October 2001 Email Thread
**************************************************************************
**************************************************************************
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
X-Sender: keahey@localhost
Date: Wed, 31 Oct 2001 15:38:50 -0600
To: nfc-sc01@fusion.gat.com
From: Kate Keahey
Subject: vizapp
Sender: owner-nfc-sc01@fusion.gat.com
Status:
Hi,
I need help instrumenting the demo with calls to viz app, please read.
We are making progress with the application visualizing interactions
during the demo to the point where I think it makes sense to instrument
the demo. Right now what we mainly see are little red circles appearing
in appropriate parts of the country when computation is started, so
nothing exciting but it looks like we'll get there. The demo can be
instrumented by putting calls reporting on events in the body of demo
components when those events happen (so for example when efit writes out
data, we report on this event and it will be visualized). There is one
problems with instrumenting the demo: unfortunately the Netlogger (which
has to be used in order for things to work with this application) does
not have a C shell API. I could either write a little program callable
from Tom's script or we could push the calls into components for which
we do have API. Let me know which you would prefer. I wrote a little
program generating events for our demo with lots of comments on how the
demo needs to be instrumented (this is the one we use for debugging the
app); it is accessible at ~keahey/publish on either the datagrid cluster
or sc desksides.
Here is how this app works. The interactions are based on a piece of
software called Netlogger (see http://www-didc.lbl.gov/NetLogger/). It
implements a database where we can post events. Then the vizapp gets the
events from there and visualizes them. We need to worry about the first
part of the interaction only. Right now and for the next few days the
database will be running on terra.mcs.anl.gov reading from port 14835
(see example). At SC it will move to the floor, so it should be
configurable.
In order to instrument a program, insert calls opening and closing
connection to the netlogger at the beginning and end of the program
(see example for C API to do this, I will be happy to provide examples
in other languages or you can go to the url below). Then insert calls
writing events pretty much as they are in the example in the appropriate
places (it should be pretty much cut and paste from the example).
Compile with netlogger header file and library; on the datagrid cluster
and sc desksides the Netlogger installation is in
~keahey/NetLogger-1.6/linux.bin. Mary, I am not sure if you have it on
diesel or natasha, installation is essentially just a matter of
unpacking. Or I could do it for you if you tell me where.
Further info: we are publishing two kinds of events (I took some
shortcuts to make things easy so for example bandwidth info is "made
up"):
1) JOB_STATUS, format: "ID=%s FRIENDLY.NAME=%s JOB.HOST=%s JOBS.SUBMITTED=%d
JOBS.COMPLETE=%d JOBS.FAILED=%d BYTES.PRODUCED=%d"
2) "TransferPerfTotal", format: "ID=%s
FRIENDLY.NAME=%s URL.SOURCE=%s URL.DEST=%s BYTES=%d
BW.CURRENT=%f BW.AVG=%f"
Here is the help I need:
1) Tom and Qian, since you know best where the event generating things
happen in your programs, could you inert the appropriate calls from the
example? 2) Mary, could you handle the installation on diesel and
natasha?
Kate
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
Sender: mrt@lbl.gov
Date: Tue, 30 Oct 2001 15:18:24 -0800
From: Mary Thompson
Organization: LBNL
X-Accept-Language: en
To: "David P. Schissel"
Subject: Re: Poster
Status:
Our poster guy and defender of DOE logos, think we should get it
reprinted. Our current ship date from here is Thursday morning.
Thanks, Mary
--
---------------------------------------------------------------------
Mary R. Thompson
Distributed Security Research Group (510) 486-7408
Lawrence Berkeley National Lab http://www-itg.lbl.gov/~mrt
----------------------------------------------------------------------
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
X-Sender: keahey@localhost
Date: Tue, 30 Oct 2001 16:29:03 -0600
To: nfc-sc01@fusion.gat.com
From: Kate Keahey
Subject: good news, bad news
Sender: owner-nfc-sc01@fusion.gat.com
Status:
The good news is that Argonne desksides have connectivity to the outside
network again. Port forwarding works, and generally things seem to work.
I tried running Tom's demo and got the GUI and the plasma picture in
color. I was not able to run it though, I got this: GRAM Job submission
failed because authentication with the remote server failed (error code
7), but I got that too when I was trying to submit "date" to natasha so
clearly something is not right with the permissions. Mary, could you
look into this? (I can submit to pitcairn fine).
The bad news is that people are threatening to take away the desksides
on Friday so essentially we have only 2 more days to test and finish the
demo. The good news is that it looks like the viznet application is
recognizing my events, and might even be able to plot them soon. More
about that tomorrow...
Kate
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Sender: keahey@localhost
Date: Tue, 30 Oct 2001 16:13:08 -0600
To: "David P. Schissel" , mrthompson@lbl.gov,
twf@psfc.mit.edu
From: Kate Keahey
Subject: Re: New Version of Handout Backpage
Status:
Looks good. Might be nice to make the picture of the Gui smaller and
move it left so that it aligns with the right margin.
At 01:04 PM 10/30/2001 -0800, David P. Schissel wrote:
> Kate, Tom, and Mary -
>
> A new version of the handout backpage is on available
>on our web site
>
>
> We have
>
> 1) added the image of Fredian's GUI
> 2) colored and made bold the 3 locations (LBNL, ANL, SC01)
> in the flow diagram
> 3) Added the words "...using dispersed computational resources."
>
>
> Please let me know what you think of this version.
>
> - Dave
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
**************************************************************************
**************************************************************************
Sender: mrt@lbl.gov
Date: Tue, 30 Oct 2001 14:04:26 -0800
From: Mary Thompson
Organization: LBNL
X-Accept-Language: en
To: "David P. Schissel" , keahey@mcs.anl.gov
Subject: Re: New Version of Handout Backpage
Status:
Looking good. I do think that you should put the Argonne and LBNL logos
on a white background like you did on the poster. They get sort of lost
in the background otherwise. The backpage looks good as it is.
I did the the poster, I am waiting to track down our "poster
co-ordinator" to see what he thinks about the DOE logo. I don't think it
is too big a deal, the printing got misaligned a bit, but the crest
looks fine.
Mary
--
---------------------------------------------------------------------
Mary R. Thompson
Distributed Security Research Group (510) 486-7408
Lawrence Berkeley National Lab http://www-itg.lbl.gov/~mrt
----------------------------------------------------------------------
**************************************************************************
**************************************************************************
Date: Mon, 29 Oct 2001 09:51:50 -0800
To: keahey@mcs.anl.gov, mrthompson@lbl.gov
From: "David P. Schissel"
Subject: Handout
Cc: schissel
Status:
Kate and Mary -
Regarding Kate's comments below (I assume these
are for the handout and not the large LBNL poster)...
I missed your new "list of components" and will make the change
as with the others you mentioned.
Regarding Tom's picture....will try to add, but am worried about
space considerations.
I am at a Long Beach physics meeting all week but am returning
to San Diego briefly Tuesday and Wednesday.
Given my schedule I intend to work with the graphic artist on
these changes today via the phone and tomorrow in person. So I
have more time I will bring the handouts (200 - 100 for ANL and
100 for LBNL) to the meeting.
Regarding the big poster.....I have heard no new comments so
I am going to have it printed and Fed Exd to Mary today.
If you need to contact me today for any reason my cell
number is 760-525-3665.
- David
to my par
>David,
>>
>I was not able to download the poster over the phone line so comments only now:
>- I changed the "list of components" part of the writeup as well as the
> subsequent paragraph; those changes did not propagate, was that intentional?
>- the leading line on the second paragraph is formatted differently than the other
> paragraphs (should be longer)
>- MDSplus is boldfaced twice instead of once
>- we talked about putting the picture beside the text and trying to squeeze in
> Tom's picture of the interface, it may be too late now perhaps...
>
>At 04:46 PM 10/26/2001 -0800, David P. Schissel wrote:
**************************************************************************
**************************************************************************
X-Sender: keahey@localhost
Date: Mon, 29 Oct 2001 09:00:06 -0500
To: "David P. Schissel" , mrthompson@lbl.gov
From: Kate Keahey
Subject: Re: New PDF of Poster
Cc: schissel@fusion.gat.com
Status:
David,
I was not able to download the poster over the phone line so comments only now:
- I changed the "list of components" part of the writeup as well as the subsequent
paragraph; those changes did not propagate, was that intentional?
- the leading line on the second paragraph is formatted differently than the other
paragraphs (should be longer)
- MDSplus is boldfaced twice instead of once
- we talked about putting the picture beside the text and trying to squeeze in
Tom's picture of the interface, it may be too late now perhaps...
At 04:46 PM 10/26/2001 -0800, David P. Schissel wrote:
> Mary and Kate -
>
> A new PDF version of the poster is also on our web site.
>This is the version I am taking to APS/DPP in Long Beach
>next week.
>
> After hearing your comments, I will talk on the phone
>with the graphics department, they can make changes,
>and print and Fed Ex to LBNL. Same holds true for the
>handout.
>
> - David
Kate
**************************************************************************
**************************************************************************
X-Sender: keahey@localhost
Date: Mon, 29 Oct 2001 08:40:37 -0500
To: Mary Thompson ,
"David P. Schissel"
From: Kate Keahey
Subject: Re: Handout
Status:
I would say another 100 for ANL. Mary, would you be able to pick up our
flyers and take them to Denver?
At 11:24 PM 10/26/2001 -0700, Mary Thompson wrote:
!00 copies of the handouts will be enough for the LBNL booth. FedExing
it all to me should be fine.
Mary
"David P. Schissel" wrote:
>
> How many copies of the handout do we want in Denver?
> I assume we need some for both the ANL and LBNL booths.
> Can I Fed Ex them all to LBNL and we can divide them
> up in Denver?
>
> - David
--
---------------------------------------------------------------------
Mary R. Thompson
Distributed Security Research Group (510) 486-7408
Lawrence Berkeley National Lab http://www-itg.lbl.gov/~mrt
----------------------------------------------------------------------
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
**************************************************************************
**************************************************************************
Sender: mrt@lbl.gov
Date: Fri, 26 Oct 2001 23:24:53 -0700
From: Mary Thompson
Organization: LBNL
X-Accept-Language: en
To: "David P. Schissel"
CC: keahey@mcs.anl.gov
Subject: Re: Handout
Status:
100 copies of the handouts will be enough for the LBNL booth. FedExing
it all to me should be fine.
Mary
"David P. Schissel" wrote:
>
> How many copies of the handout do we want in Denver?
> I assume we need some for both the ANL and LBNL booths.
> Can I Fed Ex them all to LBNL and we can divide them
> up in Denver?
>
> - David
--
---------------------------------------------------------------------
Mary R. Thompson
Distributed Security Research Group (510) 486-7408
Lawrence Berkeley National Lab http://www-itg.lbl.gov/~mrt
----------------------------------------------------------------------
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
Date: Fri, 26 Oct 2001 08:38:33 -0800
To: nfc-sc01@fusion.gat.com
From: "David P. Schissel"
Subject: New Version of Large Poster
Sender: owner-nfc-sc01@fusion.gat.com
Status:
SC01 Team:
A new version of the large LBNL poster is available at
http://www.fusiongrid.org/work/meetings/sc01/poster.pdf
- thanks, ds
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
X-Sender: keahey@localhost
Date: Fri, 26 Oct 2001 10:23:49 -0500
To: nfc-sc01@fusion.gat.com
From: Kate Keahey
Subject: remainder: telecon today
Sender: owner-nfc-sc01@fusion.gat.com
Status:
This is a remainder for today's telecon at 11am CST.
We have 8 domestic lines (that should call into 1-888-790-1415) for the duration of one hour
Pass code:75284
Agenda:
- status of the infoviz application (bad)
- status of the various posters/flyers
- status of the rest of the demo
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
Date: Mon, 22 Oct 2001 12:31:57 -0400
From: "Thomas W. Fredian"
X-Accept-Language: en
To: nfc-sc01@fusion.gat.com
Subject: Re: Natasha now runs Globus 2.0 server code
Sender: owner-nfc-sc01@fusion.gat.com
Status:
There are several outstanding problems in getting the demo to function as planned.
I've listed these below.
- Natasha to double as backup data server:
1) Cannot globus-job-submit to natasha
$ globus-job-submit natasha -stdout data_server.log data_server
GRAM Job submission failed because the connection to the server
failed (check host and port) (error code 12)
2) twf account is defined in nis and home directory is on nfs mount.
Need these to be local to natasha
- ANL sc2001 floor systems
Cannot globus-job-submit using demo certificate:
$ globus-job-submit diesel.lbl.gov -stdout data_server.log data_server
GRAM Job submission failed because authentication failed:
GSS status: major:000a0000 minor: 00000000 token: 00000000
GSS_S_DEFECTIVE_CREDENTIAL - sslv3 handshake
Function:verify_callback Reason:Certificate verify failed:
error=self signed certificate in certificate chain
subject=/O=DOE Science Grid/OU=Certificate
Authorities/CN=Certificate Manager
issuer =/O=DOE Science Grid/OU=Certificate
Authorities/CN=Certificate Manager
Function:SSL3_GET_SERVER_CERTIFICATE Reason:certificate verify failed
Function:gs_handshake Reason:SSLv3 handshake problems
- Parallel efit
1) Can run non-parallel efit from twf account but problems with
environment when running parallel version.
$ setenv shot_number 3
$ setenv data_server _diesel.lbl.gov
$ setenv mds_event_target _natasha.lbl.gov:8001
$ /homes/twf/real_efit
shot number is set to 3
mds_event_target is set to _natasha.lbl.gov:8001
data_server is set to _diesel.lbl.gov
Agent pid 31006
Identity added: /homes/twf/.ssh/identity (twf@dg0n7.mcs.anl.gov)
LD_LIBRARY_PATH is set to /homes/twf/mdsplus/lib
/homes/peng/efit/efitd6565d: error in loading shared libraries:
libMdsLib_client.so: cannot open shared object
file: No such file or directory
2) Need to get efit running on ANL sc2001 floor systems for backup as
well.
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
Date: Mon, 22 Oct 2001 12:06:15 -0800
To: nfc-sc01@fusion.gat.com
From: "David P. Schissel"
Subject: Draft of Large Collaboratory Poster
Sender: owner-nfc-sc01@fusion.gat.com
Status:
SCO1 People:
A PDF file which is a draft of the large Collaboratory Poster
for APS/DPP and SCO1 can be found on our web site at
http://www.fusiongrid.org/work/meetings/sc01/poster.pdf
Can I ask that you look at it and give me feedback.
Issues that I have:
1) there are two pieces of text that deal with computer science
but our images are weak. Can someone send us better images.
Specifically, is there a good one that people like for grid
computing.
2) The idea of the poster is the central theme with ideas orbiting
around....making the collaboratory...does this work for people?
3) The text is "Out of order" from what I gave the graphic artist.
I can fix this.....Do we need an obvious starting and end point
for the text.
4) I have no image for one piece of text (the one with the
word SciDAC in it). Any suggestions?
- Thanks, David
P.S. We need to finish this week so we can put this up at the
APS/DPP meeting. This holds true for the handout as well.
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Sender: keahey@localhost
Date: Fri, 19 Oct 2001 03:29:56 -0500
To: schissel@fusion.gat.com, twf@psfc.mit.edu, mrthompson@lbl.gov
From: Kate Keahey
Subject: back of the sc flyer
Status:
Enclosed is a draft for the back side of the SC flyer (the one
explaining what happens in the demo) based on Tom's demo instructions.
I tried to tie the explanation to where we are going with it. Mary could
you add a sentence about Akenti? Also, I think one purpose of a flyer
would be to give the reader pointers to technologies involved in the
project so I italicized names of the technologies taking part in the
demo/project with the idea that at the bottom of the page we would give
a contact for each technology. Another idea would be to add not only the
contact but say a couple of brief sentences summarizing each technology
(say, for scientific visualization it might be a few). Let me know what
you think.
Pictures: the way things are going with the map application I am not
sure we will be in shape to have a meaningful picture of that, so I
think we should reuse the picture of demo interactions from the August
meeting.
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
Attachment converted: Macintosh_HD:Fusion flyer.doc (WDBN/MSWD) (0005167B)
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
Date: Thu, 18 Oct 2001 15:35:35 -0700
From: Mary Thompson
Organization: LBNL
X-Accept-Language: en
To: nfc-sc01@fusion.gat.com
Subject: Natasha now runs Globus 2.0 server code
Sender: owner-nfc-sc01@fusion.gat.com
Status:
Jason debugged my problems on getting natasha to behave as a globus
server as well as client. So now we should be able to run the backup
data-server on it in case the link to diesel, et.al is down.
If any one else is having trouble getting Globus 2alpha to work on a
Redhat 7.1 system running xinetd, the installation instructions at
http://www-itg.lbl.gov/Grid/public/Globus2alpha_build.html might help.
Mary
--
---------------------------------------------------------------------
Mary R. Thompson
Distributed Security Research Group (510) 486-7408
Lawrence Berkeley National Lab http://www-itg.lbl.gov/~mrt
----------------------------------------------------------------------
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
X-Sender: keahey@localhost
Date: Thu, 18 Oct 2001 14:39:12 -0500
To: nfc-sc01@fusion.gat.com
From: Kate Keahey
Subject: software requirements on anl demo machines
Sender: owner-nfc-sc01@fusion.gat.com
Status:
A remainder: please let me know the software requirements of your parts
of the demo on the anl machines by say cob today.
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
X-Sender: keahey@localhost
Date: Thu, 18 Oct 2001 13:29:40 -0500
To: nfc-sc01@fusion.gat.com
From: Kate Keahey
Subject: proposal: let's cancel the telecon tomorrow
Sender: owner-nfc-sc01@fusion.gat.com
Status:
Telecon status: Tom won't be able to make it, Mary won't be able to make
it either, and I have a slight preference for skipping (I am taking
tomorrow off but could be there for the telecon). I suggest that we skip
tomorrow unless somebody objects. Let me know by say 5 pm cst; if I hear
no objections the telecon will be cancelled. Quick overview of some
topics below:
Integrating efit: Qian got the libc problems resolved and is working
with Tom to integrate it into the demo.
Infoviz component: well this work keeps lagging behind; I finally got
the format that will be used with netlogger, and am supposed to get
today some interface to a netlogger server that will let me check if the
data I send in appears in the database as it should. At this point I
propose to connect a small interactive unit to that server and when it
works to integrate that in the demo. Then our demo will be integrated
with the infoviz component whenever it becomes available. I am also
working with Mary to figure out what we need to do to get it installed
at lbl machines.
Let me know how if you object to cancelling the telecon.
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
Date: Thu, 18 Oct 2001 09:05:24 -0400
From: "Thomas W. Fredian"
X-Accept-Language: en
To: SC01 Demo
Subject: Re: Most likely unavailable for conference call tomorrow
Sender: owner-nfc-sc01@fusion.gat.com
Status:
I just read Kate's email about the Argonne SC machines. I'll look into installing
the demo software on these machines as well but not sure if I'll get to it today.
-tom
"Thomas W. Fredian" wrote:
> Hi All,
>
> It is highly likely that I won't be able to attend the conference
> call tomorrow. If there are any issues that you would like to discuss
> with me prior to the call send me email or give me a call today. Qian
> reported a problem with the MDSplus connection from the efit code to the
> data server and I'll be looking into that today. I think this is the
> only new business regarding the data access portion of the demo since
> last weeks call.
>
> -tom
>
> ===============================================================================
>
> This message was sent to the SciDAC National Fusion Collaboratory (NFC)
> workers list nfc-sc01. Visit the Collaboratory at
> .
>
> To unsubscribe from this list, please send a message to
> majordomo@fusion.gat.com with the following text in the *body* of the
> message: unsubscribe nfc-sc01
>
> David P. Schissel:
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
X-Sender: keahey@localhost
Date: Wed, 17 Oct 2001 15:58:36 -0500
To: nfc-sc01@fusion.gat.com
From: Kate Keahey
Subject: Argonne SC machines
Sender: owner-nfc-sc01@fusion.gat.com
Status:
Here is information about the setup at Argonne. A few requests:
1) Could Argonne account holders check if they can log in to these
machines? I can log in fine, but want to confirm if we have off-site
access.
2) Please send me a list of the software you need for the parts of the
demo you are in charge of; both things that could be shared (such as
libc version) and things that are fusiondemo-specific (such as IDL,
MDSplus, etc) If you are not sure send me mail also (Qian, we'll just
have to ask them to install whatever version works for you eventually).
Note that this information is for the desksides only, the clusters are
coming later.
3) Let me know if you have any questions/suggestions/requests concerning this setup.
>From: "William E. Allcock"
>To: , "Todd Tannenbaum" ,
> "Ann Chervenak" , "Carl Kesselman" ,
> "Ewa Deelman" , "June-Sup Lee" ,
> "Karl Czajkowski" , "Laura Pearlman" ,
> "Mei-Hui Su" , "Steven Fitzgerald"
>Cc: "Miron Livny"
>Subject: SC infrastructure and Demo Needs
>Date: Wed, 17 Oct 2001 14:44:18 -0500
>X-Mailer: Microsoft Outlook IMO, Build 9.0.2416 (9.0.2910.0)
>Importance: Normal
>Sender: owner-dsl@mcs.anl.gov
>
>The booth infrastructure is operational (details below). At this point,
>everyone needs to begin to migrate their demos over to this infrastructure.
>We now need to figure out what should be installed globally in /soft, and
>what should be in your home directories. So, with that in mind, I need
>everyone who is responsible for a demo to send me a list of EXACTLY
>(including version numbers) what software you need, and I need this ASAP
>(preferably NOW). This is so that if we see multiple people needing the
>same software we can designate one person to install it in /soft and then
>point other people at it. Some of the important issues:
>
>- What version of Globus are you using and which parts
> - If we end up having to run two multiple versions of globus, some of the
> services will have to be on non-standard ports.
>- If you have any dependencies on specific glibc versions, etc
>- What versions of Perl, Python, Java, ad nauseum do you need.
>
>The general idea is that you will be responsible for installing the vast
>majority of your software. If we see that multiple demos will be using the
>same software (like Globus), we will either designate someone to install it
>in /soft or Charles will do it, particularly if it requires root access.
>
>
>
>Following is the status of the SC infrastructure:
>- The MCS home server (sc2001server.mcs.anl.gov) is in place
>- Networking is in place (currently 100 Mbs, will be GigE shortly)
>- hostnames are as they will be at SC (you are going to just love the names
>they
> picked)
>- you can log in with your MCS account names
>- Five of our six desksides are up
>- The GeForce3 cards are not installed yet, but will be by SC (for you
>Graphics
> folks), we could not get Gladiac 920s so we are using Visiontek GeForce3.
>- the clusters are not quite there yet. Hopefully, the clusters will be up
> early next week
>- No software, other than OS (RedHat 7.1), has been installed yet
>- We will take care of getting host certs installed.
>>
Directory Structure:
>- There will be home for each account served of the MCS (booth wide) server.
> - SW specific to your demo should go here
> - Data sets specific to your demo should go here.
>- There will be a shared /soft served off one of our desksides (globus wide)
> - Shared software should be here (Globus, iperf, perhaps Java if a number
>of
> people can use the same version)
>- There is a minimum of 36GB of local disk on each machine
> - It is recommended that this be used as dynamic scratch, so that demos
> can be run from any machine.
> - However, if you need data locally for performance reasons, contact
> Charles or myself and we can discuss this on a case by case basis.
>
>For now, here is how we get access to the machines:
>a031.r352.showfloor.sc2001.org
>a033.r352.showfloor.sc2001.org
>a034.r352.showfloor.sc2001.org
>a035.r352.showfloor.sc2001.org
>a036.r352.showfloor.sc2001.org
>
>Here's how you get to them:
>First, ssh to sc2001server.mcs.anl.gov. From there, you can drop the
>".r352.showfloor.sc2001.org" part of the name, and just ssh to a031,
>a033, etc. For now, these machines are only accessible through
>sc2001server. They will always be accessible this way, even if DNS on the
>show floor goes down. However, once DNS is up you will be able to log into
>the machines directly.
>
>--------------------------------------------
>William (Bill) E. Allcock
>Argonne National Laboratory
>Bldg. 221, Office C-115A
>9700 S. Cass Ave
>Argonne, IL 60439-4844
>E-Mail: allcock@mcs.anl.gov
>Office: 630-252-7573
>Mobile: 630-247-1647
>
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Sender: keahey@localhost
Date: Wed, 17 Oct 2001 10:27:14 -0500
To: "David P. Schissel" , mrthompson@lbl.gov
From: Kate Keahey
Subject: Re: Handout and Poster
Cc: schissel@fusion.gat.com
Status:
Dave,
I completely misunderstood yesterday which text you were referring to. I
hope I am looking at the right one now... (the one which is a poster for
Mary and the front page of the flyer, is this right?) It looks great.
One comment I have: at the end of the first column you say "in this new
paradigm access to resources is separated from their implementation". I
am not sure what you mean by "resources"... If you mean the network
services it might be better to say just that. Also, the period from the
end of this sentence somehow seems to have made it to the end of the
sentence in the next column and the word "new" in the second column got
misspelled.
So now having seen the poster: it probably doesn't make sense to talk
about either (1) or (2) there. I thought you were talking about the
first part of the second page which was going to explain the point of
the demo. In this case I think explaining fusion a little bit so as to
provide context for things like "experimental pulse" and what comes out
of it would be very valuable. Also, I think we should name all the
technologies we are using there but that perhaps is something I should
do.
At 03:39 PM 10/16/2001 -0800, David P. Schissel wrote:
>
>
> Kate and Mary -
>
> As I work on the words for the SC01 Poster I have two questions:
>
> On the handout:
>
> 1) I did not have the one sentence on what is fusion
> 2) I did not mention any software by name (e.g. Globus, Akenti,
> Access Grid, MDSplus, etc.)
>
> Do you think it is OK to leave both 1 and 2 out?
>
> - ds
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
Date: Wed, 10 Oct 2001 15:30:11 -0400
From: "Thomas W. Fredian"
X-Accept-Language: en
To: nfc-sc01@fusion.gat.com
Subject: demo description
Sender: owner-nfc-sc01@fusion.gat.com
Status:
We have attempted to make the fusion demo for sc01 runnable from any
account on the sc demo floor workstations. The lbl workstation, natasha,
has been set up and I'll do the same once on the anl workstation once it
is ready.
On natasha you start up the demo by issuing the following command:
# /usr/local1/fusionDemo/scripts/controller
By default, this will use diesel.lbl.gov for the data server and
dg0n7.mcs.anl.gov as the compute server. You can change which nodes to
use as the data server and compute server by adding these to the command
in that order:
# /usr/local1/fusionDemo/scripts/controller clipper.lbl.gov
dg0n7.mcs.anl.gov
Currently there are two data servers set up; diesel.lbl.gov and
clipper.lbl.gov. Shortly there will be a third host available at lbl,
fluffy.lbl.gov.
Currently there is only one compute server configured:
dg0n7.mcs.anl.gov.
I can set up more data servers and compute servers if necessary. We'll
probably want to set up systems on the sc01 floor which can behave as
data servers and compute servers.
How to operate the demo:
After invoking the controller script you should see a controll window on
the workstation. There will be a "Start Pulse" button in the window. To
run a cycle hit the "Start Pulse" button. One the left under the "Start
Pulse" button there is a window where status message will appear. After
a cycle completes you should see the following text:
Plasma pulse beginning.
Plasma formed in tokomak.
Pulse completed, beginning data acquisition.
Data acquisition complete, beginning analysis.
<<<<< globus-job-submit efit on compute server >>>>
https://dg0n7.mcs.anl.gov:36617/27619/1002738795/
Analysis done. Beginning visualization
Visualization done
There should be slight delays between most of the lines (3 seconds or
so). When you see the "<<<< globus-job-submit...", the controller is
starting the efit computation on the compute server. You will not see
any more output until the efit job completes. After the efit job
completes you will see the "Analysis done..." message and a new window
will appear which is drawing frames of an animation. Once all the frames
have been drawn, the animation will begin and continue to repeat until
you hit the "End animation" button. Once you hit the "End Animation"
button the animation window will disappear. You can hit the "Start
Pulse" button once again and a new cycle will take place. You can leave
the animation window running and take another pulse. You will get a
second animation window when the next cycle completes.
IMPORTANT: When you are done with the demo pull down the "File" menu on
the control panel and select "Exit". Do this instead of killing the demo
from the xterm window since the controller script does some cleanup
after you exit the IDL application.
IMPORTANT: You should probably only have one demo running at one time
particularly if you want to use the same data server or compute server.
I didn't put anything in the demo to prevent you from stepping on each
others toes!
How it works:
The controller script first does a grid-proxy-init using the demo
certificate. I made this work from any account by making the demo key
world readable and the controller script copies the demo key to a
temporary location and makes the copy readable only by the user. The
controller script then uses globus-job-submit to start up the data
server on the selected host. It also runs an event server as a
subprocess which will receive the completion event when the efit
application completes. The controller script then starts IDL running the
control application.
When you hit the "Start Pulse" button, the beginning status messages and
the picture of the plasma are just output at timed intervals and the
"Start Pulse" button becomes inactive. When the "<<<<< globus-job-submit
efit on compute server >>>>" message comes out, the IDL application
issues a globus-job-submit command to start the efit script on the
compute server. The globus-job-submit passes the name of the data_server
host, the name of the event_server host, and the shot number to the efit
script. The efit script analyses local data on the compute server and
writes the results back to the data_server and then sends a completion
event to the event_server. When the controller sees the completion
event, it begins the visualization procedure. The visualization
procedure reads the data from the data_server and creates an animation
with the efit data. Once the animation begins the "Start Pulse" button
becomes active ready for you to run another cycle. You can dismiss the
animation by pushing the "End Animation" button.
Security aspects.... The MDSplus servers all use the data_server
certificate and the clients all check for this identity when authorizing
the connections. The controller uses the demo certificate which has
gridmap entries on the server machines mapping to the twf account.
-tom
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
X-Sender: keahey@localhost
Date: Fri, 05 Oct 2001 10:31:14 -0500
To: nfc-sc01@fusion.gat.com
From: Kate Keahey
Subject: Some notes on GridFTP
Sender: owner-nfc-sc01@fusion.gat.com
Status:
We had an interesting discussion at the last telecon about moving files
versus moving data and where GridFTP fits into the picture; here is some
more information about what GridFTP can do for us.
First, it turned out that, without realizing it, I was talking about
some capabilities that are being worked on "even as we speak", rather
than are a part of Globus already. I heard so much about them that I
assumed that we already have them. So this is probably not something
that we can use for our SC demo, but something that might be interesting
to us after SC.
Second, here is what I was talking about. GridFTP has two ftp-ish
aspects to it: (1) a familiar client/server interface (good for moving
files, not data) and (2) a well-known protocol. In principle we could
use a different interface to that protocol, and have memory to memory
transfer. I assumed that capability was already there, but for now it is
"in the works". Here is why I think GridFTP might be of interest to us:
optimized data transfer (for example it will adjust the size of TCP
buffer for point to point transfers), plug-ins (these are modules that
you can add to the call stack to instrument it with your own
functionality such as for example monitoring), striped and parallel
transfer (which could also speed things up). If you want to know more
about GridFTP here is a pointer to the API:
http://www-unix.globus.org/api/c/globus_ftp_client/html/index.html.
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
Date: Fri, 05 Oct 2001 10:43:21 -0400
From: "Thomas W. Fredian"
X-Accept-Language: en
To: SC01 Demo
Subject: mdsplus/globus infrastructure status
Sender: owner-nfc-sc01@fusion.gat.com
Status:
Hi all,
Here is the latest status of the mdsplus/globus infrastructure for
the demo.
What is working:
Controller:
The controller now cycles between three efit shots (shot numbers
1-3). The controller script can take two optional parameters: the
data_server and the compute_server hostnames. The controller now does a
globus-job-submit command to the compute_server to start the efit
application. It passes to this efit script environment variables:
shot_number, data_server and mds_event_target. The efit application
needs to connect to the data server, open the appropriate efit tree
(using shot_number) and write the results. The efit script should then
do an: setevent EFIT_DONE.
Data servers:
Data servers can now be run on both diesel.lbl.gov and
clipper.lbl.gov (and on natasha.lbl.gov on the demo floor if you loose
connectivity to lbl). I have changed the client authentication code to
use MODE_IDENTITY and hardcoded in the identity string of a data server
certificate Mary generated for me. (This will eventually be replaced by
a MODE_CALLBACK which will examine the server identity.) I have
experimented with using globus-job-submit to start these servers. It
works but we will need to have gridmap entries for the certificate you
will use for the demo on the server hosts which will map to an account
which has write access to the data files.
Compute server:
I have a dummy efit job on dg0n7.mcs.anl.gov which successfully runs
via a globus-job-submit command from the controller.
To be done:
Controller:
1) Add picture of fusion experiment control room (C-Mod possibly).
2) Hook up real visualization (either done in IDL or the fancy
version if ready for the demo).
3) Use globus-job-submit, globus-job-cancel and globus-job-clean to
start all mdsplus servers used for a demo. This will need appropriate
gridmap entries mentioned above.
4) Perhaps add infovis database commands to drive infovis display.
5) Install on anl's demo floor workstation.
Data servers:
Essentially complete. Perhaps additional backup data server hosts?
Compute server:
1) Change to use real efit analysis code. gridmap to demo user
account. Single processor/multi processor options?
2) Add backup compute server hosts?
-tom
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
Date: Thu, 04 Oct 2001 17:43:43 -0700
From: Mary Thompson
Organization: LBNL
X-Accept-Language: en
To: "David P. Schissel"
CC: nfc-sc01@fusion.gat.com
Subject: Poster info for SC01
Sender: owner-nfc-sc01@fusion.gat.com
Status:
We currently plan to have the Fusion Collaboratory mentioned on two
posters in the LBNL booth. The one that Dave and GA are making. One real
strong suggestion from our PR guy, is to include the DOE logo on the
poster. The Project Managers will be looking for this. If you don't
happen to have a good version of it, we can send you one. Including the
word SciDAC would also be a plus.
The other poster is our DOE Science Grid one which will have an overview
of the Science Grid idea for the top half, and the bottom half will be
titled Collaborative Science on the Grid and will have a section with
the text
Magnetic Fusion Research
------------------------
Research requirements that are addressed by the Grid technologies
Need for distributed computations and visualizations to be done within a
15 minute interval between Tokamak pluses.
Need for secure distributed access to raw and processed data and
visualizations to facilitate collaborative decision making.
Dave, can you send me a copy of the graphic that was on the cover of the
proposal in a format suitable for printing.
thanks, Mary
--
--
---------------------------------------------------------------------
Mary R. Thompson
Distributed Security Research Group (510) 486-7408
Lawrence Berkeley National Lab http://www-itg.lbl.gov/~mrt
----------------------------------------------------------------------
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
X-Sender: keahey@localhost
Date: Thu, 04 Oct 2001 16:09:54 -0500
To: nfc-sc01@fusion.gat.com
From: Kate Keahey
Subject: telecon tomorrow
Sender: owner-nfc-sc01@fusion.gat.com
Status:
I set up a telecon for tomorrow, Friday, Oct 5 at 11am CST for the duration of one hour.
The 8 domestic lines should call into 1-888-790-1415
Pass code:75284
I have made this call a recurring call for every Friday until further notice.
Proposed agenda for tomorrow (add/delete/modify):
1. Discussion of status:
- a full distributed run (it looks like we will be late on this which is fine)
- infoviz component: interface
- scientific visualization
- status on flyers, posters, etc.
2. Moving beyond basic demo
- do we want to? original plans included parallel efit, more data, etc.
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender
to owner-nfc-sc01@fusion.gat.com using -f
Date: Thu, 04 Oct 2001 11:35:18 -0700
From: Mary Thompson
Organization: LBNL
X-Accept-Language: en
To: Kate Keahey
CC: nfc-sc01@fusion.gat.com, Keith Jackson
Subject: Re: Soliciting input for the information visualizationcomponent
Sender: owner-nfc-sc01@fusion.gat.com
Status:
Kate Keahey wrote:
>
> Mary,
>
> great input! What I originally discussed with the people implementing this
> was that there would be some symbol for a (super)computer and (maybe) a
> legend. Then if you want to find out more you move your mouse curson on
> thop of that symbol and it would visualize load information, free memory,
> etc. Then hopefully you could drag this "expanded" image to the bottom of
> the display and track the ones you are interested in. In your comments
> below do you mean:
>
> load factors: is that the cpu utilization? I was thinking number of
> utilized nodes, and per node cpu utilization, disk space, available memory.
> What characteristics exactly do you mean by "load"? (It will be very hard
> to add them later as this deals with screen clutter etc.)
>
I was just thinking of the the number you get out of uptime which claims
to be the "average number of jobs in the run queue over the last 1, 5,
and 15 minutes"
I'm not sure what the appropriate measure is for cluster. Node
utilization sounds good if you know how to get it.
> grid monitoring: the idea in this app is that when you are running it you
> can visualize all the stuff that's happening with Globus and was
> instrumented to use this application (we'll be running a bunch of demos),
> or you can run it with an option that will restrict the information
> visualized (to show the Fusion demo only).
Mary
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
Date: Wed, 03 Oct 2001 13:42:18 -0500
To: nfc-sc01@fusion.gat.com
From: Kate Keahey
Subject: infoviz demo description
Mime-Version: 1.0
All,
here is a description of what we currently have for the infoviz demo.
Attached are two "screendumps" of the current state of the "infoviz"
component. The first snapshot shows the full screen of this application and
visualizes data transfer (right now based on traceroute) between Argonne
and the Monash university in Australia. The little spheres on the lines
drawn along the route move and their movement corresponds roughly to the
speed with which the data is transferred. If you look closely, you will see
a little yellow cross over Monash --- that's the cursor. Positioning the
cursor over a resource causes the information about the resource to be
displayed in the upper left corner. More of that can be seen on the second
snapshot. This one zeroes in on a region of the full screen to show just
North America (that's what we will be doing) and shows connectivity from
Argonne to various places. Again, positioning the cursor over Argonne
causes information about resources to be displayed. In this particular
instance only the information about Access Grid nodes is displayed, but for
SC this will be replaced by information relevant to the demo. Of the
functionality that is absolutely critical to have the only thing it does
not do yet is change color of the node when we start the computation.
Interface: this is still in progress. There are two kinds of interfaces:
the viz application interfacing netlogger (the event database that
everybody sends their information to) and the interface between the
netlogger and our demo. The latter is pretty straightforward and I am
designing it right now based on the feedback I got from you about the
information you would like to see visualized. The former is more
general-purpose and is being worked on by somebody else in our group. I am
told they should have something within a week and I am reasonably confident
that they will.
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
--=====================_186683857==_
Content-Type: image/jpeg; name="snapshot1.jpg";
x-mac-type="4A504547"; x-mac-creator="4A565752"
Content-Transfer-Encoding: base64
Content-Disposition: attachment; filename="snapshot1.jpg"
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to owner-nfc-sc01@fusion.gat.com using -f
X-Sender: keahey@localhost
Date: Tue, 02 Oct 2001 13:44:04 -0500
To: Mary Thompson
From: Kate Keahey
Subject: Re: Soliciting input for the information visualization
component
Cc: nfc-sc01@fusion.gat.com, Keith Jackson
Sender: owner-nfc-sc01@fusion.gat.com
Status:
Mary,
great input! What I originally discussed with the people implementing
this was that there would be some symbol for a (super)computer and
(maybe) a legend. Then if you want to find out more you move your mouse
curson on thop of that symbol and it would visualize load information,
free memory, etc. Then hopefully you could drag this "expanded" image to
the bottom of the display and track the ones you are interested in. In
your comments below do you mean:
load factors: is that the cpu utilization? I was thinking number of
utilized nodes, and per node cpu utilization, disk space, available
memory. What characteristics exactly do you mean by "load"? (It will be
very hard to add them later as this deals with screen clutter etc.)
grid monitoring: the idea in this app is that when you are running it
you can visualize all the stuff that's happening with Globus and was
instrumented to use this application (we'll be running a bunch of
demos), or you can run it with an option that will restrict the
information visualized (to show the Fusion demo only).
>>At 09:46 AM 10/2/2001 -0700, Mary Thompson wrote:
>>This could be a good Grid demo/monitoring system, if we could display
>>the real-time load factors on the 4 LBL grid nodes and the ANL cluster.
>>Depending on how the ifoviz is implemented, we could put the necessary
>>software on all our Grid nodes to report current load factors. Then the
>>map could display 4 compute nodes at LBL and the cluster at ANL with
>>some sort of graphic (bar chart) that indicated loads. When we ran a
>>demo we should be able to see an increase in the load factor on one of
>>the nodes. When the other booth ran a demo, both booths would see the
>>increased use. We can also observe the back ground load at LBN before
>>starting a computation and choose the least busy node. We may need to
>>artifically increase the load (and data transfer) imposed by our demo to
>>make it visible. Or maybe like you are suggesting we would need an
>>indication that our app is running on a node, separate from the
>>loadfactor.
>>
>>We will have one machine/monitor devoted to the DOE Science Grid. When
>>it is not being actively used for the Fusion or Cosomology demos,
>>running a Grid Monitoring graphic would be great.
>>
>>Mary
>>
Kate Keahey wrote:
>
> All,
>
> Below is an excerpt describing the infoviz component for the demo that I
> sent out some time ago. I did not receive any suggestions about what we
> would like to visualize. If you have ideas about either the static or the
> dynamic information you would like to see there, please send me mail by
> tomorrow. My current ideas are
>
> a) dynamic features: visualize control transfer, data transfer (do we need
> to make that difference?), and change of state in an app on a resource
> (computing, not computing)
> b) static features: resources (disk space) and network links between resources
>
> Any other things? It would make sense to visualize the disk space
> especially for the data server, would it make sense to visualize other
> things (such as os, processor type, etc)? If you want to have input into
> this, now is the time to send me mail.
>
> >2) Infoviz component. There is a person in our group who is currently
> >working with the Futures Lab on developing such component. The component
> >will visualize computation and data transfer across the map of the US. It
> >is still being designed but chances are it will be something like this.
> >The moving data will be visualized as a series of dots moving between two
> >destinations (faster for faster bandwidth), the computing resources will
> >be say represented by some static information (such as number of
> >processors, available memory, etc), and the computation itself will be
> >mapped to some of those nodes. At least this is the current thinking, this
> >is very much work in progress which means that (1) it is not there yet (2)
> >we could have some input. Let me know if you have suggestions/ideas; not
> >all of them can be implemented (at this point) since this component will
> >be shared across many demos and has to accommodate the most popular set of
> >functionality, but I will try. The interface to this component is a bit in
> >a flux right now, but it will probably be something along the lines of a
> >message periodically sending information (during a transfer) about how
> >much data was sent. So once we have something working and also once the
> >interface is better defined we can think about integrating it into our
> >demo. At this point, it seems like the esiest way to do that would be to
> >use GridFTP (instead of Globus io) for data transfer. Doing this would
> >probably entail using the new version of Globus, etc,so there are some
> >issues here we should discuss.
>
> __________________________
> Dr. Kate Keahey
> Math & Computer Science Div.
> Argonne National Laboratory
> Argonne, IL 60439, USA
> (630) 252-1673
>
> ===============================================================================
>
> This message was sent to the SciDAC National Fusion Collaboratory (NFC)
> workers list nfc-sc01. Visit the Collaboratory at
> .
>
> To unsubscribe from this list, please send a message to
> majordomo@fusion.gat.com with the following text in the *body* of the
> message: unsubscribe nfc-sc01
>
> David P. Schissel:
--
---------------------------------------------------------------------
Mary R. Thompson
Distributed Security Research Group (510) 486-7408
Lawrence Berkeley National Lab http://www-itg.lbl.gov/~mrt
----------------------------------------------------------------------
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-sc01@fusion.gat.com using -f
Date: Tue, 02 Oct 2001 09:46:12 -0700
From: Mary Thompson
Organization: LBNL
X-Accept-Language: en
To: Kate Keahey
CC: nfc-sc01@fusion.gat.com, Keith Jackson
Subject: Re: Soliciting input for the information visualization component
Sender: owner-nfc-sc01@fusion.gat.com
Status:
This could be a good Grid demo/monitoring system, if we could display
the real-time load factors on the 4 LBL grid nodes and the ANL cluster.
Depending on how the ifoviz is implemented, we could put the necessary
software on all our Grid nodes to report current load factors. Then the
map could display 4 compute nodes at LBL and the cluster at ANL with
some sort of graphic (bar chart) that indicated loads. When we ran a
demo we should be able to see an increase in the load factor on one of
the nodes. When the other booth ran a demo, both booths would see the
increased use. We can also observe the back ground load at LBN before
starting a computation and choose the least busy node. We may need to
artifically increase the load (and data transfer) imposed by our demo to
make it visible. Or maybe like you are suggesting we would need an
indication that our app is running on a node, separate from the
loadfactor.
We will have one machine/monitor devoted to the DOE Science Grid. When
it is not being actively used for the Fusion or Cosomology demos,
running a Grid Monitoring graphic would be great.
Mary
Kate Keahey wrote:
>
> All,
>
> Below is an excerpt describing the infoviz component for the demo that I
> sent out some time ago. I did not receive any suggestions about what we
> would like to visualize. If you have ideas about either the static or the
> dynamic information you would like to see there, please send me mail by
> tomorrow. My current ideas are
>
> a) dynamic features: visualize control transfer, data transfer (do we need
> to make that difference?), and change of state in an app on a resource
> (computing, not computing)
> b) static features: resources (disk space) and network links between resources
>
> Any other things? It would make sense to visualize the disk space
> especially for the data server, would it make sense to visualize other
> things (such as os, processor type, etc)? If you want to have input into
> this, now is the time to send me mail.
>
> >2) Infoviz component. There is a person in our group who is currently
> >working with the Futures Lab on developing such component. The component
> >will visualize computation and data transfer across the map of the US. It
> >is still being designed but chances are it will be something like this.
