Using -enable-burst
-=======================
+ Running concurrent tests can also become difficult when there is no
+one "central" node. Running tests between pairs of systems may be more
+difficult, calling for remote shell commands in the for loop rather
+than netperf commands. This introduces more skew error, which the
+confidence intervals may not be able to sufficiently mitigate. One
+possibility is to actually run three consecutive netperf tests on each
+node - the first being a warm-up, the last being a cool-down. The idea
+then is to ensure that the time it takes to get all the netperfs
+started is less than the length of the first netperf command in the
+sequence of three. Similarly, it assumes that all "middle" netperfs
+will complete before the first of the "last" netperfs complete.
+7.2 Using - -enable-burst
+=========================
+
Starting in version 2.5.0 `--enable-burst=yes' is the default, which
means one no longer must:
@@ -2445,6 +2468,106 @@
if the sum of the lost requests and responses reaches the value
specified in the test-specific `-b' option.
+7.3 Using - -enable-demo
+========================
+
+One can
+ configure --enable-demo
+ and compile netperf to enable netperf to emit "interim results" at
+semi-regular intervals. This enables a global `-D' option which takes
+a reporting interval as an argument. With that specified, the output
+of netperf will then look something like
+
+ $ src/netperf -D 1.25
+ MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to localhost.localdomain () port 0 AF_INET : demo
+ Interim result: 25425.52 10^6bits/s over 1.25 seconds ending at 1327962078.405
+ Interim result: 25486.82 10^6bits/s over 1.25 seconds ending at 1327962079.655
+ Interim result: 25474.96 10^6bits/s over 1.25 seconds ending at 1327962080.905
+ Interim result: 25523.49 10^6bits/s over 1.25 seconds ending at 1327962082.155
+ Interim result: 25053.57 10^6bits/s over 1.27 seconds ending at 1327962083.429
+ Interim result: 25349.64 10^6bits/s over 1.25 seconds ending at 1327962084.679
+ Interim result: 25292.84 10^6bits/s over 1.25 seconds ending at 1327962085.932
+ Recv Send Send
+ Socket Socket Message Elapsed
+ Size Size Size Time Throughput
+ bytes bytes bytes secs. 10^6bits/sec
+
+ 87380 16384 16384 10.00 25375.66
+ The units of the "Interim result" lines will follow the units
+selected via the global `-f' option. If the test-specific `-o' option
+is specified on the command line, the format will be CSV:
+ ...
+ 2978.81,MBytes/s,1.25,1327962298.035
+ ...
+ If the test-specific `-k' option is used the format will be keyval
+with each keyval being given an index:
+ ...
+ NETPERF_INTERIM_RESULT[2]=25.00
+ NETPERF_UNITS[2]=10^9bits/s
+ NETPERF_INTERVAL[2]=1.25
+ NETPERF_ENDING[2]=1327962357.249
+ ...
+ The expectation is it may be easier to utilize the keyvals if they
+have indices.
+
+ But how does this help with aggregate tests? Well, what one can do
+is start the netperfs via a script, giving each a Very Long (tm) run
+time. Direct the output to a file per instance. Then, once all the
+netperfs have been started, take a timestamp and wait for some desired
+test interval. Once that interval expires take another timestamp and
+then start terminating the netperfs by sending them a SIGALRM signal
+via the likes of the `kill' or `pkill' command. The netperfs will
+terminate and emit the rest of the "usual" output, and you can then
+bring the files to a central location for post processing to find the
+aggregate performance over the "test interval."
+
+ This method has the advantage that it does not require advance
+knowledge of how long it takes to get netperf tests started and/or
+stopped. It does though require sufficiently synchronized clocks on
+all the test systems.
+
+ While calls to get the current time can be inexpensive, that neither
+has been nor is universally true. For that reason netperf tries to
+minimize the number of such "timestamping" calls (eg `gettimeofday')
+calls it makes when in demo mode. Rather than take a timestamp after
+each `send' or `recv' call completes netperf tries to guess how many
+units of work will be performed over the desired interval. Only once
+that many units of work have been completed will netperf check the
+time. If the reporting interval has passed, netperf will emit an
+"interim result." If the interval has not passed, netperf will update
+its estimate for units and continue.
