May 2012 - mpiwg-io - mailman3.cels.anl.gov

Re: [MPI3-IO] [EXTERNAL] New MPI-IO routines
by Mohamad Chaarawi 24 May '12

24 May '12

Hi Jay, On 5/24/2012 3:08 PM, Lofstead, Gerald F II wrote: > I can see the usefulness of this beyond the SWMR case (essentially queue a > bunch of IO ops in the background and come back when they are all done) yes that is definitely useful in many cases, especially if the file manipulation routines are nonblocking too.. > and wonder is there a broader agenda that should be looked at for this? > For example, is the non-blocking, but ordered idea something useful for > messaging as well? Personally, I think so. Given that, is it worth > exploring this in a broader context to add the non-blocking, ordered style > to MPI as a whole? I am not aware of anyone exploring this beyond I/O. I can't answer the question if it's worthwhile to do this for ALL MPI, but I don't see why it would not be possible.. Datatype creation is something that I could think of, which would benefit well from this and would go nice with the I/O version of such routines. > > Other than an explicit queue mechanism to execute these in series, what > are the complexity problems you envision? It seems really straightforward. There's that, and there is the consistency semantics issue, where the library needs to make sure that the operations are atomic. Thanks, Mohamad > > Jay Lofstead > > On 5/24/12 12:39 PM, "Mohamad Chaarawi"<chaarawi(a)hdfgroup.org> wrote: > >> Hi all, >> >> We would like to get a discussion going on adding new routines to the >> standard that would support non-blocking but ordered access routines, >> and non-blocking ordered file manipulation routines. They would be two >> separate tickets but they share similar semantics. >> >> So basically what we would like is that when we call: >> 1) iwrite_at() >> 2) iread_at() >> 3) iwrite_at() >> ... >> 4) waitall() >> >> We would like to see the data accessed as if the calls were blocking. >> This could translate to something like: >> iwrite_at() >> iwait() >> iread_at() >> iwait() >> iwrite_at() >> iwait() >> >> There is ofcourse no such thing as iwait, but you get the idea :-) >> >> Our use case for this is the SWMR functionality that is being worked on, >> where the non-blocking version would require the MPI library to remember >> the order in which the operations were called; otherwise I don't see how >> we can enforce this ordering and at the same time keep the entire I/O >> access nonblocking. >> We probably need to rename the routines (something other than the i >> prefix) because the semantics are different from the current >> non-blocking routines. Maybe aread/awrite (a for asynchronous). >> >> Another feature we are considering is the non-blocking file manipulation >> routines. Similarly to the semantics described above, the library needs >> to remember the order they are called. >> iopen >> iset_view >> iwrite >> iclose >> ... >> waitall() >> >> Again since the semantics are different in the way other immediate >> routines are defined, we need to reconsider the naming. >> >> Any thoughts? >> >> Thanks, >> Mohamad >> >> _______________________________________________ >> MPI3-IO mailing list >> MPI3-IO(a)lists.mpi-forum.org >> http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-io >> > > > _______________________________________________ > MPI3-IO mailing list > MPI3-IO(a)lists.mpi-forum.org > http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-io

1 0

Re: [MPI3-IO] [EXTERNAL] New MPI-IO routines
by Dries Kimpe 24 May '12

24 May '12

* Lofstead, Gerald F II <gflofst(a)sandia.gov> [2012-05-24 20:08:51]: > I can see the usefulness of this beyond the SWMR case (essentially queue a > bunch of IO ops in the background and come back when they are all done) > and wonder is there a broader agenda that should be looked at for this? > For example, is the non-blocking, but ordered idea something useful for > messaging as well? Personally, I think so. Given that, is it worth > exploring this in a broader context to add the non-blocking, ordered style > to MPI as a whole? > Other than an explicit queue mechanism to execute these in series, what > are the complexity problems you envision? It seems really straightforward. Also, what (if anything) would prevent implementing this on top of MPI, using existing the MPI_File_iread/iwrite routines? Dries

1 0

Re: [MPI3-IO] [EXTERNAL] New MPI-IO routines
by Lofstead, Gerald F II 24 May '12

24 May '12

I can see the usefulness of this beyond the SWMR case (essentially queue a bunch of IO ops in the background and come back when they are all done) and wonder is there a broader agenda that should be looked at for this? For example, is the non-blocking, but ordered idea something useful for messaging as well? Personally, I think so. Given that, is it worth exploring this in a broader context to add the non-blocking, ordered style to MPI as a whole? Other than an explicit queue mechanism to execute these in series, what are the complexity problems you envision? It seems really straightforward. Jay Lofstead On 5/24/12 12:39 PM, "Mohamad Chaarawi" <chaarawi(a)hdfgroup.org> wrote: >Hi all, > >We would like to get a discussion going on adding new routines to the >standard that would support non-blocking but ordered access routines, >and non-blocking ordered file manipulation routines. They would be two >separate tickets but they share similar semantics. > >So basically what we would like is that when we call: >1) iwrite_at() >2) iread_at() >3) iwrite_at() >... >4) waitall() > >We would like to see the data accessed as if the calls were blocking. >This could translate to something like: >iwrite_at() >iwait() >iread_at() >iwait() >iwrite_at() >iwait() > >There is ofcourse no such thing as iwait, but you get the idea :-) > >Our use case for this is the SWMR functionality that is being worked on, >where the non-blocking version would require the MPI library to remember >the order in which the operations were called; otherwise I don't see how >we can enforce this ordering and at the same time keep the entire I/O >access nonblocking. >We probably need to rename the routines (something other than the i >prefix) because the semantics are different from the current >non-blocking routines. Maybe aread/awrite (a for asynchronous). > >Another feature we are considering is the non-blocking file manipulation >routines. Similarly to the semantics described above, the library needs >to remember the order they are called. >iopen >iset_view >iwrite >iclose >... >waitall() > >Again since the semantics are different in the way other immediate >routines are defined, we need to reconsider the naming. > >Any thoughts? > >Thanks, >Mohamad > >_______________________________________________ >MPI3-IO mailing list >MPI3-IO(a)lists.mpi-forum.org >http://lists.mpi-forum.org/mailman/listinfo.cgi/mpi3-io >

1 0

[MPI3-IO] New MPI-IO routines
by Mohamad Chaarawi 24 May '12

24 May '12

Hi all, We would like to get a discussion going on adding new routines to the standard that would support non-blocking but ordered access routines, and non-blocking ordered file manipulation routines. They would be two separate tickets but they share similar semantics. So basically what we would like is that when we call: 1) iwrite_at() 2) iread_at() 3) iwrite_at() ... 4) waitall() We would like to see the data accessed as if the calls were blocking. This could translate to something like: iwrite_at() iwait() iread_at() iwait() iwrite_at() iwait() There is ofcourse no such thing as iwait, but you get the idea :-) Our use case for this is the SWMR functionality that is being worked on, where the non-blocking version would require the MPI library to remember the order in which the operations were called; otherwise I don't see how we can enforce this ordering and at the same time keep the entire I/O access nonblocking. We probably need to rename the routines (something other than the i prefix) because the semantics are different from the current non-blocking routines. Maybe aread/awrite (a for asynchronous). Another feature we are considering is the non-blocking file manipulation routines. Similarly to the semantics described above, the library needs to remember the order they are called. iopen iset_view iwrite iclose ... waitall() Again since the semantics are different in the way other immediate routines are defined, we need to reconsider the naming. Any thoughts? Thanks, Mohamad

1 0

Re: [MPI3-IO] Joint IO/FT Teleconf
by Mohamad Chaarawi 01 May '12

01 May '12

Hi Josh, On page 541, line 5 Since collective I/O operations may not synchronize with other processes, process failures may not be reported during a collective I/O operation. maybe should read: Since collective I/O operations are not necessarily synchronizing, process failures may not be reported during a collective I/O operation. Thanks, Mohamad On 05/01/2012 02:50 PM, Josh Hursey wrote: > I just posted the current draft of the proposal text to the ticket. > Not too much has changed except the name of a few functions, per the > recommendation of the forum. > https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/323 > https://svn.mpi-forum.org/trac/mpi-forum-web/attachment/ticket/323/2012-05-… > > We'll use this document in our discussion today. > > -- Josh > > On Tue, May 1, 2012 at 1:30 PM, Josh Hursey<jjhursey(a)open-mpi.org> wrote: >> Just a reminder that we are meeting today at 4 pm eastern. >> >> -- Josh >> >> On Thu, Apr 19, 2012 at 4:17 PM, Josh Hursey<jjhursey(a)open-mpi.org> wrote: >>> It looks like May 1 from 4-5 pm Eastern works best for everyone that >>> responded. Below are the teleconf details: >>> Date: May 1, 2012 >>> Time: 4 pm Eastern/New York >>> Dial-in information: 877-801-8130 >>> Code: 1044056 >>> >>> -- Josh >>> >>> On Tue, Apr 17, 2012 at 10:44 AM, Josh Hursey<jjhursey(a)open-mpi.org> wrote: >>>> The FT working group would like to have a joint teleconf with the IO >>>> working group to discuss the fault tolerance proposal. >>>> - https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/323 >>>> - https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/326 >>>> >>>> A Doodle Poll link is below to schedule: >>>> - http://www.doodle.com/8iu4nryqiahfa3d9 >>>> >>>> If you are interested in participating in this teleconf, fill out the >>>> poll by 2 pm Eastern on Thursday, April 19. >>>> >>>> Thanks, >>>> Josh >>>> >>>> -- >>>> Joshua Hursey >>>> Postdoctoral Research Associate >>>> Oak Ridge National Laboratory >>>> http://users.nccs.gov/~jjhursey >>> >>> >>> -- >>> Joshua Hursey >>> Postdoctoral Research Associate >>> Oak Ridge National Laboratory >>> http://users.nccs.gov/~jjhursey >> >> >> -- >> Joshua Hursey >> Postdoctoral Research Associate >> Oak Ridge National Laboratory >> http://users.nccs.gov/~jjhursey > >

1 0

Re: [MPI3-IO] Joint IO/FT Teleconf
by Josh Hursey 01 May '12

01 May '12

I just posted the current draft of the proposal text to the ticket. Not too much has changed except the name of a few functions, per the recommendation of the forum. https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/323 https://svn.mpi-forum.org/trac/mpi-forum-web/attachment/ticket/323/2012-05-… We'll use this document in our discussion today. -- Josh On Tue, May 1, 2012 at 1:30 PM, Josh Hursey <jjhursey(a)open-mpi.org> wrote: > Just a reminder that we are meeting today at 4 pm eastern. > > -- Josh > > On Thu, Apr 19, 2012 at 4:17 PM, Josh Hursey <jjhursey(a)open-mpi.org> wrote: >> It looks like May 1 from 4-5 pm Eastern works best for everyone that >> responded. Below are the teleconf details: >> ï¿½Date: May 1, 2012 >> ï¿½Time: 4 pm Eastern/New York >> ï¿½Dial-in information: 877-801-8130 >> ï¿½Code: 1044056 >> >> -- Josh >> >> On Tue, Apr 17, 2012 at 10:44 AM, Josh Hursey <jjhursey(a)open-mpi.org> wrote: >>> The FT working group would like to have a joint teleconf with the IO >>> working group to discuss the fault tolerance proposal. >>> ï¿½- https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/323 >>> ï¿½- https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/326 >>> >>> A Doodle Poll link is below to schedule: >>> ï¿½- http://www.doodle.com/8iu4nryqiahfa3d9 >>> >>> If you are interested in participating in this teleconf, fill out the >>> poll by 2 pm Eastern on Thursday, April 19. >>> >>> Thanks, >>> Josh >>> >>> -- >>> Joshua Hursey >>> Postdoctoral Research Associate >>> Oak Ridge National Laboratory >>> http://users.nccs.gov/~jjhursey >> >> >> >> -- >> Joshua Hursey >> Postdoctoral Research Associate >> Oak Ridge National Laboratory >> http://users.nccs.gov/~jjhursey > > > > -- > Joshua Hursey > Postdoctoral Research Associate > Oak Ridge National Laboratory > http://users.nccs.gov/~jjhursey -- Joshua Hursey Postdoctoral Research Associate Oak Ridge National Laboratory http://users.nccs.gov/~jjhursey

1 0

Re: [MPI3-IO] Joint IO/FT Teleconf
by Josh Hursey 01 May '12

01 May '12

Just a reminder that we are meeting today at 4 pm eastern. -- Josh On Thu, Apr 19, 2012 at 4:17 PM, Josh Hursey <jjhursey(a)open-mpi.org> wrote: > It looks like May 1 from 4-5 pm Eastern works best for everyone that > responded. Below are the teleconf details: > ï¿½Date: May 1, 2012 > ï¿½Time: 4 pm Eastern/New York > ï¿½Dial-in information: 877-801-8130 > ï¿½Code: 1044056 > > -- Josh > > On Tue, Apr 17, 2012 at 10:44 AM, Josh Hursey <jjhursey(a)open-mpi.org> wrote: >> The FT working group would like to have a joint teleconf with the IO >> working group to discuss the fault tolerance proposal. >> ï¿½- https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/323 >> ï¿½- https://svn.mpi-forum.org/trac/mpi-forum-web/ticket/326 >> >> A Doodle Poll link is below to schedule: >> ï¿½- http://www.doodle.com/8iu4nryqiahfa3d9 >> >> If you are interested in participating in this teleconf, fill out the >> poll by 2 pm Eastern on Thursday, April 19. >> >> Thanks, >> Josh >> >> -- >> Joshua Hursey >> Postdoctoral Research Associate >> Oak Ridge National Laboratory >> http://users.nccs.gov/~jjhursey > > > > -- > Joshua Hursey > Postdoctoral Research Associate > Oak Ridge National Laboratory > http://users.nccs.gov/~jjhursey -- Joshua Hursey Postdoctoral Research Associate Oak Ridge National Laboratory http://users.nccs.gov/~jjhursey

1 0