From shubhada.nandarshi at gmail.com Thu Mar 1 13:04:13 2007 From: shubhada.nandarshi at gmail.com (shubhada nandarshi) Date: Thu, 1 Mar 2007 23:34:13 +0530 Subject: [Disksim-users] Facing problems in Disksim Message-ID: Hi, Is there any available code which we can refer for getting more idea about 'How to write a parameter file and output file' , so that we will be able to write a code for that. Thanks & Regards, Shubhada/Nilofer -------------- next part -------------- An HTML attachment was scrubbed... URL: From bucy at gloop.org Thu Mar 1 13:20:46 2007 From: bucy at gloop.org (John Bucy) Date: Thu, 1 Mar 2007 10:20:46 -0800 Subject: [Disksim-users] Facing problems in Disksim In-Reply-To: References: Message-ID: <4fc1e0430703011020i666a7f0u28fed498c7e818ce@mail.gmail.com> You generally shouldn't write one from scratch; look in the valid/ subdirectory of the distribution for many examples. john On 3/1/07, shubhada nandarshi wrote: > Hi, > Is there any available code which we can refer for getting more idea about > 'How to write a parameter file and output file' , so that we will be able to > write a code for that. > > Thanks & Regards, > Shubhada/Nilofer > > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > > From shahrukh at cs.virginia.edu Thu Mar 1 13:24:34 2007 From: shahrukh at cs.virginia.edu (Shahrukh Rohinton Tarapore) Date: Thu, 1 Mar 2007 13:24:34 -0500 Subject: [Disksim-users] Facing problems in Disksim In-Reply-To: References: Message-ID: <1017d5510703011024s3584affap147448763a94dd45@mail.gmail.com> Checkout this database of disksim parameter files some commonly modelled disks. Its unlikely you would want to write an entirely new parameter file, so if there are just a few parameters you want to adjust I would simply duplicate one of these parameter files and make the appropriate changes. If there is a specific disk you want to create a parameter file for you can try using DIXtrac, I'm not familiar with it but it basically extracts the parameters of a real disk which you can use to create a config file for disksim. As for the output file, you do not write these. The output file simply contains the statistics of the execution of the simulator on a given parameter file. The output file gives you the results of your simulation, so disksim will be the only one that writes to this file. Earlier you asked how to run disksim, there is an example in the documentation in section 2.2. Hope this helps. -- shahrukh On 3/1/07, shubhada nandarshi < shubhada.nandarshi at gmail.com> wrote: > > Hi, > Is there any available code which we can refer for getting more idea about > 'How to write a parameter file and output file' , so that we will be able to > write a code for that. > > Thanks & Regards, > Shubhada/Nilofer > > > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From shubhada.nandarshi at gmail.com Sat Mar 3 04:57:48 2007 From: shubhada.nandarshi at gmail.com (shubhada nandarshi) Date: Sat, 3 Mar 2007 15:27:48 +0530 Subject: [Disksim-users] facing problem Message-ID: yes we tried but we are facing a comment like"*parameter file overrides must be 3-tuples" * in command prompt we are using the follwing command : "*disksim cheetah9LP.parv cheetah9LP.runvalid valid/ascii.trace src/disksim_global.h 0 "disk0 .. disk17"" T*hanks & Regards,. Shubhada /Nilofer -------------- next part -------------- An HTML attachment was scrubbed... URL: From shubhada.nandarshi at gmail.com Sat Mar 3 07:14:02 2007 From: shubhada.nandarshi at gmail.com (shubhada nandarshi) Date: Sat, 3 Mar 2007 17:44:02 +0530 Subject: [Disksim-users] How to run the given example. Message-ID: i saw the 'database of the disksim parameter files' . can i run directly the 'diskname.runvalid' ? i tried one disk using this command. But it is giving me an error 'command not found' . I also saw the examples given in the valid directory. But i m still confused with final output that i will get after running the 'disksim' command. Uptil now i understood that, my i/p file will have '.parv' , o/p file will have '.outv' extention, trace file will have '.trace' extention.But what about other command line parameters? Thanks & regards, Shubhada -------------- next part -------------- An HTML attachment was scrubbed... URL: From shahrukh at cs.virginia.edu Sat Mar 3 07:27:10 2007 From: shahrukh at cs.virginia.edu (Shahrukh Rohinton Tarapore) Date: Sat, 3 Mar 2007 07:27:10 -0500 Subject: Fwd: [Disksim-users] Facing problems in Disksim In-Reply-To: <1017d5510703030425v2c85849epc7ace53255d7b0ae@mail.gmail.com> References: <1017d5510703011024s3584affap147448763a94dd45@mail.gmail.com> <1017d5510703030425v2c85849epc7ace53255d7b0ae@mail.gmail.com> Message-ID: <1017d5510703030427s6e82f5c4r22e9a472c8142d6e@mail.gmail.com> ---------- Forwarded message ---------- From: Shahrukh Rohinton Tarapore Date: Mar 3, 2007 7:25 AM Subject: Re: [Disksim-users] Facing problems in Disksim To: shubhada nandarshi Yes, because you included "disk0 .. disk17". See disksim by default requires only 5 parameters. If you add more then they must be in multiples of three (3-tuples). These 3-tuples are meant to easily change parameters already defined in the parameter file. You will probably not want to do this. Second the first 5 parameters you are using are not correct. To run disksim you need to enter this at the terminal: diskim where, is a file which contains properly formatted parameters for disksim is a file (which may or may not exist) where disksim can dump the statistics tells disksim what format the trace is in a file containing properly formatted trace of disk requests (in format) is set to 1 if you will manually generate the disk requests. (this is usually set to zero since you have a trace file) With all that the proper way to execute disksim would be: *disksim cheetah9LP.parv cheetah9LP.out validate cheetah9LP.trace 0 This will execute disksim with the cheetah9LP parameter file, and the statistics can be found in a file called cheetah9LP.out when the simulation is complete, and the simulation executed on a trace found in cheetah9LP.trace which is formatted in the validate type. Finally no synthetic generation was used. Once the simulation is complete go and view cheetah9LP.out to see the results of the simulation. -- shahrukh *** On 3/3/07, shubhada nandarshi wrote: > > yes we tried but we are facing a comment like"*parameter file overrides > must be 3-tuples" * > > in command prompt we are using the follwing command : > > "*disksim cheetah9LP.parv cheetah9LP.runvalid valid/ascii.trace > src/disksim_global.h 0 "disk0 .. disk17"" > > * > On 3/1/07, Shahrukh Rohinton Tarapore wrote: > > > > Checkout this database of disksim parameter files some commonly modelled > > disks. Its unlikely you would want to write an entirely new parameter file, > > so if there are just a few parameters you want to adjust I would simply > > duplicate one of these parameter files and make the appropriate changes. If > > there is a specific disk you want to create a parameter file for you can try > > using DIXtrac, I'm not familiar with it but it basically extracts the > > parameters of a real disk which you can use to create a config file for > > disksim. > > > > As for the output file, you do not write these. The output file simply > > contains the statistics of the execution of the simulator on a given > > parameter file. The output file gives you the results of your simulation, > > so disksim will be the only one that writes to this file. > > > > Earlier you asked how to run disksim, there is an example in the > > documentation in section 2.2. > > > > Hope this helps. > > > > -- shahrukh > > > > On 3/1/07, shubhada nandarshi < shubhada.nandarshi at gmail.com> wrote: > > > > > > Hi, > > > Is there any available code which we can refer for getting more > > > idea about 'How to write a parameter file and output file' , so that we will > > > be able to write a code for that. > > > > > > Thanks & Regards, > > > Shubhada/Nilofer > > > > > > > > > _______________________________________________ > > > Disksim-users mailing list > > > Disksim-users at ece.cmu.edu > > > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > > > > > > > > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From shubhada.nandarshi at gmail.com Mon Mar 5 06:22:56 2007 From: shubhada.nandarshi at gmail.com (shubhada nandarshi) Date: Mon, 5 Mar 2007 16:52:56 +0530 Subject: [Disksim-users] Not able to understand..what is a problem. Message-ID: Hi, I triend the following command, *disksim cheetah9LP.parv cheetah9LP.out validate vheetah9LP.trace 0* I am getting the following message, *No configuration for stat Physical access time given in statdefs file* Why i am getting this message? do i need to change in output file or what? Thaks & Regards, Shubhada -------------- next part -------------- An HTML attachment was scrubbed... URL: From swschlosser at gmail.com Mon Mar 5 09:53:49 2007 From: swschlosser at gmail.com (Steve Schlosser) Date: Mon, 5 Mar 2007 09:53:49 -0500 Subject: [Disksim-users] Not able to understand..what is a problem. In-Reply-To: References: Message-ID: <4d362c350703050653ke58e6f5xed49dd66a06977fa@mail.gmail.com> Make sure you have a statdefs file in the directory where you're running disksim. The path to the statdefs file is defined in the parv file. You should be able to find an example statdefs file in the disksim/valid directory. -steve On 3/5/07, shubhada nandarshi wrote: > Hi, > I triend the following command, > disksim cheetah9LP.parv cheetah9LP.out validate vheetah9LP.trace 0 > I am getting the following message, > No configuration for stat Physical access time given in statdefs file > Why i am getting this message? do i need to change in output file or what? > > Thaks & Regards, > Shubhada > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > > From shubhada.nandarshi at gmail.com Tue Mar 6 07:48:46 2007 From: shubhada.nandarshi at gmail.com (shubhada nandarshi) Date: Tue, 6 Mar 2007 18:18:46 +0530 Subject: [Disksim-users] Problems using Disksim Message-ID: HI, We wanted to know the *contents of trace file*.We can see inside some integers,floating point numbers & R/W hits.But we are not able to understand what exactly those number means.Also we require a brief discription of " *output file*".We are not able to understand what are its contents.We understood that in the beginning there are parv file contents.But whatever is after that we did'nt understand. Regards, Shubhada/Nilofer -------------- next part -------------- An HTML attachment was scrubbed... URL: From sgovinda at cse.psu.edu Tue Mar 6 08:32:11 2007 From: sgovinda at cse.psu.edu (Sriram Govindan) Date: Tue, 6 Mar 2007 08:32:11 -0500 (EST) Subject: [Disksim-users] Problems using Disksim In-Reply-To: References: Message-ID: Whatever you wanted is in the disksim reference manual. sriram.G On Tue, 6 Mar 2007, shubhada nandarshi wrote: > HI, > We wanted to know the *contents of trace file*.We can see inside some > integers,floating point numbers & R/W hits.But we are not able to understand > what exactly those number means.Also we require a brief discription of > " *output > file*".We are not able to understand what are its contents.We understood > that in the beginning there are parv file contents.But whatever is after > that we did'nt understand. > > Regards, > Shubhada/Nilofer > From ouki at hotmail.com Wed Mar 7 13:58:05 2007 From: ouki at hotmail.com (Jack Wang) Date: Wed, 7 Mar 2007 10:58:05 -0800 Subject: [Disksim-users] Does DiskSim support disk array reconstruction/rebuild? Message-ID: Hello Disksim user community, I am working on a project and I would like to use Disksim to simulate my algorithms. But I am not sure if the Disksim supports what I am trying to do. Does Disksim support disk array reconstruction simulations? Let's say I have RAID5 array with five disks. In case of hard disk failure, I need to simulate the disk rebuilding process while serving I/O requests. The reconstruction time need to be calculated and the drawback to the I/O performance needs to be counted as well. I would appreciate if anyone could give me an answer, together with a brief hint on how to accomplish that. Thanks. Jack _________________________________________________________________ Explore the seven wonders of the world http://search.msn.com/results.aspx?q=7+wonders+world&mkt=en-US&form=QBRE -------------- next part -------------- An HTML attachment was scrubbed... URL: From swschlosser at gmail.com Wed Mar 7 14:16:19 2007 From: swschlosser at gmail.com (Steve Schlosser) Date: Wed, 7 Mar 2007 14:16:19 -0500 Subject: [Disksim-users] Does DiskSim support disk array reconstruction/rebuild? In-Reply-To: References: Message-ID: <4d362c350703071116h67a70e82j250c480b98b8030d@mail.gmail.com> No, Disksim does not support its own rebuild. You would have to generate this workload yourself. I would do this by simulating an 5-disk array with no redundancy, generating simultaneous reads from the four non-failed disks, adding in some think time to simulate re-building the data from parity, then issuing writes to the fifth disk. While this is running, you could run some foreground requests as well. You could do this pretty easily by writing a program that uses the disksim_interface to issue your requests to the disk and drive the simulator - see the syssim program as an example of how to use disksim_interface. -steve On 3/7/07, Jack Wang wrote: > > Hello Disksim user community, > > I am working on a project and I would like to use Disksim