1sockperf(3)                        sockperf                        sockperf(3)
2
3
4

NAME

6       sockperfSockPerf is a tool for network performance measurement written
7       in C++.
8

1. SUMMARY

10       SockPerf is a network testing tool oriented to measure network latency
11       and also spikes of network latency. Tool can create UDP/TCP data
12       streams and measure the throughput and latency of a network that is
13       carrying them. SockPerf allows the user to define different parameters
14       that can be used for testing a network, or alternately for optimizing
15       or tuning a network. Tool provides a client and server functionality,
16       and can measure the throughput and latency between the two end-points,
17       either unidirectionally or bidirectionally. This utility can be used in
18       Linux systems.
19

2. INTRODUCTION

21       People are often concerned about measuring the maximum data throughput
22       rate of a communications link or network access. A typical method of
23       performing a measurement is to transfer a 'large' file and measure the
24       time taken to do so. The throughput is then calculated by dividing the
25       file size by the time to get the throughput in megabits, kilobits, or
26       bits per second. Unfortunately, the results of such an exercise will
27       result in the goodput which is less than the maximum throughput,
28       leading to people believing that their communications link is not
29       operating correctly. In fact, there are many overheads accounted for in
30       good case in addition to transmission overheads, including latency, TCP
31       Receive Window size and machine limitations, which means the calculated
32       goodput does not reflect the maximum achievable throughput.
33
34       Another important thing of tool capacity is latency measurement.
35       Latency - is the time it takes packet to go from user space program on
36       one machine to user space program on another machine. Being able to
37       quantify latency in terms other than millisecond response time is
38       important when determining the quality of a network. One of available
39       tool that can help administrators do just that is Sockperf.
40
41       SockPerf works as an on-demand client and server test. How this works
42       is that one system runs the Sockperf server over a specified port and
43       another system functions as a client running the Sockperf client. The
44       binaries are the same, and there is an option to have the role of
45       client or server, so the roles can easily be reversed if necessary.
46

3. OVERVIEW

48       Sockperf tests UDP/TCP network connection and maintenance following
49       functionality:
50
51       · Measure latency;
52
53       · Measure TX/RX bandwidth;
54
55       · Measure packet loss;
56
57       · Multicast;
58
59       · Multi-threaded;
60
61       features:
62
63       · Measure the RTT of packets in descrete way;
64
65       · Provide full log of packet times;
66
67       · Provide few modes to monitor multiple file descriptors as
68         recvfrom/select/poll/epoll;
69
70       · Improved CPU utilization;
71
72       Initially the tool was developed to demonstrate advantages of
73       Mellanox's Messaging Accelerator (VMA). VMA is a socket API based,
74       dynamically linked, user space Linux library which serves to
75       transparently enhance the performance of Multicast/UDP/TCP networking
76       heavy applications over the InfiniBand and Ethernet network. More
77       interested user can read detail information at http://www.mellanox.com.
78       Actually Sockperf can be used natively, or with VMA acceleration and
79       see the benefit of VMA.
80
81       SockPerf operates by sending packets from the client to the server,
82       which then sends the packets back to the client. This measured round
83       trip time is the route trip time (RTT) between the two machines on a
84       specific network path. The average RTT is calculated by dividing the
85       total number of packets that perform this round trip by some fixed
86       period of time. The average latency for a given one-way path between
87       the two machines is the average RTT divided by two.
88
89       SockPerf can work as server or execute under-load, ping-pong, playback
90       and throughput tests and be a server or a client.
91
92       SockPerf can be launched in single point manner that is name as the
93       first mode and using special formatted feed file named as the second
94       mode.
95
96       Mode One:
97
98       $sockperf server -i 224.18.7.81 -p 5001
99       sockperf: == version #3.5-no.git ==
100       sockperf: [SERVER] listen on:
101       [ 0] IP = 224.18.7.81     PORT =  5001 # UDP
102       sockperf: Warmup stage (sending a few dummy messages)...
103       sockperf: [tid 4701] using recvfrom() to block on socket(s
104
105
106       Mode Two:
107
108       $sockperf server -f conf.file -F e
109       sockperf: == version #3.5-no.git ==
110       sockperf: [SERVER] listen on:
111       [ 0] IP = 5.2.1.3        PORT =  6671 # TCP
112       [ 1] IP = 5.2.1.3        PORT =  6672 # TCP
113       [ 2] IP = 5.2.1.3        PORT =  6673 # TCP
114       [ 3] IP = 5.2.1.3        PORT =  6674 # TCP
115       [ 4] IP = 5.2.1.3        PORT =  6675 # TCP
116       sockperf: Warmup stage (sending a few dummy messages)...
117       sockperf: [tid 4805] using epoll() to block on socket(s)
118
119
120       Every line in feed file should have following format as
121
122       where
123
124       · [U|T] - UDP or TCP protocol;
125
126       · address - Internet Protocol (IP) address;
127
128       · port - Port number;
129
130   3.1 Available options
131       The following table describes Sockperf options, and their possible
132       values:
133
134       -h,-?   --help,--usage         -Show the help message and exit.
135               --tcp                  -Use TCP protocol (default UDP).
136       -i      --ip                   -Listen on/send to ip <ip>.
137       -p      --port                 -Listen on/connect to port <port> (default 11111).
138       -f      --file                 -Read list of connections from file (used in pair with -F option).
139       -F      --iomux-type           -Type of multiple file descriptors handle [s|select|p|poll|e|epoll|r|recvfrom|x|socketxtreme](default epoll).
140               --timeout              -Set select/poll/epoll timeout to <msec>, -1 for infinite (default is 10 msec).
141       -a      --activity             -Measure activity by printing a '.' for the last <N> messages processed.
142       -A      --Activity             -Measure activity by printing the duration for last <N>  messages processed.
143               --tcp-avoid-nodelay    -Stop/Start delivering TCP Messages Immediately (Enable/Disable Nagel). Default is Nagel Disabled except in Throughput where the default is Nagel enabled.
144               --tcp-skip-blocking-send
145                                      -Enables non-blocking send operation (default OFF).
146               --tos                  -Allows setting tos
147               --mc-rx-if             -Set address <ip> of interface on which to receive multicast messages (can be other then route table).
148               --mc-tx-if             -Set address <ip> of interface on which to transmit multicast messages (can be other then route table).
149               --mc-loopback-enable   -Enables mc loopback (default disabled).
150               --mc-ttl               -Limit the lifetime of the message (default 2).
151               --mc-source-filter     -Set address <ip, hostname> of multicast messages source which is allowed to receive from.
152               --uc-reuseaddr         -Enables unicast reuse address (default disabled).
153               --lls                  -Turn on LLS via socket option (value = usec to poll).
154               --buffer-size          -Set total socket receive/send buffer <size> in bytes (system defined by default).
155               --nonblocked           -Open non-blocked sockets.
156               --recv_looping_num     -Set Sockperf to loop over recvfrom() until EAGAIN or <N> good received packets, -1 for infinite, must be used with --nonblocked (default 1).
157               --dontwarmup           -Don't send warm up messages on start.
158               --pre-warmup-wait      -Time to wait before sending warm up messages (seconds).
159               --vmazcopyread         -Use VMA's zero copy reads API (See VMA's readme).
160               --daemonize            -Run as daemon.
161               --no-rdtsc             -Don't use register when taking time; instead use monotonic clock.
162               --load-vma             -Load VMA dynamically even when LD_PRELOAD was not used.
163               --rate-limit           -use rate limit (packet-pacing), with VMA must be run with VMA_RING_ALLOCATION_LOGIC_TX mode.
164               --set-sock-accl        -Set socket acceleration before run (available for some of Mellanox systems)
165       -d      --debug                -Print extra debug information.
166
167
168   3.2 Server
169       Server options are:
170
171               --threads-num          -Run <N> threads on server side (requires '-f' option).
172               --cpu-affinity         -Set threads affinity to the given core ids in list format (see: cat /proc/cpuinfo).
173               --vmarxfiltercb        -Use VMA's receive path message filter callback API (See VMA's readme).
174               --force-unicast-reply  -Force server to reply via unicast.
175               --dont-reply           -Server won't reply to the client messages.
176       -m      --msg-size             -Set maximum message size that the server can receive <size> bytes (default 65507).
177       -g      --gap-detection        -Enable gap-detection.
178
179
180   3.3 Client
181       Sockperf supports different scenarios to run itself as a client. There
182       are under-load, ping-pong, playback and throughput subcommands to
183       select one of the scenarios.
184
185       · under-load - run sockperf client for latency under load test;
186
187       · ping-pong - run sockperf client for latency test in ping pong mode;
188
189       · playback - run sockperf client for latency test using playback of
190         predefined traffic, based on timeline and message size;
191
192       · throughput - run sockperf client for one way throughput test;
193
194       General client options are:
195
196               --srv-num              -Set num of servers the client works with to N.
197               --sender-affinity      -Set sender thread affinity to the given core ids in list format (see: cat /proc/cpuinfo).
198               --receiver-affinity    -Set receiver thread affinity to the given core ids in list format (see: cat /proc/cpuinfo).
199               --full-log             -Dump full log of all messages send/receive time to the given file in CSV format.
200               --giga-size            -Print sizes in GigaByte.
201               --increase_output_precision
202                                      -Increase number of digits after decimal point of the throughput output (from 3 to 9).
203               --dummy-send           -Use VMA's dummy send API instead of busy wait, must be higher than regular msg rate.
204                                       optional: set dummy-send rate per second (default 10,000), usage: --dummy-send [<rate>|max]
205       -t      --time                 -Run for <sec> seconds (default 1, max = 36000000).
206               --client_port          -Force the client side to bind to a specific port (default = 0).
207               --client_ip            -Force the client side to bind to a specific ip address (default = 0).
208       -b      --burst                -Control the client's number of a messages sent in every burst.
209               --mps                  -Set number of messages-per-second (default = 10000 - for under-load mode, or max - for ping-pong and throughput modes; for maximum use --mps=max;
210                                       support --pps for old compatibility).
211       -m      --msg-size             -Use messages of size <size> bytes (minimum default 14).
212       -r      --range                -comes with -m <size>, randomly change the messages size in range: <size> +- <N>.
213               --data-integrity       -Perform data integrity test
214
215
216   3.4 Tools
217       SockPerf package contains few scripts that allow to generate special
218       formatted file to launch tool in different configurations.
219
220       · filter.awk - can be used for filtering lines from the full log file
221         based on given latency range;
222
223       · gen1.awk - this awk script generates playback files (it is for stable
224         PPS playback file);
225
226       · gen2.awk - this awk script generates playback files using the input
227         for this script is file with lines of the format: startTime;
228         duration; startPPS; endPPS; msgSize (it is for linear increased and
229         decreased PPS playback file);
230
231          create playback file using gen1.awk > pfile
232          generated file:
233       # ==== playback file for sockperf - generated by gen1.awk ====
234       #baseTime=1.000000; PPS=200000; runtime=1.000000; interval=0.000005; NUM_RECORDS=200000
235       # file contains 200000 records
236       1.000005000, 12
237       1.000010000, 12
238       1.000015000, 12
239       1.000020000, 12
240       1.000025000, 12
241       1.000030000, 12
242       1.000035000, 12
243       1.000040000, 12
244       ...
245       1.999950000, 12
246       1.999955000, 12
247       1.999960000, 12
248       1.999965000, 12
249       1.999970000, 12
250       1.999975000, 12
251       1.999980000, 12
252       1.999985000, 12
253       1.999990000, 12
254       1.999995000, 12
255       2.000000000, 12
256       #200000 records were written successfully
257          start server on ipX
258          start client using: ./sockperf ping-pong -i <ip-address> -p <port> --playback=pfile
259
260   3.5 Usage
261   3.5.1 Running Multicast over IPoIB
262       · Configure the routing table to map multicast addresses to the IPoIB
263         interface on both client and server machines, as follows:
264
265       route add -net 224.0.0.0 netmask 240.0.0.0 dev ib0
266
267
268        In this case, ib0 is the IPoIB interface.
269
270       · Run the server as follows:
271
272       $sockperf server -i 224.18.7.81 -p 5001
273       sockperf: == version #3.5-no.git ==
274       sockperf: [SERVER] listen on:
275       [ 0] IP = 224.18.7.81     PORT =  5001 # UDP
276       sockperf: Warmup stage (sending a few dummy messages)...
277       sockperf: [tid 30399] using recvfrom() to block on socket(s)
278
279
280       · Run the client as follows:
281
282       $sockperf ping-pong -i 224.18.7.81 -p 5001 -m 16384 -t 10 --mps=max
283       sockperf: == version #3.5-no.git ==
284       sockperf[CLIENT] send on:sockperf: using recvfrom() to block on socket(s)
285
286       [ 0] IP = 224.18.7.81     PORT =  5001 # UDP
287       sockperf: Warmup stage (sending a few dummy messages)...
288       sockperf: Starting test...
289       sockperf: Test end (interrupted by timer)
290       sockperf: Test ended
291       sockperf: [Total Run] RunTime=10.000 sec; Warm up time=400 msec; SentMessages=240464; ReceivedMessages=240463
292       sockperf: ========= Printing statistics for Server No: 0
293       sockperf: [Valid Duration] RunTime=9.550 sec; SentMessages=229630; ReceivedMessages=229630
294       sockperf: ====> avg-lat= 20.771 (std-dev=5.266)
295       sockperf: # dropped messages = 0; # duplicated messages = 0; # out-of-order messages = 0
296       sockperf: Summary: Latency is 20.771 usec
297       sockperf: Total 229630 observations; each percentile contains 2296.30 observations
298       sockperf: ---> <MAX> observation =  120.108
299       sockperf: ---> percentile 99.999 =  106.349
300       sockperf: ---> percentile 99.990 =   63.772
301       sockperf: ---> percentile 99.900 =   55.940
302       sockperf: ---> percentile 99.000 =   48.619
303       sockperf: ---> percentile 90.000 =   24.295
304       sockperf: ---> percentile 75.000 =   20.358
305       sockperf: ---> percentile 50.000 =   19.279
306       sockperf: ---> percentile 25.000 =   18.641
307       sockperf: ---> <MIN> observation =   16.748
308
309
310   3.5.2 Running TCP over Ethernet
311       · Run the server as follows:
312
313       $sockperf server -i 22.0.0.3 -p 5001 --tcp
314       sockperf: == version #3.5-no.git ==
315       sockperf: [SERVER] listen on:
316       [ 0] IP = 22.0.0.3        PORT =  5001 # TCP
317       sockperf: Warmup stage (sending a few dummy messages)...
318       sockperf: [tid 1567] using recvfrom() to block on socket(s)
319
320
321       · Run the client as follows:
322
323       $sockperf ping-pong -i 22.0.0.3 -p 5001 --tcp -m 64 -t 10 --mps=max
324       sockperf: == version #3.5-no.git ==
325       sockperf[CLIENT] send on:sockperf: using recvfrom() to block on socket(s)
326
327       [ 0] IP = 22.0.0.3        PORT =  5001 # TCP
328       sockperf: Warmup stage (sending a few dummy messages)...
329       sockperf: Starting test...
330       sockperf: Test end (interrupted by timer)
331       sockperf: Test ended
332       sockperf: [Total Run] RunTime=10.000 sec; Warm up time=400 msec; SentMessages=553625; ReceivedMessages=553624
333       sockperf: ========= Printing statistics for Server No: 0
334       sockperf: [Valid Duration] RunTime=9.550 sec; SentMessages=528579; ReceivedMessages=528579
335       sockperf: ====> avg-lat=  9.017 (std-dev=4.171)
336       sockperf: # dropped messages = 0; # duplicated messages = 0; # out-of-order messages = 0
337       sockperf: Summary: Latency is 9.017 usec
338       sockperf: Total 528579 observations; each percentile contains 5285.79 observations
339       sockperf: ---> <MAX> observation =   98.777
340       sockperf: ---> percentile 99.999 =   72.628
341       sockperf: ---> percentile 99.990 =   17.980
342       sockperf: ---> percentile 99.900 =   16.824
343       sockperf: ---> percentile 99.000 =   16.193
344       sockperf: ---> percentile 90.000 =   14.731
345       sockperf: ---> percentile 75.000 =   14.301
346       sockperf: ---> percentile 50.000 =    6.222
347       sockperf: ---> percentile 25.000 =    5.759
348       sockperf: ---> <MIN> observation =    4.629
349
350
351   3.5.3 Running UDP over Ethernet using VMA
352       · More interested user can read detail information about VMA at
353         http://www.mellanox.com.
354
355       · VMA_SPEC=latency is a predefined specification profile for latency.
356
357       · Run the server as follows:
358
359       $VMA_SPEC=latency LD_PRELOAD=libvma.so sockperf server -i 22.0.0.3 -p 5001
360        VMA INFO: ---------------------------------------------------------------------------
361        VMA INFO: VMA_VERSION: 8.6.10-0 Development Snapshot built on Jun 27 2018 16:06:47
362        VMA INFO: Cmd Line: sockperf server -i 22.0.0.3 -p 5001
363        VMA INFO: Current Time: Tue Sep 18 08:49:23 2018
364        VMA INFO: Pid:  2201
365        VMA INFO: OFED Version: MLNX_OFED_LINUX-4.4-1.0.0.0:
366        VMA INFO: Architecture: x86_64
367        VMA INFO: Node: r-aa-apollo03.mtr.labs.mlnx
368        VMA INFO: ---------------------------------------------------------------------------
369        VMA INFO: VMA Spec                       Latency                    [VMA_SPEC]
370        VMA INFO: Log Level                      INFO                       [VMA_TRACELEVEL]
371        VMA INFO: Ring On Device Memory TX       16384                      [VMA_RING_DEV_MEM_TX]
372        VMA INFO: Tx QP WRE                      256                        [VMA_TX_WRE]
373        VMA INFO: Tx QP WRE Batching             4                          [VMA_TX_WRE_BATCHING]
374        VMA INFO: Rx QP WRE                      256                        [VMA_RX_WRE]
375        VMA INFO: Rx QP WRE Batching             4                          [VMA_RX_WRE_BATCHING]
376        VMA INFO: Rx Poll Loops                  -1                         [VMA_RX_POLL]
377        VMA INFO: Rx Prefetch Bytes Before Poll  256                        [VMA_RX_PREFETCH_BYTES_BEFORE_POLL]
378        VMA INFO: GRO max streams                0                          [VMA_GRO_STREAMS_MAX]
379        VMA INFO: Select Poll (usec)             -1                         [VMA_SELECT_POLL]
380        VMA INFO: Select Poll OS Force           Enabled                    [VMA_SELECT_POLL_OS_FORCE]
381        VMA INFO: Select Poll OS Ratio           1                          [VMA_SELECT_POLL_OS_RATIO]
382        VMA INFO: Select Skip OS                 1                          [VMA_SELECT_SKIP_OS]
383        VMA INFO: CQ Drain Interval (msec)       100                        [VMA_PROGRESS_ENGINE_INTERVAL]
384        VMA INFO: CQ Interrupts Moderation       Disabled                   [VMA_CQ_MODERATION_ENABLE]
385        VMA INFO: CQ AIM Max Count               128                        [VMA_CQ_AIM_MAX_COUNT]
386        VMA INFO: CQ Adaptive Moderation         Disabled                   [VMA_CQ_AIM_INTERVAL_MSEC]
387        VMA INFO: CQ Keeps QP Full               Disabled                   [VMA_CQ_KEEP_QP_FULL]
388        VMA INFO: TCP nodelay                    1                          [VMA_TCP_NODELAY]
389        VMA INFO: Avoid sys-calls on tcp fd      Enabled                    [VMA_AVOID_SYS_CALLS_ON_TCP_FD]
390        VMA INFO: Internal Thread Affinity       0                          [VMA_INTERNAL_THREAD_AFFINITY]
391        VMA INFO: Thread mode                    Single                     [VMA_THREAD_MODE]
392        VMA INFO: Mem Allocate type              2 (Huge Pages)             [VMA_MEM_ALLOC_TYPE]
393        VMA INFO: ---------------------------------------------------------------------------
394       sockperf: == version #3.5-no.git ==
395       sockperf: [SERVER] listen on:
396       [ 0] IP = 22.0.0.3        PORT =  5001 # UDP
397       sockperf: Warmup stage (sending a few dummy messages)...
398       sockperf: [tid 2201] using recvfrom() to block on socket(s)
399
400
401       · Run the client as follows:
402
403       $VMA_SPEC=latency LD_PRELOAD=libvma.so sockperf ping-pong -i 22.0.0.3 -p 5001 -m 64 -t 10 --mps=max
404        VMA INFO: ---------------------------------------------------------------------------
405        VMA INFO: VMA_VERSION: 8.6.10-0 Development Snapshot built on Jun 27 2018 16:06:47
406        VMA INFO: Cmd Line: sockperf ping-pong -i 22.0.0.3 -p 5001 -m 64 -t 10 --mps=max
407        VMA INFO: Current Time: Tue Sep 18 08:47:50 2018
408        VMA INFO: Pid: 20134
409        VMA INFO: OFED Version: MLNX_OFED_LINUX-4.4-1.0.0.0:
410        VMA INFO: Architecture: x86_64
411        VMA INFO: Node: r-aa-apollo04.mtr.labs.mlnx
412        VMA INFO: ---------------------------------------------------------------------------
413        VMA INFO: VMA Spec                       Latency                    [VMA_SPEC]
414        VMA INFO: Log Level                      INFO                       [VMA_TRACELEVEL]
415        VMA INFO: Ring On Device Memory TX       16384                      [VMA_RING_DEV_MEM_TX]
416        VMA INFO: Tx QP WRE                      256                        [VMA_TX_WRE]
417        VMA INFO: Tx QP WRE Batching             4                          [VMA_TX_WRE_BATCHING]
418        VMA INFO: Rx QP WRE                      256                        [VMA_RX_WRE]
419        VMA INFO: Rx QP WRE Batching             4                          [VMA_RX_WRE_BATCHING]
420        VMA INFO: Rx Poll Loops                  -1                         [VMA_RX_POLL]
421        VMA INFO: Rx Prefetch Bytes Before Poll  256                        [VMA_RX_PREFETCH_BYTES_BEFORE_POLL]
422        VMA INFO: GRO max streams                0                          [VMA_GRO_STREAMS_MAX]
423        VMA INFO: Select Poll (usec)             -1                         [VMA_SELECT_POLL]
424        VMA INFO: Select Poll OS Force           Enabled                    [VMA_SELECT_POLL_OS_FORCE]
425        VMA INFO: Select Poll OS Ratio           1                          [VMA_SELECT_POLL_OS_RATIO]
426        VMA INFO: Select Skip OS                 1                          [VMA_SELECT_SKIP_OS]
427        VMA INFO: CQ Drain Interval (msec)       100                        [VMA_PROGRESS_ENGINE_INTERVAL]
428        VMA INFO: CQ Interrupts Moderation       Disabled                   [VMA_CQ_MODERATION_ENABLE]
429        VMA INFO: CQ AIM Max Count               128                        [VMA_CQ_AIM_MAX_COUNT]
430        VMA INFO: CQ Adaptive Moderation         Disabled                   [VMA_CQ_AIM_INTERVAL_MSEC]
431        VMA INFO: CQ Keeps QP Full               Disabled                   [VMA_CQ_KEEP_QP_FULL]
432        VMA INFO: TCP nodelay                    1                          [VMA_TCP_NODELAY]
433        VMA INFO: Avoid sys-calls on tcp fd      Enabled                    [VMA_AVOID_SYS_CALLS_ON_TCP_FD]
434        VMA INFO: Internal Thread Affinity       0                          [VMA_INTERNAL_THREAD_AFFINITY]
435        VMA INFO: Thread mode                    Single                     [VMA_THREAD_MODE]
436        VMA INFO: Mem Allocate type              2 (Huge Pages)             [VMA_MEM_ALLOC_TYPE]
437        VMA INFO: ---------------------------------------------------------------------------
438       sockperf: == version #3.5-no.git ==
439       sockperf[CLIENT] send on:sockperf: using recvfrom() to block on socket(s)
440
441       [ 0] IP = 22.0.0.3        PORT =  5001 # UDP
442       sockperf: Warmup stage (sending a few dummy messages)...
443       sockperf: Starting test...
444       sockperf: Test end (interrupted by timer)
445       sockperf: Test ended
446       sockperf: [Total Run] RunTime=10.000 sec; Warm up time=400 msec; SentMessages=5166035; ReceivedMessages=5166034
447       sockperf: ========= Printing statistics for Server No: 0
448       sockperf: [Valid Duration] RunTime=9.550 sec; SentMessages=4951987; ReceivedMessages=4951987
449       sockperf: ====> avg-lat=  0.951 (std-dev=0.034)
450       sockperf: # dropped messages = 0; # duplicated messages = 0; # out-of-order messages = 0
451       sockperf: Summary: Latency is 0.951 usec
452       sockperf: Total 4951987 observations; each percentile contains 49519.87 observations
453       sockperf: ---> <MAX> observation =    4.476
454       sockperf: ---> percentile 99.999 =    1.318
455       sockperf: ---> percentile 99.990 =    1.270
456       sockperf: ---> percentile 99.900 =    1.179
457       sockperf: ---> percentile 99.000 =    1.110
458       sockperf: ---> percentile 90.000 =    0.967
459       sockperf: ---> percentile 75.000 =    0.952
460       sockperf: ---> percentile 50.000 =    0.943
461       sockperf: ---> percentile 25.000 =    0.936
462       sockperf: ---> <MIN> observation =    0.895
463
464

4. LICENSING

466       Read 'copying' file in the root place.
467

5. INSTALLATION

469   5.1 Requirements
470       What you will need to compile sockperf on Unix systems
471
472       · perl 5.8+ (used by the automake tools)
473
474       · GNU make tools: automake 1.7+, autoconf 2.57+, m4 1.4+ and libtool
475         1.4+
476
477       · A Compiler, among those tested are:
478
479         · gcc4+ (Ubuntu)
480
481         · gcc4+ (Red Hat)
482
483   5.2 Options to compile
484   5.3 How to install
485       Download sockperf-<version>.tar.gz.
486
487       Uncompress *.tar.gz file in Unix systems in the same folder with the
488       file by runing the following command in the shell:
489
490       tar -zxvf sockperf-<version>.tar.gz
491
492
493        or 2 command:
494
495       gzip -d ./sockperf-<version>.tar.gz
496       tar -xf ./sockperf-<version>.tar
497
498
499       The sockperf package uses the GNU autotools compilation and
500       installation framework.
501
502       These are generic installation instructions.
503
504       The `configure' shell script attempts to guess correct values for
505       various system-dependent variables used during compilation. It uses
506       those values to create a `Makefile' in each directory of the package.
507       It may also create one or more `.h' files containing system-dependent
508       definitions. Finally, it creates a shell script `config.status' that
509       you can run in the future to recreate the current configuration, a file
510       `config.cache' that saves the results of its tests to speed up
511       reconfiguring, and a file `config.log' containing compiler output
512       (useful mainly for debugging `configure').
513
514       If you need to do unusual things to compile the package, please try to
515       figure out how `configure' could check whether to do them, and mail
516       diffs or instructions to the address given in the `README' so they can
517       be considered for the next release. If at some point `config.cache'
518       contains results you don't want to keep, you may remove or edit it.
519
520       The file `configure.in' is used to create `configure' by a program
521       called `autoconf'. You only need `configure.in' if you want to change
522       it or regenerate `configure' using a newer version of `autoconf'.
523
524       The simplest way to compile this package is:
525
526       1.  `cd' to the directory containing the package's source code and type
527           `./configure' to configure the package for your system. If you're
528           using `csh' on an old version of System V, you might need to type
529           `sh ./configure' instead to prevent `csh' from trying to execute
530           `configure' itself.
531
532       Running `configure' takes awhile. While running, it prints some
533       messages telling which features it is checking for.
534
535       $ ./configure --prefix=<path to install>
536
537
538       There are several options to ./config (or ./Configure) to customize the
539       build:
540
541       To enable test scripts
542
543       $ ./configure --prefix=<path to install> --enable-test
544
545
546       To enable the documentation
547
548       $ ./configure --prefix=<path to install> --enable-doc
549
550
551       To enable the special scripts
552
553       $ ./configure --prefix=<path to install> --enable-tool
554
555
556       To compile with debug symbols and information:
557
558       $ ./configure --prefix=<path to install> --enable-debug
559
560
561       This will define the _DEBUG variable at compile time.
562
563       Type './configure --help' for a list of all the configure options. Some
564       of the options are generic autoconf options, while the SockPerf
565       specific options are prefixed with 'SOCKPERF:' in the help text.
566
567       2.  Type `make' to compile the package.
568
569       $ make
570
571
572       3.  Optionally, type `make check' to run any self-tests that come with
573           the package.
574
575       4.  Type `make install' to install the programs and any data files and
576           documentation.
577
578       $ make install
579
580
581       5.  You can remove the program binaries and object files from the
582           source code directory by typing `make clean'. To also remove the
583           files that `configure' created (so you can compile the package for
584           a different kind of computer), type `make distclean'. There is also
585           a `make maintainer-clean' target, but that is intended mainly for
586           the package's developers. If you use it, you may have to get all
587           sorts of other programs in order to regenerate files that came with
588           the distribution.
589
590Version 3.6-no.git              Wed Jul 29 2020                    sockperf(3)
Impressum