> >The moving data will be visualized as a series of dots moving between two
> >destinations (faster for faster bandwidth), the computing resources will
> >be say represented by some static information (such as number of
> >processors, available memory, etc), and the computation itself will be
> >mapped to some of those nodes. At least this is the current thinking, this
> >is very much work in progress which means that (1) it is not there yet (2)
> >we could have some input. Let me know if you have suggestions/ideas; not
> >all of them can be implemented (at this point) since this component will
> >be shared across many demos and has to accommodate the most popular set of
> >functionality, but I will try. The interface to this component is a bit in
> >a flux right now, but it will probably be something along the lines of a
> >message periodically sending information (during a transfer) about how
> >much data was sent. So once we have something working and also once the
> >interface is better defined we can think about integrating it into our
> >demo. At this point, it seems like the esiest way to do that would be to
> >use GridFTP (instead of Globus io) for data transfer. Doing this would
> >probably entail using the new version of Globus, etc,so there are some
> >issues here we should discuss.
>
> __________________________
> Dr. Kate Keahey
> Math & Computer Science Div.
> Argonne National Laboratory
> Argonne, IL 60439, USA
> (630) 252-1673
>
> ===============================================================================
>
> This message was sent to the SciDAC National Fusion Collaboratory (NFC)
> workers list nfc-sc01. Visit the Collaboratory at
> .
>
> To unsubscribe from this list, please send a message to
> majordomo@fusion.gat.com with the following text in the *body* of the
> message: unsubscribe nfc-sc01
>
> David P. Schissel:
--
---------------------------------------------------------------------
Mary R. Thompson
Distributed Security Research Group (510) 486-7408
Lawrence Berkeley National Lab http://www-itg.lbl.gov/~mrt
----------------------------------------------------------------------
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to owner-nfc-sc01@fusion.gat.com using -f
Date: Tue, 2 Oct 2001 09:29:24 -0800
To: nfc-sc01@fusion.gat.com
From: "David P. Schissel"
Subject: Graphics Artists for SC01 Poster and Handout
Sender: owner-nfc-sc01@fusion.gat.com
Status:
All,
I have secured the time of one of our graphic artists to
help create the one-page handout and the large size poster
that will be used in the LBNL booth.
Mary - Can you get me either the exact dimensions or at least the
range of allowable sizes for the poster.
The one-page handout will have some generic description on the
front and on the back some words about our demo.
The first page generic description should be able to be used
at other meetings. For example, the APS/DPP meeting at the
end of October.
My intention is to create a draft of both the handout and poster
and place them on our web site for comments.
Regards,
David
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender
to owner-nfc-sc01@fusion.gat.com using -f
X-Sender: keahey@localhost
Date: Tue, 02 Oct 2001 07:38:42 -0500
To: nfc-sc01@fusion.gat.com
From: Kate Keahey
Subject: Soliciting input for the information visualization component
Sender: owner-nfc-sc01@fusion.gat.com
Status:
All,
Below is an excerpt describing the infoviz component for the demo that I
sent out some time ago. I did not receive any suggestions about what we
would like to visualize. If you have ideas about either the static or
the dynamic information you would like to see there, please send me mail
by tomorrow. My current ideas are
a) dynamic features: visualize control transfer, data transfer (do we
need to make that difference?), and change of state in an app on a
resource (computing, not computing)
b) static features: resources (disk space) and network links between resources
Any other things? It would make sense to visualize the disk space
especially for the data server, would it make sense to visualize other
things (such as os, processor type, etc)? If you want to have input into
this, now is the time to send me mail.
>2) Infoviz component. There is a person in our group who is currently
>working with the Futures Lab on developing such component. The component
>will visualize computation and data transfer across the map of the US.
>It is still being designed but chances are it will be something like
>this. The moving data will be visualized as a series of dots moving
>between two destinations (faster for faster bandwidth), the computing
>resources will be say represented by some static information (such as
>number of processors, available memory, etc), and the computation itself
>will be mapped to some of those nodes. At least this is the current
>thinking, this is very much work in progress which means that (1) it is
>not there yet (2) we could have some input. Let me know if you have
>suggestions/ideas; not all of them can be implemented (at this point)
>since this component will be shared across many demos and has to
>accommodate the most popular set of functionality, but I will try. The
>interface to this component is a bit in a flux right now, but it will
>probably be something along the lines of a message periodically sending
>information (during a transfer) about how much data was sent. So once we
>have something working and also once the interface is better defined we
>can think about integrating it into our demo. At this point, it seems
>like the esiest way to do that would be to use GridFTP (instead of
>Globus io) for data transfer. Doing this would probably entail using the
>new version of Globus, etc,so there are some issues here we should
>discuss.
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-sc01. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-sc01
David P. Schissel:
**************************************************************************
**************************************************************************
X-Authentication-Warning: apollo.gat.com: majordom set sender to
owner-nfc-workers@fusion.gat.com using -f
X-Sender: keahey@localhost
Date: Mon, 01 Oct 2001 11:56:36 -0500
To: nfc-workers@fusion.gat.com
From: Kate Keahey
Subject: summary of Friday SC01 demo telecon
Sender: owner-nfc-workers@fusion.gat.com
Status:
All,
Below is a summary of issues discussed at the telecon on Friday; my
apologies for sending it out late, busy part of the year. As usualy send
me comments, proposal and disagreement (make the last one violent ;-).
1) Status: Tom implemented an interactive scenario consisting of a
controller, data server, a "pseudoefit" program (to be replaced with
real efit), and IDL-based visulization. The development was carried out
on LBNL solaris machines. Tom and Qian obtained accounts on the datagrid
cluster and Qian installed the efit software there. Qian also got some
Fusion data to Chris so he can see what can be done by way of
visualizing things better.
2) Todo list: we want to try for following for the next week:
1. Tom will install Globized MDSplus on the datagrid cluster at Argonne
and will try to repeat the interactive scenario he implemented last week
with the difference that the "pseudoefit" program will run on the
datagrid cluster
2. Qian will make sure that the version of EFIT for the
demo runs remotely with MDSplus and writes data to the Data Server
through MDSplus
3. After 1 and 2 are completed we will try for a
distributed run with real efit at Argonne and the rest at LBNL
4. Kate will try to get a small demo of the Info viz component
5. Chris will try to come up with some interesting visualization
6. David will set up an SC01 mailing list
3) We will all have a telecon at the usual time next Friday (i will post information soon).
Propose agenda:
- status and where we want to go from here (demo enchancements revisited)
- specific plans for loss of connectivity at SC01 ("backup plans")
- plans for integrating of the visualization components.
We also had an interesting discussion about moving data and GridFTP; I
will try to post more information soon.
__________________________
Dr. Kate Keahey
Math & Computer Science Div.
Argonne National Laboratory
Argonne, IL 60439, USA
(630) 252-1673
===============================================================================
This message was sent to the SciDAC National Fusion Collaboratory (NFC)
workers list nfc-workers. Visit the Collaboratory at
.
To unsubscribe from this list, please send a message to
majordomo@fusion.gat.com with the following text in the *body* of the
message: unsubscribe nfc-workers
David P. Schissel:
**************************************************************************
**************************************************************************
