From kazemi.samaneh at gmail.com Sat Feb 5 11:53:55 2011 From: kazemi.samaneh at gmail.com (Samane Kazemi) Date: Sat, 5 Feb 2011 20:23:55 +0330 Subject: [Disksim-users] questions about adding prefetching method to disksim Message-ID: <7CC53E28-4EE0-4438-903E-9AC55355A283@gmail.com> Dear all, I am going to add my own prefetching method to disksim. After debugging the disksim code, I think I should add this scheme to the "cache_read_continue" function which is implemented in the "disksim_cachemem.c" file. I don't know if I am right or not. I also think I must define a "prefetching request" as an event. and treat it like a "I/O request" event. I have some questions. I hope you have time to help me about them. 1. Would you please tell me what is the difference between "extraq" and "intq"? 2. It seems "extraq" is like a stack which holds all events. If I want to send a new I/O request , I don't know if it is a good idea to add the request to this stack. Because the new request should wait till the prior read disk has been completed. Thanks and best regards, Samaneh From frajaei55 at gmail.com Sun Feb 6 05:35:57 2011 From: frajaei55 at gmail.com (f.rajaei) Date: Sun, 6 Feb 2011 14:05:57 +0330 Subject: [Disksim-users] SSD elements Message-ID: Dear all, I want to know if parallel I/O (RAID 0) is performed among elements of an SSD in Disksim 4.0. Regards, Farzaneh Rajaei -------------- next part -------------- An HTML attachment was scrubbed... URL: From pbehzadn at mail.usf.edu Tue Feb 8 17:32:54 2011 From: pbehzadn at mail.usf.edu (Peyman Behzadnia) Date: Tue, 8 Feb 2011 17:32:54 -0500 Subject: [Disksim-users] How to Fix the Saturation Error Due to Heavy Workload! Message-ID: Dear All, This is Peyman Behzadnia, a PhD student in Computer Science & Engineering. I'm contacting you guys regarding the 'Saturation Error' of the disksim. I've run a simulation on top of the disksim4 in which i have to feed the simulator with my ascii-format workload with high intensity (100-700 requests per second). The problem is that the disksim has constantly given the saturation error: the simulation stopped due to saturation. I have re-checked all of the detailed parameters in my parameter file and also have tested my workload with the sample parameter files provided by the disksim. But, it gives the same error. When i decrease the intensity into 1 request per 1-2seconds, it works well. I personally do not believe that such disk simulator can not even handle 20 requests per second. It might be something about a configuration. I appreciate if somebody can give me a hint or comment about how to fix this saturation error. Best, Peyman -------------- next part -------------- An HTML attachment was scrubbed... URL: From ganger at ece.cmu.edu Tue Feb 8 19:30:08 2011 From: ganger at ece.cmu.edu (Greg Ganger) Date: Tue, 8 Feb 2011 19:30:08 -0500 (EST) Subject: [Disksim-users] How to Fix the Saturation Error Due to Heavy Workload! In-Reply-To: References: Message-ID: The saturation error happens because the workload is heavier than the simualted storage system can handle... not because the simulator itself can't keep up. Good luck, Greg On Tue, 8 Feb 2011, Peyman Behzadnia wrote: > Dear All, > > This is Peyman Behzadnia, a PhD student in Computer Science & Engineering. > I'm contacting you guys regarding the 'Saturation Error' of the disksim. > > I've run a simulation on top of the disksim4 in which i have to feed the > simulator with my ascii-format workload with high intensity (100-700 > requests per second). The problem is that the disksim has constantly given > the saturation error: the simulation stopped due to saturation. I have > re-checked all of the detailed parameters in my parameter file and also have > tested my workload with the sample parameter files provided by the disksim. > But, it gives the same error. When i decrease the intensity into 1 request > per 1-2seconds, it works well. > I personally do not believe that such disk simulator can not even handle 20 > requests per second. It might be something about a configuration. I > appreciate if somebody can give me a hint or comment about how to fix this > saturation error. > > Best, > Peyman > From pbehzadn at mail.usf.edu Tue Feb 8 19:52:44 2011 From: pbehzadn at mail.usf.edu (Peyman Behzadnia) Date: Tue, 8 Feb 2011 19:52:44 -0500 Subject: [Disksim-users] Fwd: How to Fix the Saturation Error Due to Heavy Workload! In-Reply-To: References: Message-ID: Thanks Greg. I appreciate if someone has an idea about parameters&configurations to fix