Freescale iMX6

Description: i.MX6Q SABRE LITE BOARD
Silicon Manufacturer:Freescale
Core Architecture:ARM
Core Sub-Architecture:Cortex - A9
Silicon Core Number:i.MX6
Silicon Family Name:i.MX6 Quad

Benchmark CPU performance

Build CoreMark
For x86 platform:
[ ] # make compile XCFLAGS="-g -DMULTITHREAD=8 -DUSE_FORK=1 -DPERFORMANCE_RUN=1"

[ ] # make compile XCFLAGS="-g -DMULTITHREAD=4 -DUSE_FORK=1 -DPERFORMANCE_RUN=1"

[ ] # make compile XCFLAGS="-g -DPERFORMANCE_RUN=1"

For ARM platform:
[ ] # make compile CC=arm-linux-gcc XCFLAGS="-g -DPERFORMANCE_RUN=1"

Execute CoreMark
[ ]# ./coremark.exe  0x0 0x0 0x66 0 7 1 2000

Sketch the scores
Data format in "coremark.gnuplot_x86.data"
1       7526.256372
2       15053.542714
3       16116.625765
4       20295.202952

[ ] # gnuplot
set xlabel "Core"
set ylabel "Iterations/Sec"
set xzeroaxis
set yzeroaxis
set xrange [0:5]
set yrange [0:30000]
set term png size 600, 400
set title "CoreMark with different x86 core number"
set output "x86-MP.CoreMark.png"

plot "coremark.gnuplot_x86.data" using 1:2 title "4 Processes" with linespoint

Other Example:
gnuplot> plot "coremark.gnuplot_x86.data" using 1:2 title "1 Process" with linespoint, "coremark.gnuplot.data" using 1:3 title "4 Processes" with linespoint, "coremark.gnuplot.data" using 1:4 title "8 Processes" with linespoint

Other Benchmark Tools:

Linpack

Quadrant

Geekbench 2

Vellamo

Andebench

Antutu Benchmark-59

Caffeine mark (example)

Nbench

GLBenchmark 2.1.4-10

Reference:
Tegra II vs. TI OMAP PandaBoard

IPv6 over IPv4

IPv6 tunneling provides a way to encapsulate IPv6 packets into IPv4 packets. That can be used to connect two IPv6 networks over an IPv4-only path.

SIT
This SIT driver implements encapsulation of IPv6 into IPv4 packets, so it can provide IPv6 service over the IPv4 network environment.

Setup and Configuration Script
ipv6_sit_dut.sh
ipv6_sit_linux.sh

6RD

Setup and Configuration Script
ipv6_6rd_dut.sh
ipv6_6rd_linux.sh

ARMvisor

ARMvisor is a Kernel-based virtual machine on ARM architecture.

The Blog of ARMvisor.

The presentation of ARMvisor in Linux Symposium 2012.

IPv6

IPv6

IPv6 NAT

Why IPv6 NAT

Load Balancing

Multi-homing (Uplink Balance, Failover)

NAT is demanded by enterprises for multi-homing.
Multi-homing is a situation that describes a single computer host that makes use of several IP addresses associated with various connected networks. Within this scenario, the multihomed computer host is physically linked to a variety of data connections or ports. These connections or ports may all be associated with the same network or with a variety of different networks. Depending on the exact configuration, multi-homing may allow a computer host to function as an IP router.

Dynamic IPv6 prefixes

Implementations

NF NAT66 (1:1, N:1): NAT66:A first implementation

    http://sourceforge.net/projects/nfnat66/

MAP66 (1:1):

    http://sourceforge.net/projects/map66/

RAWNAT (Xtables Addons): 

Standard

RFC6296 - IPv6-to-IPv6 Network Prefix Translation, NPTv6

Reference:
Multi-homing: http://www.wisegeek.com/what-is-multi-homing.htm

Java Benchmark - CaffeineMark

1. Install Oracle’s Java SE-E 7 JVM (The size of JVM is around 32MB)
ejre-7u4-fcs-b20-linux-arm-vfp-client_headful-12_apr_2012.tar.gz

2. CaffeineMark-3.0

After enter Linux prompt,
Setup your PATH environment variable on your target filesystem to point to the location of the "java".
[ ]# PATH=$PATH:/mnt/ejre1.7.0_04/bin

[ ]# cd /mnt/CaffeineMark-3.0
[/mnt/CaffeineMark-3.0] # java CaffeineMarkEmbeddedApp
Sieve score = 1231 (98)
Loop score = 2787 (2017)
Logic score = 2312 (0)
String score = 596 (708)
Float score = 1702 (185)
Method score = 1619 (166650)
Overall score = 1533

CPU affinity

taskset - retrieve or set a process's CPU affinity

Usage: taskset [-p] [MASK] [PID | PROG ARGS]
   Set or get CPU affinity
      -p Operate on an existing PID


Description
MASK:
   The CPU affinity is represented as a bitmask, with the lowest order bit corresponding to the first logical CPU and the highest order bit corresponding to the last logical CPU.

For example:
   * 1 is CPU core #0 (1st processor)
   * 3 is CPU core #0 and #1
   * 4 is CPU core #2 (3rd processor)

To set the processor affinity of process 112 to CPU core #0 type following command:
   [ ]# taskset -p 1 112
To set the processor affinity of process 112 to CPU core #1 type following command:
   [ ]# taskset -p 2 112
To set the processor affinity of process 112 to CPU core #2 type following command:
   [ ]# taskset -p 4 112
To set the processor affinity of process 112 to CPU core #3 type following command:
   [ ]# taskset -p 8 112

Example:

[ ]# ./stress -c 2

[ ]# ps aux

 ......

 188 root       0:00 ./stress -c 2

 189 root       0:05 ./stress -c 2

 190 root       0:06 ./stress -c 2

 192 root       0:00 ps aux

[ ]# htop

 1  [################100.0%] Tasks: 10, 0 thr, 39 kthr; 3 running

 2  [################100.0%] Load average: 2.06 1.44 1.10

 3  [                  0.0%] Uptime: 01:10:55

 4  [##**             14.3%]

 Mem[||******       5/122MB]

 Swp[                 0/0MB]

# taskset -p 8 189

pid 189's current affinity mask: f

pid 189's new affinity mask: 8

# taskset -p 8 190

pid 190's current affinity mask: f

pid 190's new affinity mask: 8

[ ]# htop

 1  [                  0.0%] Tasks: 10, 0 thr, 39 kthr; 3 running

 2  [                  0.0%] Load average: 1.47 1.08 0.95

 3  [##**             12.7%] Uptime: 01:13:26

 4  [################100.0%]

 Mem[||******       5/122MB]

 Swp[                 0/0MB]