Remake: Unixbench

Preparando el servidor OpenVZ para la "I Noite Drupal & GNU/Linux" de Mugardos he encontrado una perla en Google Code: UnixBench. El objetivo de la aplicación es muy claro: ser un indicador de rendimiento para sistemas operativos basados en Unix partiendo de los resultados base de un SPARCstation 20-60(valor 10,0)

Entre los múltiples tests realizados destacan:
.- Dhrystone : Prueba de manejo de cadenas(sin coma flotante :P)
.- Whetstone: Mide la velocidad y efiencia de las operaciones con coma flotante.
.- Execl Throughput : mide la velocidad a la cual los datos pueden ser transferidos de un archivo a otro, con diferentes tamaños de búfer.

Un consejo. No es un test rápido. En un AMD Athlon(tm) 64 X2 Dual Core Processor 4800+ con frecuencia de 2,5ghz y 8GB de RAM el test necesitó más de 40 minutos para finalizar y mostrar resultados.
Para curiosos, geek y demás fauna, ahí van los resultados:



Version 5.1.3 Based on the Byte Magazine Unix Benchmark

Multi-CPU version Version 5 revisions by Ian Smith,
Sunnyvale, CA, USA
January 13, 2011 johantheghost at yahoo period com


1 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10

1 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10

1 x Execl Throughput 1 2 3

1 x File Copy 1024 bufsize 2000 maxblocks 1 2 3

1 x File Copy 256 bufsize 500 maxblocks 1 2 3

1 x File Copy 4096 bufsize 8000 maxblocks 1 2 3

1 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10

1 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10

1 x Process Creation 1 2 3

1 x System Call Overhead 1 2 3 4 5 6 7 8 9 10

1 x Shell Scripts (1 concurrent) 1 2 3

1 x Shell Scripts (8 concurrent) 1 2 3

2 x Dhrystone 2 using register variables 1 2 3 4 5 6 7 8 9 10

2 x Double-Precision Whetstone 1 2 3 4 5 6 7 8 9 10

2 x Execl Throughput 1 2 3

2 x File Copy 1024 bufsize 2000 maxblocks 1 2 3

2 x File Copy 256 bufsize 500 maxblocks 1 2 3

2 x File Copy 4096 bufsize 8000 maxblocks 1 2 3

2 x Pipe Throughput 1 2 3 4 5 6 7 8 9 10

2 x Pipe-based Context Switching 1 2 3 4 5 6 7 8 9 10

2 x Process Creation 1 2 3

2 x System Call Overhead 1 2 3 4 5 6 7 8 9 10

2 x Shell Scripts (1 concurrent) 1 2 3

2 x Shell Scripts (8 concurrent) 1 2 3

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

System: polinico: GNU/Linux
OS: GNU/Linux -- 2.6.32-5-openvz-amd64 -- #1 SMP Mon Mar 7 22:25:57 UTC 2011
Machine: x86_64 (unknown)
Language: en_US.utf8 (charmap="ANSI_X3.4-1968", collate="ANSI_X3.4-1968")
CPU 0: AMD Athlon(tm) 64 X2 Dual Core Processor 4800+ (2009.1 bogomips)
Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, AMD virtualization, SYSCALL/SYSRET
CPU 1: AMD Athlon(tm) 64 X2 Dual Core Processor 4800+ (2009.1 bogomips)
Hyper-Threading, x86-64, MMX, AMD MMX, Physical Address Ext, SYSENTER/SYSEXIT, AMD virtualization, SYSCALL/SYSRET
18:09:05 up 1:48, 3 users, load average: 0.25, 0.30, 0.23; runlevel 2

------------------------------------------------------------------------
Benchmark Run: sáb abr 09 2011 18:09:05 - 18:38:11
2 CPUs in system; running 1 parallel copy of tests

Dhrystone 2 using register variables 18476798.9 lps (10.0 s, 7 samples)
Double-Precision Whetstone 2613.2 MWIPS (9.9 s, 7 samples)
Execl Throughput 1260.8 lps (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 308577.4 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 100308.1 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 697625.5 KBps (30.0 s, 2 samples)
Pipe Throughput 987893.9 lps (10.0 s, 7 samples)
Pipe-based Context Switching 102266.6 lps (10.0 s, 7 samples)
Process Creation 3968.2 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 2277.5 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 804.0 lpm (60.0 s, 2 samples)
System Call Overhead 2051427.4 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 18476798.9 1583.3
Double-Precision Whetstone 55.0 2613.2 475.1
Execl Throughput 43.0 1260.8 293.2
File Copy 1024 bufsize 2000 maxblocks 3960.0 308577.4 779.2
File Copy 256 bufsize 500 maxblocks 1655.0 100308.1 606.1
File Copy 4096 bufsize 8000 maxblocks 5800.0 697625.5 1202.8
Pipe Throughput 12440.0 987893.9 794.1
Pipe-based Context Switching 4000.0 102266.6 255.7
Process Creation 126.0 3968.2 314.9
Shell Scripts (1 concurrent) 42.4 2277.5 537.2
Shell Scripts (8 concurrent) 6.0 804.0 1340.0
System Call Overhead 15000.0 2051427.4 1367.6
========
System Benchmarks Index Score 667.9

------------------------------------------------------------------------
Benchmark Run: sáb abr 09 2011 18:38:11 - 19:07:26
2 CPUs in system; running 2 parallel copies of tests

Dhrystone 2 using register variables 36832151.8 lps (10.0 s, 7 samples)
Double-Precision Whetstone 5246.4 MWIPS (9.9 s, 7 samples)
Execl Throughput 3706.6 lps (29.6 s, 2 samples)
File Copy 1024 bufsize 2000 maxblocks 402547.4 KBps (30.0 s, 2 samples)
File Copy 256 bufsize 500 maxblocks 121746.1 KBps (30.0 s, 2 samples)
File Copy 4096 bufsize 8000 maxblocks 911624.0 KBps (30.0 s, 2 samples)
Pipe Throughput 1990029.1 lps (10.0 s, 7 samples)
Pipe-based Context Switching 437120.2 lps (10.0 s, 7 samples)
Process Creation 10823.0 lps (30.0 s, 2 samples)
Shell Scripts (1 concurrent) 6206.0 lpm (60.0 s, 2 samples)
Shell Scripts (8 concurrent) 809.3 lpm (60.1 s, 2 samples)
System Call Overhead 2618061.3 lps (10.0 s, 7 samples)

System Benchmarks Index Values BASELINE RESULT INDEX
Dhrystone 2 using register variables 116700.0 36832151.8 3156.1
Double-Precision Whetstone 55.0 5246.4 953.9
Execl Throughput 43.0 3706.6 862.0
File Copy 1024 bufsize 2000 maxblocks 3960.0 402547.4 1016.5
File Copy 256 bufsize 500 maxblocks 1655.0 121746.1 735.6
File Copy 4096 bufsize 8000 maxblocks 5800.0 911624.0 1571.8
Pipe Throughput 12440.0 1990029.1 1599.7
Pipe-based Context Switching 4000.0 437120.2 1092.8
Process Creation 126.0 10823.0 859.0
Shell Scripts (1 concurrent) 42.4 6206.0 1463.7
Shell Scripts (8 concurrent) 6.0 809.3 1348.9
System Call Overhead 15000.0 2618061.3 1745.4
========
System Benchmarks Index Score 1258.5