gridsim-users — For general queries and feedbacks

Re: [GridSim-users] GridSim questions

[Anthony S. <an...@cs...>]

I prefer that you send all your GridSim questions to the mailing list.

In the README file:
Please subscribe to the following mailing lists:
     gridsim-users (at) lists.sourceforge.net - for any queries and feedbacks
     gridsim-developers (at) lists.sourceforge.net - for contributing to GridSim

To subscribe, go to
     https://lists.sourceforge.net/lists/listinfo/gridsim-users



> I'm using GridSim for simulation of my grid scheduling policy, and
> some jobs need to be specified a future time as their start time.
> I'm wondering if method setExecStartTime in Class Gridlet can
> guarantee that the gridlet will be starting at the given time.
> From my experiment result, it seems that this method does not take effect.

you need advance reservation functionality for the above purpose.

> Besides, for a job which is submitted to the scheduler just now,
> how can I get the job estimated start time on a specific resource?
> Especially in the case that the resource holds both executing jobs
> and the jobs which will be starting in a futhure time.

this more advanced feature is not yet implemented.
It would be nice if someone could do that.

At the moment, the user can check the status of his/her job
via the GridSim#gridletStatus() method.


anthony



On Thu, 25 Sep 2008, liuwt wrote:

> Hi Anthony,
>
> I'm using GridSim for simulation of my grid scheduling policy, and
> some jobs need to be specified a future time as their start time.
> I'm wondering if method setExecStartTime in Class Gridlet can
> guarantee that the gridlet will be starting at the given time.
> From my experiment result, it seems that this method does not take effect.
>
> Besides, for a job which is submitted to the scheduler just now,
> how can I get the job estimated start time on a specific resource? 
> Especially in the case that the resource holds both executing jobs
> and the jobs which will be starting in a futhure time.
>
> Appreciated for any help.
>
> Sincerely,
>
> Wantao
>

Re: [GridSim-users] Help: Source Code missing

[Anthony S. <an...@cs...>]

Please read the below README file for the directory structure,
and explore other directories in your downloaded GridSim directory.

http://www.gridbus.org/gridsim/doc/README.txt


anthony


On Fri, 3 Oct 2008, Amel Hamdi wrote:

> Hi all,
> I'm a new GridSim User, I'm a Phd student at University of Paris-Sud
> Orsay(France).
> Is there anyone who knows where we can find the source code(.java) of the
> jar files "gridsim.jar" and "simjava2.jar" (not .Class files whitch are
> uncomprehensible).
> I need these files in order to better understand Grid simulation process.
>
> Thanks a lot
> Best regards
> Amel

[GridSim-users] Help: Source Code missing

[Amel H. <ame...@u-...>]

 Hi all,
I'm a new GridSim User, I'm a Phd student at University of Paris-Sud
Orsay(France).
Is there anyone who knows where we can find the source code(.java) of the
jar files "gridsim.jar" and "simjava2.jar" (not .Class files whitch are
uncomprehensible).
I need these files in order to better understand Grid simulation process.

Thanks a lot
Best regards
Amel

Re: [GridSim-users] help

[Marcos D. de A. <ma...@cs...>]

Hi Amrutha,

I think I understood what you need, but I am afraid you will have to  
implement that. You can extend the GridResource class in order to  
make it (i) query the policy for information about the resource  
utilised and (ii) make it request a job from whoever has it in your  
case. That would be the receiver-initiated case. For the sender- 
initiated case, you can query the GridResource for the  
ResourceCharacteristics and make the decision based on the number of  
processing elements available. Please have a look at the method  
getResourceDynamicInfo() of GridSim class:

     /**
      * Gets the GridResource dynamic fnformation
      * @param resourceID   the resource ID
      * @return An object of Accumulator containing the GridResource  
load or
      *         <tt>null</tt> if a GridResource doesn't exist or an  
error occurs
      * @pre resourceID > 0
      * @post $none
      */
     public Accumulator getResourceDynamicInfo(int resourceID)

That might be what you need. I apologise if I have not understood  
what you need.

Thanks for your interest in GridSim.

Regards,

Marcos


On 26/09/2008, at 3:20 AM, amrutha karunakaran wrote:

> hi.thanks for replying.sorry for the late reply.i actually need the  
> push(sender-initiated), pull algorithm(receiver-initiated) which is  
> used to schedule jobs across different grid resource.In sender- 
> initiated algorithms the load on the resource is calculated and  
> compared with a threshold value(i think this can be self defined)  
> if its below threshold then the job is given to that resource or  
> migrated to the other resource where the same process of  
> calculating and comparing is carried out. In receiver-initiated  
> algorithms the load on the resource is calculated and if its below  
> a certain threshold then the resources take jobs.i am sorry if its  
> not clear.i can explain again.your reply would help me a lot.
>
> Sorry forgot the difference.the difference between both is that in  
> sender initiated the sender initiates while in the receiver  
> initiated the receiver initiates.In receiver intiated the resource  
> which intends to recieves does not migrate the job as in sender.

Marcos Dias de Assuncao
Grid Computing and Distributed Systems (GRIDS) Laboratory
Department of Computer Science and Software Engineering
The University of Melbourne, Australia
Email: ma...@cs...

-------------
"No serious sociologist any longer believes that the voice of the  
people expresses any divine or specially wise idea. The voice of the  
people expresses the mind of the people, and that mind is made up for  
it by the group leaders in whom it believes and by those persons who  
understand the manipulation of the public opinion. It is composed of  
inherited prejudices and symbols and cliché's and verbal formulas  
supplied to them by the leaders."
Edward L. Bernays

Re: [GridSim-users] [GridSim-developers] usage of WorkLoad class?

[Marcos D. de A. <ma...@cs...>]

Hi Ye,

The Workload class loads a workload trace file and creates gridlets  
according to the information in the trace. In other words, you need  
to download a file that represents the workload of the resource you  
are modelling from http://www.cs.huji.ac.il/labs/parallel/workload/ 
logs.html. Then, you provide this file, or part of it, to the  
workload object which will in turn create gridlets that have the same  
number of processors and submission times of the jobs in the trace.

The examples fail because they cannot find those workload files in  
your system. You need to download them.

Regards,

Marcos


On 29/09/2008, at 4:44 AM, ye huang wrote:

> Hi, Dear all:
> I am a little bit confused by the usage of WorkLoad class.
> 1. Does it provide the workload of a resource/machine, like the
> information presented in  http://www.cs.huji.ac.il/labs/parallel/ 
> workload/logs.html
>   ?
> 2. Or it traces the jobs submitted via same grid user (user's jobs
> workload trace?), since it's declared as "This class can be classified
> as one grid user entity" in the comment.
> 3. What's the type of this traced workload information? Dynamic or
> statistic?
>
> I tried to run the WorkLoadTrace demo codes from sample, however, i
> always got the following errors:
> ---
> Initializing GridSim package
> Initialising...
> Creates one Grid resource with name = Res_0
> Creates one Grid resource with name = Res_1
> Load_0: Creating a workload object ...
> Load_1: Creating a workload object ...
> Custom: Creating a workload object ...
> Starting GridSim version 4.0
> Entities started.
>
> Load_0.body() :%%%% Start ...
>
> Load_1.body() :%%%% Start ...
> Load_1: Error - the file was not found: ../l_sdsc_blue.swf.txt.gz (No
> such file or directory)
> Load_1.body(): Error - unable to parse from a file.
>
> Custom.body() :%%%% Start ...
> Custom: Error - the file was not found: ../custom_trace.txt (No such
> file or directory)
> Custom.body(): Error - unable to parse from a file.
> Load_0: Error - an IOException occurred: No such file or directory
> Load_0.body(): Error - unable to parse from a file.
> Load_0.body() : %%%% Exit ...
> Load_1.body() : %%%% Exit ...
> Custom.body() : %%%% Exit ...
> GridInformationService: Notify all GridSim entities for shutting down.
> Sim_system: No more future events
> Gathering simulation data.
> Simulation completed.
> java.lang.NullPointerException
> 	at gridsim.util.Workload.printGridletList(Unknown Source)
> 	at WorkloadTrace.TraceEx01.TraceEx01.main(TraceEx01.java:141)
> ---
>
> It warns some files are missing, does it mean my file hierarchy is
> incorrect:
> ---
> ye-Mac:WorkloadTrace yehuang$ pwd
> /Users/yehuang/workspace/GridSimDemo/src/WorkloadTrace
> ye-Mac:WorkloadTrace yehuang$ ls
> README.txt		TraceEx02		custom_trace.txt	l_sdsc_blue.swf.txt
> TraceEx01		TraceEx03		l_lanl_o2k.swf.txt
> ye-Mac:WorkloadTrace yehuang$ cd TraceEx01/
> ye-Mac:TraceEx01 yehuang$ ls
> README.txt		custom_trace.txt	l_sdsc_blue.swf.txt
> TraceEx01.java		l_lanl_o2k.swf.txt	output.txt
> ---
>
> Thanks a lot!
>
> regards
> ye
>
> --
>
> Ye Huang, Department of Informatics
> University of Fribourg / Pérolles 2 - Bld de Pérolles 90
> 1700 Fribourg, Switzerland
>
> e-mail: ye....@he...,  ye....@un...
> http://diuf.unifr.ch/people/huangy/
> Office: +41 26 429 65 95
>
>
>
>
> ---------------------------------------------------------------------- 
> ---
> This SF.Net email is sponsored by the Moblin Your Move Developer's  
> challenge
> Build the coolest Linux based applications with Moblin SDK & win  
> great prizes
> Grand prize is a trip for two to an Open Source event anywhere in  
> the world
> http://moblin-contest.org/redirect.php?banner_id=100&url=/
> _______________________________________________
> Gridsim-developers mailing list
> Gri...@li...
> https://lists.sourceforge.net/lists/listinfo/gridsim-developers

Marcos Dias de Assuncao
Grid Computing and Distributed Systems (GRIDS) Laboratory
Department of Computer Science and Software Engineering
The University of Melbourne, Australia
Email: ma...@cs...

-------------
"No serious sociologist any longer believes that the voice of the  
people expresses any divine or specially wise idea. The voice of the  
people expresses the mind of the people, and that mind is made up for  
it by the group leaders in whom it believes and by those persons who  
understand the manipulation of the public opinion. It is composed of  
inherited prejudices and symbols and cliché's and verbal formulas  
supplied to them by the leaders."
Edward L. Bernays

Re: [GridSim-users] [GridSim-developers] How GridResource "real" process gridlets? Is it possible to get the workload of resource?

[Marcos D. de A. <ma...@cs...>]

Hi Ye,

The gridlet is not returned as soon as it arrives at the resource.  
The only thing that is returned as soon as the gridlet arrives is an  
ack., if the user requested it. The gridlet is returned to the user  
after its processing is complete. The processing time is calculated  
based on the gridlet's number of MIs and the resource's MIPS  
capability. The allocation policies schedule internal events (i.e.  
events sent to themselves) to know when a job completes. See for  
example the method allocatePEtoGridlet(ResGridlet rgl) of  
SpaceShared. After the execution time is calculated, the method sends  
an event to the policy itself, which will be handled at the event's  
time (i.e. this event is the job's completion):

  // Identify Completion Time and Set Interrupt
  int rating = machineRating_[ rgl.getMachineID() ];
  double time = forecastFinishTime( rating ,
                             rgl.getRemainingGridletLength() );

  int roundUpTime = (int) (time+1);   // rounding up
  rgl.setFinishTime(roundUpTime);

// then send this into itself
super.sendInternalEvent(roundUpTime);
return true;

Regards,

Marcos

On 29/09/2008, at 2:41 AM, ye huang wrote:

> Hi, all:
> Is there anyone could help to explain the job executing process of a
> GridResource?
> If I understand right, once the GridResource receives submitted jobs
> via "processGridletSubmit", it only calculates the cost for processing
> the gridlet, and send the gridlet back. That means, the GridResource
> won't wait a while for "real job processing".
>
> If I am right, is it possible to trace the resource's workload? I
> mean, once a resource received a lot of gridlets, since each gridlet
> needs some time for its execution, is it possible to simulate the
> "busy status" of a resource? For example, the resource will be wait
> for while to process the next gridlet request? Further more, could the
> users be able to get the workload of a resource?
>
> regards
> ye
>
> --
>
> Ye Huang, Department of Informatics
> University of Fribourg / Pérolles 2 - Bld de Pérolles 90
> 1700 Fribourg, Switzerland
>
> e-mail: ye....@he...,  ye....@un...
> http://diuf.unifr.ch/people/huangy/
> Office: +41 26 429 65 95
>
>
>
>
> ---------------------------------------------------------------------- 
> ---
> This SF.Net email is sponsored by the Moblin Your Move Developer's  
> challenge
> Build the coolest Linux based applications with Moblin SDK & win  
> great prizes
> Grand prize is a trip for two to an Open Source event anywhere in  
> the world
> http://moblin-contest.org/redirect.php?banner_id=100&url=/
> _______________________________________________
> Gridsim-developers mailing list
> Gri...@li...
> https://lists.sourceforge.net/lists/listinfo/gridsim-developers

Marcos Dias de Assuncao
Grid Computing and Distributed Systems (GRIDS) Laboratory
Department of Computer Science and Software Engineering
The University of Melbourne, Australia
Email: ma...@cs...

-------------
"No serious sociologist any longer believes that the voice of the  
people expresses any divine or specially wise idea. The voice of the  
people expresses the mind of the people, and that mind is made up for  
it by the group leaders in whom it believes and by those persons who  
understand the manipulation of the public opinion. It is composed of  
inherited prejudices and symbols and cliché's and verbal formulas  
supplied to them by the leaders."
Edward L. Bernays

[GridSim-users] usage of WorkLoad class?

[ye h. <ye....@un...>]

Hi, Dear all:
I am a little bit confused by the usage of WorkLoad class.
1. Does it provide the workload of a resource/machine, like the  
information presented in  http://www.cs.huji.ac.il/labs/parallel/workload/logs.html 
  ?
2. Or it traces the jobs submitted via same grid user (user's jobs  
workload trace?), since it's declared as "This class can be classified  
as one grid user entity" in the comment.
3. What's the type of this traced workload information? Dynamic or  
statistic?

I tried to run the WorkLoadTrace demo codes from sample, however, i  
always got the following errors:
---
Initializing GridSim package
Initialising...
Creates one Grid resource with name = Res_0
Creates one Grid resource with name = Res_1
Load_0: Creating a workload object ...
Load_1: Creating a workload object ...
Custom: Creating a workload object ...
Starting GridSim version 4.0
Entities started.

Load_0.body() :%%%% Start ...

Load_1.body() :%%%% Start ...
Load_1: Error - the file was not found: ../l_sdsc_blue.swf.txt.gz (No  
such file or directory)
Load_1.body(): Error - unable to parse from a file.

Custom.body() :%%%% Start ...
Custom: Error - the file was not found: ../custom_trace.txt (No such  
file or directory)
Custom.body(): Error - unable to parse from a file.
Load_0: Error - an IOException occurred: No such file or directory
Load_0.body(): Error - unable to parse from a file.
Load_0.body() : %%%% Exit ...
Load_1.body() : %%%% Exit ...
Custom.body() : %%%% Exit ...
GridInformationService: Notify all GridSim entities for shutting down.
Sim_system: No more future events
Gathering simulation data.
Simulation completed.
java.lang.NullPointerException
	at gridsim.util.Workload.printGridletList(Unknown Source)
	at WorkloadTrace.TraceEx01.TraceEx01.main(TraceEx01.java:141)
---

It warns some files are missing, does it mean my file hierarchy is  
incorrect:
---
ye-Mac:WorkloadTrace yehuang$ pwd
/Users/yehuang/workspace/GridSimDemo/src/WorkloadTrace
ye-Mac:WorkloadTrace yehuang$ ls
README.txt		TraceEx02		custom_trace.txt	l_sdsc_blue.swf.txt
TraceEx01		TraceEx03		l_lanl_o2k.swf.txt
ye-Mac:WorkloadTrace yehuang$ cd TraceEx01/
ye-Mac:TraceEx01 yehuang$ ls
README.txt		custom_trace.txt	l_sdsc_blue.swf.txt
TraceEx01.java		l_lanl_o2k.swf.txt	output.txt
---

Thanks a lot!

regards
ye

--

Ye Huang, Department of Informatics
University of Fribourg / Pérolles 2 - Bld de Pérolles 90
1700 Fribourg, Switzerland

e-mail: ye....@he...,  ye....@un...
http://diuf.unifr.ch/people/huangy/
Office: +41 26 429 65 95

[GridSim-users] How GridResource "real" process gridlets? Is it possible to get the workload of resource?

[ye h. <hua...@gm...>]

Hi, all:
Is there anyone could help to explain the job executing process of a  
GridResource?
If I understand right, once the GridResource receives submitted jobs  
via "processGridletSubmit", it only calculates the cost for processing  
the gridlet, and send the gridlet back. That means, the GridResource  
won't wait a while for "real job processing".

If I am right, is it possible to trace the resource's workload? I  
mean, once a resource received a lot of gridlets, since each gridlet  
needs some time for its execution, is it possible to simulate the  
"busy status" of a resource? For example, the resource will be wait  
for while to process the next gridlet request? Further more, could the  
users be able to get the workload of a resource?

regards
ye

--

Ye Huang, Department of Informatics
University of Fribourg / Pérolles 2 - Bld de Pérolles 90
1700 Fribourg, Switzerland

e-mail: ye....@he...,  ye....@un...
http://diuf.unifr.ch/people/huangy/
Office: +41 26 429 65 95

Re: [GridSim-users] [GridSim-developers] simulation fails(OOME)with 1000 resources

[Shuo Y. <ya...@cs...>]

Dear Marcos,

Many thanks for your reply and contribution. 

So do you mean that the monster that eats up all JVM memory is the event
queue containing close to 1 million events?

It seems that your library is more efficient. Have you tested it against
the original one? Would you like to share your modified simjava2 library
such that we can all benefit?


Alex

On Tue, 2008-09-23 at 15:11 +1000, Marcos Dias de Assuncao wrote:
> Hi Shuo,
> 
> I was cleaning my inbox after a few days without reading e-mails and  
> found this one. :-)
> 
> I have made some changes in SimJava because I also face some problems  
> about scalability. As discussed beforehand, GridSim uses SimJava 2.  
> The event queue in SimJava 2 is a linked list:
> 
> public class Evqueue extends LinkedList
> 
> Also, please note that when an event is inserted in the queue,  
> SimJava does only a silly optimisation. That is, an Evqueue instance  
> maintains an attribute called max_time, which is the time of the last  
> event that would be processed. Evqueue will not iterate the list when  
> it adds an event to the queue only if the event's time is greater  
> than max_time:
> 
> public void add_event(Sim_event new_event) {
>   double new_event_time = new_event.event_time();
>      if (new_event_time >= max_time) {
>        add(new_event);
>        max_time = new_event_time;
>        return;
>      }
>      ListIterator iterator = listIterator();
>      Sim_event event;
>      while (iterator.hasNext()) {
>        event = (Sim_event)iterator.next();
>        if (event.event_time() > new_event_time) {
>          iterator.previous();
>          iterator.add(new_event);
>          return;
>        }
>      }
>      add(new_event);
> }
> 
> You can see what is going to happen if things in the simulator are  
> not managed properly. If you consider the Workload class for example,  
> it reads a job trace file and creates job submissions (events)  
> according to this trace. If you have only one Workload entity in your  
> simulation creating events and reading, let's say, 1000 jobs, you  
> will have 1000 events in the future queue right when you start the  
> simulation. Also, consider that one of these jobs is to be submitted  
> (i.e. received by the resource) far in the future. All events created  
> from the start until the end of the simulation (i.e. job completion,  
> internal messages, packets, etc) will probably lead to the iteration  
> of the event queue because of one event that was created at the start  
> of the simulation and changed max_time. If you are simulating a Grid,  
> it is very likely that you will have multiple Workloads dispatching  
> jobs, changing max_time and making one another's events to iterate  
> the queue. The deferred event queue is not a problem because you will  
> hardly have a very long deferred queue.
> 
> In some simulations I have run, the future event queue can contain  
> close to 1 million events at a particular time. This way, I've  
> changed the future event queue to use a modified version of TreeMap.  
> TreeMaps are quicker to insert an object into, but one may argue that  
> they are costly to iterate. In that sense, I modified the Java's  
> implementation of TreeMap to keep a double linked list between the  
> siblings nodes. This way, the iterator uses the list to iterate and  
> not the java's red-black tree.
> 
> Moreover, the event  this is not the only scalability issue of  
> SimJava. Each simulation entity is a Thread and SimJava puts them to  
> wait and notifies entities at each clock tick, that is, each time the  
> simulation clock is changed.
> 
> Regards,
> 
> Marcos
> 
> 
> On 06/09/2008, at 12:55 AM, Shuo Yang wrote:
> 
> > All,
> >
> > I think the problem also lies in the scalability of the underlying  
> > simjava
> > package. Simjava uses an event queue to manage all internal events  
> > flying
> > between entities. The event queue is a Vector. If you refer to
> > eduni.simjava.Evqueue.java, you can see the doc:
> >
> > /**
> >  * This class implements an event queue used internally by the  
> > Sim_system to
> >  * manage
> >  * the list of future and deferred Sim_events. It should not be  
> > needed in
> >  * a user simulation. It works like a normal FIFO
> >  * queue, but during insertion events are kept in order from the  
> > smallest
> > time
> >  * stamp to the largest. This means the next event to occur will be  
> > at the
> > top
> >  * of the queue. <P>
> >  * The current implementation
> >  * is uses a Vector to store the queue and is inefficient for popping
> >  * and inserting elements because the rest of the array has to be
> >  * moved down one space. A better method would be to use a circular  
> > array.
> >  * @see		eduni.simjava.Sim_system
> >  * @version     0.1, 25 June 1995
> >  * @author      Ross McNab
> >  */
> >
> > Also, the event queue in Sim_system is accessed using  
> > 'synchronized' to
> > ensure consistency and the simulation clock. Therefore when there  
> > are a huge
> > amount of entities/messages, the event queue becomes the system  
> > bottleneck -
> > only one entity/thread can write to event queue while the others  
> > will wait,
> > and wait, and wait, and wait...
> >
> > It may have problem with java's handling large memories. But a re- 
> > design and
> > re-implemenation of the underlying thread pool is ideal, which is  
> > exactly
> > what I'm doing now.
> >
> > Cheers,
> >
> > Shuo 'Alex' Yang
> > University of Manchester
> >
> >
> > ----- Original Message -----
> > From: "Agustín Caminero Herráez" <ag...@ds...>
> > To: "ye" <hua...@gm...>
> > Cc: <gri...@li...>;
> > <gri...@li...>
> > Sent: Friday, September 05, 2008 3:35 PM
> > Subject: Re: [GridSim-developers] [GridSim-users] simulation fails 
> > (OOME)with
> > 1000 resources
> >
> >
> > Hi Ye,
> >
> > I've also suffered the problems u describe, and I'm afraid there is no
> > solution for them. The only suggestion I can give to u is to scale  
> > down
> > your simulations.
> >
> > The problem comes from Java's inability to handle more than 1.5 GB of
> > memory, so there is nothing u can do.
> >
> > Just one thing, are u using Sun Java? Because using another different
> > java may cause problems... The java I us is Sun  v1.4.2
> >
> > Regards,
> >
> > Agustin
> >
> > ye escribió:
> >> Hi, Dear all:
> >> Although I have asked a similar question in gridsim-user maillist,
> >> there seems no similar experience from other developers. Since  
> >> it's an
> >> crucial problem for me, I'd to make the scenario much clear and beg
> >> for help.
> >>
> >> For brief, is there any scale limit for simulation created via  
> >> GridSim?
> >>
> >> I was trying to set up a gridsim simulation with 1000 resource; each
> >> resource contains one machine, each machine has two PEs. Then, I  
> >> wrote
> >> a user to retrieve resource list within its body(), and print the
> >> total size. However, the program halts with an OutOfMemoryError,  
> >> every
> >> time before "Entities started" was printed. The user's body() was
> >> never visited.
> >>
> >> I am working on a mac 10.5, 2GB 667 Mhz memory, mac JVM 1.5;
> >> meanwhile, I already adjust the vm parameter into "-Xms512m - 
> >> Xmx1024m".
> >>
> >> Later, I tried the same program on my server (ubuntu 8.04, 3.2GB).
> >> Fortunately, it works... but, it halts again with OOME while i decide
> >> create 1100 resources.
> >>
> >> I am not sure the problem is caused by lacking of memory? Is there  
> >> any
> >> limit for gridsim simulation scale, or just for GridSim Resource? Or
> >> it's bug derived from simjava?
> >>
> >> Finally, is it possible to solve it?
> >>
> >> Thank you guys a lot!!
> >>
> >> regards
> >> ye
> >>
> >> -- 
> >> Ye Huang, Department of Informatics
> >> University of Fribourg / Pérolles 2 - Bld de Pérolles 90
> >> 1700 Fribourg, Switzerland
> >>
> >> e-mail: ye....@he..., ye....@un...
> >> http://diuf.unifr.ch/people/huangy/
> >> Office: +41 26 429 65 95
> >> --------------------------------------------------------------------- 
> >> ---
> >>
> >> --------------------------------------------------------------------- 
> >> ----
> >> This SF.Net email is sponsored by the Moblin Your Move Developer's
> >> challenge
> >> Build the coolest Linux based applications with Moblin SDK & win  
> >> great
> >> prizes
> >> Grand prize is a trip for two to an Open Source event anywhere in the
> >> world
> >> http://moblin-contest.org/redirect.php?banner_id=100&url=/
> >> --------------------------------------------------------------------- 
> >> ---
> >>
> >> _______________________________________________
> >> Gridsim-users mailing list
> >> Gri...@li...
> >> https://lists.sourceforge.net/lists/listinfo/gridsim-users
> >>
> >
> > -- 
> > ===============================================
> > Agustin Caminero
> > Research Assistant.
> > Computing Systems Department.
> > Albacete Research Institute of Informatics (I3A).
> > The University of Castilla La Mancha.
> > Campus Universitario s/n, 02071, Albacete. Spain.
> > Phone: +34 967 599 200 Ext. 2693. Fax: +34 967 599 343
> > http://www.i3a.uclm.es/
> > ===============================================
> >
> >
> >
> >
> > ---------------------------------------------------------------------- 
> > ----------
> >
> >
> >> --------------------------------------------------------------------- 
> >> ----
> >> This SF.Net email is sponsored by the Moblin Your Move Developer's
> >> challenge
> >> Build the coolest Linux based applications with Moblin SDK & win  
> >> great
> >> prizes
> >> Grand prize is a trip for two to an Open Source event anywhere in the
> >> world
> >> http://moblin-contest.org/redirect.php?banner_id=100&url=/
> >
> >
> > ---------------------------------------------------------------------- 
> > ----------
> >
> >
> >> _______________________________________________
> >> Gridsim-developers mailing list
> >> Gri...@li...
> >> https://lists.sourceforge.net/lists/listinfo/gridsim-developers
> >>
> >
> >
> > ---------------------------------------------------------------------- 
> > ---
> > This SF.Net email is sponsored by the Moblin Your Move Developer's  
> > challenge
> > Build the coolest Linux based applications with Moblin SDK & win  
> > great prizes
> > Grand prize is a trip for two to an Open Source event anywhere in  
> > the world
> > http://moblin-contest.org/redirect.php?banner_id=100&url=/
> > _______________________________________________
> > Gridsim-users mailing list
> > Gri...@li...
> > https://lists.sourceforge.net/lists/listinfo/gridsim-users
> 
> Marcos Dias de Assuncao
> Grid Computing and Distributed Systems (GRIDS) Laboratory
> Department of Computer Science and Software Engineering
> The University of Melbourne, Australia
> Email: ma...@cs...
> 
> -------------
> "No serious sociologist any longer believes that the voice of the  
> people expresses any divine or specially wise idea. The voice of the  
> people expresses the mind of the people, and that mind is made up for  
> it by the group leaders in whom it believes and by those persons who  
> understand the manipulation of the public opinion. It is composed of  
> inherited prejudices and symbols and cliché's and verbal formulas  
> supplied to them by the leaders."
> Edward L. Bernays
> 

Re: [GridSim-users] help

[Marcos D. de A. <ma...@cs...>]

Hi Amrutha,

I am not quite sure whether I understood your request. Could you give  
me more details about the sender initiated algorithm you are  
referring to?

Regards,

Marcos


On 19/09/2008, at 7:23 AM, amrutha karunakaran wrote:

> i am an student. it would be of great help if you could send sender  
> initiated algorithm implemented using GridSim in case you have it  
> or help me in calculating the load on a resource using GridSim. It  
> is only to help me with my project.

Marcos Dias de Assuncao
Grid Computing and Distributed Systems (GRIDS) Laboratory
Department of Computer Science and Software Engineering
The University of Melbourne, Australia
Email: ma...@cs...

-------------
"No serious sociologist any longer believes that the voice of the  
people expresses any divine or specially wise idea. The voice of the  
people expresses the mind of the people, and that mind is made up for  
it by the group leaders in whom it believes and by those persons who  
understand the manipulation of the public opinion. It is composed of  
inherited prejudices and symbols and cliché's and verbal formulas  
supplied to them by the leaders."
Edward L. Bernays

Re: [GridSim-users] [GridSim-developers] simulation fails(OOME)with 1000 resources

[Marcos D. de A. <ma...@cs...>]

Hi Shuo,

I was cleaning my inbox after a few days without reading e-mails and  
found this one. :-)

I have made some changes in SimJava because I also face some problems  
about scalability. As discussed beforehand, GridSim uses SimJava 2.  
The event queue in SimJava 2 is a linked list:

public class Evqueue extends LinkedList

Also, please note that when an event is inserted in the queue,  
SimJava does only a silly optimisation. That is, an Evqueue instance  
maintains an attribute called max_time, which is the time of the last  
event that would be processed. Evqueue will not iterate the list when  
it adds an event to the queue only if the event's time is greater  
than max_time:

public void add_event(Sim_event new_event) {
  double new_event_time = new_event.event_time();
     if (new_event_time >= max_time) {
       add(new_event);
       max_time = new_event_time;
       return;
     }
     ListIterator iterator = listIterator();
     Sim_event event;
     while (iterator.hasNext()) {
       event = (Sim_event)iterator.next();
       if (event.event_time() > new_event_time) {
         iterator.previous();
         iterator.add(new_event);
         return;
       }
     }
     add(new_event);
}

You can see what is going to happen if things in the simulator are  
not managed properly. If you consider the Workload class for example,  
it reads a job trace file and creates job submissions (events)  
according to this trace. If you have only one Workload entity in your  
simulation creating events and reading, let's say, 1000 jobs, you  
will have 1000 events in the future queue right when you start the  
simulation. Also, consider that one of these jobs is to be submitted  
(i.e. received by the resource) far in the future. All events created  
from the start until the end of the simulation (i.e. job completion,  
internal messages, packets, etc) will probably lead to the iteration  
of the event queue because of one event that was created at the start  
of the simulation and changed max_time. If you are simulating a Grid,  
it is very likely that you will have multiple Workloads dispatching  
jobs, changing max_time and making one another's events to iterate  
the queue. The deferred event queue is not a problem because you will  
hardly have a very long deferred queue.

In some simulations I have run, the future event queue can contain  
close to 1 million events at a particular time. This way, I've  
changed the future event queue to use a modified version of TreeMap.  
TreeMaps are quicker to insert an object into, but one may argue that  
they are costly to iterate. In that sense, I modified the Java's  
implementation of TreeMap to keep a double linked list between the  
siblings nodes. This way, the iterator uses the list to iterate and  
not the java's red-black tree.

Moreover, the event  this is not the only scalability issue of  
SimJava. Each simulation entity is a Thread and SimJava puts them to  
wait and notifies entities at each clock tick, that is, each time the  
simulation clock is changed.

Regards,

Marcos


On 06/09/2008, at 12:55 AM, Shuo Yang wrote:

> All,
>
> I think the problem also lies in the scalability of the underlying  
> simjava
> package. Simjava uses an event queue to manage all internal events  
> flying
> between entities. The event queue is a Vector. If you refer to
> eduni.simjava.Evqueue.java, you can see the doc:
>
> /**
>  * This class implements an event queue used internally by the  
> Sim_system to
>  * manage
>  * the list of future and deferred Sim_events. It should not be  
> needed in
>  * a user simulation. It works like a normal FIFO
>  * queue, but during insertion events are kept in order from the  
> smallest
> time
>  * stamp to the largest. This means the next event to occur will be  
> at the
> top
>  * of the queue. <P>
>  * The current implementation
>  * is uses a Vector to store the queue and is inefficient for popping
>  * and inserting elements because the rest of the array has to be
>  * moved down one space. A better method would be to use a circular  
> array.
>  * @see		eduni.simjava.Sim_system
>  * @version     0.1, 25 June 1995
>  * @author      Ross McNab
>  */
>
> Also, the event queue in Sim_system is accessed using  
> 'synchronized' to
> ensure consistency and the simulation clock. Therefore when there  
> are a huge
> amount of entities/messages, the event queue becomes the system  
> bottleneck -
> only one entity/thread can write to event queue while the others  
> will wait,
> and wait, and wait, and wait...
>
> It may have problem with java's handling large memories. But a re- 
> design and
> re-implemenation of the underlying thread pool is ideal, which is  
> exactly
> what I'm doing now.
>
> Cheers,
>
> Shuo 'Alex' Yang
> University of Manchester
>
>
> ----- Original Message -----
> From: "Agustín Caminero Herráez" <ag...@ds...>
> To: "ye" <hua...@gm...>
> Cc: <gri...@li...>;
> <gri...@li...>
> Sent: Friday, September 05, 2008 3:35 PM
> Subject: Re: [GridSim-developers] [GridSim-users] simulation fails 
> (OOME)with
> 1000 resources
>
>
> Hi Ye,
>
> I've also suffered the problems u describe, and I'm afraid there is no
> solution for them. The only suggestion I can give to u is to scale  
> down
> your simulations.
>
> The problem comes from Java's inability to handle more than 1.5 GB of
> memory, so there is nothing u can do.
>
> Just one thing, are u using Sun Java? Because using another different
> java may cause problems... The java I us is Sun  v1.4.2
>
> Regards,
>
> Agustin
>
> ye escribió:
>> Hi, Dear all:
>> Although I have asked a similar question in gridsim-user maillist,
>> there seems no similar experience from other developers. Since  
>> it's an
>> crucial problem for me, I'd to make the scenario much clear and beg
>> for help.
>>
>> For brief, is there any scale limit for simulation created via  
>> GridSim?
>>
>> I was trying to set up a gridsim simulation with 1000 resource; each
>> resource contains one machine, each machine has two PEs. Then, I  
>> wrote
>> a user to retrieve resource list within its body(), and print the
>> total size. However, the program halts with an OutOfMemoryError,  
>> every
>> time before "Entities started" was printed. The user's body() was
>> never visited.
>>
>> I am working on a mac 10.5, 2GB 667 Mhz memory, mac JVM 1.5;
>> meanwhile, I already adjust the vm parameter into "-Xms512m - 
>> Xmx1024m".
>>
>> Later, I tried the same program on my server (ubuntu 8.04, 3.2GB).
>> Fortunately, it works... but, it halts again with OOME while i decide
>> create 1100 resources.
>>
>> I am not sure the problem is caused by lacking of memory? Is there  
>> any
>> limit for gridsim simulation scale, or just for GridSim Resource? Or
>> it's bug derived from simjava?
>>
>> Finally, is it possible to solve it?
>>
>> Thank you guys a lot!!
>>
>> regards
>> ye
>>
>> -- 
>> Ye Huang, Department of Informatics
>> University of Fribourg / Pérolles 2 - Bld de Pérolles 90
>> 1700 Fribourg, Switzerland
>>
>> e-mail: ye....@he..., ye....@un...
>> http://diuf.unifr.ch/people/huangy/
>> Office: +41 26 429 65 95
>> --------------------------------------------------------------------- 
>> ---
>>
>> --------------------------------------------------------------------- 
>> ----
>> This SF.Net email is sponsored by the Moblin Your Move Developer's
>> challenge
>> Build the coolest Linux based applications with Moblin SDK & win  
>> great
>> prizes
>> Grand prize is a trip for two to an Open Source event anywhere in the
>> world
>> http://moblin-contest.org/redirect.php?banner_id=100&url=/
>> --------------------------------------------------------------------- 
>> ---
>>
>> _______________________________________________
>> Gridsim-users mailing list
>> Gri...@li...
>> https://lists.sourceforge.net/lists/listinfo/gridsim-users
>>
>
> -- 
> ===============================================
> Agustin Caminero
> Research Assistant.
> Computing Systems Department.
> Albacete Research Institute of Informatics (I3A).
> The University of Castilla La Mancha.
> Campus Universitario s/n, 02071, Albacete. Spain.
> Phone: +34 967 599 200 Ext. 2693. Fax: +34 967 599 343
> http://www.i3a.uclm.es/
> ===============================================
>
>
>
>
> ---------------------------------------------------------------------- 
> ----------
>
>
>> --------------------------------------------------------------------- 
>> ----
>> This SF.Net email is sponsored by the Moblin Your Move Developer's
>> challenge
>> Build the coolest Linux based applications with Moblin SDK & win  
>> great
>> prizes
>> Grand prize is a trip for two to an Open Source event anywhere in the
>> world
>> http://moblin-contest.org/redirect.php?banner_id=100&url=/
>
>
> ---------------------------------------------------------------------- 
> ----------
>
>
>> _______________________________________________
>> Gridsim-developers mailing list
>> Gri...@li...
>> https://lists.sourceforge.net/lists/listinfo/gridsim-developers
>>
>
>
> ---------------------------------------------------------------------- 
> ---
> This SF.Net email is sponsored by the Moblin Your Move Developer's  
> challenge
> Build the coolest Linux based applications with Moblin SDK & win  
> great prizes
> Grand prize is a trip for two to an Open Source event anywhere in  
> the world
> http://moblin-contest.org/redirect.php?banner_id=100&url=/
> _______________________________________________
> Gridsim-users mailing list
> Gri...@li...
> https://lists.sourceforge.net/lists/listinfo/gridsim-users

Marcos Dias de Assuncao
Grid Computing and Distributed Systems (GRIDS) Laboratory
Department of Computer Science and Software Engineering
The University of Melbourne, Australia
Email: ma...@cs...

-------------
"No serious sociologist any longer believes that the voice of the  
people expresses any divine or specially wise idea. The voice of the  
people expresses the mind of the people, and that mind is made up for  
it by the group leaders in whom it believes and by those persons who  
understand the manipulation of the public opinion. It is composed of  
inherited prejudices and symbols and cliché's and verbal formulas  
supplied to them by the leaders."
Edward L. Bernays

[GridSim-users] need help

[attiqa r. <att...@ya...>]

Hello dear All! 

I have some questions, could anybody please answer them?
1. I have seen in many papers, the authors use GridSim with real grid resources from WWG [1]. I want to exactly know what it means.
2. While simulating the resources from WWG (as reported in many papers [e.g. 2]) in GridSim, how to mimic the behaviour of resources with specific workloads. 
3. Could anybody guide me about producing Directed Acyclic Graph DAG based tasks/gridlets.

Looking forward for your answers and thanking you in anticipation. 

1. World Wide Grid WWG http://www.gridbus.org/wwg/
2. Rajkumar Buyya, Manzur Murshed, David Abramson, A Deadline and Budget Constrained Cost-Time
Optimisation Algorithm for Scheduling Task Farming Applications on Global Grids2002 — In Int. Conf. on
Parallel and Distributed Processing Techniques and Applications, Las Vegas

Best  Regards
Attiqa Rehman
       
---------------------------------
  New Email names for you!  
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!

Re: [GridSim-users] Working with Gridsim tool reg

[Anthony S. <an...@cs...>]

You can find the definition of GridSim methods below
http://www.gridbus.org/gridsim/doc/api/

Also included in the gridsim package that you have downloaded.

> Two more questions...
> 1. How jobs from different users are submitted to same resource
>    when the following constraints are included?
>        - User's policy may differ
>        - Multiple Brokers submitting multiple jobs to the same resorce may
> compete with each other to complete their own job first. Whose job will be
> done first? How the problem is resolved?
>

the provided resource schedulers are basically a simple FCFS and round
robin. If you want more complex scenarios,
you have to implement a new resource scheduler based on your scenario.
That's why Example8 shows you on how to write/code the scheduler.

anthony

Re: [GridSim-users] Gridlet input transfer to a grid resource

[Anthony S. <an...@cs...>]

This is a design decision, where you need to consider the pros and cons
of each approach.

I think the Replica Manager should be in-charge of this notification,
since it deals with getting/receiving input files.
However, the Replica Manager already has many things to do.
It may burden this class further.

anthony


On Wed, 27 Aug 2008, Leonardo de Assis wrote:

> Hello again,
>
> Can I create a new Link class that simulate this behavior? Or it is better
> to create a new Machine class that warns the application that the input
> transfer of a Gridlet finished?
>
> Thanks
>
> []'s
> Leonardo

Re: [GridSim-users] [GridSim-developers] simulation fails(OOME)with 1000 resources

[Anthony S. <an...@cs...>]

GridSim uses SimJava2 not 1.2!
I specifically label the jar file to simjava2.jar for this reason.
That's why in the SimJava2, it has the distribution package.
Also, according to the SimJava2 report, the underlying simulation kernel
has changed. I can't remember exactly what the changes are.

No, GridSim doesn't modify any of existing SimJava2 classes.
GridSim only takes the class files.
Hence, only the jar file is included not the SimJava2 source files.

anthony


On Fri, 5 Sep 2008, ye wrote:

> Hi, Dear all:
> to Shuo, Thanks for your advice and help!
>
> I have downloaded simjava1.2 from its original website. However, I am afraid
> it's not the same thing used within gridsim currently, at least partially.
>
> The source code included by GridSim concerns only the src package started
> from "gridsim.", such as gridsim.auction, gridsim.util. However, after I
> unfold the class package "gridsim.jar" (/gridsimtoolkit-4.1/jars/), I
> noticed it contains two aditional src package started as "eduni", e.g.
> eduni.simjava.distributions. These packages also appear in
> /gridsimtoolkit-4.1/jars/simjava2.jar.
>
> The trick is, original simjava1.2 doesn't have
> "eduni.simjava.distributions".
>
> Does that mean gridsim has modified some classes under package
> "eduni.simjava" (e.g. Evqueue) and "eduni.simjava.distributions", which is
> not from simjava itself. If the answer is true, then I am wondering about
> two questions:
> 1. Is there anyone have the source code of the modified simjava classes? I
> couldn't find it from gridsim source directory.
> 2. What's the reason of these modification? Did Dr. Buyya encounter the same
> problem what we have now? Then maybe people could contribute without tooooo
> much work. (what do you say, shuo? :-)
>
> Best Regards
> ye

Re: [GridSim-users] How to do partial file transfer

[Anthony S. <an...@cs...>]

DataGridUser.getFile() returns the full file transfer.

If you want to simulate a partial file transfer, you have to do/code it 
yourself.

anthony


On Thu, 4 Sep 2008, Ekasit Kijsipongse wrote:

> Hi,
>     I wonder if there is a way to simulate partial transfer of a file.  The DataGridUser.getFile() can't, right?
>
> Best,
> Ekasit K

Re: [GridSim-users] help in grid sim

[Rajkumar B. <ra...@cs...>]

  attiqa rehman wrote:
> Hello Dear All!
> 
> I am a PhD candidate at University of Hagen, Germany. I am doing 
> Directed Acylic Graphs DAG based schedulinh simulation in GridSim. I 
> have following questions, could anybody please help me?
> 
> 1) I want to access real world grid workloads from World Wide Grid 
> (http://www.gridbus.org/wwg/) with custom resource characteristics like 
> peak load and offtime load.

We don't have such workload as we have NOT collected them.


> 2) I want guidance regarding simulating Astronomical applications (some 
> usecase for DAG) in GridSim.
> 3) I want to know about previous efforts (if any) in DAG based 
> scheduling simulation in GridSim.

Check out various papers gridbus.org related to Workflow 
Scheduling...many of them have used GridSim.
including: http://www.gridbus.org/students/JiaYuPhDThesis.pdf

Thanks
Raj
> 
> Looking forward to an early response and thanking you in anticipation!
> 
> Best Regards
> Attiqa Rehman
> 
> ------------------------------------------------------------------------
> New Email addresses available on Yahoo! 
> <http://sg.rd.yahoo.com/aa/mail/domainchoice/mail/signature/*http://mail.promotions.yahoo.com/newdomains/aa/> 
> 
> Get the Email name you've always wanted on the new @ymail and @rocketmail.
> Hurry before someone else does!

[GridSim-users] help in grid sim

[attiqa r. <att...@ya...>]

Hello Dear All!


I am a PhD candidate at University of Hagen, Germany. I am doing Directed Acylic Graphs DAG based schedulinh simulation in GridSim. I have following questions, could anybody please help me?


1) I want to access real world grid workloads from World Wide Grid (http://www.gridbus.org/wwg/) with custom resource characteristics like peak load and offtime load.
2) I want guidance regarding simulating Astronomical applications (some usecase for DAG) in GridSim.
3) I want to know about previous efforts (if any) in DAG based scheduling simulation in GridSim.


Looking forward to an early response and thanking you in  anticipation!


Best Regards
Attiqa Rehman
       
---------------------------------
  New Email addresses available on Yahoo!  
Get the Email name you've always wanted on the new @ymail and @rocketmail.
Hurry before someone else does!

Re: [GridSim-users] [GridSim-developers] simulation fails(OOME)with 1000 resources

[ye <hua...@gm...>]

Hi, Dear all:
to Shuo, Thanks for your advice and help!

I have downloaded simjava1.2 from its original website. However, I am afraid
it's not the same thing used within gridsim currently, at least partially.

The source code included by GridSim concerns only the src package started
from "gridsim.", such as gridsim.auction, gridsim.util. However, after I
unfold the class package "gridsim.jar" (/gridsimtoolkit-4.1/jars/), I
noticed it contains two aditional src package started as "eduni", e.g.
eduni.simjava.distributions. These packages also appear in
/gridsimtoolkit-4.1/jars/simjava2.jar.

The trick is, original simjava1.2 doesn't have
"eduni.simjava.distributions".

Does that mean gridsim has modified some classes under package
"eduni.simjava" (e.g. Evqueue) and "eduni.simjava.distributions", which is
not from simjava itself. If the answer is true, then I am wondering about
two questions:
1. Is there anyone have the source code of the modified simjava classes? I
couldn't find it from gridsim source directory.
2. What's the reason of these modification? Did Dr. Buyya encounter the same
problem what we have now? Then maybe people could contribute without tooooo
much work. (what do you say, shuo? :-)

Best Regards
ye


On Fri, Sep 5, 2008 at 4:55 PM, Shuo Yang <ya...@cs...> wrote:

> All,
>
> I think the problem also lies in the scalability of the underlying simjava
> package. Simjava uses an event queue to manage all internal events flying
> between entities. The event queue is a Vector. If you refer to
> eduni.simjava.Evqueue.java, you can see the doc:
>
> /**
> * This class implements an event queue used internally by the Sim_system to
> * manage
> * the list of future and deferred Sim_events. It should not be needed in
> * a user simulation. It works like a normal FIFO
> * queue, but during insertion events are kept in order from the smallest
> time
> * stamp to the largest. This means the next event to occur will be at the
> top
> * of the queue. <P>
> * The current implementation
> * is uses a Vector to store the queue and is inefficient for popping
> * and inserting elements because the rest of the array has to be
> * moved down one space. A better method would be to use a circular array.
> * @see          eduni.simjava.Sim_system
> * @version     0.1, 25 June 1995
> * @author      Ross McNab
> */
>
> Also, the event queue in Sim_system is accessed using 'synchronized' to
> ensure consistency and the simulation clock. Therefore when there are a huge
> amount of entities/messages, the event queue becomes the system bottleneck -
> only one entity/thread can write to event queue while the others will wait,
> and wait, and wait, and wait...
>
> It may have problem with java's handling large memories. But a re-design
> and re-implemenation of the underlying thread pool is ideal, which is
> exactly what I'm doing now.
>
> Cheers,
>
> Shuo 'Alex' Yang
> University of Manchester
>
>
> ----- Original Message ----- From: "Agustín Caminero Herráez" <
> ag...@ds...>
> To: "ye" <hua...@gm...>
> Cc: <gri...@li...>; <
> gri...@li...>
> Sent: Friday, September 05, 2008 3:35 PM
> Subject: Re: [GridSim-developers] [GridSim-users] simulation
> fails(OOME)with 1000 resources
>
>
>
> Hi Ye,
>
> I've also suffered the problems u describe, and I'm afraid there is no
> solution for them. The only suggestion I can give to u is to scale down
> your simulations.
>
> The problem comes from Java's inability to handle more than 1.5 GB of
> memory, so there is nothing u can do.
>
> Just one thing, are u using Sun Java? Because using another different
> java may cause problems... The java I us is Sun  v1.4.2
>
> Regards,
>
> Agustin
>
> ye escribió:
>
>> Hi, Dear all:
>> Although I have asked a similar question in gridsim-user maillist,
>> there seems no similar experience from other developers. Since it's an
>> crucial problem for me, I'd to make the scenario much clear and beg
>> for help.
>>
>> For brief, is there any scale limit for simulation created via GridSim?
>>
>> I was trying to set up a gridsim simulation with 1000 resource; each
>> resource contains one machine, each machine has two PEs. Then, I wrote
>> a user to retrieve resource list within its body(), and print the
>> total size. However, the program halts with an OutOfMemoryError, every
>> time before "Entities started" was printed. The user's body() was
>> never visited.
>>
>> I am working on a mac 10.5, 2GB 667 Mhz memory, mac JVM 1.5;
>> meanwhile, I already adjust the vm parameter into "-Xms512m -Xmx1024m".
>>
>> Later, I tried the same program on my server (ubuntu 8.04, 3.2GB).
>> Fortunately, it works... but, it halts again with OOME while i decide
>> create 1100 resources.
>>
>> I am not sure the problem is caused by lacking of memory? Is there any
>> limit for gridsim simulation scale, or just for GridSim Resource? Or
>> it's bug derived from simjava?
>>
>> Finally, is it possible to solve it?
>>
>> Thank you guys a lot!!
>>
>> regards
>> ye
>>
>> --
>> Ye Huang, Department of Informatics
>> University of Fribourg / Pérolles 2 - Bld de Pérolles 90
>> 1700 Fribourg, Switzerland
>>
>> e-mail: ye....@he..., ye....@un...
>> http://diuf.unifr.ch/people/huangy/
>> Office: +41 26 429 65 95
>> ------------------------------------------------------------------------
>>
>> -------------------------------------------------------------------------
>> This SF.Net email is sponsored by the Moblin Your Move Developer's
>> challenge
>> Build the coolest Linux based applications with Moblin SDK & win great
>> prizes
>> Grand prize is a trip for two to an Open Source event anywhere in the
>> world
>> http://moblin-contest.org/redirect.php?banner_id=100&url=/
>> ------------------------------------------------------------------------
>>
>> _______________________________________________
>> Gridsim-users mailing list
>> Gri...@li...
>> https://lists.sourceforge.net/lists/listinfo/gridsim-users
>>
>>
> --
> ===============================================
> Agustin Caminero
> Research Assistant.
> Computing Systems Department.
> Albacete Research Institute of Informatics (I3A).
> The University of Castilla La Mancha.
> Campus Universitario s/n, 02071, Albacete. Spain.
> Phone: +34 967 599 200 Ext. 2693. Fax: +34 967 599 343
> http://www.i3a.uclm.es/
> ===============================================
>
>
>
>
>
> --------------------------------------------------------------------------------
>
>
>  -------------------------------------------------------------------------
>> This SF.Net email is sponsored by the Moblin Your Move Developer's
>> challenge
>> Build the coolest Linux based applications with Moblin SDK & win great
>> prizes
>> Grand prize is a trip for two to an Open Source event anywhere in the
>> world
>> http://moblin-contest.org/redirect.php?banner_id=100&url=/
>>
>
>
>
> --------------------------------------------------------------------------------
>
>
>  _______________________________________________
>> Gridsim-developers mailing list
>> Gri...@li...
>> https://lists.sourceforge.net/lists/listinfo/gridsim-developers
>>
>>
>


-- 
Ye Huang, Department of Informatics
University of Fribourg / Pérolles 2 - Bld de Pérolles 90
1700 Fribourg, Switzerland

e-mail: ye....@he..., ye....@un...
http://diuf.unifr.ch/people/huangy/
Office: +41 26 429 65 95

Re: [GridSim-users] simulation fails(OOME) with 1000 resources

[ye <hua...@gm...>]

Hi, Agustín:
Thanks for reply!
Unfortunately, I am using mac jvm 1.5.0 and openjdk 1.6 instead of sun java.
However, are you sure your problem is caused by java's inability to handle
memory upto 1.5GB? Does it mean that you have monitored the memory use of
your machine has exceeded (or close) 1.5GB.

For my scenario, the simulation memory usage is only around 300MB, far
before the jvm configuration (1024M).

In the other hand, although I never have the expirence of using 1GB memory
with java, I suppose most of the real OutOfMemoryError should be caused by
the limit of machine. The limit of memory usage of 32-bit system is 4GB
(2e32), and some OSs will reserve certain amount of memory for kernel
process, e.g. windows 2000 normally reserve 2GB for its own. For your
problem, if you are sure the crash is caused by memory overload (> 1.5GB), I
think it might not be a bad news. You should be able to solve this problem
by using a 64-bit system.

Best Regards
ye

On Fri, Sep 5, 2008 at 4:35 PM, Agustín Caminero Herráez <
ag...@ds...> wrote:

> Hi Ye,
>
> I've also suffered the problems u describe, and I'm afraid there is no
> solution for them. The only suggestion I can give to u is to scale down your
> simulations.
>
> The problem comes from Java's inability to handle more than 1.5 GB of
> memory, so there is nothing u can do.
>
> Just one thing, are u using Sun Java? Because using another different java
> may cause problems... The java I us is Sun  v1.4.2
>
> Regards,
>
> Agustin
>
> ye escribió:
>
>> Hi, Dear all:
>> Although I have asked a similar question in gridsim-user maillist, there
>> seems no similar experience from other developers. Since it's an crucial
>> problem for me, I'd to make the scenario much clear and beg for help.
>>
>> For brief, is there any scale limit for simulation created via GridSim?
>>
>> I was trying to set up a gridsim simulation with 1000 resource; each
>> resource contains one machine, each machine has two PEs. Then, I wrote a
>> user to retrieve resource list within its body(), and print the total size.
>> However, the program halts with an OutOfMemoryError, every time before
>> "Entities started" was printed. The user's body() was never visited.
>>
>> I am working on a mac 10.5, 2GB 667 Mhz memory, mac JVM 1.5; meanwhile, I
>> already adjust the vm parameter into "-Xms512m -Xmx1024m".
>>
>> Later, I tried the same program on my server (ubuntu 8.04, 3.2GB).
>> Fortunately, it works... but, it halts again with OOME while i decide create
>> 1100 resources.
>>
>> I am not sure the problem is caused by lacking of memory? Is there any
>> limit for gridsim simulation scale, or just for GridSim Resource? Or it's
>> bug derived from simjava?
>>
>> Finally, is it possible to solve it?
>>
>> Thank you guys a lot!!
>>
>> regards
>> ye
>>
>> --
>> Ye Huang, Department of Informatics
>> University of Fribourg / Pérolles 2 - Bld de Pérolles 90
>> 1700 Fribourg, Switzerland
>>
>> e-mail: ye....@he..., ye....@un...
>> http://diuf.unifr.ch/people/huangy/
>> Office: +41 26 429 65 95
>> ------------------------------------------------------------------------
>>
>> -------------------------------------------------------------------------
>> This SF.Net email is sponsored by the Moblin Your Move Developer's
>> challenge
>> Build the coolest Linux based applications with Moblin SDK & win great
>> prizes
>> Grand prize is a trip for two to an Open Source event anywhere in the
>> world
>> http://moblin-contest.org/redirect.php?banner_id=100&url=/
>> ------------------------------------------------------------------------
>>
>> _______________________________________________
>> Gridsim-users mailing list
>> Gri...@li...
>> https://lists.sourceforge.net/lists/listinfo/gridsim-users
>>
>>
>
> --
> ===============================================
> Agustin Caminero
> Research Assistant.
> Computing Systems Department.
> Albacete Research Institute of Informatics (I3A).
> The University of Castilla La Mancha.
> Campus Universitario s/n, 02071, Albacete. Spain.
> Phone: +34 967 599 200 Ext. 2693. Fax: +34 967 599 343
> http://www.i3a.uclm.es/
> ===============================================
>
>


-- 
Ye Huang, Department of Informatics
University of Fribourg / Pérolles 2 - Bld de Pérolles 90
1700 Fribourg, Switzerland

e-mail: ye....@he..., ye....@un...
http://diuf.unifr.ch/people/huangy/
Office: +41 26 429 65 95

Re: [GridSim-users] [GridSim-developers] simulation fails(OOME)with 1000 resources

[Shuo Y. <ya...@cs...>]

All,

I think the problem also lies in the scalability of the underlying simjava 
package. Simjava uses an event queue to manage all internal events flying 
between entities. The event queue is a Vector. If you refer to 
eduni.simjava.Evqueue.java, you can see the doc:

/**
 * This class implements an event queue used internally by the Sim_system to
 * manage
 * the list of future and deferred Sim_events. It should not be needed in
 * a user simulation. It works like a normal FIFO
 * queue, but during insertion events are kept in order from the smallest 
time
 * stamp to the largest. This means the next event to occur will be at the 
top
 * of the queue. <P>
 * The current implementation
 * is uses a Vector to store the queue and is inefficient for popping
 * and inserting elements because the rest of the array has to be
 * moved down one space. A better method would be to use a circular array.
 * @see		eduni.simjava.Sim_system
 * @version     0.1, 25 June 1995
 * @author      Ross McNab
 */

Also, the event queue in Sim_system is accessed using 'synchronized' to 
ensure consistency and the simulation clock. Therefore when there are a huge 
amount of entities/messages, the event queue becomes the system bottleneck - 
only one entity/thread can write to event queue while the others will wait, 
and wait, and wait, and wait...

It may have problem with java's handling large memories. But a re-design and 
re-implemenation of the underlying thread pool is ideal, which is exactly 
what I'm doing now.

Cheers,

Shuo 'Alex' Yang
University of Manchester


----- Original Message ----- 
From: "Agustín Caminero Herráez" <ag...@ds...>
To: "ye" <hua...@gm...>
Cc: <gri...@li...>; 
<gri...@li...>
Sent: Friday, September 05, 2008 3:35 PM
Subject: Re: [GridSim-developers] [GridSim-users] simulation fails(OOME)with 
1000 resources


Hi Ye,

I've also suffered the problems u describe, and I'm afraid there is no
solution for them. The only suggestion I can give to u is to scale down
your simulations.

The problem comes from Java's inability to handle more than 1.5 GB of
memory, so there is nothing u can do.

