With my work at Fermilab’s HPC department, I help keep several clusters up and running. Our fastest production cluster is called J/Psi and it placed as #308 on this 36th edition of the list. This J/Psi cluster placed as #188 on the list last June. When J/Psi was in burn-in testing, it placed as #110 on the June 2009 list. We have a new cluster not yet in production and undergoing burn-in testing. We ran the Linpack benchmark against it and it is listed as #216 on the list.

Those of you who were at the LISA 2010 conference last week may have sat in on the “Storage Performance Management” presentation by Matt Provost of Weta Digital. He mentioned their five clusters of high performance compute nodes. Those five clusters placed as #462 through #466 on this November list. These same clusters were ranked #279-283 on the list last June. They were listed as #144-144 a year earlier in June 2009.

The one other fact I wanted to note from this current list. Of the top 30 clusters listed, nine of them are DOE (U.S. Dept of Energy) related sites. Being as Fermilab is a DOE site, I’ll point out with pride that 30% of the Top 30 sites are DOE research facilities. There are lots of other facts and/or statistics that one can draw from these lists. But these are the ones that are of interest to me.

I encourage you to check out the list. What jumps out as interesting to you? Do you work with or use a system on this list? Or is there some Top … list that your systems are listed on?

I’m pleased to see different things being mentioned on Twitter. I’m very pleased to see that the LISA’10 web page lists the #lisa10 tag right at the top. I know that I found Twitter to be quite useful at the conference last year. I have a #lisa10 tag search column defined on my TweetDeck client.

I firmly believe that the “Hallway Track” is one of the most valuable things about a LISA conference. It is no surprise to me that when they listed “reasons to attend” right there on the first web page, they list “Face Time with Industry Leaders” as their first reason. I have been able to sit and chat with a number of the people who teach tutorials and write the books that we all read. I’ve learned that these folks are quite approachable. I’ve offered some detailed feedback to a few of the presenters after I sat through their sessions. They appreciated the constructive comments that help them polish their presentations.

I’m particularly looking forward to connecting face to face with several friends I have met through Twitter. I met Matt (@standalone) on twitter before the conference. I attended his BoF session on Blogging. I believe Matt will be leading the Blogging team for this year’s conference. It was great to get to know him in Baltimore and I look forward to seeing him again in San Jose. There are several other folks I met in Baltimore and I’m not sure how many of them I will see again next month.

For me, it is the people that I meet and get to know at the conference that make it so very valuable. I’ve attended many of these since my first back in 1995. It gets a little easier to choose training sessions and Workshops when I can look at the lists and say “I’ve already been in Tom Limoncelli’s (@YesThatTom) Time Management class“. That leaves me open this year so I can attend the Knowledge Management workshop on Monday morning, led by Mark Burgess.

I will be leading two BoF (Birds of a Feather) sessions again this year. I’m repeating the two I did last year. The first is a GPG Key Signing BoF and the second is a CAcert BoF, both on Tuesday evening. I will be submitting more detailed descriptions for both of these soon. And I plan to put up some added comments and instructions for those who plan to attend.

I recently came across another Blog post that confirms everyone’s need to be concerned about the new Facebook privacy (or should we say lack-of-privacy) policies. Check out Dan Raine’s post called “I Know Everything About You from Your Email Address“.  Dan’s posting offers a link to an article at Wired.com entitled “Rogue Marketers Can Mine Your Info on Facebook” discusses how truly scary it is when you look at how much information people can collect through Facebook under their new privacy poolicies.

I respect that Dan is up front and honest about what information he collects about people who visit his site.  And I see the red flag that he points out.  There is so much information that is so easy to collect now that Facebook has changed its default settings making more of every users publicly accessible, unless you the user go in and change those settings.

