ちゃんと覚えておけよ?

忘れちゃいけない事のメモ、覚え書き

WebARENAのSSD100G 4コア 6Gのunixbenchを取ってみた

WebARENAのテストサーバでunixbenchを取ってみた。

■unixbenchのインストール手順

yum install libXext-devel freeglut freeglut-devel perl-Time-HiRes wget
yum groupinstall 'Development tools'
# wget http://byte-unixbench.googlecode.com/files/UnixBench5.1.3.tgz
# tar zxvf UnixBench5.1.3.tgz
# cd UnixBench
# make

■unixbenchの実行

./Run

ベンチは30分くらい。

出来る限り正確な数値を取るなら、その間は放置

 

■1回目

========================================================================
BYTE UNIX Benchmarks (Version 5.1.3)

System: v5pnrej2: GNU/Linux
OS: GNU/Linux — 2.6.32-042stab079.6 — #1 SMP Mon Aug 26 19:47:50 MSK 2013
Machine: x86_64 (x86_64)
Language: en_US.utf8 (charmap=”UTF-8″, collate=”UTF-8″)
CPU 0: Intel(R) Xeon(R) CPU E5-2650 0 @ 2.00GHz (3990.3 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 1: Intel(R) Xeon(R) CPU E5-2650 0 @ 2.00GHz (3990.3 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 2: Intel(R) Xeon(R) CPU E5-2650 0 @ 2.00GHz (3990.3 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
CPU 3: Intel(R) Xeon(R) CPU E5-2650 0 @ 2.00GHz (3990.3 bogomips)
Hyper-Threading, x86-64, MMX, Physical Address Ext, SYSENTER/SYSEXIT, SYSCALL/SYSRET, Intel virtualization
17:12:06 up 1:14, 1 user, load average: 0.10, 4.66, 5.13; runlevel 3

————————————————————————
Benchmark Run: Thu Aug 28 2014 17:12:06 – 17:39:40
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables 28337452.1 lps (10.0 s, 7 samples)
Double-Precision Whetstone 3067.2 MWIPS (7.5 s, 7 samples)
Execl Throughput 1342.0 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 511152.5 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 140345.1 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1341056.6 KBps (30.0 s, 2 samples)
Pipe Throughput 1128910.9 lps (10.0 s, 7 samples)
Pipe-based Context Switching 72552.8 lps (10.0 s, 7 samples)
Process Creation 3104.5 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2414.0 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 847.2 lpm (60.1 s, 2 samples)
System Call Overhead 1473608.8 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 28337452.1 2428.2
Double-Precision Whetstone 55.0 3067.2 557.7
Execl Throughput 43.0 1342.0 312.1
File Copy 1024 bufsize 2000 maxblocks 3960.0 511152.5 1290.8
File Copy 256 bufsize 500 maxblocks 1655.0 140345.1 848.0
File Copy 4096 bufsize 8000 maxblocks 5800.0 1341056.6 2312.2
Pipe Throughput 12440.0 1128910.9 907.5
Pipe-based Context Switching 4000.0 72552.8 181.4
Process Creation 126.0 3104.5 246.4
Shell Scripts (1 concurrent) 42.4 2414.0 569.3
Shell Scripts (8 concurrent) 6.0 847.2 1412.1
System Call Overhead 15000.0 1473608.8 982.4
========
System Benchmarks Index Score 754.9

————————————————————————
Benchmark Run: Thu Aug 28 2014 17:39:40 – 18:07:23
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables 104766822.4 lps (10.0 s, 7 samples)
Double-Precision Whetstone 11586.2 MWIPS (8.0 s, 7 samples)
Execl Throughput 12712.1 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 368000.6 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 92045.4 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1556757.4 KBps (30.0 s, 2 samples)
Pipe Throughput 4319410.1 lps (10.0 s, 7 samples)
Pipe-based Context Switching 636153.3 lps (10.0 s, 7 samples)
Process Creation 10916.4 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 7722.2 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1397.0 lpm (60.0 s, 2 samples)
System Call Overhead 3489390.7 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 104766822.4 8977.4
Double-Precision Whetstone 55.0 11586.2 2106.6
Execl Throughput 43.0 12712.1 2956.3
File Copy 1024 bufsize 2000 maxblocks 3960.0 368000.6 929.3
File Copy 256 bufsize 500 maxblocks 1655.0 92045.4 556.2
File Copy 4096 bufsize 8000 maxblocks 5800.0 1556757.4 2684.1
Pipe Throughput 12440.0 4319410.1 3472.2
Pipe-based Context Switching 4000.0 636153.3 1590.4
Process Creation 126.0 10916.4 866.4
Shell Scripts (1 concurrent) 42.4 7722.2 1821.3
Shell Scripts (8 concurrent) 6.0 1397.0 2328.3
System Call Overhead 15000.0 3489390.7 2326.3
========
System Benchmarks Index Score 1981.3

 

■2回目

————————————————————————
Benchmark Run: Fri Aug 29 2014 09:14:26 – 09:42:17
4 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables 21645599.0 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2328.6 MWIPS (9.9 s, 7 samples)
Execl Throughput 1354.5 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 696005.0 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 217470.0 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1743909.9 KBps (30.0 s, 2 samples)
Pipe Throughput 972938.2 lps (10.0 s, 7 samples)
Pipe-based Context Switching 72768.5 lps (10.0 s, 7 samples)
Process Creation 3180.7 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2520.0 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 860.8 lpm (60.0 s, 2 samples)
System Call Overhead 1445298.9 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 21645599.0 1854.8
Double-Precision Whetstone 55.0 2328.6 423.4
Execl Throughput 43.0 1354.5 315.0
File Copy 1024 bufsize 2000 maxblocks 3960.0 696005.0 1757.6
File Copy 256 bufsize 500 maxblocks 1655.0 217470.0 1314.0
File Copy 4096 bufsize 8000 maxblocks 5800.0 1743909.9 3006.7
Pipe Throughput 12440.0 972938.2 782.1
Pipe-based Context Switching 4000.0 72768.5 181.9
Process Creation 126.0 3180.7 252.4
Shell Scripts (1 concurrent) 42.4 2520.0 594.3
Shell Scripts (8 concurrent) 6.0 860.8 1434.7
System Call Overhead 15000.0 1445298.9 963.5
========
System Benchmarks Index Score 780.0

————————————————————————
Benchmark Run: Fri Aug 29 2014 09:42:17 – 10:10:05
4 CPUs in system; running 4 parallel copies of tests

Dhrystone 2 using register variables 102600664.7 lps (10.0 s, 7 samples)
Double-Precision Whetstone 11018.1 MWIPS (8.5 s, 7 samples)
Execl Throughput 12641.6 lps (30.0 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 691136.0 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 217507.9 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 1602631.4 KBps (30.0 s, 2 samples)
Pipe Throughput 4168205.2 lps (10.0 s, 7 samples)
Pipe-based Context Switching 604579.7 lps (10.0 s, 7 samples)
Process Creation 11631.3 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 7561.1 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 1406.7 lpm (60.1 s, 2 samples)
System Call Overhead 3087612.4 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 102600664.7 8791.8
Double-Precision Whetstone 55.0 11018.1 2003.3
Execl Throughput 43.0 12641.6 2939.9
File Copy 1024 bufsize 2000 maxblocks 3960.0 691136.0 1745.3
File Copy 256 bufsize 500 maxblocks 1655.0 217507.9 1314.2
File Copy 4096 bufsize 8000 maxblocks 5800.0 1602631.4 2763.2
Pipe Throughput 12440.0 4168205.2 3350.6
Pipe-based Context Switching 4000.0 604579.7 1511.4
Process Creation 126.0 11631.3 923.1
Shell Scripts (1 concurrent) 42.4 7561.1 1783.3
Shell Scripts (8 concurrent) 6.0 1406.7 2344.6
System Call Overhead 15000.0 3087612.4 2058.4
========
System Benchmarks Index Score 2204.9

ちなみに回線速度は

wget --output-document=/dev/null http://speedtest.wdc01.softlayer.com/downloads/test500.zip
2014-08-28 18:58:04 (8.23 MB/s) - “/dev/null” saved [524288000/524288000]

apache abベンチ

 

ab -n 1000 -c 100 http://localhost/
This is ApacheBench, Version 2.3 <$Revision: 655654 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/

Benchmarking localhost (be patient)
Completed 100 requests
Completed 200 requests
Completed 300 requests
Completed 400 requests
Completed 500 requests
Completed 600 requests
Completed 700 requests
Completed 800 requests
Completed 900 requests
Completed 1000 requests
Finished 1000 requests

Server Software: Apache/2.2.15
Server Hostname: localhost
Server Port: 80

Document Path: /
Document Length: 4958 bytes

Concurrency Level: 100
Time taken for tests: 0.208 seconds
Complete requests: 1000
Failed requests: 0
Write errors: 0
Non-2xx responses: 1004
Total transferred: 5176624 bytes
HTML transferred: 4977832 bytes
Requests per second: 4807.60 [#/sec] (mean)
Time per request: 20.800 [ms] (mean)
Time per request: 0.208 [ms] (mean, across all concurrent requests)
Transfer rate: 24303.84 [Kbytes/sec] received

Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 2 2.3 1 10
Processing: 7 18 5.1 19 30
Waiting: 4 18 5.0 19 29
Total: 8 20 5.7 20 38

Percentage of the requests served within a certain time (ms)
50% 20
66% 21
75% 22
80% 25
90% 27
95% 28
98% 33
99% 35
100% 38 (longest request)

2回目

ab -n 1000 -c 100 http://localhost/
This is ApacheBench, Version 2.3 <$Revision: 655654 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/

Benchmarking localhost (be patient)
Completed 100 requests
Completed 200 requests
Completed 300 requests
Completed 400 requests
Completed 500 requests
Completed 600 requests
Completed 700 requests
Completed 800 requests
Completed 900 requests
Completed 1000 requests
Finished 1000 requests
Server Software: Apache/2.2.15
Server Hostname: localhost
Server Port: 80

Document Path: /
Document Length: 4958 bytes

Concurrency Level: 100
Time taken for tests: 0.126 seconds
Complete requests: 1000
Failed requests: 0
Write errors: 0
Non-2xx responses: 1003
Total transferred: 5171468 bytes
HTML transferred: 4972874 bytes
Requests per second: 7950.52 [#/sec] (mean)
Time per request: 12.578 [ms] (mean)
Time per request: 0.126 [ms] (mean, across all concurrent requests)
Transfer rate: 40152.19 [Kbytes/sec] received

Connection Times (ms)
min mean[+/-sd] median max
Connect: 0 1 1.3 1 6
Processing: 3 11 3.4 11 20
Waiting: 3 11 3.4 11 20
Total: 8 12 3.2 12 21

Percentage of the requests served within a certain time (ms)
50% 12
66% 12
75% 12
80% 13
90% 17
95% 19
98% 21
99% 21
100% 21 (longest request)

dbench(ストレージ性能 )

dbench 5 –timelimit=10
dbench version 4.00 – Copyright Andrew Tridgell 1999-2004

Running for 10 seconds with load ‘/usr/local/share/client.txt’ and minimum warmup 2 secs
0 of 5 processes prepared for launch 0 sec
5 of 5 processes prepared for launch 0 sec
releasing clients
5 68193 1921.36 MB/sec warmup 1 sec latency 21.100 ms
5 236427 2462.43 MB/sec execute 1 sec latency 21.028 ms
5 326832 2454.17 MB/sec execute 2 sec latency 17.050 ms
5 417205 2458.22 MB/sec execute 3 sec latency 19.025 ms
5 509438 2469.18 MB/sec execute 4 sec latency 20.040 ms
5 600760 2471.61 MB/sec execute 5 sec latency 19.032 ms
5 693914 2481.45 MB/sec execute 6 sec latency 17.105 ms
5 784933 2481.54 MB/sec execute 7 sec latency 18.016 ms
5 875160 2475.71 MB/sec execute 8 sec latency 16.211 ms
5 963159 2464.69 MB/sec execute 9 sec latency 18.050 ms
5 cleanup 10 sec
0 cleanup 10 sec

Operation Count AvgLat MaxLat
—————————————-
NTCreateX 783483 0.015 17.159
Close 575448 0.001 17.100
Rename 33183 0.029 13.403
Unlink 158251 0.015 17.099
Deltree 16 1.936 6.098
Mkdir 8 0.004 0.006
Qpathinfo 710183 0.008 19.021
Qfileinfo 124329 0.001 15.016
Qfsinfo 130224 0.004 15.014
Sfileinfo 63824 0.005 14.012
Find 274545 0.029 20.038
WriteX 389899 0.014 17.194
ReadX 1228455 0.004 16.228
LockX 2552 0.003 0.017
UnlockX 2552 0.002 0.015
Flush 54910 0.001 11.169

Throughput 2464.69 MB/sec 5 clients 5 procs max_latency=21.028 ms


Comment

*