Just one thing, are u using Sun Java? Because using another different
java may cause problems... The java I us is Sun  v1.4.2

Regards,

Agustin

ye escribió:
> Hi, Dear all:
> Although I have asked a similar question in gridsim-user maillist,
> there seems no similar experience from other developers. Since it's an
> crucial problem for me, I'd to make the scenario much clear and beg
> for help.
>
> For brief, is there any scale limit for simulation created via GridSim?
>
> I was trying to set up a gridsim simulation with 1000 resource; each
> resource contains one machine, each machine has two PEs. Then, I wrote
> a user to retrieve resource list within its body(), and print the
> total size. However, the program halts with an OutOfMemoryError, every
> time before "Entities started" was printed. The user's body() was
> never visited.
>
> I am working on a mac 10.5, 2GB 667 Mhz memory, mac JVM 1.5;
> meanwhile, I already adjust the vm parameter into "-Xms512m -Xmx1024m".
>
> Later, I tried the same program on my server (ubuntu 8.04, 3.2GB).
> Fortunately, it works... but, it halts again with OOME while i decide
> create 1100 resources.
>
> I am not sure the problem is caused by lacking of memory? Is there any
> limit for gridsim simulation scale, or just for GridSim Resource? Or
> it's bug derived from simjava?
>
> Finally, is it possible to solve it?
>
> Thank you guys a lot!!
>
> regards
> ye
>
> -- 
> Ye Huang, Department of Informatics
> University of Fribourg / Pérolles 2 - Bld de Pérolles 90
> 1700 Fribourg, Switzerland
>
> e-mail: ye....@he..., ye....@un...
> http://diuf.unifr.ch/people/huangy/
> Office: +41 26 429 65 95
> ------------------------------------------------------------------------
>
> -------------------------------------------------------------------------
> This SF.Net email is sponsored by the Moblin Your Move Developer's 
> challenge
> Build the coolest Linux based applications with Moblin SDK & win great 
> prizes
> Grand prize is a trip for two to an Open Source event anywhere in the 
> world
> http://moblin-contest.org/redirect.php?banner_id=100&url=/
> ------------------------------------------------------------------------
>
> _______________________________________________
> Gridsim-users mailing list
> Gri...@li...
> https://lists.sourceforge.net/lists/listinfo/gridsim-users
>

-- 
===============================================
Agustin Caminero
Research Assistant.
Computing Systems Department.
Albacete Research Institute of Informatics (I3A).
The University of Castilla La Mancha.
Campus Universitario s/n, 02071, Albacete. Spain.
Phone: +34 967 599 200 Ext. 2693. Fax: +34 967 599 343
http://www.i3a.uclm.es/
===============================================




--------------------------------------------------------------------------------


> -------------------------------------------------------------------------
> This SF.Net email is sponsored by the Moblin Your Move Developer's 
> challenge
> Build the coolest Linux based applications with Moblin SDK & win great 
> prizes
> Grand prize is a trip for two to an Open Source event anywhere in the 
> world
> http://moblin-contest.org/redirect.php?banner_id=100&url=/


--------------------------------------------------------------------------------


> _______________________________________________
> Gridsim-developers mailing list
> Gri...@li...
> https://lists.sourceforge.net/lists/listinfo/gridsim-developers
> 

Re: [GridSim-users] simulation fails(OOME) with 1000 resources

[Agustín C. H. <ag...@ds...>]

Hi Ye,

I've also suffered the problems u describe, and I'm afraid there is no 
solution for them. The only suggestion I can give to u is to scale down 
your simulations.

The problem comes from Java's inability to handle more than 1.5 GB of 
memory, so there is nothing u can do.

Just one thing, are u using Sun Java? Because using another different 
java may cause problems... The java I us is Sun  v1.4.2

Regards,

Agustin

ye escribió:
> Hi, Dear all:
> Although I have asked a similar question in gridsim-user maillist, 
> there seems no similar experience from other developers. Since it's an 
> crucial problem for me, I'd to make the scenario much clear and beg 
> for help.
>
> For brief, is there any scale limit for simulation created via GridSim?
>
> I was trying to set up a gridsim simulation with 1000 resource; each 
> resource contains one machine, each machine has two PEs. Then, I wrote 
> a user to retrieve resource list within its body(), and print the 
> total size. However, the program halts with an OutOfMemoryError, every 
> time before "Entities started" was printed. The user's body() was 
> never visited.
>
> I am working on a mac 10.5, 2GB 667 Mhz memory, mac JVM 1.5; 
> meanwhile, I already adjust the vm parameter into "-Xms512m -Xmx1024m".
>
> Later, I tried the same program on my server (ubuntu 8.04, 3.2GB). 
> Fortunately, it works... but, it halts again with OOME while i decide 
> create 1100 resources.
>
> I am not sure the problem is caused by lacking of memory? Is there any 
> limit for gridsim simulation scale, or just for GridSim Resource? Or 
> it's bug derived from simjava?
>
> Finally, is it possible to solve it?
>
> Thank you guys a lot!!
>
> regards
> ye
>
> -- 
> Ye Huang, Department of Informatics
> University of Fribourg / Pérolles 2 - Bld de Pérolles 90
> 1700 Fribourg, Switzerland
>
> e-mail: ye....@he..., ye....@un...
> http://diuf.unifr.ch/people/huangy/
> Office: +41 26 429 65 95
> ------------------------------------------------------------------------
>
> -------------------------------------------------------------------------
> This SF.Net email is sponsored by the Moblin Your Move Developer's challenge
> Build the coolest Linux based applications with Moblin SDK & win great prizes
> Grand prize is a trip for two to an Open Source event anywhere in the world
> http://moblin-contest.org/redirect.php?banner_id=100&url=/
> ------------------------------------------------------------------------
>
> _______________________________________________
> Gridsim-users mailing list
> Gri...@li...
> https://lists.sourceforge.net/lists/listinfo/gridsim-users
>   

-- 
===============================================
Agustin Caminero
Research Assistant.
Computing Systems Department.
Albacete Research Institute of Informatics (I3A).
The University of Castilla La Mancha.
Campus Universitario s/n, 02071, Albacete. Spain.
Phone: +34 967 599 200 Ext. 2693. Fax: +34 967 599 343
http://www.i3a.uclm.es/
===============================================

[GridSim-users] simulation fails(OOME) with 1000 resources

[ye <hua...@gm...>]

Hi, Dear all:
Although I have asked a similar question in gridsim-user maillist, there
seems no similar experience from other developers. Since it's an crucial
problem for me, I'd to make the scenario much clear and beg for help.

For brief, is there any scale limit for simulation created via GridSim?

I was trying to set up a gridsim simulation with 1000 resource; each
resource contains one machine, each machine has two PEs. Then, I wrote a
user to retrieve resource list within its body(), and print the total size.
However, the program halts with an OutOfMemoryError, every time before
"Entities started" was printed. The user's body() was never visited.

I am working on a mac 10.5, 2GB 667 Mhz memory, mac JVM 1.5; meanwhile, I
already adjust the vm parameter into "-Xms512m -Xmx1024m".

Later, I tried the same program on my server (ubuntu 8.04, 3.2GB).
Fortunately, it works... but, it halts again with OOME while i decide create
1100 resources.

I am not sure the problem is caused by lacking of memory? Is there any limit
for gridsim simulation scale, or just for GridSim Resource? Or it's bug
derived from simjava?

Finally, is it possible to solve it?

Thank you guys a lot!!

regards
ye

-- 
Ye Huang, Department of Informatics
University of Fribourg / Pérolles 2 - Bld de Pérolles 90
1700 Fribourg, Switzerland

e-mail: ye....@he..., ye....@un...
http://diuf.unifr.ch/people/huangy/
Office: +41 26 429 65 95

[GridSim-users] How to do partial file transfer

[Ekasit K. <g46...@st...>]

Hi,
     I wonder if there is a way to simulate partial transfer of a file.  The DataGridUser.getFile() can't, right?

Best,
Ekasit K

[GridSim-users] simulation scale benchmark available?

[ye <hua...@gm...>]

Hi, Dear all:
I was trying to set up a gridsim simulation with 1000 resource; each
resource contains one machine, each machine has two PEs.
I am working on a mac 10.5, 2GB 667 Mhz memory, mac JVM 1.5; meanwhile, I
already adjust the vm parameter into "-Xms512m -Xmx1024m".

I wrote a user to retrieve resource list within its body(), and print the
total size. However, the program halts with an OutOfMemoryError, every time
before "Entities started" was printed. The user's body() was never visited.

I am not sure the problem is caused by lacking of memory? Is there any limit
for gridsim simulation scale?

Is there any limit on resource amount or something else?

And is there any benchmark for gridsim? For instance, how much memory it
might cost if I wanna simulate 2000 resources(1 machine and totally 2 PEs)?

Thank you guys a lot!!

regards
ye

-- 
Ye Huang, Department of Informatics
University of Fribourg / Pérolles 2 - Bld de Pérolles 90
1700 Fribourg, Switzerland

e-mail: ye....@he..., ye....@un...
http://diuf.unifr.ch/people/huangy/
Office: +41 26 429 65 95