Massively parallel on single core? Post: 302395115

Sponsored Content

Special Forums UNIX and Linux Applications High Performance Computing Massively parallel on single core? Post 302395115 by Andre_Merzky on Monday 15th of February 2010 04:23:34 AM

02-15-2010

Registered User

Hi Neo,

thanks for your reply!

I agree abut your remark as distributed architectures. This is my day-job, and I like it a lot :-)

I did not make the problem clear enough I think: the workload I am talking about are mostly idle jobs, so the CPU and memory load for each job is *very* low. Yes, I can beat the problem with more cores or nodes, but that seems very much like a waste, as those would be all idling most of the time.

Assume you plan for 1000 threads per core, and use quad code nodes - that would require 25 nodes which all idle all day long :-(

Some more detail, if that helps: the idle processes/threads are basically watchers, which represent a CPU/Memory heavy remote job they spawned, and whose state they are watching. Only when that state changes they become active, and kick of data movements or spawn new jobs.

We can't control the design of the remote job startup API very well (third party, synchronous API only), thus our technical options for obtaining state information about those jobs are limited, and boil down to

Code:

void * run_job (void * data)
{
   // this call runs a remote job, and blocks for hours
   remote_api_call (data);
   store_output_data (data);
}

#define NJOBS 100000

int main ()
{
  pthread_t threads[NJOBS]
  for ( int i = 0; i < NJOBS; i++ )
  {
     pthread_create (threads[i],  run_job, ...)
  }

  for ( int i = 0; i < NJOBS; i++ )
  {
     pthread_join (threads[i]);
  }
}

So, I can throw 25 nodes on that large for loop, and that is what we do basically - but what a waste...

The *real* workload are 100.000 CPU/Memory heavy remote jobs, which have sufficient resources to run concurrently. I am talking about the management side (our workflow engine).

Thanks, Andre.

Andre_Merzky

View Public Profile for Andre_Merzky

Find all posts by Andre_Merzky

9 More Discussions You Might Find Interesting

1. Shell Programming and Scripting

parallel processing

Hi I want to run two shell script files parallely. These two scripts are interacting with the database. can any body help on this Pls Regards Audippa naidu.M

2. UNIX for Dummies Questions & Answers

difference between Dual-core & Core-to-duo

Can anybody tell What is the exact difference between a Dual-core processor and a Core-to-duo processor ?Advance thanks to all my friends.

3. Programming

how to know the application run on which core, and run how many times on this core

I have a dual core pc, I write a application with two child process. I know I can add sched_get_cpu to know the process run on which core, but, it just when the sched_get_cpu is called, it will tell me the result, my quesion is how to know the child proceess spend how many times on one core.

4. Shell Programming and Scripting

Replace single quote with two single quotes in perl

Hi I want to replace single quote with two single quotes in a perl string. If the string is <It's Simpson's book> It should become <It''s Simpson''s book>

5. Shell Programming and Scripting

Multiple lines in a single column to be merged as a single line for a record

Hi, I have a requirement with, No~Dt~Notes 1~2011/08/1~"aaa bbb ccc ddd eee fff ggg hhh" Single column alone got splitted into multiple lines. I require the output as No~Dt~Notes 1~2011/08/1~"aaa<>bbb<>ccc<>ddd<>eee<>fff<>ggg<>hhh" mean to say those new lines to be...

6. Shell Programming and Scripting

For loop in parallel

Hello, My script shell is: for i in $(seq $nb_lignes) do //command java done Please, how can i execute all iteration in parallel ? Thank you so much.

7. Shell Programming and Scripting

How to replace file massively?

Hi Gurus, I need to change a large amout of file name's. for example: current file name: file_ABCDE_sufix.txt I need to change them as file_FGHIGHKE_sufix.txt. Is there any way I can change them with script. Thanks in advance

8. Shell Programming and Scripting

Paste 2 single column files to a single file

Hi, I have 2 csv/txt files with single columns. I am trying to merge them using paste, but its not working.. output3.csv: flowerbomb everlon-jewelry sofft steve-madden dolce-gabbana-watchoutput2.csv: http://www1.abc.com/cms/slp/2/Flowerbomb http://www1.abc.com/cms/slp/2/Everlon-Jewelry...

9. Shell Programming and Scripting

Python GNU parallel single command on multiple cores

Hello, I have a 4 core machine. Here is my initial script cd /work/ python script.py input.txt output.txt 1 2 3 This script runs for 1.5hrs. So I read across the web and figured out that you can use GNU parallel to submit multiple jobs using parallel. But I am not sure if I can run...

LEARN ABOUT DEBIAN

mdm-run

MDM-RUN(1)							   User Commands							MDM-RUN(1)

NAME

       mdm-run - run a command in parallel with mdm-master

SYNOPSIS

       mdm-run command
       mdm-sync command

DESCRIPTION

       mdm-run	annotates  command  as	a  candidate  for parallel execution.  If an mdm-master process is present (i.e., the environment variable
       MDM_CMD_SOCK is defined), mdm-run submits command to the mdm-master, and it exits when the  master  issues  the	command  to  an  mdm-slave
       process	(which may be connected to another terminal) for execution.  mdm-sync runs command in place, but it coordinates with mdm-master to
       ensure that executing command does not interfere with commands that are currently executing in parallel.

       If there is no mdm-master process present (i.e., the environment variable MDM_CMD_SOCK is not defined), both mdm-run  and  mdm-sync  simply
       run command as if you entered command all by itself.

       These programs are a part of the Middleman System (mdm).

OPTIONS

       Neither mdm-run nor mdm-sync accepts any options.

EXIT STATUS

       If  there is no mdm-master process present, the exit status of mdm-run is the exit status of command.  If an mdm-master process is present,
       the exit status is 0 if and only if command is successfully issued to an mdm-slave process for execution.

       The exit status of mdm-sync is always the exit status of command.

ENVIRONMENT

       The mdm system uses the following environment variable for internal communication, and thus you should not try to set them yourself.

       MDM_CMD_SOCK
	      mdm-run uses this environment variable to decide whether a mdm-master process is present.

EXAMPLE

       See mdm.screen(1) for an example use of mdm-run.

SEE ALSO

       mdm.screen(1)

Linux								    2009-03-06								MDM-RUN(1)