Иконописwe give a quote to someone, they see a part number, find a vendor who is selling this at some enhanced discount for any number of reasons, and then ask us to match it. I am guessing that they don’t realize we actually compare our costs to various measures, and make sure our pricing is not out of whack (sometimes our suppliers just can’t seem to give us the same deals they give others, go figure). So we look at the pricing, see that it is a sale of some sort, see that the offer is below our cost and kindly decline. Seems to happen more often than not with one particular OEM (whom shall remain nameless).

I often get emails from posts like this, where another vendor (and quite a few read this blog … go figure) shares their similar experience. I bet I don’t even need to say any more, and 10′s of heads will be nodding vigorously in agreement, and even naming said OEM. I bet most of them know whom I am talking about. Please don’t guess and name them in the comments.

A rule of OEM thumb is you don’t piss off your re-sellers. If you do this enough, they stop being your re-sellers. You help them all, treat em fairly, and don’t play favorites. That is, unless you want them to stop being re-sellers.

Oh, and BTW, we’ve actually signed like 3 more (re-sellers) this month … A major goal for us is to drive lots of business through them. And these lessons that I am learning by watching others succeed, or in this case, #fail, I will try to apply. If our re-sellers are successful, we will be too. Remarkable concept.

Viewed 9582 times by 1081 viewers

I guess this gets Qlogic out of the IB arena. Good catch by Rich at InsideHPC

I had spoken to a number of folks at Intel over the years w.r.t. IB, and they said they were keeping their options open. IB riser boards are available for some of their MB’s, and from what I have seen, Intel has a renewed push into the MB space. Not sure about the server space in general, they’ve always had that and I think they will keep doing this (at least as a reference design basis).

This is good in a number of ways, as Qlogic looked to be treading water on IB (not as invested in this as they could have been).

From our perspective, its good as well, as we are seeing significant amounts of storage go out the door with IB. I like the 10GbE stack, its simpler, but there is no denying that the IB stack is faster and much less costly.

Also, its getting to be a perennial joke that this year is the year 10GbE breaks out and displaces IB. As with every year I hear this, I have to say “no”. When 10GbE switches are down at $100/port for 24 and 48 port units, yeah, maybe. Until then … no.

Understand that I am saying this as someone who prefers the simplicity of 10GbE. OFED is harder and more complex, and we have a rolling patch of install.pl that we apply to every release to make sure the right stuff gets built. The rules they put in for some of the code is pretty darned arbitrary (and I understand some of it, but it prevents people building their own kernels from using OFED, even if the bits work … its far better to include unit tests, build the stuff correctly against the kernel …. sigh … ).

In most cases we don’t need to patch 10GbE drivers, and the builds are very simple.

Regardless of this, IB at Intel is not likely to whither, rather its going to grow. Looking forward to this.

Viewed 13000 times by 1302 viewers

… just received a note indicating that our Gluster Reseller contract was voided, and that we would be seeing a new partner portal for Red Hat Storage coming soon where we could apply again for reseller status.

Hmmm ….

Reading over the information I saw on the Red Hat storage platform, it looks like they are going full on appliance route, which diminishes the value we can potentially add to the platform, and removes much of the differentiation we can do at the stack level (better kernels, up to date drivers, tweaked/tuned drivers/OS, …). Actually, their focus looks like it was laid out in pretty good detail … they are looking to make these effectively “sealed” type appliances.

I think the rationale for this is competition from Oracle, and to some degree it makes sense. But it also changes what we can and cannot do with Gluster. I have a sense that the 3.2.5 release may be one of the last public code drops … this is a hunch, I have no real information one way or another.

I suspect that work on *BSD and Solaris will be wound down (at least in the context of integrating patches for this). I don’t think we will see gluster as a separate product or tarball or … going forward.

I hope I am wrong, but to a degree, this makes sense as a strategy. Acquire a company, and monetize the product, by removing many of the other channels that it could be used with. Unfortunately for us, we got caught up in the newly non-sanctioned use cases. Its being packaged more for a Dell, or another large white box provider to throw storage together.

So 3.2.5 might be the last really publicly available system. Yeah, it is open source, and I am sure you can get it. But its going to be tightly tied to the Red Hat platform. Which isn’t a bad thing, but as a company that works hard at differentiating by replacing and tuning underperforming portions of the stack, mebbe this isn’t as good for us.

Gonna have to think about this somewhat. Some customers have been nervous about this going forward, and I’ve done all I can to get them to wait and see before acting. These changes I don’t see making them less nervous … actually more.

Again, hoping I am wrong. But I have a pretty good history of not being wrong.

Viewed 34985 times by 2318 viewers

Saw this linked from /.. UEFI boot is to be replacing the old BIOS boot. There are positives about this and negatives. New software is always buggy, and UEFI won’t magically become bug free. UEFI has security controls for signed OS booting (ostensibly to protect users).

But the abuse of security systems to exclude competitive/alternative booting … yeah … maybe not such a good idea.

It looks like Microsoft is trying to demand that its hardware ARM partners not enable anything but Windows 8 or an equivalent signed OS (is Android signed?) to run on the system.

As with other systems, I believe this will be eventually cracked, and OS mods will be created for such platforms.

This said, I really don’t expect Windows 8 to manage to make much of a difference in the market. Windows 8 for phones has a commanding … what … 2% of the market? And its not growing very fast at all? Windows tablets? Again, one has to ask “why” ? I really like my iPad2. It is very good. The android tablets I’ve tried, maybe, ok … not so good, but getting better. Still nothing compared to iPad2. The application ecosystem for both are large and growing with very low cost apps available on each.

I can’t imagine a windows pad ecosystem with cheap apps, stable OS, and non-virus infected experience. Yeah the UEFI supposedly will stop a rooted OS from booting. So … get a virus and brick the device. Er … can you say “misdesign”, or “design flaw”, or “abject failure to understand the dynamics of this market” ? I thought you could.

I am not expecting a Windows tablet to fare much better than a windows phone. Actually expecting much worse.

Viewed 34900 times by 2277 viewers

Had to get a Led Zeppelin reference in at least once a year on the blog …

Pathology report came back.

Ok, in the movie series The Matrix, there is a set of scenes where the story tellers want you to believe that the character (Neo in the clip below’s case) was moving with “super-human” speed, and able to move an accelerate a very large mass (their body) faster than a very tiny mass (the bullet). They are trying to evoke a sense of great speed, and potentially high cost of not being able to move fast enough.

This is a metaphor, obviously, for what I am going to write about. Actually all the elements of the clip are a metaphor.

Here is the clip.

So, what happened?

Continue reading »

Viewed 56666 times by 3241 viewers

Its 2-January-2012, and assuming the Mayans’ were wrong (ok technically I’ve not heard of any suggestion they did anything more than stop their calendar on a convenient-for-them boundary), an interesting question is, what has happened to the company-formerly-known-as-Sun’s HPC assets?

Lustre is one of the most well known, and it now has some type of future ahead of it. I’ll talk about that in a later post. This future was most definitely not assured 1 year ago, and there was considerable uncertainty in its longevity as Oracle had, about a year ago, let go most of the developers.

Continue reading »

Viewed 57112 times by 3595 viewers

Bilateral Mastectomy with a sentinel node biopsy. The latter appears to be clean. I can exhale now. Well, mostly. The more detailed pathology data should be ready next week.

The rebuilding part is in process. Another few hours. Readying some good jokes to keep the Mrs. happy. Let her know not to worry.

U of M hospital guest internet is … annoying. Looks like they let 3 TCP ports out to the world (22, 80, 443). Possibly some others. I had to work some VPN magic to be able to send/check email. And of course, the cell phone doesn’t work here (sigh).

[update] And its done. She’s in the wake up room, and once shes done, they’ll move her to the observation area.

Viewed 62731 times by 3840 viewers

A new code golfing site. Gaaaak!

If I have time to work on such diversions, I’ll post mine under the ID numbercruncher.

[update]

Played with the starburst code. Have something that works (though they failed to specify their input method, or their output requirement, e.g. newlines, etc.) This is at 135 characters:

$l=@a=split//,shift;$i=-1;while($i++< $l){map$x[$_]=" ",0..$l;$i==int$l/2?@x=@a:map$x[$_]=$a[$i],$i,$l/2,$l-$i-1;print join"",@x,"\n";}

which for the input “asdfd” gives

a a a
 sss
asdfd
 fff
d d d

among other things. Works well for the other input. In the debugger. Their code testing environment, not so much. So I have to reverse engineer this.

Apart from that, I see areas where I can save quite a few characters, 30-50, if I could avoid some initialization, and some of the formatting bits.

[update 2]

started exploiting some of the more powerful features of Perl, though I kept generating more temporary variables.

($l=@a=split//,<>)--;$\=pop@a;$m=$l>>1;map{@x=(" ")x$l;$_==$m?@x=@a:(@x[$_,$m,$l-$_-1]=($a[$_])x3);print@x;}0..$l;

115 characters. If I could eliminate some of the temp variables (carefully), could probably get it below 100 characters. Its still … almost … readable by humans. There are 3 vector assignments, a vector printing, and a serialized outer loop. The map{} is the core, the $l=.. gets the input and divides it up into an array.

Viewed 66784 times by 4134 viewers

On James’ blog

Heh. I think we’ve had and seen others have this conversation before.

RAID is not a backup. Backup is very important.

Ok, I did burst out laughing. The low level scan of 1PB of data to find data on the “no_backup” folder …

Yeah.

Customer has a file system. We’ve asked them “is your data important” and they’ve answered “no”. And we try to really get whether or not its important out of them, as they didn’t spend money on a backup, and there is the potential for a single failure to take down their data. Increase entropy in the universe and all that.

Sure enough, the not so important data becomes absolutely precious and must-recover-at-all-costs once there is an issue on this scratch file system.

I especially liked the Newegg parts. The “we can build it ourself” parts, and the wanting 10PB for $5k USD on a $50M USD grant. Yeah, I hate to say, we’ve seen, and heard similar requests.

But any relation to faculty members of a prestigious east coast university? Nah… Not likely.

I lost it at “I’m kind of a big deal.” Got a good chuckle out of that.

Viewed 62589 times by 4997 viewers