this error? Has anybody had a similiar situatio before? Best, Peyman ---------- Forwarded message ---------- From: Greg Ganger Date: Tue, Feb 8, 2011 at 7:42 PM Subject: Re: [Disksim-users] How to Fix the Saturation Error Due to Heavy Workload! To: Peyman Behzadnia Cc: Greg Ganger No, I'm sorry, but I can't know that. Look at the throughput you see with less intense worklaods to project what it is capable of doing. Good luck, Greg On Tue, 8 Feb 2011, Peyman Behzadnia wrote: Dear Greg, > > Thanks for your comment. > Can you please let me know how to increase the tolerance of the simulated > system through configurations and parameters? My system includes 10 disks > each connected to one bus and one controller and these are connected to one > higher level bus, controller and finally the driver. > > Thanks > Peyman > > On Tue, Feb 8, 2011 at 7:30 PM, Greg Ganger wrote: > > >> The saturation error happens because the workload is heavier than the >> simualted storage system can handle... not because the simulator itself >> can't keep up. >> >> Good luck, >> >> Greg >> >> >> >> On Tue, 8 Feb 2011, Peyman Behzadnia wrote: >> >> Dear All, >> >>> >>> This is Peyman Behzadnia, a PhD student in Computer Science & >>> Engineering. >>> I'm contacting you guys regarding the 'Saturation Error' of the disksim. >>> >>> I've run a simulation on top of the disksim4 in which i have to feed the >>> simulator with my ascii-format workload with high intensity (100-700 >>> requests per second). The problem is that the disksim has constantly >>> given >>> the saturation error: the simulation stopped due to saturation. I have >>> re-checked all of the detailed parameters in my parameter file and also >>> have >>> tested my workload with the sample parameter files provided by the >>> disksim. >>> But, it gives the same error. When i decrease the intensity into 1 >>> request >>> per 1-2seconds, it works well. >>> I personally do not believe that such disk simulator can not even handle >>> 20 >>> requests per second. It might be something about a configuration. I >>> appreciate if somebody can give me a hint or comment about how to fix >>> this >>> saturation error. >>> >>> Best, >>> Peyman >>> >>> >>> > -------------- next part -------------- An HTML attachment was scrubbed... URL: From ykwok2 at miners.utep.edu Tue Feb 8 22:25:42 2011 From: ykwok2 at miners.utep.edu (Yipkei Kwok) Date: Tue, 8 Feb 2011 20:25:42 -0700 Subject: [Disksim-users] developer's manual Message-ID: Hi, Where can I find a developer's manual for Disksim 3.0 and/or 4.0? Thank you very much. Regards, Yipkei -- ******************************************** Yipkei Kwok Ph.D. Student Research Assistant HiPerSys Lab Department of Computer Science The University of Texas at El Paso Phone: 915 747 6433 (O) E-mail: ykwok2 at miners dot utep dot edu ******************************************** From haghdoost at gmail.com Tue Feb 8 23:30:45 2011 From: haghdoost at gmail.com (Alireza Haghdoost) Date: Wed, 9 Feb 2011 08:00:45 +0330 Subject: [Disksim-users] Fwd: How to Fix the Saturation Error Due to Heavy Workload! In-Reply-To: References: Message-ID: As Prof. Ganger said your workload is very heavy. In other words, the trace file issue IO request very fast, i.e faster than a real system. You may double check the unit (s, ms) of the time in your traces. Also you can scale requests time with in a parameter in disksim parv file. Please refer to disksim manual for this time scaling parameter. Alireza Haghdoost Graduate Student Department of Computer Engineering Sharif University of Technology http://ce.sharif.edu/~haghdoost Phone: (98) (21) 6616 6689 2011/2/9 Peyman Behzadnia > Thanks Greg. > > I appreciate if someone has an idea about parameters&configurations to fix > this error? Has anybody had a similiar situatio before? > > Best, > Peyman > > ---------- Forwarded message ---------- > From: Greg Ganger > Date: Tue, Feb 8, 2011 at 7:42 PM > Subject: Re: [Disksim-users] How to Fix the Saturation Error Due to Heavy > Workload! > To: Peyman Behzadnia > Cc: Greg Ganger > > > > No, I'm sorry, but I can't know that. Look at the throughput you see > with less intense worklaods to project what it is capable of doing. > > > Good luck, > > Greg > > > On Tue, 8 Feb 2011, Peyman Behzadnia wrote: > > Dear Greg, >> >> Thanks for your comment. >> Can you please let me know how to increase the tolerance of the simulated >> system through configurations and parameters? My system includes 10 disks >> each connected to one bus and one controller and these are connected to >> one >> higher level bus, controller and finally the driver. >> >> Thanks >> Peyman >> >> >> On Tue, Feb 8, 2011 at 7:30 PM, Greg Ganger wrote: >> >> >>> The saturation error happens because the workload is heavier than the >>> simualted storage system can handle... not because the simulator itself >>> can't keep up. >>> >>> Good luck, >>> >>> Greg >>> >>> >>> >>> On Tue, 8 Feb 2011, Peyman Behzadnia wrote: >>> >>> Dear All, >>> >>>> >>>> This is Peyman Behzadnia, a PhD student in Computer Science & >>>> Engineering. >>>> I'm contacting you guys regarding the 'Saturation Error' of the disksim. >>>> >>>> I've run a simulation on top of the disksim4 in which i have to feed the >>>> simulator with my ascii-format workload with high intensity (100-700 >>>> requests per second). The problem is that the disksim has constantly >>>> given >>>> the saturation error: the simulation stopped due to saturation. I have >>>> re-checked all of the detailed parameters in my parameter file and also >>>> have >>>> tested my workload with the sample parameter files provided by the >>>> disksim. >>>> But, it gives the same error. When i decrease the intensity into 1 >>>> request >>>> per 1-2seconds, it works well. >>>> I personally do not believe that such disk simulator can not even handle >>>> 20 >>>> requests per second. It might be something about a configuration. I >>>> appreciate if somebody can give me a hint or comment about how to fix >>>> this >>>> saturation error. >>>> >>>> Best, >>>> Peyman >>>> >>>> >>>> >> > > _______________________________________________ > 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 vahldiek at mpi-sws.org Fri Feb 11 08:38:55 2011 From: vahldiek at mpi-sws.org (Anjo Vahldiek) Date: Fri, 11 Feb 2011 14:38:55 +0100 Subject: [Disksim-users] developer's manual In-Reply-To: References: Message-ID: <4D553BEF.3090909@mpi-sws.org> Hi, At the best of my knowledge there exists only a reference manual. Within the $DISKSIM/doc folder exists an Outline.txt which gives a basic understanding of the disksim code. I would not call it a developer's manual. Hope that this one might help. Regards, Anjo PhD-Student Max-Planck-Institute for Software Systems http://www.mpi-sws.org/~vahldiek On 09.02.2011 04:25, Yipkei Kwok wrote: > Hi, > > Where can I find a developer's manual for Disksim 3.0 and/or 4.0? > > Thank you very much. > > Regards, > Yipkei > From pbehzadn at mail.usf.edu Mon Feb 14 03:39:18 2011 From: pbehzadn at mail.usf.edu (Peyman Behzadnia) Date: Mon, 14 Feb 2011 03:39:18 -0500 Subject: [Disksim-users] How to change the 'Trace Time Scale' Parameter in the 'iosim' Block! Message-ID: Dear all, I have a heavy workload trace(100 req/sec) which i want to feed it into my simulation. I need to scale it through the ' Trace Time Scale' parameter such that the simulation can handle it without saturation error. The confusing thing here is that, when i simply change this parameter value in my parameter file, it does not reflect any change in the output file, even any change in any number. I tried to manually change this paramater value through the simulator's code though, but again no effect. Also, i could not modify it through 'parameter override' in the command. Has anybody touched this parameter before somehow? I appreciate your hints or comments about this issue. Thanks Peyman -------------- next part -------------- An HTML attachment was scrubbed... URL: From vahldiek at mpi-sws.org Wed Feb 16 09:41:11 2011 From: vahldiek at mpi-sws.org (Anjo Vahldiek) Date: Wed, 16 Feb 2011 15:41:11 +0100 Subject: [Disksim-users] Segmentation Fault !!! In-Reply-To: <4D02F54E.6060508@ece.cmu.edu> References: <4D02F54E.6060508@ece.cmu.edu> Message-ID: <4D5BE207.1070102@mpi-sws.org> Hi, I looked into the same issue. Abdullah it might be to late for you, but I think there is a hack which makes multiple disks and a single ssd possible. It is not a generic solution and might require to adopt defines! It would be great, if anyone of you could look into the generated diff (difftomakeahybriddisk.txt) and verify that I'm not doing something completely wrong. The basic idea is to hard code the issue with the difference indexing of devices (devno...). In addition a problem with the logorg came up which can also be hard coded, because we know which logorg should be used. For the enclosed parv I could run synthetic traces for the disk as well as the flash. Thanks, Anjo On 11.12.2010 04:51, Michael Stroucken wrote: > Abdullah Al-Dahlawi wrote: >> Greeting >> >> Can any one gibe me a feedback why I am getting a "segmentation >> fault" error when modifying a 3disk.parv faile to include an ssd >> device ????????? >> > Two issues: > 1) You are getting a segmentation fault, because you are trying to > implement a hybrid system using magnetic and SSD drives. Due to a bug > in the disksim code, getssd will use the current disk index as an > index into the table of ssd disks. > So if there are three magnetic disks, and one SSD, when trying to > access disk 3 (the SSD), it will try to getssd(3). But since the count > of SSDs is only 1, it will fall off the table. > > To avoid this, keep your system purely SSD apply the second patch to > your config. > > 2) Once this is bypassed, the code will fail on an assertion that your > page size does not match the aligned count as returned by > ssd_choose_aligned_count. The value that function returns is > MIN(count, block number % page size). If count is 4 and page size is > 8, you will have problems. > > I don't know what that means for your experiments, but you can either > change page size to 4 or apply the first patch. The patch will ignore > the difference. > > Good luck, > Michael. > > --- ssd.c.orig 2010-12-10 22:28:08.000000000 -0500 > +++ ssd.c 2010-12-10 22:34:45.000000000 -0500 > @@ -638,7 +638,7 @@ > tmp->flags = curr->flags; > tmp->blkno = blkno; > tmp->bcount = > ssd_choose_aligned_count(currdisk->params.page_size, blkno, count); > - ASSERT(tmp->bcount == currdisk->params.page_size); > + // ASSERT(tmp->bcount == currdisk->params.page_size); > > tmp->tempptr2 = curr; > blkno += tmp->bcount; > > --- t-mlc-08.parv.abdullah 2010-12-10 22:09:23.000000000 -0500 > +++ t-mlc-08.parv 2010-12-10 22:22:11.000000000 -0500 > @@ -88,42 +88,6 @@ > Use queueing in subsystem = 1 > } # end of DRV0 spec > # --------------------------------------------------------- > -disksim_bus BUS0 { > -type = 1, > -Arbitration type = 1, > -Arbitration time = 0.0, > -Read block transfer time = 0.0, > -Write block transfer time = 0.0, > -Print stats = 0 > -} # end of BUS0 spec > -# --------------------------------------------------------- > -disksim_bus BUS1 { > -type = 1, > -Arbitration type = 1, > -Arbitration time = 0.0, > -Read block transfer time = 0.0512, > -Write block transfer time = 0.0512, > -Print stats = 1 > -} # end of BUS1 spec > -# --------------------------------------------------------- > -disksim_bus BUS2 { > -type = 1, > -Arbitration type = 1, > -Arbitration time = 0.0, > -Read block transfer time = 0.0512, > -Write block transfer time = 0.0512, > -Print stats = 1 > -} # end of BUS2 spec > -# --------------------------------------------------------- > -disksim_bus BUS3 { > -type = 1, > -Arbitration type = 1, > -Arbitration time = 0.0, > -Read block transfer time = 0.0512, > -Write block transfer time = 0.0512, > -Print stats = 1 > -} # end of BUS3 spec > -# --------------------------------------------------------- > disksim_bus BUSHBA { > type = 2, > Arbitration type = 1, > @@ -252,23 +216,13 @@ > > # --------------------------------------------------------- > # HP_C3323A > -source atlas10k.diskspecs > -source ibm18es.diskspecs > -source cheetah9LP.diskspecs > # --------------------------------------------------------- > # component instantiation > instantiate [ statfoo ] as Stats > instantiate [ statfoo ] as Stats > > -instantiate [ quantum ] as QUANTUM_TORNADO_validate > -instantiate [ ibm ] as IBM_DNES-309170W_validate > -instantiate [ seagate ] as SEAGATE_ST39102LW_validate > instantiate [ ssd0x0 ] as SSD > > -instantiate [ bus0 ] as BUS0 > -instantiate [ bus1 ] as BUS1 > -instantiate [ bus2 ] as BUS2 > -instantiate [ bus3 ] as BUS3 > instantiate [ busHBA0 ] as BUSHBA > > instantiate [ driver0 ] as DRIVER0 > @@ -276,79 +230,12 @@ > # --------------------------------------------------------- > # system topology > topology disksim_iodriver driver0 [ > - disksim_bus bus0 [ > - disksim_ctlr ctlr0 [ > - disksim_bus bus1 [ > - > disksim_disk quantum [] > - ], > - disksim_bus bus2 [ > - > disksim_disk ibm [] > - ], > - disksim_bus bus3 [ > - > disksim_disk seagate [] > - ], > - disksim_bus busHBA0 [ > + disksim_bus busHBA0 [ > > ssdmodel_ssd ssd0x0 [] > > ] > ] > - ] > - ] > # no syncsets > # --------------------------------------------------------- > -disksim_logorg quantumorg { > - Addressing mode = Parts, > - Distribution scheme = Asis, > - Redundancy scheme = Noredun, > - devices = [ quantum ], > - Stripe unit = 17938986, > - Synch writes for safety = 0, > - Number of copies = 2, > - Copy choice on read = 6, > - RMW vs. reconstruct = 0.5, > - Parity stripe unit = 64, > - Parity rotation type = 1, > - Time stamp interval = 0.000000, > - Time stamp start time = 60000.000000, > - Time stamp stop time = 10000000000.000000, > - Time stamp file name = stamps > -} # end of logorg org0 spec > -# --------------------------------------------------------- > -disksim_logorg ibmorg { > - Addressing mode = Parts, > - Distribution scheme = Asis, > - Redundancy scheme = Noredun, > - devices = [ ibm ], > - Stripe unit = 17916240, > - Synch writes for safety = 0, > - Number of copies = 2, > - Copy choice on read = 6, > - RMW vs. reconstruct = 0.5, > - Parity stripe unit = 64, > - Parity rotation type = 1, > - Time stamp interval = 0.000000, > - Time stamp start time = 60000.000000, > - Time stamp stop time = 10000000000.000000, > - Time stamp file name = stamps > -} # end of logorg org0 spec > -# --------------------------------------------------------- > -disksim_logorg seagateorg { > - Addressing mode = Parts, > - Distribution scheme = Asis, > - Redundancy scheme = Noredun, > - devices = [ seagate ], > - Stripe unit = 17783240, > - Synch writes for safety = 0, > - Number of copies = 2, > - Copy choice on read = 6, > - RMW vs. reconstruct = 0.5, > - Parity stripe unit = 64, > - Parity rotation type = 1, > - Time stamp interval = 0.000000, > - Time stamp start time = 60000.000000, > - Time stamp stop time = 10000000000.000000, > - Time stamp file name = stamps > -} # end of logorg org0 spec > -# --------------------------------------------------------- > disksim_logorg org0 { > Addressing mode = Array, > Distribution scheme = Striped, > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: difftomakeahybriddisk.txt URL: -------------- next part -------------- An embedded and charset-unspecified text was scrubbed... Name: maxtor146g.parv URL: From leitian.hust at gmail.com Fri Feb 18 17:33:20 2011 From: leitian.hust at gmail.com (Lei Tian) Date: Fri, 18 Feb 2011 16:33:20 -0600 Subject: [Disksim-users] How to change the 'Trace Time Scale' Parameter in the 'iosim' Block! In-Reply-To: References: Message-ID: <225DDBD0-C4D7-42D9-9A52-84559EEE6206@gmail.com> Hi Peyman, The reason why 'Trace Time Sacle' does not work when you change the number in the configuration file, perhaps is that the function of "disksim_iosim_loadparams" is not called to load the iosim parameters. However, if you manually change the value of this parameter in disksim_iosim.c, it should work. I did it and it works. By the way, there is another way to achieve the same goal with an *ugly* minor change to the Disksim source code. Because other parameters could be loaded from a configuration file, you can use other parameter that is in other sections instead of iosim and you do not use in your test (e.g., 'Time stamp interval' in logorg if you do not configure your storage system as a parity-encoded RAID system). Then, you insert one line of code in disksim.c, something like this: disksim->iosim->ioscale = disksim -> iodriver_info -> logorgs[0] -> stampinterval; after calling the disksim_loadparams() but ahead of calling the prime_simulation() in the disksim_setup_disksim() function. I think it is worth trying for you. Lei On Feb 14, 2011, at 2:39 AM, Peyman Behzadnia wrote: > Dear all, > > I have a heavy workload trace(100 req/sec) which i want to feed it into my simulation. I need to scale it through the ' Trace Time Scale' parameter such that the simulation can handle it without saturation error. The confusing thing here is that, when i simply change this parameter value in my parameter file, it does not reflect any change in the output file, even any change in any number. I tried to manually change this paramater value through the simulator's code though, but again no effect. Also, i could not modify it through 'parameter override' in the command. Has anybody touched this parameter before somehow? > I appreciate your hints or comments about this issue. > > Thanks > Peyman > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users From ykwok2 at miners.utep.edu Sat Feb 19 14:02:15 2011 From: ykwok2 at miners.utep.edu (Yipkei Kwok) Date: Sat, 19 Feb 2011 12:02:15 -0700 Subject: [Disksim-users] g4-to-g1 disk model converter Message-ID: Hi, I am trying to use the Seagate Cheetah 15k.5 disk (files can be downloaded at http://www.pdl.cmu.edu/DiskSim/diskspecs.shtml) with Disksim 3.0 (my Disksim modifications were made on 3.0 and have not yet been ported to 4.0). The Cheetah disk files are in the G4 disk layout