to simulate my > algorithms. But I am not sure if the Disksim supports what I am trying to > do. > > Does Disksim support disk array reconstruction simulations? Let's say I > have RAID5 array with five disks. In case of hard disk failure, I need to > simulate the disk rebuilding process while serving I/O requests. The > reconstruction time need to be calculated and the drawback to the I/O > performance needs to be counted as well. > > I would appreciate if anyone could give me an answer, together with a brief > hint on how to accomplish that. Thanks. > > Jack > > ________________________________ > Explore the seven wonders of the world Learn more! > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > > From shubhada.nandarshi at gmail.com Thu Mar 8 05:06:36 2007 From: shubhada.nandarshi at gmail.com (shubhada nandarshi) Date: Thu, 8 Mar 2007 15:36:36 +0530 Subject: [Disksim-users] Usage of Disksim Message-ID: Hello, I reade all manual of disksim, now i got the concept of disk simulator. In our project we are getting *' queue of packets ' *as input from network simulator. I have to read the *time delay * at each step when data is transferring from controller -> bus->disk. Kindly give your suggestions. Thanks & Regards, Shubhada. -------------- next part -------------- An HTML attachment was scrubbed... URL: From shubhada.nandarshi at gmail.com Sun Mar 11 06:16:30 2007 From: shubhada.nandarshi at gmail.com (shubhada nandarshi) Date: Sun, 11 Mar 2007 15:46:30 +0530 Subject: [Disksim-users] Disk Scheduling algorithms disksim. Message-ID: Hi , i want to use the disk scheduling algorithms (FIFO,SCAN,LOOK,CSCAN etc) in disksim. how should i proceed? Thanks & Regards, Shubhada. -------------- next part -------------- An HTML attachment was scrubbed... URL: From shubhada.nandarshi at gmail.com Sun Mar 11 06:37:03 2007 From: shubhada.nandarshi at gmail.com (shubhada nandarshi) Date: Sun, 11 Mar 2007 16:07:03 +0530 Subject: [Disksim-users] Not able to understand trace file. Message-ID: Hi , i am not able to understand the contents of the trace file. I am referring * cheetah9LP.trace* (which is in valid directory) for reference. In this file , the first column tells whether it is read / write instruction. I am not understanding what other values are? Thanks & Regards, Shubhada. -------------- next part -------------- An HTML attachment was scrubbed... URL: From bucy at gloop.org Tue Mar 13 13:20:25 2007 From: bucy at gloop.org (John Bucy) Date: Tue, 13 Mar 2007 10:20:25 -0700 Subject: [Disksim-users] Re: Not able to understand trace file. In-Reply-To: References: Message-ID: <4fc1e0430703131020q1b9485c1g6fcb093480245e73@mail.gmail.com> Look in src/disksim_iotrace.c john On 3/11/07, shubhada nandarshi wrote: > Hi , > > i am not able to understand the contents of the trace file. I am referring > cheetah9LP.trace (which is in valid directory) for reference. In this file , > the first column tells whether it is read / write instruction. I am not > understanding what other values are? > > > Thanks & Regards, > Shubhada. > From bucy at gloop.org Tue Mar 13 13:21:33 2007 From: bucy at gloop.org (John Bucy) Date: Tue, 13 Mar 2007 10:21:33 -0700 Subject: [Disksim-users] Re: Disk Scheduling algorithms disksim. In-Reply-To: References: Message-ID: <4fc1e0430703131021v2b07eb46q7af6bc0c7322f0fd@mail.gmail.com> You'll want to set the "Scheduling policy" parameter; details are in the manual. john On 3/11/07, shubhada nandarshi wrote: > Hi , > i want to use the disk scheduling algorithms (FIFO,SCAN,LOOK,CSCAN etc) > in disksim. how should i proceed? > > > Thanks & Regards, > Shubhada. From amareshwari at csa.iisc.ernet.in Thu Mar 15 05:09:10 2007 From: amareshwari at csa.iisc.ernet.in (AMARESHWARI) Date: Thu, 15 Mar 2007 14:39:10 +0530 (IST) Subject: [Disksim-users] Regarding .parv .seek .model .diskspecs files In-Reply-To: <4fc1e0430703131021v2b07eb46q7af6bc0c7322f0fd@mail.gmail.com> References: <4fc1e0430703131021v2b07eb46q7af6bc0c7322f0fd@mail.gmail.com> Message-ID: Hi, Could someone help in the following issue? If I want to run traces generated for a disk that is not present in 'valid' directory, How should i generate .parv, .seek, .model and .diskspecs files for that disk? I got the traces on a solaris machine. On linux machine, we could know the geometry and some other parameters using 'hdparm'. Is there any equivalent command in Solaris? (I didnt find any...) Thanks and Regards, Amareshwari From swschlosser at gmail.com Thu Mar 15 12:03:23 2007 