Perhaps a good part of why I enjoy his stories is that it seems like he comes from “my people”.  No I’m not from Minnesota and he’s not from Illinois.  But we both come from good Lutheran traditions.  There’s lots of Germans, Norwegians and Swedes in our history.  We both have fond childhood memories of church potlucks, large family gatherings and growing up in public schools with unique personalities all around you.  We both love the fact that when you sing in a Lutheran church, there will be people singing all four voice parts and that’s Okay.  One of my favoirite parts of this program was when he was wondering around the Minnesota State Fair and talking to people about one of his favorite rites of spring, Rhubarb pie.

I think the part that I most appreciated tonight was his love of writing.  He was an English Major in college and I believe he even got a Masters Degree in English.  He mentioned one of his early jobs in radio where he would play music like big long symphonies. Then he could write while the music played and just have to turn on his microphone to tell the listeners what it was they had just heard or were about to hear.  He enjoyed that in part because of the time it gave him for writing.

I have aspirations of doing more writing. I have a variety of blogs that I keep.  Most are not updated often, but I do enjoy writing when I make time to do so.  I want to make more time for writing.  It takes a different kind of thinking than what I do all day where I work.  Oh, there is some creative thought that goes into the problem solving, programming and customer support things I do at my job.  But writing requires that I try to let my creative side out for more of  a long walk rather than just a quick trip to the mailbox.

So what drove me to write this long note.  It was a part of this program where Mr Keillor was talking to a group of students about writing that piqued my interest. Part of what he said was:

“You start with what you know.  But writing is a process of discovery.  It is not as if we are taking a (photo) plate out of our head and laying it down on paper and printing from it.  We’re not. Writing is an act of discovery.  And the moment you start, with a character or maybe with yourself,  and you learn about that character by writing about that character and you wind up in places that you never thought you were going to go.  That’s the whole reason for writing, is for discovery. You do not know what you yourself think, until you put it into words.”

It seems like many of the things in my life are changing.  The kids are out of the house, one in an apartment and one in a college dorm.  My wife and I are reconnecting as we learn to live in an empty nest.  My position at work changed significantly last year.  And I’m dealing with a few new health challenges.  And on the plus side there are 30 pounds less of me than there were 6 months ago.  This is a time of adjustment and discovery for me.  I look forward to seeing what writing can help me discover.

I am one of those people who reads those privacy agreements. It is not because I enjoy legalize or boring documents.  It is because these documents tell one more about what privacy you give up when you agree with them, than they tell about how your privacy is protected.  I am particularly troubled by the changes at Facebook this week.  This morning, they initiated new changes to their privacy settings. They warned us this was coming.  But what I have seen so far has not been very clear about how these changes affect your privacy.  And I believe we all need to look carefully at this.  To be fair, they did put up a decent page to explain the new choices, but it is only a good start.

Hopefully you have visited the Facebook privacy settings area, where you can adjust how much of your information is visible and who can see it.  If you have never changed those settings from their defaults, you were probably sharing more information that you thought you were.  And if you have agreed to allow various applications to have access to your information, then your information is almost certainly more public than you thought.

What data are we talking about sharing

I expect most of us have a profile picture up and maybe your birthday, the name of your significant other, your home town and/or one or more phone numbers. That’s not a bad thing as long as it is only shared with those you choose to share then with.  I have all that information and more, but I am careful to make sure that only my acknowledged Facebook friends see this.  I had to adjust the default settings for this limited privacy.  Now even if I go in today and select “old settings” for my new Facebook privacy policy, there are things shared now that were not shared before.

Facebook’s new “privacy policy” now defines the set of publicly available information to include: Name, Profile Picture, Gender, Current City, Networks, Friend List, and Pages.  These are bits of information that you can not restrict access to by any means short of not sharing it with Facebook.

There are other things which you do get to decide who does and does not get to see it.  These include your birthdate, your family and relationships,  your education and work information and any phone numbers you have listed.  And from my perspective, the biggy is that Facebook wants to make all your status updates public. I don’t mind my friends seeing all this, but I don’t want it all publicly searchable.

I know that all my postings on twitter are public and searchable.  But since I know that, I am careful what I post there.  Up until today, I was fairly certain which things I post on Facebook are public and searchable and which are not.

The most important thing to consider is that under the new default basically everything that Facebook knows about you will be publicly available and searchable by places like Google and Yahoo.  The old policy let you choose which information was available only to your friends, or even friends of friends or to friends and a network you may belong to.  If you have set these privacy settings so that your information is only shared with your friends, that will still be true, if you select “Old Settings” when prompted about today’s privacy policy changes.  With some noteworthy exceptions, please read on.

Applications and Websites

I have adjusted privacy settings so that most of my information on Facebook is only shared with those I approve as friends.  The Applications and Websites area (let’s just call this Apps, to keep things readable) allows a Facebook friend to share information through Apps that they have joined. I am unhappy that even though I have said the info should only be shared with my friends, Facebook will by default allow those friends to share the information via Apps that I have not joined myself.  That’s right, by default my friends can share information that I want restricted.  I had to go into the Apps area under privacy settings to change this and restrict that data, that I already thought was restricted.

Consider carefully when you do join applications on Facebook.  Most of them ask if they can access your information so “they can better serve you” or to improve your experience.  I understand that having my information makes them better able to customize my experience.  But when I choose to play chess with a Facebook, friend, I do not think they need access to my birthday or my e-mail address.  Most applications do not let me control or restrict what information I share with them.

Know what you are sharing

So why this big long article?  I want to make you aware of the importance of knowing who has access to what information.  I’m sure most people don’t read those privacy statements.  I think it is important that you make an effort to review your privacy settings.  And as Facebook makes broad changes in their privacy settings, I want to strongly urge everyone to take the time to go through the Privacy Settings section of your Facebook account.  I think you will be surprised at what you find.

If you have questions about what you find, please feel free to post comments here.  If you find something that is now made more widely visible than you expected, please post that in a comment as well.  Perhaps you will find something that I missed.  Or maybe someone else will read this and find something they had not thought to look at.

Thanks for taking the time to read this far.  I try to keep my Blog posts shorter than this.  But our privacy (mine and yours) is worth a little extra effort.

For those who may not be familiar with the whole FollowFriday concept, I’ll recommend you read an article by Sharon Hayes-Tucci entitled “FollowFriday on Twitter“.  I’ll also offer this brief example (posted via my @n9kju twitter account today).

#followfriday @jordansissel and the SysAdvent Blog (http://sysadvent.blogspot.com/)

The #followfriday hashtag marks this as suggestions for others that you might consider following on Twitter.  If you visit the profile of the username(s) suggested (ie. @jordansissel) you can check to see if this is a twitter user that you might want to follow.

I’ve not seen anyone else tweet to suggest a blog for following. I want to suggest a blog that you should consider following.  Tweets are limited to 140 characters and that’s hardly enough to properly suggest the SysAdvent Calendar Blog.  But by posting this FollowFriday blog suggestion in my own blog, I overcome that limitation.

So what is this SysAdvent Calendar Blog.  Jordan Sissel created the Blog last year (2008). There have been perl advent calendars in years past. The idea was to put out one blog post each day starting Dec 1rst and then for the next 25 days.  This is just like an Advent calendar that you may have had in your house when you were growing up.  At my house, my siblings and I  took turns opening one door on the Advent caledar each day.  Last year, Jordan offered to take postings from other SysAdmins, but he ended up doing almost all the writing himself.  This year, Matt Simmons has been helping contact other SysAdmins to seek submissions for this years calendar.

Each article is written to focus on a single, somewhat-specific idea related to systems administration.  The target audience is the intermediate or senior level SysAdmin.  Having said that, I know that they hope to have at least one posting by a junior SysAdmin this year.

When you do visit the SysAdvent Blog, you will find the most recent posting listed first and older entries are sequenced below that most recent entry.  In fact, if you keep going down the list (back in time) you will find the 25 articles that made up last years inaugural version of the SysAdvent Calendar.

I think this is a really great idea.  I’ve enjoyed browsing through many of the posts from last year.  And I look forward to reading new posts as they come on-line this year.

Please let me know if you find this sort of Blog following article helpful.  I follow a quite a few and I expect several of them would be worthy of a FollowFriday Blog article.

One of Chris’ tweets was to a neat blog post by @deepakdas.  The author shared his thoughts on Google’s “product proliferation strategy”.  It reminded me of the old days when people talked about how Apple computers were in all the schools in hopes that student’s would graduate having experience with Apple and buy those over PCs.  It also reminded of another strategy I had discussed several months ago.  That one was focused on Starbucks Coffee.

I was sitting with a friend who works for a distributor that delivers product to Starbucks stores.  My friend explained to me that Starbucks had a goal to (as she put it) “become your third place”.  I’ve heard this same idea elsewhere, so I’m sure it is no secret and it may be a topic for various case studies.  The basic premise is this:

We all spend time in various places.  The top two places for most people are their home and their work.  If you count the time spent sleeping, most people spend most of their time at home.  And it is easy to see that where you work would be the next most common place for you to spend your time.  There may be a third place which stands out as the place where you spend the next most significant portion of your time.  The idea is that Starbucks wants you to be so comfortable meeting people or just hanging out at a Starbucks store.

Personally, I believe my church is my third place.  But I must admit that Starbucks must be in my top ten.  And at the same time, I think Google (Gmail, GoogleWave, Google Reader, etc.) is very likely my forth place. OK, so it is not a physical place, but it is where I spend a bunch of time. On the whole, Google is obviously trying to move up everyone’s list of “places” where we spend our time.  They are adding services constantly and getting themselves inserted into as much of our on-line experience as possible. (Look at today’s announcement of Google’s Public DNS service)

So Twitter has once again led me to some valuable information on topics that I am already thinking about and trying to understand.  I suppose that TweetDeck is another of my top 10 “places” where I hang out.  I wonder how long it will be before Google tries to buy up Twitter.  Or might they just find a way to assimilate it into Google Wave.

Where do Google and/or Twitter fall on your list? Your thoughts and comments would be appreciated.

How should I  decide who to block and who to report as SPAM?

I suppose in part, the answer to the question depends on how and why I use Twitter.  One has to ask who do I hope my tweets are getting too.  I have a network of friends, peers and community members.  I found Twitter quite valuable at events like the recent #LISA09 conference. And I have met some really great contacts through Twitter.

I read nearly every tweet that comes to my TweetDeck screen. It keeps me up on what’s going on with those I follow. And it keeps me up on news and hot topics. I’ve learned a lot since joining Twitter.  Mostly by following very interesting folks like @CaliLewis, @Pogue and @ChrisBrogan.  I keep up on #HEP (High Energy Physics) by following @CERN and @USLHC.

I’m sure that folks @ThinkGeek want followers as a way to promote their products to as many people as possible.  I understand that.  It is good marketing.  And I follow them back to watch for sales.

At present, I have no commercial interest in Twitter.  My blog generates no income and I have no affiliations that bring me any sort of compensation.  Still, I’d like to think that by tweeting each new Blog post I may pick up some new followers, or the Blog or my tweets.  I do appreciate when someone finds a Blog post interesting enough to mention in a tweet to their followers

I am careful about who I do and do not follow on Twitter.  I do not automatically follow anyone who follows me.  I do not even check the profile of everyone who follows me.  I do not see the numbers of how many I follow or how many follow me as at all significant.  Am I unique in my careful approach to followers?  It certainly seems that minority of the Twitter users  who follow me are in it for a numbers game.  I can’t believe they read every post by everyone they follow.

I have blocked people whose follower count is up in four digits while there posts are counted with one or two digits.  I have reported some people as SPAM when the majority of the posts I find on their profile are obviously sales hype. But I don’t have time to review everyone who starts following me.  Some who follow me are disabled by the time I go to check their profile after others reported them as SPAM.

I have used tools like @Foller.Me to help me prune my followers. I can’t get to TwitBlock any longer.  I just wonder if even that is worth my time. I expect to write a blog post on SPAM fighting tools some time soon.  I’d love to hear what your favorite such tool is.

How do you decide who to block and who to report as SPAM?  Please share your opinion via a comment.

The National Labs here in the US are well represented.  The Jaguar Cray XT5 Supercomputer at the Department of Energy’s Oak Ridge Leadership Computing Facility  is the new #1.  Jaguar has bumped the  Los Alamos Roadrunner system down to the #2 slot.  Note that the Roadrunner was the world’s first petaflop/s supercomputer,  topping the June 2008 list. These ratings are based on Linpack benchmark results.

Let’s talk about what makes a supercomputer.  Back in the day, a big monster computer was more often than not a large IBM Mainframe.  It was one computer with lots of hardware that could do lots of processing and talk to lots of users through lots of terminals.   It was designed for size, not speed.  In 1960, Seymour Cray designed the first supercomputer, engineered  for high capacity and high speed processing.  Today’s supercomputers are sometimes a large system like Jaguar, a Cray XT5.  But more often todays supercomputer is actually a large cluster of smaller systems, configured and tuned for tightly coupled multi-processing cluster performance.  An example would be the rendering farms that were used by Weta Digital for CG work on films like the Lord of the Rings.  They have five cluster listings around #195 on the current TOP500 list.

I work at Fermi National Accelerator Lab in the HPC (High Performance Computing) department.  We support several experiments, primarily the LQCD project.  LQCD stands for Lattice Quantum Chromodynamics.  Lattice QCD calculations allow us to understand the results of particle and nuclear physics experiments in terms of QCD, the theory of quarks and gluons. The 7N cluster at JLab is also used by this collaboration.

I get to work as part of a team supporting Fermilab’s HPC systems which are  used for running large scale numerical simulations.  Our J/PSI cluster is made up of 856 nodes, each running an instance of Linux.  They each have two 2.1 GHz Quad Core Opteron processors.   That’s 6720 cores altogether, tightly coupled with a double data rate Infiniband switch.  Our Linpack results were 37.42 TFlops maximal performance achieved.  That put our cluster at #141 on the TOP500 list published earlier this month.  On the list that was published just 12 months ago, that same result would have placed us as #69.

Supercomputing and HPC in general can be  a mind boggling field.  I’m fairly new to this arena having only started with this department about 12 months ago.  I find this stuff pretty exciting.  We expect the J/PSI cluster to more than double in size in the next 12 months.  I can’t wait to see what the next year brings.

More later,

Ken S.

http://claimid.com/bestpractices

Now while I did not know that the page existed, I was aware of some of these tips. I have had Google Alerts searches in place for over a year now. Not just searching for my own name, but also for my wife and two kids. I first learned that my wife set up a page at LinkedIn because of the Google Alert. And of course I quickly checked that it really was by her and about her. Whether or not you use ClaimID, running such searches on a regular basis are an important step in protecting your on-line identity.

And if you own a domain, don’t forget to check regularly to see what the search engines have that is pointing to your domain. Regrettably, when I search for SmallieFishing.com, I get hits on every page/article that discusses Smallmouth bass fishing. I guess that with my domain name, that’s not a bad thing.  I do need to keep up on that topic.

The ClaimID Best Practices also has a nice description of ways to improve a search by changing your search string. And while I rarely use search engines other than Google, they do give a good list that you can use.

One would think that a lot of these best practices would obvious just as good common sense. But even those of us who are interested in on-line identity protection can learn a new trick. You would think that as much as I depend on a spell checker, I would think of the value of searching for things by using common misspellings. While you may not get any interesting hits this way, I’d rather not miss something just because I assume everyone knows how to spell my 10 character last name.

If you have a suggestion for another best practice that could be applied here, please leave a comment. You might also consider e-mailing it to the ‘info’ at ‘claimid.com’ address.  Their page does say that will keep this list of best practices updated.   Pages like this are a very good thing.  And let’s not forget that the internet is more valuable when we all share our best practices.

More later, Ken S.