<html><body><div style="color:#000; background-color:#fff; font-family:times new roman, new york, times, serif;font-size:12pt"><div><span>Kaz, Thank you very much for detailed clarification.</span></div><div><br><span></span></div><div><span>Regards</span></div><div><span>Emalayan</span></div><div><br></div> <div style="font-family: times new roman, new york, times, serif; font-size: 12pt;"> <div style="font-family: times new roman, new york, times, serif; font-size: 12pt;"> <div dir="ltr"> <font size="2" face="Arial"> <hr size="1"> <b><span style="font-weight:bold;">From:</span></b> Kazutomo Yoshii <kazutomo@mcs.anl.gov><br> <b><span style="font-weight: bold;">To:</span></b> Emalayan Vairavanathan <svemalayan@yahoo.com> <br><b><span style="font-weight: bold;">Cc:</span></b> "mosastore@googlegroups.com" <mosastore@googlegroups.com>; "swift-devel@ci.uchicago.edu" <swift-devel@ci.uchicago.edu> <br> <b><span style="font-weight:
bold;">Sent:</span></b> Wednesday, 7 March 2012 8:38 AM<br> <b><span style="font-weight: bold;">Subject:</span></b> Re: [Swift-devel] Torus rank<br> </font> </div> <br><br>Thanks! Zhao<br><br>This is 99.99% guaranteed. Let me explain why not 100%.<br><br>The control system loads personality (e.g. torus coordinate)<br>into memory on each node when they create a new partition via jtag.<br>No operating system runs at that point. The boot loader passes<br>the location of the personality to operating system (CNK or Linux).<br><br>NODE: personality information on node is a binary data of<br>the BGP personality struct; technically _BGP_Personality_t in<br>/bgsys/drivers/ppcfloor/arch/include/common/bgp_personality.h<br><br>Linux creates /proc/personality.sh by reading each member of<br>_BGP_Personality_t for convenience. CNK doesn't provide this.<br><br>If IBM change _BGP_Personality_t, personality.sh can be corrupted.<br>(probably won't happen but we
can't guarantee this).<br><br>Linux also provides /proc/personality, which is a binary structure,<br>so you can can cast it to _BGP_Personality_t, which is more reliable.<br><br>Due to other job pressure, I couldn't maintain all combinations.<br>However, I'm still updating zepto-vn-eval's compute node linux for<br>my kernel work.<br><br>As for the torus hardware rank, I would definitely notice if that<br>gets corrupted because Linux kernel and BGP native MPI heavily<br>depends on personality.<br><br>Thanks,<br>Kaz<br><br>On 03/06/2012 03:22 PM, Emalayan Vairavanathan wrote:<br>> Great. Thank you Zhao.<br>> <br>> ------------------------------------------------------------------------<br>> *From:* Zhao Zhang <<a ymailto="mailto:zhaozhang@uchicago.edu" href="mailto:zhaozhang@uchicago.edu">zhaozhang@uchicago.edu</a>><br>> *To:* Emalayan Vairavanathan <<a ymailto="mailto:svemalayan@yahoo.com"
href="mailto:svemalayan@yahoo.com">svemalayan@yahoo.com</a>><br>> *Cc:* Kazutomo Yoshii <<a ymailto="mailto:kazutomo@mcs.anl.gov" href="mailto:kazutomo@mcs.anl.gov">kazutomo@mcs.anl.gov</a>>;<br>> "<a ymailto="mailto:swift-devel@ci.uchicago.edu" href="mailto:swift-devel@ci.uchicago.edu">swift-devel@ci.uchicago.edu</a>" <<a ymailto="mailto:swift-devel@ci.uchicago.edu" href="mailto:swift-devel@ci.uchicago.edu">swift-devel@ci.uchicago.edu</a>>; MosaStore<br>> <<a ymailto="mailto:mosastore@googlegroups.com" href="mailto:mosastore@googlegroups.com">mosastore@googlegroups.com</a>><br>> *Sent:* Tuesday, 6 March 2012 12:41 PM<br>> *Subject:* Re: [Swift-devel] Torus rank<br>> <br>> Hi, Emalayan<br>> <br>> Emalayan Vairavanathan wrote:<br>>> Hi Kaz,<br>>><br>>> I found the following about tours rank from<br>>> <a href="http://wiki.mcs.anl.gov/zeptoos/index.php/FAQ"