From: swschlosser at gmail.com (Steve Schlosser) Date: Thu, 15 Mar 2007 12:03:23 -0400 Subject: [Disksim-users] Regarding .parv .seek .model .diskspecs files In-Reply-To: References: <4fc1e0430703131021v2b07eb46q7af6bc0c7322f0fd@mail.gmail.com> Message-ID: <4d362c350703150903o7c9fdfb9l692e6630b167f88e@mail.gmail.com> Hi Generating configurations for new disks is the goal of another tool called DIXtrac (http://www.pdl.cmu.edu/Dixtrac/index.html), which is not currently available online, although we are hoping to make a public release soon. You can try to edit your configuration files to reflect the parameters of another disk, but it will probably be tricky to get it right. -steve On 3/15/07, AMARESHWARI wrote: > > Hi, > > Could someone help in the following issue? > > If I want to run traces generated for a disk that is not present in > 'valid' directory, How should i generate .parv, .seek, .model and > .diskspecs files for that disk? > > I got the traces on a solaris machine. On linux machine, we could know the > geometry and some other parameters using 'hdparm'. Is there any equivalent > command in Solaris? (I didnt find any...) > > Thanks and Regards, > Amareshwari > > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > From nilofer.tauseef at gmail.com Fri Mar 16 05:19:25 2007 From: nilofer.tauseef at gmail.com (Nilofer Tauseef) Date: Fri, 16 Mar 2007 14:49:25 +0530 Subject: [Disksim-users] Output file Message-ID: Hi, We are unable to understand the contents of output file.It is around 6000 lines.Is there any way by which we can get only the desired contents instead of all the reapeated data that are already present in parv file & statdefs file.Or is there any use of those contents. Thanks and Regards, Nilofer/Shubhada -------------- next part -------------- An HTML attachment was scrubbed... URL: From shubhada.nandarshi at gmail.com Fri Mar 16 08:21:35 2007 From: shubhada.nandarshi at gmail.com (shubhada nandarshi) Date: Fri, 16 Mar 2007 17:51:35 +0530 Subject: [Disksim-users] contents of output file. Message-ID: Hi, Please explain the term bin and bin boundry. and also please explain the following line. VALIDATE Trace access diff time distribution < -5 < -1 < 0 < 1 < 2 < 5 < 10 < 11 < 12 12+ 10 1111 595 6474 628 1059 121 1 1 0 Thanks, Shubhada. -------------- next part -------------- An HTML attachment was scrubbed... URL: From ganger at ece.cmu.edu Fri Mar 16 13:37:57 2007 From: ganger at ece.cmu.edu (Greg Ganger) Date: Fri, 16 Mar 2007 13:37:57 -0400 (EDT) Subject: [Disksim-users] Output file In-Reply-To: References: Message-ID: This is covered in the DiskSim User Manual. Greg On Fri, 16 Mar 2007, Nilofer Tauseef wrote: > Hi, > > We are unable to understand the contents of output file.It is around 6000 > lines.Is there any way by which we can get only the desired contents instead > of all the reapeated data that are already present in parv file & statdefs > file.Or is there any use of those contents. > > Thanks and Regards, > Nilofer/Shubhada > From swschlosser at gmail.com Mon Mar 19 11:42:58 2007 From: swschlosser at gmail.com (Steve Schlosser) Date: Mon, 19 Mar 2007 11:42:58 -0400 Subject: [Disksim-users] contents of output file. In-Reply-To: References: Message-ID: <4d362c350703190842m412fc107xd7fab206491cd4df@mail.gmail.com> These specify bins for the histograms which are output by DiskSim for a particular statistic. The statistic you've shown here is described in section 5.2.2 of the DiskSim 2.0 manual. The output is the histogram of the VALIDATE Trace access diff time statistic. -steve On 3/16/07, shubhada nandarshi wrote: > Hi, > Please explain the term bin and bin boundry. and also please explain the > following line. > > VALIDATE Trace access diff time distribution > < -5 < -1 < 0 < 1 < 2 < 5 < 10 < 11 < 12 > 12+ > 10 1111 595 6474 628 1059 121 1 1 > 0 > > > Thanks, > Shubhada. > > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > > From nilofer.tauseef at gmail.com Thu Mar 22 07:00:47 2007 From: nilofer.tauseef at gmail.com (Nilofer Tauseef) Date: Thu, 22 Mar 2007 16:30:47 +0530 Subject: [Disksim-users] Scheduling Policy Message-ID: Hi, We have tried changing the "Scheduling Policy" in disksim_ioqueue in .parv file.But we cannot see any difference in the output file.How should we make changes so as to see the difference in the output file after changing the "Scheduling Policy" in .parv file. Awaiting for Reply, Nilofer/Shubhada -------------- next part -------------- An HTML attachment was scrubbed... URL: