amedeosapio / daiet Goto Github PK

Hi,I want to try your work on my machine (Ubuntu 16.04).
I have followed the instructions in README.md. Everything goes well before step 9. (I saw step 8 is marked as optional and i skipped it).

Since i only have 8 cores, I have changed these two lines to specify the CPU core:
print self.run_cmd("screen -S bmv2 -d -m docker container run --name bmv2 --cpuset-cpus=\"1,2\" --network host -v "+self.folder+":/Testbed -e CMD_LINE=\""+cmdline+"\" -ti p4lang/behavioral-model bash")
print self.run_cmd("screen -S h"+str(i)+" -d -m docker container run --name h"+str(i)+" -h h"+str(i)+" --cpuset-cpus=\""+"5,6"+","+"7,8"+"\" --cap-add=NET_ADMIN --cap-add=SYS_ADMIN -v "+self.folder+":/Testbed -ti openjdk bash")
Like the code above, I assign switched to use core 1 and 2, hosts to use 5,6,7,8.
Then I execute step 9:
I get following mistakes:

First I thought is was the time for sleep() is too short to create the container, I set this to 50 but it still goes wrong.

Thanks in advance.

Hi,
I am trying to reproduce the experiment from the published paper and followed the instructions from README.md ,

9. Start the testbed:

wd=`pwd`
cd DAIET/tests/single_switch/
./Experiment.py ${wd}

and then I got the error

Traceback (most recent call last):
  File "./Experiment.py", line 154, in <module>
    exp.run()
  File "./Experiment.py", line 59, in run
    pid = int(self.run_cmd("docker inspect --format '{{.State.Pid}}' h"+str(i)))
ValueError: invalid literal for int() with base 10: '\x1b[91m\x1b[0m'

I have tried ubuntu16.04 and 14.04 but two machines got the same error.

any ideas? Appreciated your help.

Hello,

When I exec the step 10

sudo screen -r h13
# Now you are in the master container

# Load the data file in the DFS
./DAIET-MapReduce/dist/bin/dfs-load -rh h13 -rp 7777 -r 12 \
    random_text_500mb.txt

# Start a job without DAIET (24 mappers, 12 reducers)
./DAIET-MapReduce/dist/bin/examples-wordcount \
    random_text_500mb.txt result.txt -m 24 -r 12 -rh h13 \
    -rp 7777

# Check the job status
./DAIET-MapReduce/dist/bin/mapreduce-jobs -rh h13 -rp 7777

And wait for minutes, the result is failed like follow:

root@h13:/# ./DAIET-MapReduce/dist/bin/mapreduce-jobs -rh h13 -rp 7777
#0      wordcount       FAILED  (mapper task: 18 pending, 0 succeeded, 6 failed || reducer task: 0 pending, 0 succeeded, 12 failed), start time to now (ms)= 23575, totalTime = 0

I don't know how to do make it success?

Ps: I use a virtual machine Ubuntu16.04 with 8 cores

hi,
when I do the step12 as readme, I run "sudo screen -r bmv2" and "simple_switch_CLI
< /Testbed/DAIET/tests/single_switch/commands.txt" in command line. It occurs error:

Could not connect to thrift client on port 9090
Make sure the switch is running and that you have the right port

thx

hello
when I exec the step 9, there are errors like OCI runtime exec failed: exec failed: container_linux.go:349: starting container process caused "exec: "sudo": executable file not found in $PATH": unknown
I have tried for several times, but I cant solve the problem.
Have you ever faced the same errors? How to solve it?
Thank you！