target="_blank">http://wiki.mcs.anl.gov/zeptoos/index.php/FAQ</a> and want to double check<br>>> with you still this information valid.<br>>><br>>><br>>> Torus rank:-<br>>><br>>><br>>> A torus rank is a number identifying a compute node within a<br>>> whole partition. In a way, it is much "nicer" than a pset rank<br>>> since it is unique within a job and it also starts from 0.<br>>><br>>> - A shell script can easily calculate it from other fields:<br>>> TORUS_RANK=`echo $BG_PSETORG | awk "{print \\$1 + \\$2 * $BG_XSIZE + \<br>>> \\$3 * $BG_XSIZE * $BG_YSIZE}"<br>>><br>>> It would be great if you can make sure that the tours rank is unique<br>>> within a partition and always starts from zero regardless of the<br>>>
following.<br>>><br>>> - Partition size (fraction of pset / multiple of psets / both )<br>>> - Platform (Surveyor / Intrepid)<br>>> - Kernel profiles.<br>>><br>> yes, this is true regardless of partition size, platform, and ZeptoOS<br>> kernel profiles(zeptoos, zepto-vn-eval, and the one you use for mosa).<br>> <br>> best<br>> zhao<br>>><br>>> (Note: I am asking this in order to figure out a easy way to deploy<br>>> MosaStore at BG/P at large scale. I did few tests with different<br>>> partition size in Surveyor and it seems the tours rank is unique and<br>>> always starts from zero.)<br>>><br>>> Thank you<br>>> Emalayan<br>>><br>>><br>>> <br>>> ------------------------------------------------------------------------<br>>><br>>> _______________________________________________<br>>> Swift-devel mailing
list<br>>> <a ymailto="mailto:Swift-devel@ci.uchicago.edu" href="mailto:Swift-devel@ci.uchicago.edu">Swift-devel@ci.uchicago.edu</a> <mailto:<a ymailto="mailto:Swift-devel@ci.uchicago.edu" href="mailto:Swift-devel@ci.uchicago.edu">Swift-devel@ci.uchicago.edu</a>><br>>> <a href="https://lists.ci.uchicago.edu/cgi-bin/mailman/listinfo/swift-devel" target="_blank">https://lists.ci.uchicago.edu/cgi-bin/mailman/listinfo/swift-devel</a><br>>> <br>> <br>> -- <br>> You received this message because you are subscribed to the Google<br>> Groups "MosaStore" group.<br>> To post to this group, send email to <a ymailto="mailto:mosastore@googlegroups.com" href="mailto:mosastore@googlegroups.com">mosastore@googlegroups.com</a><br>> <mailto:<a ymailto="mailto:mosastore@googlegroups.com" href="mailto:mosastore@googlegroups.com">mosastore@googlegroups.com</a>>.<br>> To unsubscribe from this group, send email to<br>>
mosastore+<a ymailto="mailto:unsubscribe@googlegroups.com" href="mailto:unsubscribe@googlegroups.com">unsubscribe@googlegroups.com</a><br>> <mailto:<a ymailto="mailto:unsubscribe@googlegroups.com" href="mailto:unsubscribe@googlegroups.com">unsubscribe@googlegroups.com</a>>.<br>> For more options, visit this group at<br>> <a href="http://groups.google.com/group/mosastore?hl=en" target="_blank">http://groups.google.com/group/mosastore?hl=en</a>.<br>> <br>> <br>> <br><br><br><br> </div> </div> </div></body></html>