From invite+kjdmhkjk13_i at facebookmail.com Thu Mar 4 02:20:00 2010 From: invite+kjdmhkjk13_i at facebookmail.com (Amit Yadav) Date: Wed, 3 Mar 2010 23:20:00 -0800 Subject: [Disksim-users] Check out my photos on Facebook Message-ID: <1c6a4765aeaf7febd59328497675e108@www.facebook.com> I set up a Facebook profile where I can post my pictures, videos and events and I want to add you as a friend so you can see it. First, you need to join Facebook! Once you join, you can also create your own profile. Thanks, Amit To sign up for Facebook, follow the link below: http://www.facebook.com/p.php?i=100000818266151&k=Z6E3Y56Z43XA5GEJPB63QTVTQUGD3T5NUWFVEKRFV2&r Already have an account? Add this email address to your account http://www.facebook.com/n/?merge_accounts.php&e=disksim-users at ece.cmu.edu&c=e333f4dc6284a636d126d95178401d6c.disksim-users at ece.cmu.edu was invited to join Facebook by Amit Yadav. If you do not wish to receive this type of email from Facebook in the future, please click on the link below to unsubscribe. http://www.facebook.com/o.php?k=386dfb&u=100000772047391&mid=1f95c4dG5af33e7ec21fG0G8 Facebook's offices are located at 1601 S. California Ave., Palo Alto, CA 94304. -------------- next part -------------- An HTML attachment was scrubbed... URL: From fei33423 at gmail.com Sat Mar 6 01:52:33 2010 From: fei33423 at gmail.com (fei fei) Date: Sat, 6 Mar 2010 14:52:33 +0800 Subject: [Disksim-users] help for the construction of raid 5 in disksim and the way of trace acquisition Message-ID: question 1 : i have read the manul ,and i want to use the disksim to simulate a raid 5 system about reading and writing. in the manual ,i find that the parameter concerned with raid 5 is "redundancy scheme "in the section "disk array date organization" of the manual and i find the file synthraid5.parv in the "valid" folder of the disksim source code .however i can not find the configuration about raid 5 in the file. *how do the disksim make the data stored in the way of raid 5?* *if i will reach my purpose ,which one in the "src" folder of the disksim source code should i change ??* question 2 : in a paper i find that the author use the trace of the software " cpp ,andrew benchmark and wc"as a input to disksim [The C preprocessor (cpp) is the preprocessor for the C programming language. ] [The Andrew benchmark is used to compare BFS with two other file systems] [The wc command stands for " word count ] *how can i get the trace of the software ? utilise some tool??* -------------- next part -------------- An HTML attachment was scrubbed... URL: From yueyinliang at gmail.com Sat Mar 6 02:07:06 2010 From: yueyinliang at gmail.com (Yinliang Yue) Date: Sat, 6 Mar 2010 15:07:06 +0800 Subject: [Disksim-users] help for the construction of raid 5 in disksim and the way of trace acquisition In-Reply-To: References: Message-ID: The answers to the first question: The following combination in synthraid5.parv shows that you are using a RAID5. For the reason, please see the manual. Distribution scheme = Striped, Redundancy scheme = Parity_rotated, Please see the the function named logorg_maprequest() in disksim_logorg.c if you want to make a deep analysis of the mechanism of RAID5. 2010/3/6 fei fei > question 1 : i have read the manul ,and i want to use the disksim to > simulate a raid 5 system about reading and writing. > in the manual ,i find that the parameter concerned with raid 5 > is "redundancy scheme "in the section "disk array date organization" of the > manual > and i find the file synthraid5.parv in the "valid" folder of > the disksim source code .however i can not find the configuration about raid > 5 in the file. > *how do the disksim make the data stored in the way of raid > 5?* > *if i will reach my purpose ,which one in the "src" folder of > the disksim source code should i change ??* > > question 2 : in a paper i find that the author use the trace of the > software " cpp ,andrew benchmark and wc"as a input to disksim > [The C preprocessor (cpp) is the preprocessor for the C > programming language. ] > [The Andrew benchmark is used to compare BFS with two other > file systems] > [The wc command stands for " word count ] > *how can i get the trace of the software ? utilise some tool?? > * > > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > > -- Regards! Yinliang Yue F301, WNLO, HUST, Wuhan, China Tel: +86-27-87792302-801 -------------- next part -------------- An HTML attachment was scrubbed... URL: From fei33423 at gmail.com Sun Mar 7 22:32:41 2010 From: fei33423 at gmail.com (fei fei) Date: Mon, 8 Mar 2010 11:32:41 +0800 Subject: [Disksim-users] Disksim-users Digest, Vol 54, Issue 2 In-Reply-To: References: Message-ID: thank u for your help.. about question 2 i find that"* there are many linux kernel patches can do this ** such as LL_TRACE for 2.4 kernel" in https://sos.ece.cmu.edu/pipermail/disksim-users/2006-July/000043.html* 2010/3/7 > Send Disksim-users mailing list submissions to > disksim-users at ece.cmu.edu > > To subscribe or unsubscribe via the World Wide Web, visit > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > or, via email, send a message with subject or body 'help' to > disksim-users-request at ece.cmu.edu > > You can reach the person managing the list at > disksim-users-owner at ece.cmu.edu > > When replying, please edit your Subject line so it is more specific > than "Re: Contents of Disksim-users digest..." > > Today's Topics: > > 1. help for the construction of raid 5 in disksim and the way of > trace acquisition (fei fei) > 2. Re: help for the construction of raid 5 in disksim and the > way of trace acquisition (Yinliang Yue) > > > ---------- ????? ---------- > From: fei fei > To: disksim-users at ece.cmu.edu > Date: Sat, 6 Mar 2010 14:52:33 +0800 > Subject: [Disksim-users] help for the construction of raid 5 in disksim and > the way of trace acquisition > question 1 : i have read the manul ,and i want to use the disksim to > simulate a raid 5 system about reading and writing. > in the manual ,i find that the parameter concerned with raid 5 > is "redundancy scheme "in the section "disk array date organization" of the > manual > and i find the file synthraid5.parv in the "valid" folder of > the disksim source code .however i can not find the configuration about raid > 5 in the file. > *how do the disksim make the data stored in the way of raid > 5?* > *if i will reach my purpose ,which one in the "src" folder of > the disksim source code should i change ??* > > question 2 : in a paper i find that the author use the trace of the > software " cpp ,andrew benchmark and wc"as a input to disksim > [The C preprocessor (cpp) is the preprocessor for the C > programming language. ] > [The Andrew benchmark is used to compare BFS with two other > file systems] > [The wc command stands for " word count ] > *how can i get the trace of the software ? utilise some tool?? > * > > > ---------- ????? ---------- > From: Yinliang Yue > To: fei fei > Date: Sat, 6 Mar 2010 15:07:06 +0800 > Subject: Re: [Disksim-users] help for the construction of raid 5 in disksim > and the way of trace acquisition > The answers to the first question: > > The following combination in synthraid5.parv shows that you are using a > RAID5. For the reason, please see the manual. > > Distribution scheme = Striped, > Redundancy scheme = Parity_rotated, > > > Please see the the function named logorg_maprequest() in disksim_logorg.c > if you want to make a deep analysis of the mechanism of RAID5. > > > > > 2010/3/6 fei fei > >> question 1 : i have read the manul ,and i want to use the disksim to >> simulate a raid 5 system about reading and writing. >> in the manual ,i find that the parameter concerned with raid 5 >> is "redundancy scheme "in the section "disk array date organization" of the >> manual >> and i find the file synthraid5.parv in the "valid" folder of >> the disksim source code .however i can not find the configuration about raid >> 5 in the file. >> *how do the disksim make the data stored in the way of raid >> 5?* >> *if i will reach my purpose ,which one in the "src" folder >> of the disksim source code should i change ??* >> >> question 2 : in a paper i find that the author use the trace of the >> software " cpp ,andrew benchmark and wc"as a input to disksim >> [The C preprocessor (cpp) is the preprocessor for the C >> programming language. ] >> [The Andrew benchmark is used to compare BFS with two other >> file systems] >> [The wc command stands for " word count ] >> *how can i get the trace of the software ? utilise some >> tool??