From roaslin at gmail.com Thu Apr 2 12:21:10 2009 From: roaslin at gmail.com (Raul) Date: Thu, 2 Apr 2009 18:21:10 +0200 Subject: [Disksim-users] Scheduling Algorithm Message-ID: hello again! I changed the queue length from 1 to 100 and from 1 to 5 and so on, random changes. Disk response time average is always the same value as I posted first. do I need to change something else?? thank you From john.carter at gmail.com Fri Apr 3 13:45:43 2009 From: john.carter at gmail.com (John Carter) Date: Fri, 3 Apr 2009 13:45:43 -0400 Subject: [Disksim-users] Disksim performance Message-ID: <28c1b0010904031045n27949913g29647bb747e0d753@mail.gmail.com> Hi all - I am considering extending DiskSim to explore some ideas related to improving storage system energy-efficiency using flash. One consideration is DiskSim's simulation performance, since I hope to evaluate the ideas on traces with over 1B IOs. When I compile and run DiskSim on a 1M-entry trace file (ascii.trace replicated 10X with the timestamps updated using the same configuration as the runvalid test for ascii.trace), it takes 91 seconds to execute on 3.2GHz Xeon (quad-core, but I don't think that matters since DiskSim is single-threaded, right?). That translates into a bit over 10K simulated IOPs, which is slower than real-time for some of the high-end configurations I'd like to explore. And it translates into a little over 24 hours to simulation 1B IOs, which could get painful. One of my colleagues asked Greg (Ganger) about DiskSim's performance at FAST, and Greg apparently replied that 10K simulated IOPs was slower than he would have predicted. He further suggested that I contact this list to see if it fits other people's experience. What kind of simulation speeds are y'all seeing? Obviously it depends on the configuration being evaluated, but the ascii.parv configuration did not look at all onerous. Are there ways to improve simulation performance that a new DiskSim user like myself might not have found? For the DiskSim implementors out there, how tightly tuned is DiskSim's performance -- has it already been tuned pretty hard (so there isn't likely much more performance to squeeze out) or has performance tuning not been a focus (so perhaps simulation speed could be improved a lot if somebody were to focus on it)? Thanks for your input! Cheers, John From ganger at ece.cmu.edu Sat Apr 4 11:45:22 2009 From: ganger at ece.cmu.edu (Greg Ganger) Date: Sat, 4 Apr 2009 11:45:22 -0400 (EDT) Subject: [Disksim-users] Disksim performance In-Reply-To: <28c1b0010904031045n27949913g29647bb747e0d753@mail.gmail.com> References: <28c1b0010904031045n27949913g29647bb747e0d753@mail.gmail.com> Message-ID: I can answer a few of the last questions: DiskSim performance tuning happened some in its very early days (early 90s), with some regretable long-term code ickiness, and not at all since. I imagine performance can be improved by minimizing configurations, such as by minimizing layers of busses/controllers. I'm sure that it is far from efficient, though I was surprised by the 10Kops/second number... doesn't mean that it's not accurate, but was quite surprising to me. Greg On Fri, 3 Apr 2009, John Carter wrote: > Hi all - > > I am considering extending DiskSim to explore some ideas related > to improving storage system energy-efficiency using flash. One > consideration is DiskSim's simulation performance, since I hope to > evaluate the ideas on traces with over 1B IOs. > > When I compile and run DiskSim on a 1M-entry trace file > (ascii.trace replicated 10X with the timestamps updated using the same > configuration as the runvalid test for ascii.trace), it takes 91 > seconds to execute on 3.2GHz Xeon (quad-core, but I don't think that > matters since DiskSim is single-threaded, right?). That translates > into a bit over 10K simulated IOPs, which is slower than real-time for > some of the high-end configurations I'd like to explore. And it > translates into a little over 24 hours to simulation 1B IOs, which > could get painful. > > One of my colleagues asked Greg (Ganger) about DiskSim's > performance at FAST, and Greg apparently replied that 10K simulated > IOPs was slower than he would have predicted. He further suggested > that I contact this list to see if it fits other people's experience. > What kind of simulation speeds are y'all seeing? Obviously it depends > on the configuration being evaluated, but the ascii.parv configuration > did not look at all onerous. Are there ways to improve simulation > performance that a new DiskSim user like myself might not have found? > For the DiskSim implementors out there, how tightly tuned is DiskSim's > performance -- has it already been tuned pretty hard (so there isn't > likely much more performance to squeeze out) or has performance tuning > not been a focus (so perhaps simulation speed could be improved a lot > if somebody were to focus on it)? > > Thanks for your input! > > Cheers, > John > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > From savulescucostin at yahoo.com Sun Apr 5 19:16:53 2009 From: savulescucostin at yahoo.com (Savulescu) Date: Sun, 5 Apr 2009 16:16:53 -0700 (PDT) Subject: [Disksim-users] Can't install Disksim Message-ID: <387208.95307.qm@web30108.mail.mud.yahoo.com> Hello everybody! I need to use Disksim 3.0 for my Bachelor's Degree project and there is no way I can install it. I am using Ubuntu 8.1 and the Makefile always fails, it says there are errors in the sources (I took the sources from http://www.pdl.cmu.edu/DiskSim, version 3.0). Is there anything I am missing? Can anyone help with an already compiled version, with?a .deb or .run file? Thank you in advance, all the best! -------------- next part -------------- An HTML attachment was scrubbed... URL: From savulescucostin at yahoo.com Mon Apr 13 11:36:52 2009 From: savulescucostin at yahoo.com (Savulescu) Date: Mon, 13 Apr 2009 08:36:52 -0700 (PDT) Subject: [Disksim-users] Compiled Disksim? Message-ID: <92097.59081.qm@web30103.mail.mud.yahoo.com> Hello everybody! Can anyone help with an already-compiled variant of DiskSim 3.0? There is no way I can compile without errors the sources available for download on http://www.pdl.cmu.edu/DiskSim. Please give me a hand. Thanks in advance, all the best! -------------- next part -------------- An HTML attachment was scrubbed... URL: From yueyinliang at gmail.com Mon Apr 13 11:40:37 2009 From: yueyinliang at gmail.com (Yinliang Yue) Date: Mon, 13 Apr 2009 23:40:37 +0800 Subject: [Disksim-users] Compiled Disksim? In-Reply-To: <92097.59081.qm@web30103.mail.mud.yahoo.com> References: <92097.59081.qm@web30103.mail.mud.yahoo.com> Message-ID: I think you can have a try to "make clean" first, and then "make". Regards! Yinliang On 4/13/09, Savulescu wrote: > > Hello everybody! Can anyone help with an already-compiled variant of > DiskSim 3.0? There is no way I can compile without errors the sources > available for download on http://www.pdl.cmu.edu/*DiskSim. *Please give me > a hand. Thanks in advance, all the best! > > > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > > -- Best regards! Yinliang Yue HUST, Wuhan, China -------------- next part -------------- An HTML attachment was scrubbed... URL: From zgy04 at 126.com Mon Apr 13 19:55:24 2009 From: zgy04 at 126.com (Steve) Date: Tue, 14 Apr 2009 07:55:24 +0800 Subject: [Disksim-users] Compiled Disksim? References: <92097.59081.qm@web30103.mail.mud.yahoo.com> Message-ID: <200904140755139355511@126.com> Why not try DiskSim 4.0. It is very easy to build it. Good Luck. All the best. ????????Steve ????????zgy04 at 126.com ????????2009-04-14 ======= 2009-04-13 23:37:12 Savulescu Written: ======= >Hello everybody! Can anyone help with an already-compiled variant of DiskSim 3.0? There is no way I can compile without errors the sources available for download on http://www.pdl.cmu.edu/DiskSim. Please give me a hand. Thanks in advance, all the best! > > > > >_______________________________________________ >Disksim-users mailing list >Disksim-users at ece.cmu.edu >https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > = = = = = = = = = = = = = = = = = = = = ?? From courageous at gmail.com Sun Apr 19 19:20:27 2009 From: courageous at gmail.com (Krithika) Date: Sun, 19 Apr 2009 19:20:27 -0400 Subject: [Disksim-users] storage benchmarks Message-ID: Hi all, I am not sure if this is a right place to ask this .. As most of the members of this group will be storage system researchers, can anyone please tell me where to get codes for SPC benchmarks ? I use OSDL-DBT for running TPC workloads but I am not able to find any open-source benchmark kit for SPC benchmarks. Please give me some pointers in case you know of anything, so that it would greatly save my time. Thanks! KK. -------------- next part -------------- An HTML attachment was scrubbed... URL: From roaslin at gmail.com Sun Apr 26 13:56:29 2009 From: roaslin at gmail.com (Raul) Date: Sun, 26 Apr 2009 19:56:29 +0200 Subject: [Disksim-users] RAID5 Message-ID: Hi everyone! I ?m still working on Disksim , I?m testing RAID 5 with 9 HDD with an ASCII trace I made by myself accesing blocks from Disk0 to Disk 8. But Disksim returned me this error: unexpected request location It seems to be that it doesn?t find the disks, is it necessary to do an IOMapping? I copied one from valid directory from a synthraid.parv but It still doesn?t work... Can you help me with this one? I don?t know how to do an IO Mappiing, but It wiil work without it?? thank you all! From roaslin at gmail.com Mon Apr 27 04:53:11 2009 From: roaslin at gmail.com (Raul) Date: Mon, 27 Apr 2009 10:53:11 +0200 Subject: [Disksim-users] RAID5 Message-ID: Hi, Could it be the "tracedev "paramenter in IOmapping?? So, What is the method to fill this parameter? In ascii.parv from valid directory this parameter is written in Hexadecimal but I don?t konw how to do it for my disks. thank you!