+
+ After a bit of thought one can see that if things "speed-up" netperf
+will still honor the interval. However, if things "slow-down" netperf
+may be late with an "interim result." Here is an example of both of
+those happening during a test - with the interval being honored while
+throughput increases, and then about half-way through when another
+netperf (not shown) is started we see things slowing down and netperf
+not hitting the interval as desired.
+ $ src/netperf -D 2 -H tardy.hpl.hp.com -l 20
+ MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to tardy.hpl.hp.com () port 0 AF_INET : demo
+ Interim result: 36.46 10^6bits/s over 2.01 seconds ending at 1327963880.565
+ Interim result: 59.19 10^6bits/s over 2.00 seconds ending at 1327963882.569
+ Interim result: 73.39 10^6bits/s over 2.01 seconds ending at 1327963884.576
+ Interim result: 84.01 10^6bits/s over 2.03 seconds ending at 1327963886.603
+ Interim result: 75.63 10^6bits/s over 2.21 seconds ending at 1327963888.814
+ Interim result: 55.52 10^6bits/s over 2.72 seconds ending at 1327963891.538
+ Interim result: 70.94 10^6bits/s over 2.11 seconds ending at 1327963893.650
+ Interim result: 80.66 10^6bits/s over 2.13 seconds ending at 1327963895.777
+ Interim result: 86.42 10^6bits/s over 2.12 seconds ending at 1327963897.901
+ Recv Send Send
+ Socket Socket Message Elapsed
+ Size Size Size Time Throughput
+ bytes bytes bytes secs. 10^6bits/sec
+
+ 87380 16384 16384 20.34 68.87
+ So long as your post-processing mechanism can account for that, there
+should be no problem. As time passes there may be changes to try to
+improve the netperf's honoring the interval but one should not ass-u-me
+it will always do so. One should not assume the precision will remain
+fixed - future versions may change it - perhaps going beyond tenths of
+seconds in reporting the interval length etc.
+
8 Using Netperf to Measure Bidirectional Transfer
*************************************************
@@ -3741,99 +3864,99 @@
Concept Index
*************
-Aggregate Performance: See 7. (line 2141)
-Bandwidth Limitation: See 2.2. (line 316)
-Connection Latency: See 6.2.2. (line 1984)
-CPU Utilization: See 3.1. (line 465)
-Design of Netperf: See 3. (line 435)
-Installation: See 2. (line 197)
-Introduction: See 1. (line 84)
-Latency, Connection Establishment <1>: See 6.2.7. (line 2111)
-Latency, Connection Establishment <2>: See 6.2.6. (line 2101)
-Latency, Connection Establishment <3>: See 6.2.3. (line 2027)
-Latency, Connection Establishment: See 6.2.2. (line 1984)
-Latency, Request-Response <1>: See 6.2.11. (line 2138)
-Latency, Request-Response <2>: See 6.2.10. (line 2135)
-Latency, Request-Response <3>: See 6.2.9. (line 2132)
-Latency, Request-Response <4>: See 6.2.8. (line 2121)
-Latency, Request-Response <5>: See 6.2.7. (line 2111)
-Latency, Request-Response <6>: See 6.2.5. (line 2090)
-Latency, Request-Response <7>: See 6.2.4. (line 2047)
-Latency, Request-Response <8>: See 6.2.3. (line 2027)
-Latency, Request-Response: See 6.2.1. (line 1935)
-Limiting Bandwidth <1>: See 5.2.4. (line 1563)
-Limiting Bandwidth: See 2.2. (line 316)
-Measuring Latency: See 6.2.1. (line 1935)
-Packet Loss: See 6.2.4. (line 2047)
-Port Reuse: See 6.2.2. (line 1991)
-TIME_WAIT: See 6.2.2. (line 1991)
+Aggregate Performance: See 7. (line 2142)
+Bandwidth Limitation: See 2.2. (line 317)
+Connection Latency: See 6.2.2. (line 1985)
+CPU Utilization: See 3.1. (line 466)
+Design of Netperf: See 3. (line 436)
+Installation: See 2. (line 198)
+Introduction: See 1. (line 85)
+Latency, Connection Establishment <1>: See 6.2.7. (line 2112)
+Latency, Connection Establishment <2>: See 6.2.6. (line 2102)
+Latency, Connection Establishment <3>: See 6.2.3. (line 2028)
+Latency, Connection Establishment: See 6.2.2. (line 1985)
+Latency, Request-Response <1>: See 6.2.11. (line 2139)
+Latency, Request-Response <2>: See 6.2.10. (line 2136)
+Latency, Request-Response <3>: See 6.2.9. (line 2133)
+Latency, Request-Response <4>: See 6.2.8. (line 2122)
+Latency, Request-Response <5>: See 6.2.7. (line 2112)
+Latency, Request-Response <6>: See 6.2.5. (line 2091)
+Latency, Request-Response <7>: See 6.2.4. (line 2048)
+Latency, Request-Response <8>: See 6.2.3. (line 2028)
+Latency, Request-Response: See 6.2.1. (line 1936)
+Limiting Bandwidth <1>: See 5.2.4. (line 1564)
+Limiting Bandwidth: See 2.2. (line 317)
+Measuring Latency: See 6.2.1. (line 1936)
+Packet Loss: See 6.2.4. (line 2048)
+Port Reuse: See 6.2.2. (line 1992)
+TIME_WAIT: See 6.2.2. (line 1992)
Option Index
************
---enable-burst, Configure: See 7. (line 2141)
---enable-cpuutil, Configure: See 2.2. (line 276)
---enable-dlpi, Configure: See 2.2. (line 282)
---enable-histogram, Configure: See 2.2. (line 316)
---enable-intervals, Configure: See 2.2. (line 316)
---enable-omni, Configure: See 2.2. (line 288)
---enable-sctp, Configure: See 2.2. (line 282)
---enable-unixdomain, Configure: See 2.2. (line 282)
---enable-xti, Configure: See 2.2. (line 282)
--4, Global: See 4.2. (line 1173)
--4, Test-specific <1>: See 6.2. (line 1921)
--4, Test-specific: See 5.2. (line 1394)
--6 Test-specific: See 6.2. (line 1927)
--6, Global: See 4.2. (line 1182)
--6, Test-specific: See 5.2. (line 1400)
--A, Global: See 4.2. (line 702)
--a, Global: See 4.2. (line 690)
--B, Global: See 4.2. (line 713)
--b, Global: See 4.2. (line 706)
--C, Global: See 4.2. (line 726)
--c, Global: See 4.2. (line 717)
--c, Test-specific: See 9.1. (line 2623)
--D, Global: See 4.2. (line 740)
--d, Global: See 4.2. (line 731)
--d, Test-specific: See 9.1. (line 2627)
--F, Global: See 4.2. (line 760)
--f, Global: See 4.2. (line 751)
--H, Global: See 4.2. (line 779)
--h, Global: See 4.2. (line 775)
--H, Test-specific: See 6.2. (line 1850)
--h, Test-specific <1>: See 6.2. (line 1843)
--h, Test-specific: See 5.2. (line 1294)
--i, Global: See 4.2. (line 863)
--I, Global: See 4.2. (line 814)
--j, Global: See 4.2. (line 889)
--k, Test-specific: See 9.1. (line 2647)
--L, Global: See 4.2. (line 947)
--l, Global: See 4.2. (line 926)
--L, Test-specific <1>: See 6.2. (line 1859)
--L, Test-specific: See 5.2. (line 1309)
--M, Test-specific: See 5.2. (line 1332)
--m, Test-specific: See 5.2. (line 1316)
--N, Global: See 4.2. (line 977)
--n, Global: See 4.2. (line 959)
--O, Global: See 4.2. (line 1022)
--o, Global: See 4.2. (line 1013)
--O, Test-specific: See 9.1. (line 2672)
--o, Test-specific: See 9.1. (line 2660)
--P, Global: See 4.2. (line 1047)
--p, Global: See 4.2. (line 1027)
--P, Test-specific <1>: See 6.2. (line 1866)
--P, Test-specific: See 5.2. (line 1345)
--r, Test-specific: See 6.2. (line 1869)
--S Test-specific: See 5.2. (line 1371)
--S, Global: See 4.2. (line 1065)
--s, Global: See 4.2. (line 1056)
--S, Test-specific: See 6.2. (line 1901)
--s, Test-specific <1>: See 6.2. (line 1881)
--s, Test-specific: See 5.2. (line 1348)
--T, Global: See 4.2. (line 1107)
--t, Global: See 4.2. (line 1075)
--T, Test-specific: See 9.1. (line 2691)
--t, Test-specific: See 9.1. (line 2686)
--V, Global: See 4.2. (line 1152)
--v, Global: See 4.2. (line 1124)
--W, Global: See 4.2. (line 1164)
--w, Global: See 4.2. (line 1157)
+--enable-burst, Configure: See 7. (line 2142)
+--enable-cpuutil, Configure: See 2.2. (line 277)
+--enable-dlpi, Configure: See 2.2. (line 283)
+--enable-histogram, Configure: See 2.2. (line 317)
+--enable-intervals, Configure: See 2.2. (line 317)
+--enable-omni, Configure: See 2.2. (line 289)
+--enable-sctp, Configure: See 2.2. (line 283)
+--enable-unixdomain, Configure: See 2.2. (line 283)
+--enable-xti, Configure: See 2.2. (line 283)
+-4, Global: See 4.2. (line 1174)
+-4, Test-specific <1>: See 6.2. (line 1922)
+-4, Test-specific: See 5.2. (line 1395)
+-6 Test-specific: See 6.2. (line 1928)
+-6, Global: See 4.2. (line 1183)
+-6, Test-specific: See 5.2. (line 1401)
+-A, Global: See 4.2. (line 703)
+-a, Global: See 4.2. (line 691)
+-B, Global: See 4.2. (line 714)
+-b, Global: See 4.2. (line 707)
+-C, Global: See 4.2. (line 727)
+-c, Global: See 4.2. (line 718)
+-c, Test-specific: See 9.1. (line 2746)
+-D, Global: See 4.2. (line 741)
+-d, Global: See 4.2. (line 732)
+-d, Test-specific: See 9.1. (line 2750)
+-F, Global: See 4.2. (line 761)
+-f, Global: See 4.2. (line 752)
+-H, Global: See 4.2. (line 780)
+-h, Global: See 4.2. (line 776)
+-H, Test-specific: See 6.2. (line 1851)
+-h, Test-specific <1>: See 6.2. (line 1844)
+-h, Test-specific: See 5.2. (line 1295)
+-i, Global: See 4.2. (line 864)
+-I, Global: See 4.2. (line 815)
+-j, Global: See 4.2. (line 890)
+-k, Test-specific: See 9.1. (line 2770)
+-L, Global: See 4.2. (line 948)
+-l, Global: See 4.2. (line 927)
+-L, Test-specific <1>: See 6.2. (line 1860)
+-L, Test-specific: See 5.2. (line 1310)
+-M, Test-specific: See 5.2. (line 1333)
+-m, Test-specific: See 5.2. (line 1317)
+-N, Global: See 4.2. (line 978)
+-n, Global: See 4.2. (line 960)
+-O, Global: See 4.2. (line 1023)
+-o, Global: See 4.2. (line 1014)
+-O, Test-specific: See 9.1. (line 2795)
+-o, Test-specific: See 9.1. (line 2783)
+-P, Global: See 4.2. (line 1048)
+-p, Global: See 4.2. (line 1028)
+-P, Test-specific <1>: See 6.2. (line 1867)
+-P, Test-specific: See 5.2. (line 1346)
+-r, Test-specific: See 6.2. (line 1870)
+-S Test-specific: See 5.2. (line 1372)
+-S, Global: See 4.2. (line 1066)
+-s, Global: See 4.2. (line 1057)
+-S, Test-specific: See 6.2. (line 1902)
+-s, Test-specific <1>: See 6.2. (line 1882)
+-s, Test-specific: See 5.2. (line 1349)
+-T, Global: See 4.2. (line 1108)
+-t, Global: See 4.2. (line 1076)
+-T, Test-specific: See 9.1. (line 2814)
+-t, Test-specific: See 9.1. (line 2809)
+-V, Global: See 4.2. (line 1153)
+-v, Global: See 4.2. (line 1125)
+-W, Global: See 4.2. (line 1165)
+-w, Global: See 4.2. (line 1158)
More information about the netperf-dev
mailing list