[petsc-dev] helping PETSc user get started the right way!

[Barry Smith]

  We should consider a system that helps PETSc users auto-magically set up bitbucket (or similar but better place) repository for their PETSc derived code. Now we tell people to copy a PETSc example and its make file and start developing from that. Perhaps we could provide a python script that 

1) made a directory
2) hg init it
3) copy over the makefile and example
4) hg add them
5) hg commit them
6) hg clone up to somewhere (bitbucket or elsewhere, PETSc machine?) and fix the .hg/hgrc location 

 Then they need only do hg commit; hg push to share their latest work anytime.


Barry


Begin forwarded message:

> From: Jed Brown <jedbrown at mcs.anl.gov>
> Date: July 13, 2012 5:53:54 PM CDT
> To: Barry Smith <bsmith at mcs.anl.gov>
> Cc: Lulu Liu <lulu.liu at kaust.edu.sa>, Satish Balay <balay at mcs.anl.gov>, Hong Zhang <hzhang at mcs.anl.gov>
> Subject: Re: null space in Lulu's model
> 
> On Fri, Jul 13, 2012 at 5:45 PM, Barry Smith <bsmith at mcs.anl.gov> wrote:
>    I am talking about NOW at this stage, regardless we need a good robust Newton style approach and it takes like 10 minutes to test with fieldsplit. Come on Jed, you're sounding like a usual brain-dead PETSc user "jump to the hard-stuff before doing the needed background work".
> 
> Sure.
> 
> Lulu, where is your source repository? If it's not somewhere yet, create an account at bitbucket.org and put it there. You can make it private if you like, but give "jedbrown", "prbrune", and "barrysmith" access. Then we can quickly experiment and give you feedback.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20120713/a5bedcfe/attachment.html>