Merge in all updates (new manual files as well).
[awesomized/libmemcached] / docs / man / memaslap.1
1 .TH "MEMASLAP" "1" "January 26, 2012" "1.0.3" "libmemcached"
2 .SH NAME
3 memaslap \- libmemcached Documentation
4 .
5 .nr rst2man-indent-level 0
6 .
7 .de1 rstReportMargin
8 \\$1 \\n[an-margin]
9 level \\n[rst2man-indent-level]
10 level margin: \\n[rst2man-indent\\n[rst2man-indent-level]]
11 -
12 \\n[rst2man-indent0]
13 \\n[rst2man-indent1]
14 \\n[rst2man-indent2]
15 ..
16 .de1 INDENT
17 .\" .rstReportMargin pre:
18 . RS \\$1
19 . nr rst2man-indent\\n[rst2man-indent-level] \\n[an-margin]
20 . nr rst2man-indent-level +1
21 .\" .rstReportMargin post:
22 ..
23 .de UNINDENT
24 . RE
25 .\" indent \\n[an-margin]
26 .\" old: \\n[rst2man-indent\\n[rst2man-indent-level]]
27 .nr rst2man-indent-level -1
28 .\" new: \\n[rst2man-indent\\n[rst2man-indent-level]]
29 .in \\n[rst2man-indent\\n[rst2man-indent-level]]u
30 ..
31 .\" Man page generated from reStructeredText.
32 .
33 .SH SYNOPSIS
34 .sp
35 memaslap [options]
36 .INDENT 0.0
37 .TP
38 .B \-\-help
39 .UNINDENT
40 .SH DESCRIPTION
41 .sp
42 \fBmemaslap\fP is a load generation and benchmark tool for memcached
43 servers. It generates configurable workload such as threads, concurrencies,
44 connections, run time, overwrite, miss rate, key size, value size, get/set
45 proportion, expected throughput, and so on. Furthermore, it also testss data
46 verification, expire\-time verification, UDP, binary protocol, facebook test,
47 replication test, multi\-get and reconnection, etc.
48 .sp
49 Memaslap manages network connections like memcached with
50 libevent. Each thread of memaslap is bound with a CPU core, all
51 the threads don\(aqt communicate with each other, and there are several socket
52 connections in each thread. Each connection keeps key size distribution,
53 value size distribution, and command distribution by itself.
54 .sp
55 You can specify servers via the \fI\-\-servers\fP option or via the
56 environment variable \fBMEMCACHED_SERVERS\fP.
57 .SH FEATURES
58 .sp
59 Memslap is developed to for the following purposes:
60 .sp
61 Manages network connections with libevent asynchronously.
62 .sp
63 Set both TCP and UDP up to use non\-blocking IO.
64 .sp
65 Improves parallelism: higher performance in multi\-threads environments.
66 .sp
67 Improves time efficiency: faster processing speed.
68 .sp
69 Generates key and value more efficiently; key size distribution and value size distribution are configurable.
70 .sp
71 Supports get, multi\-get, and set commands; command distribution is configurable.
72 .sp
73 Supports controllable miss rate and overwrite rate.
74 .sp
75 Supports data and expire\-time verification.
76 .sp
77 Supports dumping statistic information periodically.
78 .sp
79 Supports thousands of TCP connections.
80 .sp
81 Supports binary protocol.
82 .sp
83 Supports facebook test (set with TCP and multi\-get with UDP) and replication test.
84 .SH DETAILS
85 .SS Effective implementation of network.
86 .sp
87 For memaslap, both TCP and UDP use non\-blocking network IO. All
88 the network events are managed by libevent as memcached. The network module
89 of memaslap is similar to memcached. Libevent can ensure
90 memaslap can handle network very efficiently.
91 .SS Effective implementation of multi\-threads and concurrency
92 .sp
93 Memslap has the similar implementation of multi\-threads to
94 memcached. Memslap creates one or more self\-governed threads;
95 each thread is bound with one CPU core if the system testss setting CPU
96 core affinity.
97 .sp
98 In addition, each thread has a libevent to manage the events of the network;
99 each thread has one or more self\-governed concurrencies; and each
100 concurrency has one or more socket connections. All the concurrencies don’t
101 communicate with each other even though they are in the same thread.
102 .sp
103 Memslap can create thousands of socket connections, and each
104 concurrency has tens of socket connections. Each concurrency randomly or
105 sequentially selects one socket connection from its socket connection pool
106 to run, so memaslap can ensure each concurrency handles one
107 socket connection at any given time. Users can specify the number of
108 concurrency and socket connections of each concurrency according to their
109 expected workload.
110 .SS Effective implementation of generating key and value
111 .sp
112 In order to improve time efficiency and space efficiency,
113 memaslap creates a random characters table with 10M characters. All the
114 suffixes of keys and values are generated from this random characters table.
115 .sp
116 Memslap uses the offset in the character table and the length
117 of the string to identify a string. It can save much memory.