model format, which is not supported by Disksim 3.0. Is there any way to convert the disk files from G4 disk layout model format to the G1 disk layout model format, which is supported by Disksim 3.0? Or, where can I find disk model files for disks (year 2006 or after) in a disk layout model format accepted by Disksim 3.0? Thank you very much. Regards, Yipkei -- ******************************************** Yipkei Kwok Ph.D. Student Research Assistant HiPerSys Lab Department of Computer Science The University of Texas at El Paso Phone: 915 747 6433 (O) E-mail: ykwok2 at miners dot utep dot edu ******************************************** From kollapurushotham at gmail.com Sun Feb 20 19:45:07 2011 From: kollapurushotham at gmail.com (kolla purushotham) Date: Sun, 20 Feb 2011 19:45:07 -0500 Subject: [Disksim-users] System Level Vs Controller Level RAID Message-ID: Hello all, In the section 3.8(Disk Array Data Organizations) of the disksim-4.0 manual it is given that: Although DiskSim is organized to allow organizations both at the system-level (i.e., at front end of the device drivers) and at the controller-level, only system-level organizations are supported in the ?rst released version. Is this still valid in the Current release of Disksim( i.e. ver4). Will I be able to simulate a RAID5 array on DIsksim at the controller level. And can someone please explain the difference between the two Organizations apart from their topology. -- Regards, Purushotham -------------- next part -------------- An HTML attachment was scrubbed... URL: From ganger at ece.cmu.edu Sun Feb 20 19:56:34 2011 From: ganger at ece.cmu.edu (Greg Ganger) Date: Sun, 20 Feb 2011 19:56:34 -0500 (EST) Subject: [Disksim-users] System Level Vs Controller Level RAID In-Reply-To: References: Message-ID: Yes, still true. The difference is just topology -- can only do a logical organization at the driver level of the topology. Greg On Sun, 20 Feb 2011, kolla purushotham wrote: > Hello all, > > In the section 3.8(Disk Array Data Organizations) of the disksim-4.0 manual > it is given that: > > Although DiskSim is organized to allow organizations both at the > system-level > (i.e., at front end of the device drivers) and at the controller-level, only > system-level organizations are supported in the ???rst released version. > > Is this still valid in the Current release of Disksim( i.e. ver4). Will I be > able to simulate a RAID5 array on DIsksim at the controller level. And can > someone please explain the difference between the two Organizations apart > from their topology. > > -- > Regards, > Purushotham > From kollapurushotham at gmail.com Sun Feb 20 21:12:28 2011 From: kollapurushotham at gmail.com (kolla purushotham) Date: Sun, 20 Feb 2011 21:12:28 -0500 Subject: [Disksim-users] System Level Vs Controller Level RAID In-Reply-To: References: Message-ID: Dr Ganger, Thanks for the prompt reply. So, synthraid5.parv will be a good start in-order to work on RAID5 right?? On Sun, Feb 20, 2011 at 7:56 PM, Greg Ganger wrote: > > Yes, still true. The difference is just topology -- can only do a logical > organization at the driver level of the topology. > > Greg > > > > On Sun, 20 Feb 2011, kolla purushotham wrote: > > Hello all, >> >> In the section 3.8(Disk Array Data Organizations) of the disksim-4.0 >> manual >> it is given that: >> >> Although DiskSim is organized to allow organizations both at the >> system-level >> (i.e., at front end of the device drivers) and at the controller-level, >> only >> system-level organizations are supported in the ?rst released version. >> >> Is this still valid in the Current release of Disksim( i.e. ver4). Will I >> be >> able to simulate a RAID5 array on DIsksim at the controller level. And can >> someone please explain the difference between the two Organizations apart >> from their topology. >> >> -- >> Regards, >> Purushotham >> > -- Regards, Purushotham -------------- next part -------------- An HTML attachment was scrubbed... URL: From ganger at ece.cmu.edu Sun Feb 20 21:14:29 2011 From: ganger at ece.cmu.edu (Greg Ganger) Date: Sun, 20 Feb 2011 21:14:29 -0500 (EST) Subject: [Disksim-users] System Level Vs Controller Level RAID In-Reply-To: References: Message-ID: Yes. Good luck. Greg On Sun, 20 Feb 2011, kolla purushotham wrote: > Dr Ganger, > > Thanks for the prompt reply. So, synthraid5.parv will be a good start > in-order to work on RAID5 right?? > > On Sun, Feb 20, 2011 at 7:56 PM, Greg Ganger wrote: > >> >> Yes, still true. The difference is just topology -- can only do a logical >> organization at the driver level of the topology. >> >> Greg >> >> >> >> On Sun, 20 Feb 2011, kolla purushotham wrote: >> >> Hello all, >>> >>> In the section 3.8(Disk Array Data Organizations) of the disksim-4.0 >>> manual >>> it is given that: >>> >>> Although DiskSim is organized to allow organizations both at the >>> system-level >>> (i.e., at front end of the device drivers) and at the controller-level, >>> only >>> system-level organizations are supported in the ???rst released version. >>> >>> Is this still valid in the Current release of Disksim( i.e. ver4). Will I >>> be >>> able to simulate a RAID5 array on DIsksim at the controller level. And can >>> someone please explain the difference between the two Organizations apart >>> from their topology. >>> >>> -- >>> Regards, >>> Purushotham >>> >> > > > -- > Regards, > Purushotham > From kollapurushotham at gmail.com Mon Feb 21 03:07:29 2011 From: kollapurushotham at gmail.com (kolla purushotham) Date: Mon, 21 Feb 2011 03:07:29 -0500 Subject: [Disksim-users] System Level Vs Controller Level RAID In-Reply-To: References: Message-ID: Dr Ganger, I have one more question. In the outline.txt file it is mentioned "Graphall and grapher will use the information in par.graph and the plots dir to generate a few graphs" but I couldn't locate any file named "graphall". This question has already been asked and it got no responses. On Sun, Feb 20, 2011 at 9:14 PM, Greg Ganger wrote: > > Yes. Good luck. > > > Greg > > > On Sun, 20 Feb 2011, kolla purushotham wrote: > > Dr Ganger, >> >> Thanks for the prompt reply. So, synthraid5.parv will be a good start >> in-order to work on RAID5 right?? >> >> On Sun, Feb 20, 2011 at 7:56 PM, Greg Ganger wrote: >> >> >>> Yes, still true. The difference is just topology -- can only do a >>> logical >>> organization at the driver level of the topology. >>> >>> Greg >>> >>> >>> >>> On Sun, 20 Feb 2011, kolla purushotham wrote: >>> >>> Hello all, >>> >>>> >>>> In the section 3.8(Disk Array Data Organizations) of the disksim-4.0 >>>> manual >>>> it is given that: >>>> >>>> Although DiskSim is organized to allow organizations both at the >>>> system-level >>>> (i.e., at front end of the device drivers) and at the controller-level, >>>> only >>>> system-level organizations are supported in the ?rst released version. >>>> >>>> Is this still valid in the Current release of Disksim( i.e. ver4). Will >>>> I >>>> be >>>> able to simulate a RAID5 array on DIsksim at the controller level. And >>>> can >>>> someone please explain the difference between the two Organizations >>>> apart >>>> from their topology. >>>> >>>> -- >>>> Regards, >>>> Purushotham >>>> >>>> >>> >> >> -- >> Regards, >> Purushotham >> > -- Regards, Purushotham -------------- next part -------------- An HTML attachment was scrubbed... URL: From ganger at ece.cmu.edu Mon Feb 21 12:23:32 2011 From: ganger at ece.cmu.edu (Greg Ganger) Date: Mon, 21 Feb 2011 12:23:32 -0500 (EST) Subject: [Disksim-users] System Level Vs Controller Level RAID In-Reply-To: References: Message-ID: I don't know. Greg On Mon, 21 Feb 2011, kolla purushotham wrote: > Dr Ganger, > > I have one more question. In the outline.txt file it is mentioned > "Graphall and grapher will use the information in par.graph and the plots > dir to generate a few graphs" > > but I couldn't locate any file named "graphall". This question has already > been asked and it got no responses. > > > On Sun, Feb 20, 2011 at 9:14 PM, Greg Ganger wrote: > >> >> Yes. Good luck. >> >> >> Greg >> >> >> On Sun, 20 Feb 2011, kolla purushotham wrote: >> >> Dr Ganger, >>> >>> Thanks for the prompt reply. So, synthraid5.parv will be a good start >>> in-order to work on RAID5 right?? >>> >>> On Sun, Feb 20, 2011 at 7:56 PM, Greg Ganger wrote: >>> >>> >>>> Yes, still true. The difference is just topology -- can only do a >>>> logical >>>> organization at the driver level of the topology. >>>> >>>> Greg >>>> >>>> >>>> >>>> On Sun, 20 Feb 2011, kolla purushotham wrote: >>>> >>>> Hello all, >>>> >>>>> >>>>> In the section 3.8(Disk Array Data Organizations) of the disksim-4.0 >>>>> manual >>>>> it is given that: >>>>> >>>>> Although DiskSim is organized to allow organizations both at the >>>>> system-level >>>>> (i.e., at front end of the device drivers) and at the controller-level, >>>>> only >>>>> system-level organizations are supported in the ???rst released version. >>>>> >>>>> Is this still valid in the Current release of Disksim( i.e. ver4). Will >>>>> I >>>>> be >>>>> able to simulate a RAID5 array on DIsksim at the controller level. And >>>>> can >>>>> someone please explain the difference between the two Organizations >>>>> apart >>>>> from their topology. >>>>> >>>>> -- >>>>> Regards, >>>>> Purushotham >>>>> >>>>> >>>> >>> >>> -- >>> Regards, >>> Purushotham >>> >> > > > -- > Regards, > Purushotham > From stroucki at ece.cmu.edu Mon Feb 21 12:45:07 2011 From: stroucki at ece.cmu.edu (Michael Stroucken) Date: Mon, 21 Feb 2011 12:45:07 -0500 Subject: [Disksim-users] System Level Vs Controller Level RAID In-Reply-To: References: Message-ID: <4D62A4A3.2010001@ece.cmu.edu> kolla purushotham wrote: > Dr Ganger, > > I have one more question. In the outline.txt file it is mentioned > "Graphall and grapher will use the information in par.graph and the > plots dir to generate a few graphs" > > but I couldn't locate any file named "graphall". This question has > already been asked and it got no responses. Hi Purushotham, I checked our code repository, and the only mention of graphall is in in the outline.txt file. But there is a directory doc.src.v3 that looks like it has a makefile that creates graphs for several drives. Perhaps that is what you may want to look at? Greetings, Michael. From ffalanga at fastwebnet.it Mon Feb 21 17:01:51 2011 From: ffalanga at fastwebnet.it (Francesco Falanga) Date: Mon, 21 Feb 2011 23:01:51 +0100 Subject: [Disksim-users] DiskSim for the first time Message-ID: Hi All, I am just approaching DiskSim for the first time. Is there available any step by step tutorial to set up DiskSim compilation with visual studio 2008? Thank you a lot & Regards Francesco Falanga. -------------- next part -------------- An HTML attachment was scrubbed... URL: From kollapurushotham at gmail.com Mon Feb 21 19:19:33 2011 From: kollapurushotham at gmail.com (kolla purushotham) Date: Mon, 21 Feb 2011 19:19:33 -0500 Subject: [Disksim-users] System Level Vs Controller Level RAID In-Reply-To: <4D62A4A3.2010001@ece.cmu.edu> References: <4D62A4A3.2010001@ece.cmu.edu> Message-ID: Dr. Stroucken, Thanks for the reply. I couldn't find the exact file/folder which you are referring to neither in disksim4/disksim3 source code nor in the CMU repository. Could you post a direct link where I can download the source. On Mon, Feb 21, 2011 at 12:45 PM, Michael Stroucken wrote: > kolla purushotham wrote: > >> Dr Ganger, >> >> I have one more question. In the outline.txt file it is mentioned >> "Graphall and grapher will use the information in par.graph and the plots >> dir to generate a few graphs" >> >> but I couldn't locate any file named "graphall". This question has already >> been asked and it got no responses. >> > > Hi Purushotham, > > I checked our code repository, and the only mention of graphall is in in > the outline.txt file. But there is a directory doc.src.v3 that looks like it > has a makefile that creates graphs for several drives. Perhaps that is what > you may want to look at? > > Greetings, > Michael. > -- Regards, Purushotham -------------- next part -------------- An HTML attachment was scrubbed... URL: From stroucki at ece.cmu.edu Mon Feb 21 22:51:34 2011 From: stroucki at ece.cmu.edu (Michael Stroucken) Date: Mon, 21 Feb 2011 22:51:34 -0500 Subject: [Disksim-users] System Level Vs Controller Level RAID In-Reply-To: References: <4D62A4A3.2010001@ece.cmu.edu> Message-ID: <4D6332C6.8030202@ece.cmu.edu> kolla purushotham wrote: > Dr. Stroucken, > > Thanks for the reply. I couldn't find the exact file/folder which you > are referring to neither in disksim4/disksim3 source code nor in the > CMU repository. Could you post a direct link where I can download the > source. Hi Puroshotham, Thanks, but I'm not a "Dr." I guess that directory is part of our internal sources, and was used to generate the document in the "doc" directory. It isn't more than taking output and writing a gnuplot script to take the data and generate an eps file. Greetings, Michael. From kollapurushotham at gmail.com Tue Feb 22 01:34:00 2011 From: kollapurushotham at gmail.com (kolla purushotham) Date: Tue, 22 Feb 2011 01:34:00 -0500 Subject: [Disksim-users] DiskSim for the first time Message-ID: Hi, I am not sure how to use DiskSim on VS, but I have been using it on CodeBlocks. If all you need is an IDE with debug capabilities, then you can give codeblocks a try. Here is the link on how to use Disksim with codeblocks. http://forums.codeblocks.org/index.php?topic=12694.0 -- Regards, Purushotham -------------- next part -------------- An HTML attachment was scrubbed... URL: