After much work w/ Peter Williams and Con Kolivas, I finally have a decent performing genetic-lib implementation on interbench. It does orders of magnitude better in the burn & compile pieces. What really screws Zaphod and the genetic-lib up is when there is one interactive child running in the background w/ a bunch of threads that are doing while(1) {}. The interactive task does not get classified as such and they miss many of their checkpoints while the cpu hogs run. This latest version has a few bug fixes and detects interactive tasks sooner. The only thing to watch is that with the quicker detection of CPU hogs, a burst of CPU activity on X will get it classified as a CPU hog. Please let me know if you see as such.

I’ve been using interbench a lot lately, and it does an excellent job of catching the “bad children”. I can see almost immediately when some child gets mutated off into the woods and performance tanks. Con did a great job with the benchmark.

I just got back from vacation in Cozumel. The vacation was much needed and I feel 100x better. A full tank is going to be needed as this is going to be a very hectic month.

One of the things I noticed is how slow life moves there. With the exception of the taxi cab drivers, people were content in just hanging out staring at the ocean.

An interesting fact I learned was that up to a few years ago, the Mayan people were isolated and had no concept of money. They just had to worry about finding their next meal. They also had the lowest rate of heart disease in the country. Now, they are starting to be concerned with things such as buying cars and luxury items. They have already started seeing a rise in heart disease.

Sorry, for the limited updates on the blog and genetic-library. Between trips to Europe, OLS paper/presentation, high IBM workload, putting TicketShuffle.com back up, looking at real-estate investments, and other ventures, it has been a busy summer. Let’s not get into the fall w/ Business school starting up.

After OLS, I am hoping to integrated plugsched into the genetic-library, and start on the workload fingerprinting. Doing workload fingerprinting will enable reintroducing good genes from previous workloads back into the gene-pool. It should hopefully speed up the convergence on optimal solutions quicker.

Rebasing the genetic-lib to 2.6.12 is also high on the priority list. I did a quick update of the AS component, but I am not seeing the same type of results that I did on 2.6.11. I’m wondering if a performance counter is not getting updated appropriately. That usually breaks the genetic-lib quickly.

Steve Jobs gave an excellent commencement speech where he said something that made an impression on me:

I have looked in the mirror every morning and asked myself: “If today were the last day of my life, would I want to do what I am about to do today?” And whenever the answer has been “No” for too many days in a row, I know I need to change something.

Is there any better barometer of when it’s time to change?

Even though when I look in the mirror, I do not say “No” too often, I know that I will not be a programmer all of my life. One reason is due to the commoditization of developers, the other is the desire to have more than IBM (or any company) can offer even the best of developers.

I am not sure if the reason why I do not say “No” more often is due to knowing that I am working towards my long-term goals via MBA school, or if I know that I need to enjoy this stage of my life as a programmer since it will not last forever.

I arrived in Germany yesterday and got my first experience of actually driving on the autobahn. I am regretting not getting a faster car.

Things that impress me in Germany:

- The bier
- The German’s ability to recognize Moilanen is a Finnish name
- The fast cars
- Their English speaking proficiency
- The cleaniness of everything

Update: I have maxed out my car at 205 km/h (127 mph). That was with it floored and going down hill (maybe even a tail wind). I am still kicking myself for not upgrading. At least I am able to drive w/o white knuckles at about 170-180 km/h (105-112 mph).

Mine is time. With more and more people vying for bits of it, I have realized that time is a finite resource, and should be cherished. In the last few years, I have noticed a fundamental difference in how I think. I the past I valued money above time. I would rather spend a day putting in a garage door opener rather than paying someone $60 to do it. Now, $60 for a free day sounds like a great trade off.

That’s not to say I just throw money around to save my time. I don’t mind spending an extra hour negotiating a car salesman to save a $1,000 (plus I find it enjoyable). The trade off of how much money saved versus how much time it took must always be made.

There are other in-tangible commodities that the time trade off should be made. Mainly, relationships. It is very important to take time to maintain relationships as they are what will get you through when times are tough. They are also one of the greatest assets. Having a friend that knows a friend goes a long ways in developing a career or a business.

The final time trade off that I am always making is an emotional investment. To keep from burning out and experiencing the time-loss that goes along with it, methods of decompressing must be constituted. Some people use television, others use sports. Whatever method is used, the recreation trade off goes a long way.

Update: As one co-worker pointed out, I am probably not old enough yet, but in time, my most valued commodity will probably change to health.

I have managed to do it again. I’ve overloaded myself w/ too much to do, with too little time. Thankfully my biggest near-term concern is nearly complete. My OLS paper is almost finished. The paper is on the genetic-library in the Linux kernel. It will be very useful for people to learn about the genetic-library and hopefully show how beneficial it is.

The biggest problem I have encountered is a regressions in performance results on the Zaphod CPU plugin. I was getting only 1%. Thankfully, my co-author, Peter Williams, was able to track down a bug in the run-delay calculation, and get the results back up to the >3% that I was originally seeing. I also noticed a trend towards the Zaphod plugin doing very well in higher CPU loads.

The best news I have gotten from doing this paper is stellar results in the Anticipatory I/O scheduler. On average, I was seeing 8.72% improvement, and up to 23.22% improvement in the random write workload.

The next thing I need to look at is a combination of RAID’d and unRAID’d disks. I was seeing huge fluxations in results on Anticipatory (which should not be used on RAID’d disks in the first place). I am theorizing that because the genetic-lib is per I/O scheduler, that it bounces back and forth for tuning for the individual SCSI disk, and then tries tuning for the RAID’d disks. Which one is tunes for depends on which one is getting more I/O. I will have to granularize the genetic-lib to operate on a per-disk basis. Thankfully there has been some support put into the kernel recently.

Watch http://linuxsymposium.org for updates.

I will hopefully have some time to do some more development work on the genetic-library soon, and a new version coming out soon.

As I walk down the streets of Barcelona, I see another poster of Vin Diesel, a Starbucks on every corner, and that Britney Spears has a new perfume. With so much of the United States culture being adapted in the world, I was left pondering what was the cause of this effect? Was it companies wanting to globalize and increase their market size, or is it the cultural elitist who believe that the western culture is to be desired?

I believe it is the synergy between the two. Because many foreigners looked to the United States as a land of opportunity, the western life and culture is appealing. Companies recognize that appeal, and market towards it.

There is one major industry that contributes more towards the Americanization than any other, named Hollywood. They sensationalizes western culture through their barrage of films. With the constant exposure of the west, there is no wonder what kind of affect there is on international culture. The cultural elite iconify this glorified view of the United States (Note: most Americans iconify hollywood as well, but that’s another blog)

As much as I agree with capitalism, I believe its affect on culture is a detriment to the world. One of the great things about diverse cultures is all of the different viewpoints. If the whole world had the same view, creativity would be stifled and new solutions to problems would never be created.

Now that I am in Spain, and having to work with a number of second-language English speakers, I have found that I speak way too quickly. Or rather they have told me so. So in an effort to actually communicate, I am making a conscientious effort to speak very slow. Painfully slow. While the people I work with are very good English speakers, their glazed eyes give away when I start talking fast again.

I have also found that I must limit my vocabulary considerably and I can not use any of my clever play-on-words (who said I did this to begin with). Now without my insatiable wit, I feel reduced to a person who can’t figure out what they want to say, nor can use anything but single-syllable words. I feel dumb when I speak.

I just arrived in Spain for two weeks of work. Hopefully I’ll have a chance to see something besides the inside of a computer lab.

One of the things I enjoy most about visiting a country for the first time is seeing all the different ways something can be done, and trying to figure out what something is supposed to do. It’s also a little humbling when it takes you 5 minute to figure out how to turn on the lights.

Notes so far:

I’m glad I’m not claustrophobic.

Taxi cab drivers know the words to American songs I’ve never heard before.

Even the “Second nicest hotel in Barcelona” can have paper-thin walls.

Tipping 20% is a HUGE deal.

A whole hotel can share one DSL connection.

I talk too fast.

Three cars can fit across two lanes.

A cup of coffee is really a shot of espresso.

America could be more environmentally friendly.

Spain is beautiful.