118 Each key contains two parts, a prefix and a suffix. The prefix is an
119 uint64_t, 8 bytes. In order to verify the data set before,
120 memaslap need to ensure each key is unique, so it uses the prefix to identify
121 a key. The prefix cannot include illegal characters, such as ‘r’, ‘n’,
122 ‘0’ and ‘ ‘. And memaslap has an algorithm to ensure that.
123 .sp
124 Memslap doesn’t generate all the objects (key\-value pairs) at
125 the beginning. It only generates enough objects to fill the task window
126 (default 10K objects) of each concurrency. Each object has the following
127 basic information, key prefix, key suffix offset in the character table, key
128 length, value offset in the character table, and value length.
129 .sp
130 In the work process, each concurrency sequentially or randomly selects an
131 object from the window to do set operation or get operation. At the same
132 time, each concurrency kicks objects out of its window and adds new object
133 into it.
134 .SS Simple but useful task scheduling
135 .sp
136 Memslap uses libevent to schedule all the concurrencies of
137 threads, and each concurrency schedules tasks based on the local task
138 window. Memslap assumes that if each concurrency keeps the same
139 key distribution, value distribution and commands distribution, from
140 outside, memaslap keeps all the distribution as a whole.
141 Each task window includes a lot of objects, each object stores its basic
142 information, such as key, value, expire time, and so on. At any time, all
143 the objects in the window keep the same and fixed key and value
144 distribution. If an object is overwritten, the value of the object will be
145 updated. Memslap verifies the data or expire\-time according to
146 the object information stored in the task window.
147 .sp
148 Libevent selects which concurrency to handle based on a specific network
149 event. Then the concurrency selects which command (get or set) to operate
150 based on the command distribution. If it needs to kick out an old object and
151 add a new object, in order to keep the same key and value distribution, the
152 new object must have the same key length and value length.
153 .sp
154 If memcached server has two cache layers (memory and SSD), running
155 memaslap with different window sizes can get different cache
156 miss rates. If memaslap adds enough objects into the windows at
157 the beginning, and the cache of memcached cannot store all the objects
158 initialized, then memaslap will get some objects from the second
159 cache layer. It causes the first cache layer to miss. So the user can
160 specify the window size to get the expected miss rate of the first cache
161 layer.
162 .SS Useful implementation of multi\-servers , UDP, TCP, multi\-get and binary protocol
163 .sp
164 Because each thread is self\-governed, memaslap can assign
165 different threads to handle different memcached servers. This is just one of
166 the ways in which memaslap tests multiple servers. The only
167 limitation is that the number of servers cannot be greater than the number
168 of threads. The other way to test multiple servers is for replication
169 test. Each concurrency has one socket connection to each memcached server.
170 For the implementation, memaslap can set some objects to one
171 memcached server, and get these objects from the other servers.
172 .sp
173 By default, Memslap does single get. If the user specifies
174 multi\-get option, memaslap will collect enough get commands and
175 pack and send the commands together.
176 .sp
177 Memslap testss both the ASCII protocol and binary protocol,
178 but it runs on the ASCII protocol by default.
179 Memslap by default runs on the TCP protocol, but it also
180 tests UDP. Because UDP is unreliable, dropped packages and out\-of\-order
181 packages may occur. Memslap creates a memory buffer to handle
182 these problems. Memslap tries to read all the response data of
183 one command from the server and reorders the response data. If some packages
184 get lost, the waiting timeout mechanism can ensure half\-baked packages will
185 be discarded and the next command will be sent.
186 .SH USAGE
187 .sp
188 Below are some usage samples:
189 .sp
190 memaslap \-s 127.0.0.1:11211 \-S 5s
191 .sp
192 memaslap \-s 127.0.0.1:11211 \-t 2m \-v 0.2 \-e 0.05 \-b
193 .sp
194 memaslap \-s 127.0.0.1:11211 \-F config \-t 2m \-w 40k \-S 20s \-o 0.2
195 .sp
196 memaslap \-s 127.0.0.1:11211 \-F config \-t 2m \-T 4 \-c 128 \-d 20 \-P 40k
197 .sp
198 memaslap \-s 127.0.0.1:11211 \-F config \-t 2m \-d 50 \-a \-n 40
199 .sp
200 memaslap \-s 127.0.0.1:11211,127.0.0.1:11212 \-F config \-t 2m
201 .sp
202 memaslap \-s 127.0.0.1:11211,127.0.0.1:11212 \-F config \-t 2m \-p 2
203 .sp
204 The user must specify one server at least to run memaslap. The
205 rest of the parameters have default values, as shown below:
206 .sp
207 Thread number = 1 Concurrency = 16
208 .sp
209 Run time = 600 seconds Configuration file = NULL
210 .sp
211 Key size = 64 Value size = 1024
212 .sp
213 Get/set = 9:1 Window size = 10k
214 .sp
215 Execute number = 0 Single get = true
216 .sp
217 Multi\-get = false Number of sockets of each concurrency = 1
218 .sp
219 Reconnect = false Data verification = false
220 .sp
221 Expire\-time verification = false ASCII protocol = true
222 .sp
223 Binary protocol = false Dumping statistic information
224 .sp
225 periodically = false
226 .sp
227 Overwrite proportion = 0% UDP = false
228 .sp
229 TCP = true Limit throughput = false
230 .sp
231 Facebook test = false Replication test = false
232 .SS Key size, value size and command distribution.
