Difference between revisions of "My hobby benchmarks"

From ThorstensHome
Jump to: navigation, search
(InterNet)
(InterNet)
 
(One intermediate revision by one user not shown)
Line 790: Line 790:
  
 
http://www.speedtest.net/de/ via cabled internet from Rauenberg via 1&1 16Mb, 2015-08-27: ping 32 ms, down 13.21 Mb/s, up 0.92 Mb/s
 
http://www.speedtest.net/de/ via cabled internet from Rauenberg via 1&1 16Mb, 2015-08-27: ping 32 ms, down 13.21 Mb/s, up 0.92 Mb/s
 +
 +
http://www.speedtest.net/de/ via cabled internet from Rotenberg via Telekom, before exchanging FritzBox, while dropboxing, 2018-05-12: ping 89 ms, down 0.05 Mb/s, up 0.28 Mb/s
 +
 +
http://www.speedtest.net/de/ via cabled internet from Rotenberg Telekom, after change to Fritzbox 7430, 2018-05-12: ping 27 ms, down 4.44 Mb/s, up 1.65 Mb/s
  
 
{|
 
{|

Latest revision as of 11:47, 12 May 2018

Contents

Performance

startup times

Inspiron Mini 9 (Ubuntu): 40 seconds

Latitude 2100 (Ubuntu): 60 seconds

my QEMU benchmark

QEmu guest system openSUSE 10.2, command is

1:time (for i in $(seq 1 1 10000); do echo $i>>file;done)
2:time (for i in $(seq 1 1 10000); do echo $i>>/dev/null;done)
host command times without kqemu times with kqemu times native
XEON 1       17-7-2     
XEON 2       16-7-1
PIV  1       20-8-3              6-2-2            1-0-0

my easy benchmark

Goal: Get a rough impression of system power Command is

time (for i in $(seq 1 1 10000); do echo $i>>file;done)

Or if bash is not available, write a script that does this and call it using time

system            real time  user time  system time
Nokia N810        2.8s       0.8s         0.9s
2.4GHz Core2 Quad 0.3s       0.2s         0.1s
raspberry pi      3.7s       2.7s         1.0s

my memory benchmark

Goal: Get a rough impression of memory throughput Command is

dd if=/dev/zero of=/dev/shm/test bs=1M count=400

Results:

system           throughput/(MB/s)    command if not default
Studio XPS       4400
Inspiron Mini 9   395
raspberry pi      134             dd if=/dev/zero of=/dev/shm/test bs=1M count=40

Compilation

simple compilation

ARM processor

Nokia-N810-43-7:~# cat /proc/cpuinfo | grep Processor
Processor	: ARMv6-compatible processor rev 2 (v6l)
Nokia-N810-43-7:~# cat main.cpp
#include <iostream>
int main()
{
  std::cout << "hello world" << std::endl;
}
Nokia-N810-43-7:~# time g\+\+-3.4 main.cpp 
real	0m 7.97s
user	0m 7.60s
sys	0m 0.35s
pi@raspberrypi ~ $ cat /proc/cpuinfo | grep Processor
Processor       : ARMv6-compatible processor rev 7 (v6l)
pi@raspberrypi ~ $ cat main.cpp
#include <iostream>
int main()
{
  std::cout << "hello world" << std::endl;
}
pi@raspberrypi ~ $ time g++-4.6 main.cpp

real    0m4.230s
user    0m4.000s
sys     0m0.180s

ATOM processor

tstaerk@dell-desktop:~$ hwinfo --cpu --short
cpu:                                                            
                       Intel(R) Atom(TM) CPU N270   @ 1.60GHz, 800 MHz
                       Intel(R) Atom(TM) CPU N270   @ 1.60GHz, 800 MHz
tstaerk@dell-desktop:~$ cat main.cpp 
#include <iostream>
int main() 
{
  std::cout << "hello world" << std::endl;
}
tstaerk@dell-desktop:~$ g++ --version
g++ (Ubuntu 4.3.3-5ubuntu4) 4.3.3
Copyright (C) 2008 Free Software Foundation, Inc.
This is free software; see the source for copying conditions.  There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.

tstaerk@dell-desktop:~$ time g++ main.cpp 

real	0m0.880s
user	0m0.752s
sys	0m0.096s

Linux kernel compilation

Here I compare the compilation times of the Linux kernel 2.6.27 over different platforms. As time I use the real time that I get from e.g. time make -j4. When comparing keep in mind

  • I am a lazy guy and use default installations for all distributions
  • some compilations are on the x64 platform, others on x32
  • different distributions bring different C compilers and library environments
  • some of the results are virtualized, some not
  • yes "" | make config produces a different .config file for different hardware
  • this is a real-world benchmark, not a synthetic one
    • this is primary a CPU benchmark, but disk I/O plays a role

Commands

Here are the commands for the benchmark

wget ftp://ftp.kernel.org/pub/linux/kernel/v2.6/linux-2.6.27.2.tar.gz
rm -rf linux-2.6.27.2
tar xvzf linux-2.6.27.2.tar.gz
cd linux-2.6.27.2
yes "" | make config
time make -j4

If the make command is different, it is notified in the results table.

Results

computer OS gcc time command remark
4 SUSE 11.1 4.3.2 73min make -j4 on a USB harddisk
6 SUSE 11.1 4.3.2 14min make -j4
6 SUSE 11.1 4.3.2 25min make -j2
6 SUSE 11.1 4.3.2 50min make -j1
6.1 SUSE 11.1 4.3.2 68min make -j4
6.2 SUSE 11.1 4.3.2 54min make -j4
Latitude 2100 Ubuntu 9.04 4.3.3 137min make -j4
Studio XPS SUSE 11.2 4.4.1 1m 20s make -j8
Studio XPS SUSE 11.2 4.4.1 1m 18s make -j8 how's variance?
Studio XPS SUSE 11.2 4.4.1 1m 41s make -j4
Studio XPS SUSE 11.2 4.4.1 1m 43s make -j4 how's variance?
Studio XPS SUSE 11.2 4.4.1 2m 43s make -j2
Studio XPS SUSE 11.2 4.4.1 2m 43s make -j2 how's variance?
Studio XPS SUSE 11.2 4.4.1 5m 21s make
8.1 SUSE 11.2 4.4.1 1m 38s make -j8
8.1 SUSE 11.2 4.4.1 1m 38s make -j8 how's variance?
Computer (processors/cores/threads)
4: 2x1.83GHz P-M, 2 GB RAM (1/2/2)
6: 4x2.4GHz Intel Core2 Quad (x64), 4 GB RAM (1/4/4)
6.1: VMWare Server 2.0 virtual machine with 1 vCPUs, 1 GB RAM on (6) with SUSE 11.1
6.2: VMWare Server 2.0 virtual machine with 2 vCPUs, 1 GB RAM on (6) with SUSE 11.1
7: Intel Atom 1.6GHz (1/1/2)
8: Core i7 860 2.8GHz (1/4/8)
8.1: KVM virtual machine with 8 vCPUs, 1 GB RAM on (8) with SUSE 11.2

KDE compilation benchmark

The KDE compilation benchmark was supposed to show the KDE compilation capabilities of distinct systems. However I use it less in recent times because compile time largely differs depending on

  • what libraries you have installed
  • what library versions you have installed
  • what KDE version you compile.

To resolve all this, I use my Linux kernel compilation benchmark.

Computer command time   Env remark
1        1       2:39h  1
2        1       0:55h  1   HT on
2        1       0:59h  1   HT off
3        2       41:31m 2   
2        2       1:35h  2   HT on
4        3       16:24m 3   make -j2 
2        3       43:23  3 
5        2        2:55m 2   make -j32
6        4       15:36m 4   make -j8
6        5        1:13h 5   (virtualbox)
6        5       38:32m 6   make -j2

Computer (processors/cores/threads)
1 1.5 GHz P-IV, 256 MB RAM (1/1/1)
2 3.0 GHz P-IV, 512 MB RAM (1/1/2)
3 1.73GHz P-M, 512 MB RAM (1/1/1)
4 2x1.83GHz P-M, 2 GB RAM (1/2/2)
5 16x2.92GHz Xeon, 128 GB RAM (8/16/16)
6 4x2.4GHz x64, 4 GB RAM (1/4/4)

Environment
1: GCC 3
2: GCC 4, more and newer code
3: GCC 4, more and newer code, CMake, QT 4, KDEPIM 656855
4: GCC 4, KDEPIM Revision: 773158, Automake, QT 3
5: GCC 4, KDEPIM Revision: 854206, CMake, QT 4 on VirtualBox
6: GCC 4, KDEPIM Revision: 854206, CMake, QT 4 on VMWare VM, 2 vCPU
Command 
1 date >> date.dat && rm -rf bench && tar -xvf bench.tar && cd bench/kdepim/ && make -f Makefile.cvs && ./configure && make && make install && cd ../.. && date >> date.dat
2 date >> date.dat && rm -rf bench && tar -xvf bench.tar && cd bench/kdepim/ && make -f Makefile.cvs && ./configure && make -j4 && make install && cd ../.. && date >> date.dat
3 make clean; rm CMakeCache.txt; date >>date.txt && cmakekde && date >>date.txt
4 make clean && date>>date.dat && make -f Makefile.cvs && ./configure && unsermake -j8 && unsermake install && date >> date.dat
5 make clean; rm CMakeCache.txt; date >>date.txt && cmake . && make && make install && date >>date.txt

disk I/O

The call

bonnie -o_direct

works on SUSE 10.0, but not on SUSE 11.1.

USB disk on scorpio, the lower USB card.

scorpio:/media/disk # bonnie -o_direct -s 1
Bonnie: Warning: You have 250MB RAM, but you test with only 1MB datasize!
Bonnie:          This might yield unrealistically good results,
Bonnie:          for reading and seeking and writing.
Bonnie 1.4: File './Bonnie.4608', size: 1048576, volumes: 1
Using O_DIRECT for block based I/O
Writing with putc()...         done:    116 kB/s   5.0 %CPU

IDE disk on scorpio

scorpio:~ # bonnie -o_direct -s 1
Bonnie: Warning: You have 250MB RAM, but you test with only 1MB datasize!
Bonnie:          This might yield unrealistically good results,
Bonnie:          for reading and seeking and writing.
Bonnie 1.4: File './Bonnie.5050', size: 1048576, volumes: 1
Using O_DIRECT for block based I/O 
Writing with putc()...         done:  16079 kB/s  81.7 %CPU

USB disk on duffman (Latitude D610)

duffman:~ # bonnie -o_direct -s 1
Bonnie: Warning: You have 503MB RAM, but you test with only 1MB datasize!
Bonnie:          This might yield unrealistically good results,
Bonnie:          for reading and seeking and writing.
Bonnie 1.4: File './Bonnie.9098', size: 1048576, volumes: 1
Using O_DIRECT for block based I/O
Writing with putc()...         done:   8440 kB/s  52.8 %CPU

active USB disk on chris (Latitude D620)

duffman:~ # bonnie -o_direct -s 1
Bonnie: Warning: You have 2026MB RAM, but you test with only 1MB datasize!
Bonnie:          This might yield unrealistically good results,
Bonnie:          for reading and seeking and writing.
Bonnie 1.4: File './Bonnie.5974', size: 1048576, volumes: 1
Using O_DIRECT for block based I/O
Writing with putc()...         done:   9081 kB/s  49.7 %CPU

internal disk in bort (Inspiron 530)

bort:~ # bonnie -s 1000
Bonnie 1.4: File './Bonnie.13566', size: 1048576000, volumes: 1
Writing with putc()...         done:  67207 kB/s  92.1 %CPU

Internal 1TB 32MB Samsung disk in (bort=tweedleburg)

tweedleburg:/mnt/sdb1 # bonnie -s 1000
Bonnie 1.4: File './Bonnie.5710', size: 1048576000, volumes: 1
Writing with putc()...         done:  67345 kB/s  92.9 %CPU

Toshiba disk from 2011-07-18

I test the Toshiba 1 TB USB 3 disk on my Studio XPS formatted with

NTFS

dd write
dd if=/dev/zero of=datei bs=4096 count=1000000
1000000+0 records in
1000000+0 records out
4096000000 bytes (4.1 GB) copied, 103.429 s, 39.6 MB/s

ext4

bonnie
tweedleburg:/mnt/sdg1 # bonnie -s 1000
Bonnie 1.4: File './Bonnie.9084', size: 1048576000, volumes: 1
Writing with putc()...         done:  44337 kB/s  65.0 %CPU
tweedleburg:/mnt/sdg1 # bonnie -s 10000
Bonnie 1.4: File './Bonnie.9111', size: 10485760000, volumes: 1
Writing with putc()...         done:  36879 kB/s  54.2 %CPU

Now the disk is connected to a USB 3 port via a USB 3 cable

tweedleburg:/mnt/sdg1 # bonnie -s 1000
Bonnie 1.4: File './Bonnie.1458', size: 1048576000, volumes: 1
Writing with putc()...         done:  66572 kB/s  98.2 %CPU
tweedleburg:/mnt/sdg1 # bonnie -s 10000
Bonnie 1.4: File './Bonnie.1554', size: 10485760000, volumes: 1
Writing with putc()...         done:  66571 kB/s  97.4 %CPU
dd write
dd if=/dev/zero of=datei bs=4096 count=1000000
  • result: 37.6 MB/s; 35.0 MB/s; 34.8 MB/s
  • after using a USB 3 cable
  • result: 120 MB/s; 112 MB/s; 113 MB/s
hdparm

Using USB 3.0 port, USB 2.0 cable:

tweedleburg:/mnt/sdg1 # hdparm -tT /dev/sdg

/dev/sdg:
 Timing cached reads:   20308 MB in  2.00 seconds = 10163.04 MB/sec
 Timing buffered disk reads: 110 MB in  3.05 seconds =  36.05 MB/sec

Using USB 2.0 port, USB 2.0 cable:

hdparm -tT /dev/sdh

/dev/sdh:
 Timing cached reads:   20016 MB in  2.00 seconds = 10017.85 MB/sec
 Timing buffered disk reads: 104 MB in  3.05 seconds =  34.11 MB/sec

Using USB 3.0 port, USB 3.0 cable:

hdparm -tT /dev/sdg

/dev/sdg:
 Timing cached reads:   20762 MB in  2.00 seconds = 10391.41 MB/sec
 Timing buffered disk reads: 348 MB in  3.01 seconds = 115.57 MB/sec
iops

Disk is attached via a USB 2.0 cable to a USB 3.0 port:

wget http://hg.sickos.org/iops/raw-file/3825f2a593ff/iops
tweedleburg:/mnt/sdg1 # python iops /dev/sdg1
/dev/sdg1, 999.15 GB, 32 threads:
 512   B blocks:   65.4 IO/s,  32.7 KiB/s (267.8 kbit/s)
   1 KiB blocks:   61.6 IO/s,  61.6 KiB/s (504.3 kbit/s)
   2 KiB blocks:   59.7 IO/s, 119.4 KiB/s (978.0 kbit/s)
   4 KiB blocks:   53.3 IO/s, 213.1 KiB/s (  1.7 Mbit/s)
   8 KiB blocks:   52.2 IO/s, 417.4 KiB/s (  3.4 Mbit/s)
  16 KiB blocks:   51.1 IO/s, 816.9 KiB/s (  6.7 Mbit/s)
  32 KiB blocks:   46.1 IO/s,   1.4 MiB/s ( 12.1 Mbit/s)
  64 KiB blocks:   40.8 IO/s,   2.5 MiB/s ( 21.4 Mbit/s)
 128 KiB blocks:   31.3 IO/s,   3.9 MiB/s ( 32.8 Mbit/s)
tweedleburg:~ # python iops /mnt/sdg1/datei
/mnt/sdg1/datei,   4.10 GB, 32 threads:
 512   B blocks:  289.2 IO/s, 144.6 KiB/s (  1.2 Mbit/s)
   1 KiB blocks:  291.4 IO/s, 291.4 KiB/s (  2.4 Mbit/s)
   2 KiB blocks:  268.1 IO/s, 536.3 KiB/s (  4.4 Mbit/s)
   4 KiB blocks:  244.0 IO/s, 975.9 KiB/s (  8.0 Mbit/s)
   8 KiB blocks:  249.6 IO/s,   1.9 MiB/s ( 16.4 Mbit/s)
  16 KiB blocks:  222.2 IO/s,   3.5 MiB/s ( 29.1 Mbit/s)
  32 KiB blocks:  177.8 IO/s,   5.6 MiB/s ( 46.6 Mbit/s)
  64 KiB blocks:  130.9 IO/s,   8.2 MiB/s ( 68.6 Mbit/s)
 128 KiB blocks:  115.0 IO/s,  14.4 MiB/s (120.6 Mbit/s)
 256 KiB blocks:   82.4 IO/s,  20.6 MiB/s (172.9 Mbit/s)
 512 KiB blocks:   58.5 IO/s,  29.3 MiB/s (245.5 Mbit/s)
   1 MiB blocks:   37.2 IO/s,  37.2 MiB/s (311.8 Mbit/s)
   2 MiB blocks:   20.3 IO/s,  40.6 MiB/s (340.7 Mbit/s)

Hm, seems this datei has been read completely into memory. Or was it that we read from the disk where the executable is situated?

tweedleburg:~ # python iops /dev/sdg1
/dev/sdg1, 999.15 GB, 32 threads:
 512   B blocks:   65.4 IO/s,  32.7 KiB/s (268.0 kbit/s)
   1 KiB blocks:   63.4 IO/s,  63.4 KiB/s (519.2 kbit/s)
   2 KiB blocks:   60.4 IO/s, 120.8 KiB/s (989.2 kbit/s)
   4 KiB blocks:   53.4 IO/s, 213.8 KiB/s (  1.8 Mbit/s)
   8 KiB blocks:   52.9 IO/s, 422.8 KiB/s (  3.5 Mbit/s)
  16 KiB blocks:   51.5 IO/s, 823.8 KiB/s (  6.7 Mbit/s)
  32 KiB blocks:   48.8 IO/s,   1.5 MiB/s ( 12.8 Mbit/s)
  64 KiB blocks:   39.9 IO/s,   2.5 MiB/s ( 20.9 Mbit/s)
 128 KiB blocks:   31.8 IO/s,   4.0 MiB/s ( 33.4 Mbit/s)

Now disk is connected via a USB 3 cable to a USB 3 port:

tweedleburg:/mnt/sdg1 # python iops /dev/sdg1
/dev/sdg1, 999.15 GB, 32 threads:
 512   B blocks:   65.3 IO/s,  32.6 KiB/s (267.4 kbit/s)
   1 KiB blocks:   64.4 IO/s,  64.4 KiB/s (527.7 kbit/s)
   2 KiB blocks:   61.2 IO/s, 122.4 KiB/s (  1.0 Mbit/s)
   4 KiB blocks:   56.9 IO/s, 227.7 KiB/s (  1.9 Mbit/s)
   8 KiB blocks:   53.3 IO/s, 426.2 KiB/s (  3.5 Mbit/s)
  16 KiB blocks:   51.5 IO/s, 824.1 KiB/s (  6.8 Mbit/s)
  32 KiB blocks:   46.6 IO/s,   1.5 MiB/s ( 12.2 Mbit/s)
  64 KiB blocks:   43.3 IO/s,   2.7 MiB/s ( 22.7 Mbit/s)
 128 KiB blocks:   37.7 IO/s,   4.7 MiB/s ( 39.5 Mbit/s)
 256 KiB blocks:   29.0 IO/s,   7.3 MiB/s ( 60.9 Mbit/s)

Verbatim disk from 2010-03-13

I test the Verbatim disk 1.5TB on my Studio XPS formatted with ext4.

eSATA

Connected via eSATA port

bonnie
linux-q7sh:/mnt/sdg1 # bonnie -s 1000
Bonnie: Warning: You have 1845MB RAM, but you test with only 1000MB datasize!
Bonnie:          This might yield unrealistically good results,
Bonnie:          for reading and seeking and writing.
Bonnie 1.4: File './Bonnie.24308', size: 1048576000, volumes: 1 
Writing with putc()...         done:  69377 kB/s  99.5 %CPU
linux-q7sh:/mnt/sdg1 # bonnie -s 10000
Bonnie 1.4: File './Bonnie.27329', size: 10485760000, volumes: 1
Writing with putc()...         done:  61961 kB/s  89.8 %CPU
Rewriting...                   done:  55824 kB/s   8.2 %CPU
Writing intelligently...       done: 121668 kB/s  11.3 %CPU
Reading with getc()...         done:  71023 kB/s  91.6 %CPU
Reading intelligently...       done: 112878 kB/s   8.0 %CPU
Seeker 1...Seeker 2...Seeker 3...start 'em...done...done...done...
              ---Sequential Output (nosync)--- ---Sequential Input-- --Rnd Seek-
              -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --04k (03)-
Machine    MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU   /sec %CPU
linux- 1*10000 61961 89.8121668 11.3 55824  8.2 71023 91.6112878  8.0  186.7  0.6

The numbers are reproducible:

linux-q7sh:/mnt/sdg1 # bonnie -s 10000
Bonnie 1.4: File './Bonnie.28211', size: 10485760000, volumes: 1
Writing with putc()...         done:  60538 kB/s  87.6 %CPU
Rewriting...                   done:  56210 kB/s   8.2 %CPU
Writing intelligently...       done: 121460 kB/s  11.3 %CPU
Reading with getc()...         done:  70686 kB/s  91.5 %CPU
Reading intelligently...       done: 112567 kB/s   8.1 %CPU
Seeker 1...Seeker 2...Seeker 3...start 'em...done...done...done...
              ---Sequential Output (nosync)--- ---Sequential Input-- --Rnd Seek-
              -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --04k (03)-
Machine    MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU   /sec %CPU
linux- 1*10000 60538 87.6121460 11.3 56210  8.2 70686 91.5112567  8.1  199.5  0.6
dd write
linux-q7sh:/mnt/sdg1 # dd if=/dev/zero of=datei bs=4096 count=1000000
1000000+0 records in
1000000+0 records out
4096000000 bytes (4.1 GB) copied, 25.2149 s, 162 MB/s
linux-q7sh:/mnt/sdg1 # dd oflag=direct if=/dev/zero of=datei bs=4096 count=1000000
1000000+0 records in
1000000+0 records out
4096000000 bytes (4.1 GB) copied, 86.6259 s, 47.3 MB/s
cp
linux-q7sh:/mnt/sdg1 # ll /tmp/disk.img; sync; echo 3 > /proc/sys/vm/drop_caches; time (cp /tmp/disk.img .;sync)
-rw-r--r-- 1 root root 1024000000 Mar 13 11:00 /tmp/disk.img

real    0m13.793s
user    0m0.054s
sys     0m4.434s
linux-q7sh:/mnt/sdg1 # ll /tmp/disk.img; sync; echo 3 > /proc/sys/vm/drop_caches; time (cp /tmp/disk.img .;sync)
-rw-r--r-- 1 root root 1024000000 Mar 13 11:00 /tmp/disk.img

real    0m13.899s
user    0m0.047s
sys     0m4.533s
linux-q7sh:/mnt/sdg1 # mkdir test
linux-q7sh:/mnt/sdg1 # ll disk.img; sync; echo 3 > /proc/sys/vm/drop_caches; time (cp disk.img test;sync)
-rw-r--r-- 1 root root 1024000000 Mar 13 18:06 disk.img

real    0m18.126s
user    0m0.052s
sys     0m6.037s
linux-q7sh:/mnt/sdg1 # ll disk.img; sync; echo 3 > /proc/sys/vm/drop_caches; time (cp disk.img test;sync)
-rw-r--r-- 1 root root 1024000000 Mar 13 18:06 disk.img

real    0m17.821s
user    0m0.046s
sys     0m6.037s
hdparm
linux-q7sh:/mnt/sdg1 # hdparm -tT /dev/sdg

/dev/sdg:
 Timing cached reads:   19888 MB in  2.00 seconds = 9954.92 MB/sec
 Timing buffered disk reads:  346 MB in  3.00 seconds = 115.33 MB/sec
linux-q7sh:/mnt/sdg1 # hdparm -tT /dev/sdg1

/dev/sdg1:
 Timing cached reads:   20264 MB in  2.00 seconds = 10143.18 MB/sec
 Timing buffered disk reads:  346 MB in  3.01 seconds = 115.12 MB/sec
iotest
tweedleburg:/mnt/sdg1 # python /root/iotest/iotest /dev/sdj
Reading
/dev/sdj,   1.50 TB:
 512   B blocks:   59.4 IOs/s,  29.7 KiB/s (243.2 kbit/s)
   1 KiB blocks:   61.7 IOs/s,  61.7 KiB/s (505.3 kbit/s)
   2 KiB blocks:   60.3 IOs/s, 120.5 KiB/s (987.1 kbit/s)
   4 KiB blocks:   60.7 IOs/s, 242.6 KiB/s (  2.0 Mbit/s)
   8 KiB blocks:   59.3 IOs/s, 474.3 KiB/s (  3.9 Mbit/s)
  16 KiB blocks:   58.5 IOs/s, 936.0 KiB/s (  7.7 Mbit/s)
  32 KiB blocks:   53.1 IOs/s,   1.7 MiB/s ( 13.9 Mbit/s)
  64 KiB blocks:   53.3 IOs/s,   3.3 MiB/s ( 28.0 Mbit/s)
 128 KiB blocks:   53.0 IOs/s,   6.6 MiB/s ( 55.6 Mbit/s)
 256 KiB blocks:   49.3 IOs/s,  12.3 MiB/s (103.3 Mbit/s)
 512 KiB blocks:   43.7 IOs/s,  21.9 MiB/s (183.4 Mbit/s)
   1 MiB blocks:   34.5 IOs/s,  34.5 MiB/s (289.4 Mbit/s)
   2 MiB blocks:   23.9 IOs/s,  47.8 MiB/s (401.0 Mbit/s)
   4 MiB blocks:   16.5 IOs/s,  66.0 MiB/s (553.5 Mbit/s)
   8 MiB blocks:    9.6 IOs/s,  77.0 MiB/s (646.1 Mbit/s)
  16 MiB blocks:    5.3 IOs/s,  84.4 MiB/s (707.6 Mbit/s)
  32 MiB blocks:    1.8 IOs/s,  56.2 MiB/s (471.3 Mbit/s)
  64 MiB blocks:    0.9 IOs/s,  58.7 MiB/s (492.7 Mbit/s)

USB

Disk now connected via USB 2 port

bonnie
linux-q7sh:/mnt/sdg1 # bonnie -s 10000
Bonnie 1.4: File './Bonnie.30955', size: 10485760000, volumes: 1
Writing with putc()...         done:  32764 kB/s  50.1 %CPU
Rewriting...                   done:  13831 kB/s   2.0 %CPU
Writing intelligently...       done:  31763 kB/s   3.6 %CPU
Reading with getc()...         done:  28080 kB/s  59.0 %CPU
Reading intelligently...       done:  30322 kB/s   2.2 %CPU
Seeker 1...Seeker 2...Seeker 3...start 'em...done...done...done...
              ---Sequential Output (nosync)--- ---Sequential Input-- --Rnd Seek-
              -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --04k (03)-
Machine    MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU   /sec %CPU
linux- 1*10000 32764 50.1 31763  3.6 13831  2.0 28080 59.0 30322  2.2  165.1  0.7

This is also reproducible:

linux-q7sh:/mnt/sdg1 # bonnie -s 10000
Bonnie 1.4: File './Bonnie.1171', size: 10485760000, volumes: 1
Writing with putc()...         done:  33053 kB/s  50.5 %CPU
Rewriting...                   done:  13759 kB/s   2.0 %CPU
Writing intelligently...       done:  32133 kB/s   3.6 %CPU
Reading with getc()...         done:  30158 kB/s  61.5 %CPU
Reading intelligently...       done:  28976 kB/s   2.3 %CPU
Seeker 1...Seeker 2...Seeker 3...start 'em...done...done...done...
              ---Sequential Output (nosync)--- ---Sequential Input-- --Rnd Seek-
              -Per Char- --Block--- -Rewrite-- -Per Char- --Block--- --04k (03)-
Machine    MB K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU K/sec %CPU   /sec %CPU
linux- 1*10000 33053 50.5 32133  3.6 13759  2.0 30158 61.5 28976  2.3  174.2  0.5
cp
linux-q7sh:/mnt/sdg1 # sync; echo 3 > /proc/sys/vm/drop_caches; time (cp /tmp/disk.img .;sync)

real    0m40.560s
user    0m0.040s 
sys     0m7.571s 
linux-q7sh:/mnt/sdg1 # ll /tmp/disk.img; sync; echo 3 > /proc/sys/vm/drop_caches; time (cp /tmp/disk.img .;sync)
-rw-r--r-- 1 root root 1024000000 Mar 13 11:00 /tmp/disk.img                                                    

real    0m40.095s
user    0m0.057s 
sys     0m7.697s

SanDisk Cruzer USB Stick from 2011-12-01

iops

wget http://benjamin-schweizer.de/files/iops/iops-2011-02-11
# python iops-2011-02-11 /dev/sdc
/dev/sdc,  16.01 GB, 32 threads:
 512   B blocks:  884.7 IO/s, 442.3 KiB/s (  3.6 Mbit/s)
   1 KiB blocks:  699.3 IO/s, 699.3 KiB/s (  5.7 Mbit/s)
   2 KiB blocks:  589.0 IO/s,   1.2 MiB/s (  9.7 Mbit/s)
   4 KiB blocks:  422.4 IO/s,   1.6 MiB/s ( 13.8 Mbit/s)
   8 KiB blocks:  385.1 IO/s,   3.0 MiB/s ( 25.2 Mbit/s)
  16 KiB blocks:  285.2 IO/s,   4.5 MiB/s ( 37.4 Mbit/s)
  32 KiB blocks:  261.1 IO/s,   8.2 MiB/s ( 68.5 Mbit/s)
  64 KiB blocks:  142.9 IO/s,   8.9 MiB/s ( 74.9 Mbit/s)
 128 KiB blocks:   87.3 IO/s,  10.9 MiB/s ( 91.5 Mbit/s)
 256 KiB blocks:   66.2 IO/s,  16.5 MiB/s (138.8 Mbit/s)
 512 KiB blocks:   41.8 IO/s,  20.9 MiB/s (175.2 Mbit/s)
   1 MiB blocks:   24.8 IO/s,  24.8 MiB/s (208.4 Mbit/s)

INTEL SSDSC2MH12

Internal in my Studio XPS

iops

# python iops-2011-02-11 /dev/sda
/dev/sda, 120.03 GB, 32 threads:
 512   B blocks: 21527.2 IO/s,  10.5 MiB/s ( 88.2 Mbit/s)
   1 KiB blocks: 18599.1 IO/s,  18.2 MiB/s (152.4 Mbit/s)
   2 KiB blocks: 14790.5 IO/s,  28.9 MiB/s (242.3 Mbit/s)
   4 KiB blocks: 10359.1 IO/s,  40.5 MiB/s (339.4 Mbit/s)
   8 KiB blocks: 9719.4 IO/s,  75.9 MiB/s (637.0 Mbit/s)
  16 KiB blocks: 6171.4 IO/s,  96.4 MiB/s (808.9 Mbit/s)
  32 KiB blocks: 3697.8 IO/s, 115.6 MiB/s (969.3 Mbit/s)
  64 KiB blocks: 2109.0 IO/s, 131.8 MiB/s (  1.1 Gbit/s)
 128 KiB blocks: 1152.6 IO/s, 144.1 MiB/s (  1.2 Gbit/s)
 256 KiB blocks:  729.1 IO/s, 182.3 MiB/s (  1.5 Gbit/s)
 512 KiB blocks:  440.7 IO/s, 220.3 MiB/s (  1.8 Gbit/s)
   1 MiB blocks:  247.8 IO/s, 247.8 MiB/s (  2.1 Gbit/s)
   2 MiB blocks:  131.5 IO/s, 263.0 MiB/s (  2.2 Gbit/s)
   4 MiB blocks:   68.8 IO/s, 275.4 MiB/s (  2.3 Gbit/s)
   8 MiB blocks:   34.9 IO/s, 278.9 MiB/s (  2.3 Gbit/s)
  16 MiB blocks:   17.6 IO/s, 281.6 MiB/s (  2.4 Gbit/s)

SDHC card class 10 from 2013

iops

# python iops.py /dev/sdc
/dev/sdc,   7.96 GB, 32 threads:
 512   B blocks:  405.9 IO/s, 202.9 KiB/s (  1.7 Mbit/s)
   1 KiB blocks:  353.4 IO/s, 353.4 KiB/s (  2.9 Mbit/s)
   2 KiB blocks:  276.7 IO/s, 553.5 KiB/s (  4.5 Mbit/s)
   4 KiB blocks:  201.7 IO/s, 806.6 KiB/s (  6.6 Mbit/s)
   8 KiB blocks:  196.0 IO/s,   1.5 MiB/s ( 12.8 Mbit/s)
  16 KiB blocks:  173.9 IO/s,   2.7 MiB/s ( 22.8 Mbit/s)
  32 KiB blocks:  143.2 IO/s,   4.5 MiB/s ( 37.5 Mbit/s)
  64 KiB blocks:  100.9 IO/s,   6.3 MiB/s ( 52.9 Mbit/s)
 128 KiB blocks:   63.4 IO/s,   7.9 MiB/s ( 66.5 Mbit/s)
 256 KiB blocks:   42.5 IO/s,  10.6 MiB/s ( 89.1 Mbit/s)
 512 KiB blocks:   28.4 IO/s,  14.2 MiB/s (119.0 Mbit/s)


SDHC card class 4 from 2013

iops

# python iops.py /dev/sdc
/dev/sdc,   7.82 GB, 32 threads:
 512   B blocks:  766.6 IO/s, 383.3 KiB/s (  3.1 Mbit/s)
   1 KiB blocks:  631.0 IO/s, 631.0 KiB/s (  5.2 Mbit/s)
   2 KiB blocks:  486.6 IO/s, 973.2 KiB/s (  8.0 Mbit/s)
   4 KiB blocks:  339.2 IO/s,   1.3 MiB/s ( 11.1 Mbit/s)
   8 KiB blocks:  332.8 IO/s,   2.6 MiB/s ( 21.8 Mbit/s)
  16 KiB blocks:  273.3 IO/s,   4.3 MiB/s ( 35.8 Mbit/s)
  32 KiB blocks:  200.3 IO/s,   6.3 MiB/s ( 52.5 Mbit/s)
  64 KiB blocks:  125.7 IO/s,   7.9 MiB/s ( 65.9 Mbit/s)
 128 KiB blocks:   75.0 IO/s,   9.4 MiB/s ( 78.7 Mbit/s)
 256 KiB blocks:   48.5 IO/s,  12.1 MiB/s (101.8 Mbit/s)
 512 KiB blocks:   30.0 IO/s,  15.0 MiB/s (125.8 Mbit/s)

Internal disk

Inspiron 530n

Internal disk in (bort=tweedleburg) being /dev/sda, 1TB 32M Cache Samsung /dev/sdb:

tweedleburg:~ # hdparm -tT /dev/sda

/dev/sda:
 Timing cached reads:   7116 MB in  2.00 seconds = 3561.63 MB/sec
 Timing buffered disk reads:  212 MB in  3.03 seconds =  70.05 MB/sec
tweedleburg:~ # hdparm -tT /dev/sdb

/dev/sdb:
 Timing cached reads:   7328 MB in  2.00 seconds = 3668.03 MB/sec
 Timing buffered disk reads:  280 MB in  3.01 seconds =  93.03 MB/sec

tweedleburg:/mnt # hdparm -tT /dev/sda

Studio XPS

Testing the internal disks in my Studio XPS

hdparm
/dev/sda:
 Timing cached reads:   19312 MB in  2.00 seconds = 9666.35 MB/sec
 Timing buffered disk reads:  356 MB in  3.00 seconds = 118.48 MB/sec
iotest

IOPS tells you how many IOPS your system is capable of. Here I test my SSD vs my magnetic disk.

tweedleburg:~ # date
Sat Mar 21 09:33:50 CET 2015
tweedleburg:~ # uname -a
Linux tweedleburg 3.16.7-7-desktop #1 SMP PREEMPT Wed Dec 17 18:00:44 UTC 2014 (762f27a) x86_64 x86_64 x86_64 GNU/Linux
tweedleburg:~ # iops /dev/sda
/dev/sda, 120.03 GB, 32 threads:
 512   B blocks: 21616.6 IO/s,  10.6 MiB/s ( 88.5 Mbit/s)
   1 KiB blocks: 21706.2 IO/s,  21.2 MiB/s (177.8 Mbit/s)
   2 KiB blocks: 21747.5 IO/s,  42.5 MiB/s (356.3 Mbit/s)
   4 KiB blocks: 21792.2 IO/s,  85.1 MiB/s (714.1 Mbit/s)
   8 KiB blocks: 21756.6 IO/s, 170.0 MiB/s (  1.4 Gbit/s)
  16 KiB blocks: 13393.0 IO/s, 209.3 MiB/s (  1.8 Gbit/s)
  32 KiB blocks: 7620.6 IO/s, 238.1 MiB/s (  2.0 Gbit/s)
  64 KiB blocks: 4179.8 IO/s, 261.2 MiB/s (  2.2 Gbit/s)
 128 KiB blocks: 2169.2 IO/s, 271.2 MiB/s (  2.3 Gbit/s)
 256 KiB blocks:  747.3 IO/s, 186.8 MiB/s (  1.6 Gbit/s)
 512 KiB blocks:  445.6 IO/s, 222.8 MiB/s (  1.9 Gbit/s)
   1 MiB blocks:  248.2 IO/s, 248.2 MiB/s (  2.1 Gbit/s)
   2 MiB blocks:  131.2 IO/s, 262.5 MiB/s (  2.2 Gbit/s)
   4 MiB blocks:   68.0 IO/s, 272.0 MiB/s (  2.3 Gbit/s)
   8 MiB blocks:   33.9 IO/s, 271.3 MiB/s (  2.3 Gbit/s)
  16 MiB blocks:   17.2 IO/s, 274.6 MiB/s (  2.3 Gbit/s)
tweedleburg:~ # iops /dev/sdb
/dev/sdb,   1.00 TB, 32 threads:
 512   B blocks:   80.0 IO/s,  40.0 KiB/s (327.6 kbit/s)
   1 KiB blocks:   77.8 IO/s,  77.8 KiB/s (637.6 kbit/s)
   2 KiB blocks:   77.6 IO/s, 155.1 KiB/s (  1.3 Mbit/s)
   4 KiB blocks:   79.6 IO/s, 318.4 KiB/s (  2.6 Mbit/s)
   8 KiB blocks:   81.9 IO/s, 655.1 KiB/s (  5.4 Mbit/s)
  16 KiB blocks:   77.9 IO/s,   1.2 MiB/s ( 10.2 Mbit/s)
  32 KiB blocks:   79.3 IO/s,   2.5 MiB/s ( 20.8 Mbit/s)
  64 KiB blocks:   74.1 IO/s,   4.6 MiB/s ( 38.9 Mbit/s)
 128 KiB blocks:   78.3 IO/s,   9.8 MiB/s ( 82.1 Mbit/s)
 256 KiB blocks:   54.3 IO/s,  13.6 MiB/s (113.9 Mbit/s)
 512 KiB blocks:   39.9 IO/s,  19.9 MiB/s (167.1 Mbit/s)
   1 MiB blocks:   34.3 IO/s,  34.3 MiB/s (287.9 Mbit/s)
   2 MiB blocks:   22.6 IO/s,  45.3 MiB/s (379.7 Mbit/s)

Latitude 2100

On the Latitude 2100, not connected to power supply.

iotest
tstaerk@dell-desktop:~$ sudo python iotest-2009-09-16 /dev/sda
/dev/sda,  74 GiB:
 512   B blocks:   44.3 IOs/s,  22 KiB/s
   1 KiB blocks:   43.7 IOs/s,  43 KiB/s
   2 KiB blocks:   43.3 IOs/s,  86 KiB/s
   4 KiB blocks:   43.3 IOs/s, 173 KiB/s
   8 KiB blocks:   41.5 IOs/s, 331 KiB/s
  16 KiB blocks:   42.0 IOs/s, 672 KiB/s
  32 KiB blocks:   39.4 IOs/s,   1 MiB/s
  64 KiB blocks:   36.7 IOs/s,   2 MiB/s
 128 KiB blocks:   37.5 IOs/s,   4 MiB/s
 256 KiB blocks:   34.4 IOs/s,   8 MiB/s
 512 KiB blocks:   28.7 IOs/s,  14 MiB/s
   1 MiB blocks:   22.0 IOs/s,  22 MiB/s
   2 MiB blocks:   15.3 IOs/s,  30 MiB/s
   4 MiB blocks:    9.3 IOs/s,  37 MiB/s
   8 MiB blocks:    5.5 IOs/s,  43 MiB/s
  16 MiB blocks:    2.9 IOs/s,  47 MiB/s
  32 MiB blocks:    1.5 IOs/s,  47 MiB/s
  64 MiB blocks:    0.7 IOs/s,  43 MiB/s

graphic cards

terminal server scorpio: 55-70 FPS with 10 rows from glxgears. Connection between scorpio and bort: 100Mb. bort: 5179-5199 FPS with 10 rows from glxgears.

netWork

Testing a 100Mb connection between scorpio and bort.

WLAN

It has been said that the FritzBox 7312's WLAN is okay for a flat, but too weak for a house. The FritzBox 7270's WLAN is supposed to be strong enough for a house, it has three antennas etc.. I wanted to test this. So I put my Latitude 2100 into a cellar room and started the command

iwlist scanning | grep -Ei "quality|essid"

I used the same command with a FritzBox 7312 and with a FritzBox 7270 with the same laptop with the same distribution on the same position, same kernel etc.. I verified every result at least 3 times to make sure variance is low.

The results were

device quality of WLAN
FritzBox 7312 31/70
FritzBox 7270 41/70

InterNet

Using a Dell/Novatel UMTS card in Alzey: transmission rate from linuxintro.org to home is 6KB/s. In Frankfurt, transmission rate is 66KB/s. In Berlin: transmission rate is 158KB/s.

location Stick LED color carrier measurement date transmission speed
Alzey Dell/Novatel UMTS card - 6 KB/s
Frankfurt Dell/Novatel UMTS card - 66 KB/s
Berlin Dell/Novatel UMTS card - 158 KB/s
Berlin, Unter den Linden Fonic SurfStick blue o2 2011-08-10 54, 44, 39 KB/s
Prieros near Berlin Fonic SurfStick green o2 2011-08-10 0.2 KB/s
Berlin otelo surfstick blue VodAphOne 2011-08-12 68;73;74 KB/s
Prieros near Berlin otelo SurfStick green VodAphOne 2011-08-13 4.0;4.3;4.4 KB/s
Alzey otelo SurfStick blue VodAphOne 2011-08-15 58;8;76 KB/s
Prieros near Berlin otelo SurfStick green Telekom 2014-04-18 12 KB/s
Prieros near Berlin mobile hotspot on S3 mini H+ VodaFon 2015-05-08 408;511;557 KB/s
Prieros near Berlin mobile hotspot on S3 mini H+ VodaFon 2015-08-17 454;454;490 KB/s
Prieros near Berlin mobile hotspot on S3 mini E E+ 2015-08-20 3.9 KB/s
Rauenberg 16Kb wired internet - 1&1 2015-08-27 943;817;613 KB/s

http://www.speedtest.net/de/ from Prieros via VodafOne, 2015-08-17: ping 119 ms, down 4.83Mb/s, up 3.54Mb/s

http://www.speedtest.net/de/ from Prieros via EPlus, 2015-08-20: ping 445 ms, down 0.1Mb/s, up 0.03Mb/s

http://www.speedtest.net/de/ via cabled internet from Rauenberg via 1&1 16Mb, 2015-08-27: ping 32 ms, down 13.21 Mb/s, up 0.92 Mb/s

http://www.speedtest.net/de/ via cabled internet from Rotenberg via Telekom, before exchanging FritzBox, while dropboxing, 2018-05-12: ping 89 ms, down 0.05 Mb/s, up 0.28 Mb/s

http://www.speedtest.net/de/ via cabled internet from Rotenberg Telekom, after change to Fritzbox 7430, 2018-05-12: ping 27 ms, down 4.44 Mb/s, up 1.65 Mb/s

Place date carrier phone ping download speed upload speed
Rotenberg 2016-03-06_10-36 ePlus on Samsung 90 0.84 0.17
Rotenberg 2016 ePlus S3 376 0.07 0.03
Rotenberg 2016 ePlus S3 1524 0.09 0.04
Rotenberg 2016 ePlus S3 361 0.07 0.05
Rotenberg 2016 O2 S3 720 0.02 0.03
Rotenberg 2016 O2 S3 1158 0.03 0.04
Rotenberg 2016 O2 S3 395 0.01 0.01
Rotenberg 2016 Telekom S3 156 0.08 0.04
Rotenberg 2016 Telekom S3 297 0.04 0.03
Rotenberg 2016 Telekom S3 220 0.05 0.03
Rotenberg 2016 Vodafon iPhone 270 0.18 0.08
Rotenberg 2016 Vodafon iPhone 239 0.18 0.07
Rotenberg 2016 Vodafon iPhone 262 0.15 0.07
Rotenberg 2016 ePlus iPhone 352 0.22 0.28
Rotenberg 2016 ePlus iPhone 335 0.11 0.28
Rotenberg 2016 ePlus iPhone 316 0.18 0.28
Rotenberg 2016-12-11 Telekom iPhone 5 138 0.13 0.08
Rotenberg 2016-12-11 Telekom iPhone 5 155 0.09 0.07
Rotenberg 2016-12-11 Telekom iPhone 5 137 0.15 0.11

Latency

Connection between scorpio and bort: 100Mb over two switches. 10 pings from bort to scorpio: between 0.257 ms and 0.267 ms. Connection between scorpio and bort:1000Mb direct, no switches. 10 pings from bort to scorpio: between 0.074 ms and 0.103 ms.

ThroughPut

dd if=/dev/zero | netcat scorpio 8000
4.3 MB/s

KDE memory consumption

KDE 4

linux-gqit:~ # free
             total       used       free     shared    buffers     cached
Mem:       4060060     799476    3260584          0      30328     442632
-/+ buffers/cache:     326516    3733544
Swap:            0          0          0

KDE 3

tweedleburg:~ # free
             total       used       free     shared    buffers     cached
Mem:       4053152    2152388    1900764          0      89252    1520860
-/+ buffers/cache:     542276    3510876
Swap:            0          0          0

power consumption

Computer zero load high load
3 GHz P IV with 512MB RAM 145.7 W 217.7 W
2.4 GHz Quad Core with 4GB RAM 72.4 W 152.4 W
2.8 GHz i7 with 6GB RAM 87 W 205 W
MegaComputerWorld_Ultra_Silent 4GB RAM, 2.41GHz 9 W 11.2 W
CRT Monitor 14"                          57.5 W
TFT Monitor 22"                          30.4 W

Wii

I have driven the Luigis Piste course on Nintendo Wii and chosen different cars and different figures (Bowser and Yoshi). Here are the times: Bowser in Offroader on Luigis Piste: 1.28 Bowser in Offroader on Luigis Piste: 1.28 Bowser in Offroader on Luigis Piste: 1.28 Yoshi in Nostalgia on Luigis Piste: 1.28 Yoshi in Bopper-Bolide on Luigis Piste: 1.28 Seems I always need 1.28 on Luigis Piste.