Plus ca change, plus c'est la meme chose

The more things change, the more they stay the same. My former employer (left on good terms, between layoffs a decade ago next month) SGI has layoffs coming.
This is a tough environment folks, a very tough environment. We pulled out a nearly 12% revenue growth in it. SGI posted a profit, but if you click through to the underlying article (hit InsideHPC first though), you see some interesting analysis. First on the size of the layoff.

If you assume a fully burdened cost of an employee to be roughly $150k (that includes benefits, salary, everything), then a 90-day severance could be somewhere in the neighborhood of $50 ($150k / 4 = $37.5k, then add a bit for padding and insurance). At $6.6Million, that?s over 130 employees.
Looking back at their final quarterly filing for 2010, you can get some rough numbers on their employees (Search for ?headcount?):
Manufacturing: 581 people
R&D: 278
Sales & Marketing: 247
Administrative: 193
Total: Around 1300
That means they just axed 10% of the company. That?s more than a little trimming, that?s pretty substantial reorganization.

The assumption may be wrong on the burdened costs though, and its possible projects are being shuttered/written off. And these are speculation, but the article author is probably in the right order of magnitude, I’d even argue that the first digit may be correct within a factor of 2. His analysis is not a function of the first digit, but comparing the order of magnitude to other known quantities. The subsequent Register article does suggest that this analysis is correct.
Then on UVs …

Read morePlus ca change, plus c'est la meme chose

The spork gains support

This is goodness. Really. Peter Jones just sent out an email to the Lustre Discuss list, and it covers much of what i was hoping to see. Process ownership, agreement around the release for 2.1, central tracker, and build info. Yeah, its probably not the optimal outcome, but its a better place than we were … Read moreThe spork gains support

Interesting FUD floating about

One of our competitors, having been recently purchased by a very large storage company, seems to be telling some customers that they replaced an infrastructure that we sold to to a large supercomputer center in the northern midwest. Curious, I hadn’t heard of this. Last I checked (a few minutes ago), the infrastructure was still … Read moreInteresting FUD floating about

Cloudy expectations for HPC

I’ve mentioned in the past, where users expectations deviated, often wildly, from the reality of a system. The reason for these deviations of expectations could be internal (convincing yourself that “instant” means, literally, “instant”), external (believing marketing blurbs), or some factor between the two.
At HPCinthecloud, an article on a user running head first into the reality of cloud computing, and avoiding the hype.
Ok, a number of critical take-aways. One is that end user expectations can be wildly … badly … out of sync with reality. I am not criticizing the user here. Just noting that a 2ms window to start a new node, and have it provisioned and operational is … well … wishful thinking at best.
Boot time scales (ignoring provisioning) are on the order of 5-60 seconds depending upon the nature of the hardware (physical/virtual) to get to an OS load prompt. OS load itself could take from 5s to a few minutes.
Notice that I haven’t talked about provisioning here, as it is ancillary to the process. Really, provisioning should be done very infrequently, and not part of an “inner loop” in a load balance cycle. You want to boot pre-configured images or bring nodes out of hibernation.

Read moreCloudy expectations for HPC

Old model JackRabbit 5U bonnie++

Previous version of our JR5 unit, in the lab as a test bed for customers. Testing firmware and driver updates, among other things.
Simple bonnie++ 1.96 run. You know I am not a huge fan of this as a load generator, or as a benchmark.
Regardless, here is the output:

[root@jr5-lab ~]# bonnie++ -u root -d /data -s 144g:1024k -f
Using uid:0, gid:0.
Writing intelligently...done
Rewriting...
done
Reading intelligently...done
start 'em...done...done...done...done...done...
Create files in sequential order...done.
Stat files in sequential order...done.
Delete files in sequential order...
done.
Create files in random order...done.
Stat files in random order...done.
Delete files in random order...
done.

Read moreOld model JackRabbit 5U bonnie++

RFPs that request a pony

Yeah, I have one of those in front of me now. The requirements are for all intents and purposes, impossible to simultaneously satisfy. Q&A response from customer suggests that they may be willing to compromise some aspects, but not enough to actually satisfy their request. Sort of like “I want 1 PB … for free, … Read moreRFPs that request a pony

Pushing atoms versus pushing bits

Cloud computing is driving a disruptive change through a number of market places. It started long before virtualization, but virtualization really enabled much of what we have now.
Remember, at the end of the day, the entire process is economic in nature. Cost per cycle does matter.
When a vendor sells hardware, they are selling all the cycles of that hardware over the usable lifetime of the hardware. They push the atoms at the customer, and let the customer manage the economics of utilization.
When a vendor sells cycles, they are selling what is used. Nothing more. They push bits at the customer, and manage the economics of utilization, without handing this over to the customer.
There are two diametrically opposite views of this. First, if you will have a very high utilization rate for your system(s), then the better cost option is an acquisition of atoms, as the cost per cycle used will be extremely low relative to the cost of buying the same cycles.
The crossover point varies, but we’ve found it to be between 1/10th and 1/5th utilization. So if you use your systems less than say 1/5th the time, it might be more economical for you to buy the cycles and ignore the machines.
Which is having an impact in the market.
Call this a no good deed goes unpunished type moment. Well, no, thats not correct. This is more along the lines of mourning the loss of buggy whips as horse drawn carriages gave way to automobiles.
Basically, computer resellers are discovering that they are have a much harder time … selling.

Read morePushing atoms versus pushing bits