233 .sp
234 All the distributions are read from the configuration file specified by user
235 with “—cfg_cmd” option. If the user does not specify a configuration file,
236 memaslap will run with the default distribution (key size = 64,
237 value size = 1024, get/set = 9:1). For information on how to edit the
238 configuration file, refer to the “Configuration File” section.
239 .sp
240 The minimum key size is 16 bytes; the maximum key size is 250 bytes. The
241 precision of proportion is 0.001. The proportion of distribution will be
242 rounded to 3 decimal places.
243 .sp
244 The minimum value size is 1 bytes; the maximum value size is 1M bytes. The
245 precision of proportion is 0.001. The proportion of distribution will be
246 rounded to 3 decimal places.
247 Currently, memaslap only testss set and get commands. And it
248 testss 100% set and 100% get. For 100% get, it will preset some objects to
249 the server.
250 .SS Multi\-thread and concurrency
251 .sp
252 The high performance of memaslap benefits from the special
253 schedule of thread and concurrency. It’s important to specify the proper
254 number of them. The default number of threads is 1; the default number of
255 concurrency is 16. The user can use “—threads” and “\-\-concurrency” to
256 specify these variables.
257 .sp
258 If the system tests setting CPU affinity and the number of threads
259 specified by the user is greater than 1, memaslap will try to
260 bind each thread to a different CPU core. So if you want to get the best
261 performance memaslap, it is better to specify the number of
262 thread equal to the number of CPU cores. The number of threads specified by
263 the user can also be less or greater than the number of CPU cores. Because
264 of the limitation of implementation, the number of concurrencies could be
265 the multiple of the number of threads.
266 .INDENT 0.0
267 .IP 1. 3
268 For 8 CPU cores system
269 .UNINDENT
270 .sp
271 For example:
272 .sp
273 \-\-threads=2 \-\-concurrency=128
274 .sp
275 \-\-threads=8 \-\-concurrency=128
276 .sp
277 \-\-threads=8 \-\-concurrency=256
278 .sp
279 \-\-threads=12 \-\-concurrency=144
280 .INDENT 0.0
281 .IP 2. 3
282 For 16 CPU cores system
283 .UNINDENT
284 .sp
285 For example:
286 .sp
287 \-\-threads=8 \-\-concurrency=128
288 .sp
289 \-\-threads=16 \-\-concurrency=256
290 .sp
291 \-\-threads=16 \-\-concurrency=512
292 .sp
293 \-\-threads=24 \-\-concurrency=288
294 .sp
295 The memaslap performs very well, when
296 used to test the performance of memcached servers.
297 Most of the time, the bottleneck is the network or
298 the server. If for some reason the user wants to
299 limit the performance of memaslap, there
300 are two ways to do this:
301 .sp
302 Decrease the number of threads and concurrencies.
303 Use the option “\-\-tps” that memaslap
304 provides to limit the throughput. This option allows
305 the user to get the expected throughput. For
306 example, assume that the maximum throughput is 50
307 kops/s for a specific configuration, you can specify
308 the throughput equal to or less than the maximum
309 throughput using “\-\-tps” option.
310 .SS Window size
311 .sp
312 Most of the time, the user does not need to specify the window size. The
313 default window size is 10k. For Schooner Memcached, the user can specify
314 different window sizes to get different cache miss rates based on the test
315 case. Memslap testss cache miss rate between 0% and 100%.
316 If you use this utility to test the performance of Schooner Memcached, you
317 can specify a proper window size to get the expected cache miss rate. The
318 formula for calculating window size is as follows:
319 .sp
320 Assume that the key size is 128 bytes, and the value size is 2048 bytes, and
321 concurrency=128.
322 .sp
323 1. Small cache cache_size=1M, 100% cache miss (all data get from SSD).
324 win_size=10k
325 .INDENT 0.0
326 .IP 2. 3
327 cache_size=4G
328 .UNINDENT
329 .sp
330 (1). cache miss rate 0%
331 .sp
332 win_size=8k
333 .sp
334 (2). cache miss rate 5%
335 .sp
336 win_size=11k
337 .INDENT 0.0
338 .IP 3. 3
339 cache_size=16G
340 .UNINDENT
341 .sp
342 (1). cache miss rate 0%
343 .sp
344 win_size=32k
345 .sp
346 (2). cache miss
347 .sp
348 rate 5%
349 .sp
350 win_size=46k
351 .sp
352 The formula for calculating window size for cache miss rate 0%:
353 .sp
354 cache_size / concurrency / (key_size + value_size) * 0.5
355 .sp
356 The formula for calculating window size for cache miss rate 5%:
357 .sp
358 cache_size / concurrency / (key_size + value_size) * 0.7
359 .SS Verification
360 .sp
361 Memslap testss both data verification and expire\-time
362 verification. The user can use "\-\-verify=" or "\-v" to specify the proportion
363 of data verification. In theory, it testss 100% data verification. The
364 user can use "\-\-exp_verify=" or "\-e" to specify the proportion of
365 expire\-time verification. In theory, it testss 100% expire\-time
366 verification. Specify the "\-\-verbose" options to get more detailed error
367 information.
368 .sp
369 For example: \-\-exp_verify=0.01 –verify=0.1 , it means that 1% of the objects
370 set with expire\-time, 10% of the objects gotten will be verified. If the
371 objects are gotten, memaslap will verify the expire\-time and
372 value.
373 .SS multi\-servers and multi\-config
374 .sp
375 Memslap testss multi\-servers based on self\-governed thread.
376 There is a limitation that the number of servers cannot be greater than the
377 number of threads. Memslap assigns one thread to handle one
378 server at least. The user can use the "\-\-servers=" or "\-s" option to specify
379 multi\-servers.
380 .sp
381 For example:
382 .sp
383 \-\-servers=10.1.1.1:11211,10.1.1.2:11212,10.1.1.3:11213 \-\-threads=6 \-\-concurrency=36
384 .sp
385 The above command means that there are 6 threads, with each thread having 6
386 concurrencies and that threads 0 and 3 handle server 0 (10.1.1.1); threads 1
387 and 4 handle server 1 (10.1.1.2); and thread 2 and 5 handle server 2
388 (10.1.1.3).
389 .sp
390 All the threads and concurrencies in memaslap are self\-governed.
391 .sp
392 So is memaslap. The user can start up several
393 memaslap instances. The user can run memaslap on different client
394 machines to communicate with the same memcached server at the same. It is
395 recommended that the user start different memaslap on different
396 machines using the same configuration.
397 .SS Run with execute number mode or time mode
398 .sp
399 The default memaslap runs with time mode. The default run time
400 is 10 minutes. If it times out, memaslap will exit. Do not
401 specify both execute number mode and time mode at the same time; just
402 specify one instead.
403 .sp
404 For example:
405 .sp
406 \-\-time=30s (It means the test will run 30 seconds.)
407 .sp
408 \-\-execute_number=100000 (It means that after running 100000 commands, the test will exit.)
409 .SS Dump statistic information periodically.
410 .sp
411 The user can use "\-\-stat_freq=" or "\-S" to specify the frequency.
412 .sp
413 For example:
414 .sp
415 \-\-stat_freq=20s
416 .sp
417 Memslap will dump the statistics of the commands (get and set) at the frequency of every 20
418 seconds.
419 .sp
420 For more information on the format of dumping statistic information, refer to “Format of Output” section.
421 .SS Multi\-get
422 .sp
423 The user can use "\-\-division=" or "\-d" to specify multi\-get keys count.
424 Memslap by default does single get with TCP. Memslap also testss data
425 verification and expire\-time verification for multi\-get.
426 .sp
427 Memslap testss multi\-get with both TCP and UDP. Because of
428 the different implementation of the ASCII protocol and binary protocol,
429 there are some differences between the two. For the ASCII protocol,
430 memaslap sends one “multi\-get” to the server once. For the
431 binary protocol, memaslap sends several single get commands
432 together as “multi\-get” to the server.
433 .SS UDP and TCP
434 .sp
435 Memslap testss both UDP and TCP. For TCP,
436 memaslap does not reconnect the memcached server if socket connections are
437 lost. If all the socket connections are lost or memcached server crashes,
438 memaslap will exit. If the user specifies the “\-\-reconnect”
439 option when socket connections are lost, it will reconnect them.
440 .sp
441 User can use “\-\-udp” to enable the UDP feature, but UDP comes with some
442 limitations:
443 .sp
444 UDP cannot set data more than 1400 bytes.
445 .sp
446 UDP is not testsed by the binary protocol because the binary protocol of
447 memcached does not tests that.
448 .sp
449 UDP doesn’t tests reconnection.
450 .SS Facebook test
451 .sp
452 Set data with TCP and multi\-get with UDP. Specify the following options:
453 .sp
454 "\-\-facebook \-\-division=50"
455 .sp
456 If you want to create thousands of TCP connections, specify the
457 .sp
458 "\-\-conn_sock=" option.
459 .sp
460 For example: \-\-facebook \-\-division=50 \-\-conn_sock=200
461 .sp
462 The above command means that memaslap will do facebook test,
463 each concurrency has 200 socket TCP connections and one UDP socket.
464 .sp
465 Memslap sets objects with the TCP socket, and multi\-gets 50
466 objects once with the UDP socket.
467 .sp
468 If you specify "\-\-division=50", the key size must be less that 25 bytes
469 because the UDP packet size is 1400 bytes.
470 .SS Replication test
471 .sp
472 For replication test, the user must specify at least two memcached servers.
473 The user can use “—rep_write=” option to enable feature.
474 .sp
475 For example:
476 .sp
477 \-\-servers=10.1.1.1:11211,10.1.1.2:11212 –rep_write=2
478 .sp
479 The above command means that there are 2 replication memcached servers,
480 memaslap will set objects to both server 0 and server 1, get
481 objects which are set to server 0 before from server 1, and also get objects
482 which are set to server 1 before from server 0. If server 0 crashes,
483 memaslap will only get objects from server 1. If server 0 comes
484 back to life again, memaslap will reconnect server 0. If both
485 server 0 and server 1 crash, memaslap will exit.
486 .SS Supports thousands of TCP connections
487 .sp
488 Start memaslap with "\-\-conn_sock=" or "\-n" to enable this
489 feature. Make sure that your system can tests opening thousands of files
490 and creating thousands of sockets. However, this feature does not tests
491 reconnection if sockets disconnect.
492 .sp
493 For example:
494 .sp
495 \-\-threads=8 \-\-concurrency=128 \-\-conn_sock=128
496 .sp
497 The above command means that memaslap starts up 8 threads, each
498 thread has 16 concurrencies, each concurrency has 128 TCP socket
499 connections, and the total number of TCP socket connections is 128 * 128 =
500 16384.
501 .SS Supports binary protocol
502 .sp
503 Start memaslap with "\-\-binary" or "\-B" options to enable this
504 feature. It testss all the above features except UDP, because the latest
505 memcached 1.3.3 does not implement binary UDP protocol.
506 .sp
507 For example:
508 .sp
509 \-\-binary
510 .sp
511 Since memcached 1.3.3 doesn\(aqt implement binary UDP protocol,
512 memaslap does not tests UDP. In addition, memcached 1.3.3 does not tests
513 multi\-get. If you specify "\-\-division=50" option, it just sends 50 get
514 commands together as “mulit\-get” to the server.
515 .SH CONFIGURATION FILE
516 .sp
517 This section describes the format of the configuration file. By default
518 when no configuration file is specified memaslap reads the default
519 one located at ~/.memaslap.cnf.
520 .sp
521 Below is a sample configuration file:
522 .sp
523 .nf
524 .ft C
525 \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-
526 #comments should start with \(aq#\(aq
527 #key
528 #start_len end_len proportion
529 #
530 #key length range from start_len to end_len
531 #start_len must be equal to or greater than 16
532 #end_len must be equal to or less than 250
533 #start_len must be equal to or greater than end_len
534 #memaslap will generate keys according to the key range
535 #proportion: indicates keys generated from one range accounts for the total
536 generated keys
537 #
538 #example1: key range 16~100 accounts for 80%
539 # key range 101~200 accounts for 10%
540 # key range 201~250 accounts for 10%
541 # total should be 1 (0.8+0.1+0.1 = 1)
542 #
543 # 16 100 0.8
544 # 101 200 0.1
545 # 201 249 0.1
546 #
547 #example2: all keys length are 128 bytes
548 #
549 # 128 128 1
550 key
551 128 128 1
552 #value
553 #start_len end_len proportion
554 #
555 #value length range from start_len to end_len
556 #start_len must be equal to or greater than 1
557 #end_len must be equal to or less than 1M
558 #start_len must be equal to or greater than end_len
559 #memaslap will generate values according to the value range
560 #proportion: indicates values generated from one range accounts for the
561 total generated values
562 #
563 #example1: value range 1~1000 accounts for 80%
564 # value range 1001~10000 accounts for 10%
565 # value range 10001~100000 accounts for 10%
566 # total should be 1 (0.8+0.1+0.1 = 1)
567 #
568 # 1 1000 0.8
569 # 1001 10000 0.1
570 # 10001 100000 0.1
571 #
572 #example2: all value length are 128 bytes
573 #
574 # 128 128 1
575 value
576 2048 2048 1
577 #cmd
578 #cmd_type cmd_proportion
579 #
580 #currently memaslap only testss get and set command.
581 #
582 #cmd_type
583 #set 0
584 #get 1
585 #
586 #example: set command accounts for 50%
587 # get command accounts for 50%
588 # total should be 1 (0.5+0.5 = 1)
589 #
590 # cmd
591 # 0 0.5
592 # 1 0.5
593 cmd
594 0 0.1
595 1.0 0.9
596 .ft P
597 .fi
598 .SH FORMAT OF OUTPUT
599 .sp
600 At the beginning, memaslap displays some configuration information as follows:
601 .sp
602 servers : 127.0.0.1:11211
603 .sp
604 threads count: 1
605 .sp
606 concurrency: 16
607 .sp
608 run time: 20s
609 .sp
610 windows size: 10k
611 .sp
612 set proportion: set_prop=0.10
613 .sp
614 get proportion: get_prop=0.90
615 .SS Where
616 .sp
617 servers : "servers"
618 .INDENT 0.0
619 .INDENT 3.5
620 The servers used by memaslap.
621 .UNINDENT
622 .UNINDENT
623 .sp
624 threads count
625 .INDENT 0.0
626 .INDENT 3.5
627 The number of threads memaslap runs with.
628 .UNINDENT
629 .UNINDENT
630 .sp
631 concurrency
632 .INDENT 0.0
633 .INDENT 3.5
634 The number of concurrencies memaslap runs with.
635 .UNINDENT
636 .UNINDENT
637 .sp
638 run time
639 .INDENT 0.0
640 .INDENT 3.5
641 How long to run memaslap.
642 .UNINDENT
643 .UNINDENT
644 .sp
645 windows size
646 .INDENT 0.0
647 .INDENT 3.5
648 The task window size of each concurrency.
649 .UNINDENT
650 .UNINDENT
651 .sp
652 set proportion
653 .INDENT 0.0
654 .INDENT 3.5
655 The proportion of set command.
656 .UNINDENT
657 .UNINDENT
658 .sp
659 get proportion
660 .INDENT 0.0
661 .INDENT 3.5
662 The proportion of get command.
663 .UNINDENT
664 .UNINDENT
665 .sp
666 The output of dynamic statistics is something like this:
667 .sp
668 .nf
669 .ft C
670 \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-
671 Get Statistics
672 Type Time(s) Ops TPS(ops/s) Net(M/s) Get_miss Min(us) Max(us)
673 Avg(us) Std_dev Geo_dist
674 Period 5 345826 69165 65.3 0 27 2198 203
675 95.43 177.29
676 Global 20 1257935 62896 71.8 0 26 3791 224
677 117.79 192.60
678
679
680 Set Statistics
681 Type Time(s) Ops TPS(ops/s) Net(M/s) Get_miss Min(us) Max(us)
682 Avg(us) Std_dev Geo_dist
683 Period 5 38425 7685 7.3 0 42 628 240
684 88.05 220.21
685 Global 20 139780 6989 8.0 0 37 3790 253
686 117.93 224.83
687
688
689 Total Statistics
690 Type Time(s) Ops TPS(ops/s) Net(M/s) Get_miss Min(us) Max(us)
691 Avg(us) Std_dev Geo_dist
692 Period 5 384252 76850 72.5 0 27 2198 207
693 94.72 181.18
694 Global 20 1397720 69886 79.7 0 26 3791 227
695 117.93 195.60
696 \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-
697 .ft P
698 .fi
699 .SS Where
700 .sp
701 Get Statistics
702 .INDENT 0.0
703 .INDENT 3.5
704 Statistics information of get command
705 .UNINDENT
706 .UNINDENT
707 .sp
708 Set Statistics
709 .INDENT 0.0
710 .INDENT 3.5
711 Statistics information of set command
712 .UNINDENT
713 .UNINDENT
714 .sp
715 Total Statistics
716 .INDENT 0.0
717 .INDENT 3.5
718 Statistics information of both get and set command
719 .UNINDENT
720 .UNINDENT
721 .sp
722 Period
723 .INDENT 0.0
724 .INDENT 3.5
725 Result within a period
726 .UNINDENT
727 .UNINDENT
728 .sp
729 Global
730 .INDENT 0.0
731 .INDENT 3.5
732 Accumulated results
733 .UNINDENT
734 .UNINDENT
735 .sp
736 Ops
737 .INDENT 0.0
738 .INDENT 3.5
739 Total operations
740 .UNINDENT
741 .UNINDENT
742 .sp
743 TPS
744 .INDENT 0.0
745 .INDENT 3.5
746 Throughput, operations/second
747 .UNINDENT
748 .UNINDENT
749 .sp
750 Net
751 .INDENT 0.0
752 .INDENT 3.5
753 The rate of network
754 .UNINDENT
755 .UNINDENT
756 .sp
757 Get_miss
758 .INDENT 0.0
759 .INDENT 3.5
760 How many objects can’t be gotten
761 .UNINDENT
762 .UNINDENT
763 .sp
764 Min
765 .INDENT 0.0
766 .INDENT 3.5
767 The minimum response time
768 .UNINDENT
769 .UNINDENT
770 .sp
771 Max
772 .INDENT 0.0
773 .INDENT 3.5
774 The maximum response time
775 .UNINDENT
776 .UNINDENT
777 .sp
778 Avg:
779 .INDENT 0.0
780 .INDENT 3.5
781 The average response time
782 .UNINDENT
783 .UNINDENT
784 .sp
785 Std_dev
786 .INDENT 0.0
787 .INDENT 3.5
788 Standard deviation of response time
789 .UNINDENT
790 .UNINDENT
791 .sp
792 Geo_dist
793 .INDENT 0.0
794 .INDENT 3.5
795 Geometric distribution based on natural exponential function
796 .UNINDENT
797 .UNINDENT
798 .sp
799 At the end, memaslap will output something like this:
800 .sp
801 .nf
802 .ft C
803 \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-
804 Get Statistics (1257956 events)
805 Min: 26
806 Max: 3791
807 Avg: 224
808 Geo: 192.60
809 Std: 116.23
810 Log2 Dist:
811 4: 0 10 84490 215345
812 8: 484890 459823 12543 824
813 12: 31
814
815 Set Statistics (139782 events)
816 Min: 37
817 Max: 3790
818 Avg: 253
819 Geo: 224.84
820 Std: 116.83
821 Log2 Dist:
822 4: 0 0 4200 16988
823 8: 50784 65574 2064 167
824 12: 5
825
826 Total Statistics (1397738 events)
827 Min: 26
828 Max: 3791
829 Avg: 227
830 Geo: 195.60
831 Std: 116.60
832 Log2 Dist:
833 4: 0 10 88690 232333
834 8: 535674 525397 14607 991
835 12: 36
836
837 cmd_get: 1257969
838 cmd_set: 139785
839 get_misses: 0
840 verify_misses: 0
841 verify_failed: 0
842 expired_get: 0
843 unexpired_unget: 0
844 written_bytes: 242516030
845 read_bytes: 1003702556
846 object_bytes: 152086080
847 packet_disorder: 0
848 packet_drop: 0
849 udp_timeout: 0
850
851 Run time: 20.0s Ops: 1397754 TPS: 69817 Net_rate: 59.4M/s
852 \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-
853 .ft P
854 .fi
855 .SS Where
856 .sp
857 Get Statistics
858 .INDENT 0.0
859 .INDENT 3.5
860 Get statistics of response time
861 .UNINDENT
862 .UNINDENT
863 .sp
864 Set Statistics
865 .INDENT 0.0
866 .INDENT 3.5
867 Set statistics of response time
868 .UNINDENT
869 .UNINDENT
870 .sp
871 Total Statistics
872 .INDENT 0.0
873 .INDENT 3.5
874 Both get and set statistics of response time
875 .UNINDENT
876 .UNINDENT
877 .sp
878 Min
879 .INDENT 0.0
880 .INDENT 3.5
881 The accumulated and minimum response time
882 .UNINDENT
883 .UNINDENT
884 .sp
885 Max
886 .INDENT 0.0
887 .INDENT 3.5
888 The accumulated and maximum response time
889 .UNINDENT
890 .UNINDENT
891 .sp
892 Avg
893 .INDENT 0.0
894 .INDENT 3.5
895 The accumulated and average response time
896 .UNINDENT
897 .UNINDENT
898 .sp
899 Std
900 .INDENT 0.0
901 .INDENT 3.5
902 Standard deviation of response time
903 .UNINDENT
904 .UNINDENT
905 .sp
906 Log2 Dist
907 .INDENT 0.0
908 .INDENT 3.5
909 Geometric distribution based on logarithm 2
910 .UNINDENT
911 .UNINDENT
912 .sp
913 cmd_get
914 .INDENT 0.0
915 .INDENT 3.5
916 Total get commands done
917 .UNINDENT
918 .UNINDENT
919 .sp
920 cmd_set
921 .INDENT 0.0
922 .INDENT 3.5
923 Total set commands done
924 .UNINDENT
925 .UNINDENT
926 .sp
927 get_misses
928 .INDENT 0.0
929 .INDENT 3.5
930 How many objects can’t be gotten from server
931 .UNINDENT
932 .UNINDENT
933 .sp
934 verify_misses
935 .INDENT 0.0
936 .INDENT 3.5
937 How many objects need to verify but can’t get them
938 .UNINDENT
939 .UNINDENT
940 .sp
941 verify_failed
942 .INDENT 0.0
943 .INDENT 3.5
944 How many objects with insistent value
945 .UNINDENT
946 .UNINDENT
947 .sp
948 expired_get
949 .INDENT 0.0
950 .INDENT 3.5
951 How many objects are expired but we get them
952 .UNINDENT
953 .UNINDENT
954 .sp
955 unexpired_unget
956 .INDENT 0.0
957 .INDENT 3.5
958 How many objects are unexpired but we can’t get them
959 .UNINDENT
960 .UNINDENT
961 .sp
962 written_bytes
963 .INDENT 0.0
964 .INDENT 3.5
965 Total written bytes
966 .UNINDENT
967 .UNINDENT
968 .sp
969 read_bytes
970 .INDENT 0.0
971 .INDENT 3.5
972 Total read bytes
973 .UNINDENT
974 .UNINDENT
975 .sp
976 object_bytes
977 .INDENT 0.0
978 .INDENT 3.5
979 Total object bytes
980 .UNINDENT
981 .UNINDENT
982 .sp
983 packet_disorder
984 .INDENT 0.0
985 .INDENT 3.5
986 How many UDP packages are disorder
987 .UNINDENT
988 .UNINDENT
989 .sp
990 packet_drop
991 .INDENT 0.0
992 .INDENT 3.5
993 How many UDP packages are lost
994 .UNINDENT
995 .UNINDENT
996 .sp
997 udp_timeout
998 .INDENT 0.0
999 .INDENT 3.5
1000 How many times UDP time out happen
1001 .UNINDENT
1002 .UNINDENT
1003 .sp
1004 Run time
1005 .INDENT 0.0
1006 .INDENT 3.5
1007 Total run time
1008 .UNINDENT
1009 .UNINDENT
1010 .sp
1011 Ops
1012 .INDENT 0.0
1013 .INDENT 3.5
1014 Total operations
1015 .UNINDENT
1016 .UNINDENT
1017 .sp
1018 TPS
1019 .INDENT 0.0
1020 .INDENT 3.5
1021 Throughput, operations/second
1022 .UNINDENT
1023 .UNINDENT
1024 .sp
1025 Net_rate
1026 .INDENT 0.0
1027 .INDENT 3.5
1028 The average rate of network
1029 .UNINDENT
1030 .UNINDENT
1031 .SH OPTIONS
1032 .INDENT 0.0
1033 .TP
1034 .B \-s, \-\-servers=
1035 List one or more servers to connect. Servers count must be less than
1036 threads count. e.g.: \-\-servers=localhost:1234,localhost:11211
1037 .TP
1038 .B \-T, \-\-threads=
1039 Number of threads to startup, better equal to CPU numbers. Default 8.
1040 .TP
1041 .B \-c, \-\-concurrency=
1042 Number of concurrency to simulate with load. Default 128.
1043 .TP
1044 .B \-n, \-\-conn_sock=
1045 Number of TCP socks per concurrency. Default 1.
1046 .TP
1047 .B \-x, \-\-execute_number=
1048 Number of operations(get and set) to execute for the
1049 given test. Default 1000000.
1050 .TP
1051 .B \-t, \-\-time=
1052 How long the test to run, suffix: s\-seconds, m\-minutes, h\-hours,
1053 d\-days e.g.: \-\-time=2h.
1054 .TP
1055 .B \-F, \-\-cfg_cmd=
1056 Load the configure file to get command,key and value distribution list.
1057 .TP
1058 .B \-w, \-\-win_size=
1059 Task window size of each concurrency, suffix: K, M e.g.: \-\-win_size=10k.
1060 Default 10k.
1061 .TP
1062 .B \-X, \-\-fixed_size=
1063 Fixed length of value.
1064 .TP
1065 .B \-v, \-\-verify=
1066 The proportion of date verification, e.g.: \-\-verify=0.01
1067 .TP
1068 .B \-d, \-\-division=
1069 Number of keys to multi\-get once. Default 1, means single get.
1070 .TP
1071 .B \-S, \-\-stat_freq=
1072 Frequency of dumping statistic information. suffix: s\-seconds,
1073 m\-minutes, e.g.: \-\-resp_freq=10s.
1074 .TP
1075 .B \-e, \-\-exp_verify=
1076 The proportion of objects with expire time, e.g.: \-\-exp_verify=0.01.
1077 Default no object with expire time
1078 .TP
1079 .B \-o, \-\-overwrite=
1080 The proportion of objects need overwrite, e.g.: \-\-overwrite=0.01.
1081 Default never overwrite object.
1082 .UNINDENT
1083 .INDENT 0.0
1084 .TP
1085 .B \-R, \-\-reconnect
1086 Reconnect tests, when connection is closed it will be reconnected.
1087 .TP
1088 .B \-U, \-\-udp
1089 UDP tests, default memaslap uses TCP, TCP port and UDP port of
1090 server must be same.
1091 .TP
1092 .B \-a, \-\-facebook
1093 Whether it enables facebook test feature, set with TCP and multi\-get with UDP.
1094 .TP
1095 .B \-B, \-\-binary
1096 Whether it enables binary protocol. Default with ASCII protocol.
1097 .UNINDENT
1098 .INDENT 0.0
1099 .TP
1100 .B \-P, \-\-tps=
1101 Expected throughput, suffix: K, e.g.: \-\-tps=10k.
1102 .TP
1103 .B \-p, \-\-rep_write=
1104 The first nth servers can write data, e.g.: \-\-rep_write=2.
1105 .UNINDENT
1106 .INDENT 0.0
1107 .TP
1108 .B \-b, \-\-verbose
1109 Whether it outputs detailed information when verification fails.
1110 .TP
1111 .B \-h, \-\-help
1112 Display this message and then exit.
1113 .TP
1114 .B \-V, \-\-version
1115 Display the version of the application and then exit.
1116 .UNINDENT
1117 .SH EXAMPLES
1118 .sp
1119 memaslap \-s 127.0.0.1:11211 \-S 5s
1120 .sp
1121 memaslap \-s 127.0.0.1:11211 \-t 2m \-v 0.2 \-e 0.05 \-b
1122 .sp
1123 memaslap \-s 127.0.0.1:11211 \-F config \-t 2m \-w 40k \-S 20s \-o 0.2
1124 .sp
1125 memaslap \-s 127.0.0.1:11211 \-F config \-t 2m \-T 4 \-c 128 \-d 20 \-P 40k
1126 .sp
1127 memaslap \-s 127.0.0.1:11211 \-F config \-t 2m \-d 50 \-a \-n 40
1128 .sp
1129 memaslap \-s 127.0.0.1:11211,127.0.0.1:11212 \-F config \-t 2m
1130 .sp
1131 memaslap \-s 127.0.0.1:11211,127.0.0.1:11212 \-F config \-t 2m \-p 2
1132 .SH HOME
1133 .sp
1134 To find out more information please check:
1135 \fI\%http://libmemcached.org/\fP
1136 .SH AUTHORS
1137 .sp
1138 Mingqiang Zhuang <\fI\%mingqiangzhuang@hengtiansoft.com\fP> (Schooner Technolgy)
1139 Brian Aker, <\fI\%brian@tangent.org\fP>
1140 .SH SEE ALSO
1141 .sp
1142 \fImemcached(1)\fP \fIlibmemcached(3)\fP
1143 .SH AUTHOR
1144 Brian Aker
1145 .SH COPYRIGHT
1146 2011, Brian Aker DataDifferential, http://datadifferential.com/
1147 .\" Generated by docutils manpage writer.
1148 .\"
1149 .