* >> >> _______________________________________________ >> Disksim-users mailing list >> Disksim-users at ece.cmu.edu >> https://sos.ece.cmu.edu/mailman/listinfo/disksim-users >> >> > > > -- > Regards! > > Yinliang Yue > F301, WNLO, HUST, Wuhan, China > Tel: +86-27-87792302-801 > > _______________________________________________ > 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 lorizhuang at gmail.com Mon Mar 8 03:36:42 2010 From: lorizhuang at gmail.com (lori zhuang) Date: Mon, 8 Mar 2010 16:36:42 +0800 Subject: [Disksim-users] Can Disksim work with Simics or GEMS? Message-ID: Hi all, Can Disksim work with Simics or GEMS? I can't find any information about it through Google. Any help is highly appreciated. Thanks, lorizhuang -------------- next part -------------- An HTML attachment was scrubbed... URL: From ganger at ece.cmu.edu Mon Mar 8 12:03:00 2010 From: ganger at ece.cmu.edu (Greg Ganger) Date: Mon, 8 Mar 2010 12:03:00 -0500 (EST) Subject: [Disksim-users] Can Disksim work with Simics or GEMS? In-Reply-To: References: Message-ID: I'm not aware of it being integrated, but there is no reason that it could not be... would require effort. Greg On Mon, 8 Mar 2010, lori zhuang wrote: > Hi all, > Can Disksim work with Simics or GEMS? I can't find any information > about it through Google. Any help is highly appreciated. > > Thanks, > lorizhuang > From haghdoost at gmail.com Mon Mar 8 12:36:06 2010 From: haghdoost at gmail.com (Alireza Haghdoost) Date: Mon, 8 Mar 2010 22:06:06 +0430 Subject: [Disksim-users] Can Disksim work with Simics or GEMS? Message-ID: <396d8f7c1003080936s3581794dv590788d2e63fee91@mail.gmail.com> I think a good way to work with Disk-Sim is using disk-trace that captured from full system simulator like SIMICS, In the other word we can install a guest OS on top of the SIMICS virtual machine. In this guest OS we can run our disk-stressing benchmarks and try to monitor disk access trace in host machine by the means of SIMICS API functions. are there any comment or idea in this topic ? Note that since GEMS is a well known memory system simulator based on SIMICS, I don't think that it need or can be used with Disksim. Alireza Haghdoost Graduate Student Department of Computer Engineering Sharif University of Technology http://ce.sharif.edu/~haghdoost Phone: (98) (21) 6616 6689 > Date: Mon, 8 Mar 2010 16:36:42 +0800 > From: lori zhuang > Subject: [Disksim-users] Can Disksim work with Simics or GEMS? > To: disksim-users at ece.cmu.edu > Message-ID: > > Content-Type: text/plain; charset="iso-8859-1" > > Hi all, > Can Disksim work with Simics or GEMS? I can't find any information > about it through Google. Any help is highly appreciated. > > Thanks, > lorizhuang > -------------- next part -------------- > An HTML attachment was scrubbed... > URL: < > http://sos.ece.cmu.edu/pipermail/disksim-users/attachments/20100308/efbccb82/attachment-0001.html > > > > ------------------------------ > > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > > > End of Disksim-users Digest, Vol 54, Issue 3 > ******************************************** > -------------- next part -------------- An HTML attachment was scrubbed... URL: From mauricxe at netscape.net Sun Mar 21 18:00:21 2010 From: mauricxe at netscape.net (mauricxe at netscape.net) Date: Sun, 21 Mar 2010 18:00:21 -0400 Subject: [Disksim-users] Response Time and Access Time In-Reply-To: References: Message-ID: <8CC9759090811CA-104C-2E47@webmail-m033.sysops.aol.com> Hello all, I have a question about two of the numbers reported by Disksim at the end of a simulation. Is my understanding of the following two metrics accurate? If not, could you supplement my definition or point out what I am missing? Access Time- Is this determined by a sum of the spin-up time, seek time, rotational delay, and transfer time? Response Time-The amount of time it takes to issue the request and to receive the results. This would also include Queue time. Is my understanding of these two accurate? Thanks!!!! -------------- next part -------------- An HTML attachment was scrubbed... URL: From ganger at ece.cmu.edu Sun Mar 21 19:51:46 2010 From: ganger at ece.cmu.edu (Greg Ganger) Date: Sun, 21 Mar 2010 19:51:46 -0400 (EDT) Subject: [Disksim-users] Response Time and Access Time In-Reply-To: <8CC9759090811CA-104C-2E47@webmail-m033.sysops.aol.com> References: <8CC9759090811CA-104C-2E47@webmail-m033.sysops.aol.com> Message-ID: It depends on which component you are looking at... those two metrics are captured at every "level" of a configuration (disk, controller, device driver). In each case, the latter includes queue time and the former does not. Greg On Sun, 21 Mar 2010, mauricxe at netscape.net wrote: > > Hello all, > > I have a question about two of the numbers reported by Disksim at the end of a simulation. > > Is my understanding of the following two metrics accurate? If not, could you supplement my definition or point out what I am missing? > > > Access Time- Is this determined by a sum of the spin-up time, seek time, rotational delay, and transfer time? > > Response Time-The amount of time it takes to issue the request and to receive the results. This would also include Queue time. > > Is my understanding of these two accurate? > > Thanks!!!! > > > > > From mauricxe at netscape.net Sun Mar 21 20:41:51 2010 From: mauricxe at netscape.net (mauricxe at netscape.net) Date: Sun, 21 Mar 2010 20:41:51 -0400 Subject: [Disksim-users] Response Time and Access Time In-Reply-To: References: <8CC9759090811CA-104C-2E47@webmail-m033.sysops.aol.com> Message-ID: <8CC976F98E52903-104C-4592@webmail-m033.sysops.aol.com> Thanks -----Original Message----- From: Greg Ganger To: mauricxe at netscape.net Cc: disksim-users at ece.cmu.edu; Greg Ganger Sent: Sun, Mar 21, 2010 7:51 pm Subject: Re: [Disksim-users] Response Time and Access Time It depends on which component you are looking at... those two metrics are captured at every "level" of a configuration (disk, controller, device driver). In each case, the latter includes queue time and the former does not. Greg On Sun, 21 Mar 2010, mauricxe at netscape.net wrote: > > Hello all, > > I have a question about two of the numbers reported by Disksim at the end of a simulation. > > Is my understanding of the following two metrics accurate? If not, could you supplement my definition or point out what I am missing? > > > Access Time- Is this determined by a sum of the spin-up time, seek time, rotational delay, and transfer time? > > Response Time-The amount of time it takes to issue the request and to receive the results. This would also include Queue time. > > Is my understanding of these two accurate? > > Thanks!!!! > > > > > -------------- next part -------------- An HTML attachment was scrubbed... URL: From mauricxe at netscape.net Sun Mar 21 23:24:55 2010 From: mauricxe at netscape.net (mauricxe at netscape.net) Date: Sun, 21 Mar 2010 23:24:55 -0400 Subject: [Disksim-users] Energy Consumption In-Reply-To: <8CC976F98E52903-104C-4592@webmail-m033.sysops.aol.com> References: <8CC9759090811CA-104C-2E47@webmail-m033.sysops.aol.com> <8CC976F98E52903-104C-4592@webmail-m033.sysops.aol.com> Message-ID: <8CC978660B5F6FE-2D2C-117C3@Webmail-d123.sysops.aol.com> Hello all, I have another question :) Can Disksim track energy consumption? I didn't see anything inside themanual. I am currently running the SSD model from microsoft. Wouldthe power consumption statistics be their responsibility? Thanks again! -------------- next part -------------- An HTML attachment was scrubbed... URL: From yueyinliang at gmail.com Sun Mar 21 23:34:40 2010 From: yueyinliang at gmail.com (Yinliang Yue) Date: Mon, 22 Mar 2010 11:34:40 +0800 Subject: [Disksim-users] Energy Consumption In-Reply-To: <8CC978660B5F6FE-2D2C-117C3@Webmail-d123.sysops.aol.com> References: <8CC9759090811CA-104C-2E47@webmail-m033.sysops.aol.com> <8CC976F98E52903-104C-4592@webmail-m033.sysops.aol.com> <8CC978660B5F6FE-2D2C-117C3@Webmail-d123.sysops.aol.com> Message-ID: Hi, I think the following paper maybe useful for you. http://www.usenix.org/events/fast03/tech/full_papers/zedlewski/zedlewski.pdf Yinliang Yue 2010/3/22 > Hello all, > > I have another question :) > > Can Disksim track energy consumption? I didn't see anything inside the > manual. I am currently running the SSD model from microsoft. Would the > power consumption statistics be their responsibility? > > Thanks again! > _______________________________________________ > Disksim-users mailing list > Disksim-users at ece.cmu.edu > https://sos.ece.cmu.edu/mailman/listinfo/disksim-users > > -- Regards! Yinliang Yue F301, WNLO, HUST, Wuhan, China Tel: +86-27-87792302-801 -------------- next part -------------- An HTML attachment was scrubbed... URL: From fei33423 at gmail.com Mon Mar 22 08:26:24 2010 From: fei33423 at gmail.com (wan wan) Date: Mon, 22 Mar 2010 20:26:24 +0800 Subject: [Disksim-users] how to debug disksim in codeblocks Message-ID: hi disksim-users: i am succeed in using the* gdb comand to* debug the disksim ... but when i use the tool *codeblocks* to debug the disksim,,there are some errors.. for example error: E:\coldblockdisksim\disksim-4.0\diskmodel\dm_load.c line 40 ( #include "*modules/modules.h*") *modules/modules.h*: No such file or directory error: E:\coldblockdisksim\disksim-4.0\diskmodel\dm_load.c line:52 ( lp_loadparams(result, b, &*dm_disk_mod*); ) "*dm_disk_mod*" undeclared (first use in this function) in fact i can not find the "*modules/modules.h*" in " disksim-4.0" does anybody debug successfully using *tool codeblocks*? thank you for your help -------------- next part -------------- An HTML attachment was scrubbed... URL: