*scottstuff*

The Inquirer is reporting that the CompactFlash trade group released a newer CF spec at CES, bumping the top speed for CF cards from 16 MBps to 66 MBps. This should be great news for photographers–most DSLRs use CF cards, but they’ve been falling behind in the flash speed race. For example, on Canon’s newest 1D-series cameras, the camera’s SD slot runs rings around the CF slot. In fact, the SD slot on Canon’s new cameras seems to be faster then any CF slot on any camera, so it’s not just an issue for Canon’s CF implementation. CF has been falling behind; hopefully this speed boost will let the next generation of cards and devices double or triple their CF transfer speeds.

It’s not widely appreciated just how many different modes of operation modern CF cards have. They’re basically miniature PCMCIA cards, with their own ISA-style IDE controller built in. They’re also IDE devices–you can get an adapter to connect them directly to your motherboard’s IDE interfaces. In addition, modern CF+ cards have a USB interface onboard. I think there are a couple other modes of operation as well, like legacy PCMCIA flash stuff, but I’m a bit hazy on the details.

In spite of all of the complexity, they’re still the cheapest type of flash media on the market.

CNet has a summary of AMD’s latest analyst meeting, including details on future chips:

On the high end, AMD will release chips with two processing cores in 2005 and then follow in 2006 with chips based around a new chip core code-named Pacifica.

The company is relatively tight-lipped about Pacifica, but said it will be a dual-core chip that also contains virtualization technology–which allows a computer to run multiple OSes–and a security technology called Presidio. Pacifica will appear in desktops, notebooks and servers in 2006. AMD says it will also come out with a new ultra low-power chip for notebooks.

The article also mentions that Intel has been talking about virtualization lately. Considering that PCs have been fighting with virtualization since the 386 was first introduced, I’m amazed that it’s taken 20 years to get full-blown virtualization support in mainstream PC chips. Anyone who’s been around PCs for a while remembers the whole mess with 386–they could run multiple DOS programs at the same time, given a decent vm86 environment, like Desqview or Windows/386–but as soon as you tried to run something that needed 286- or 386-specific features, the whole house of cards came tumbling down, because the 386 couldn’t virtualize itself. Neither could the 486, Pentium, or any of the other x86 chips that have shown up since then.

Of course, we’re better at cheating now: programs like VMWare and Xen have shown that it isn’t really that hard to work around the CPU’s virtualization problems, but you end up paying a price. With VMWare, it’s performance; with Xen it’s patching the guest OSes to not use specific CPU instructions.

Even once that CPU’s been virtualized, the hardest part remains: virtualizing the rest of the machine. Xen’s approach is very open-source centric: they require the guest OS to be ported to Xen, including Xen-specific drivers, rather then emulate specific PC hardware in the virtual machine monitor. Long-term, that’s probably the most reasonable way to handle things, at least in the open-source world.

I’m looking forward to AMD’s new offerings. Pity we have to wait more then a year for them.

According to CNET, Intel has dropped their plans for a 4 GHz Pentium 4 chip, replacing it with a 3.8 GHz chip with a 2 MB cache. Intel is spinning this as a deliberate move to distance themselves from the “more MHz is better” mindset:

Behind the shift is Intel President Paul Otellini, who wants the company to move away from focusing on increases in chip speed, measured in megahertz, as the primary way to increase performance. Intel has talked about such a shift for years, but remained fond of the clock-speed approach until recently. Speeches by executives about moving away from megahertz were often closely followed by announcements of faster chips.

Of course, the spin is wearing a bit thin on this–if Intel could release a 4 GHz P4, then they’d jump at the opportunity. It’s certainly cheaper to produce P4s with 1 MB of cache then with 2 MB; replacing their entire 1 MB line with 2 MB models will lower their profit (assuming that the replacement chips sell for more or less the same price).

On a similar note, Om Malik points out that Intel’s latest quarterly earnings were quite a bit worse then Intel’s been spinning.

There’s been a fair bit of discussion online about ”Horus”, Newisys’s glue chip for building 8–32 processor Opteron systems. The Horus architecture glues 4-processor clumps of CPUs into a larger system. This lets them overcome the Opteron’s 8-processor scaling limit and build really big boxes.

Fortunately, one of Horus’s designers has posted some details to comp.arch. Here’s a quick summary:

• Each Horus chip has 7 links; 1 to each local CPU and 3 to other Horus chips.
• The inter-Horus link is a proprietary version of HyperTransport, modified to work better over cables.
• While they can scale to 32 processors, going past 16 costs extra latency, because Horus only has 3 inter-Horus links. The sweet spot is 8–16 CPUs.
• Their reference design uses 2 HT links per quad for I/O. This means that some intra-quad IPC has to go through an intermediary.
• They designed for a NUMA factor of 3–remote memory costs 3x what local memory costs.
• The Horus architecture can support up to 64 MB of “remote cache.” It’s still unclear if that’s 64 MB total spread across 8 Horus chips, 64 MB per chip, or 64 MB on a dedicated “Horus Cache Chip” that replaces a CPU quad in the design.
• The inter-Horus links can be reconfigured and reset on the fly; this will allow for hot-swapping and partitioning.

We can expect to see Horus systems show up late next year. Since AMD’s dual-core Opterons are due in about the same timeframe, we should see some fascinatingly huge PCs by Christmas 2004. The basic design should be similar to Sun’s Enterprise Server [3456]xxx systems–a bunch of plug-in slots that take 4 CPUs and a bunch of RAM each. Since Horus clearly wants I/O to be local to each quad, it’s unclear exactly how networking and disk I/O will work–will there be FC and GigE controllers on each quad, and the system routes them through to the backplane? Will each card have I/O on the front panel, even though that makes swapping CPU cards a royal pain? Will the manufacturers include an “I/O node” on the motherboard with its own Horus and a bunch of HT-to-PCI-X bridge chips? Hopefully, we’ll see a few of each design and the market can sort it out.

Around a year and a half ago, there was a story going around about a boatload of bad motherboard capacitors. It had all sorts of fun elements–industrial espionage, corporate cost-cutting, bad customer support, and so on. The general gist of the story was that a lot of motherboards were going to fail after a few months of use due to bad capacitors.

Interesting story, but it didn’t really affect me much. I hadn’t seen any failed systems in a while, and I was down to a dozen or so systems, from the 700+ that I managed at my previous job, so it wasn’t that big of a deal. I forgot all about it.

Fast-forward a year. At work, we have a handful of really cheap test boxes. Lowest bidder, no-name parts, lousy design, but they work. Or, they did until a few weeks ago, when one failed. Then another. We lost a third one today. The first two were running the same software, so we were concerned–had we broken something? The third one was completely different, though, but it died with the same symptoms, and I was able to reproduce the problem running “known good” software from a year ago. My boss looked a bit skeptical and wanted to know how you get 3 machines from the same batch to all fail synchronously. It was a good question, and I didn’t have an answer, until I remembered the capacitor story.

I went back to my office and popped the cover off of one of the bad cases and there it was–half of the caps on the motherboard were leaking khaki-colored gunk. The other two dying boxes showed the same problem, as did one box that hasn’t failed yet. It’s nice to know what’s wrong. Now we’re just one little order from newegg away from having the boxes back in use.

I’ve been a full-time professional computer guy now for at least 12 years, and I’ve had paying jobs doing computer support back to 1988. So, it’s not very often that I can say “I did something completely new” today. Sure, things change, I grow professionally, and I take on new responsibilities, but the old mundane stuff is still old and mundane. Except today.

We have a pile of Dell PowerEdge 350 1U servers sitting around the office that we bought for testing and demo purposes a couple years ago. I hate the things–they’re unexpandable, they boot slowly, the front panel is basically a layer of vinyl over a bare circuit board, they use a PCI video card that pops out of its slot every other time you move the system, and they use a bunch of dinky little screws that are too small for reasonable screwdrivers. We’ve had to have Dell replace hardware on about half of the ones that we’ve bought. So anyway, we had to ship one a few weeks ago in what I’ll be charitable and call an “unapproved shipping container,” and USPS returned it a bit the worse for wear. Like, the rack ears were bent back against the case, the CPU heat sink was sliding around the inside of the case, and the hard drives had popped out of their retaining clips. Amazingly enough, it still boots, but we’d be insane to ever trust the system again. So, it sat collecting dust on one end of my desk for a few weeks, until we found ourselves needing another test system.

So, a few minutes ago, I finally re-assembled the system. When I went to put the cover on it, I discovered that the cover didn’t fit–the hard drive carriers had popped out of their little retaining clips, and the back end of the carriers was popping up far enough to keep the case from closing. The clips are really just metal pegs welded to the bottom of the case, but 3 of the 4 of them were visibly crooked, and neither drive would fit.

No problem. I know how to bend sheet metal. So, today, after 16 years of working on computers, I finally got to use a hammer as a computer repair tool. It worked, too–the pins bent, the drives fit, the lid went on, and the system is up and running in the test rack, where it’ll remain far away from any mission-critical work for the rest of its life.

Network World has a fascinating article on what it takes to achieve NEBS compliance. NEBS is Network Equipment Building System; telcos won’t buy CO equipment unless it’s NEBS certified. Ever wonder why Cisco’s pricier routers have cards that run vertically, while the cheaper ones run horizontally? It’s so the pricier routers can pass the fire part of the NEBS certification.

It looks like Tyan is getting into the server business. Their hot new 4-proc Opteron motherboard just started shipping, and they’re going down the same road as Supermicro, selling motherboards as well as bare-bones servers based on the motherboards.

By and large, this is a good thing–this class of system tends to be a bit better-integrated then the usual generic white box rackmount server. I’m still waiting for someone to put a decent managed power supply into a cheap server, though. Intel’s had specs for extending IPMI into power supplies for years, but no one really seems to care enough. Since power supplies are the flakiest component in most systems, anything that can be done to improve their reliability would be great. Even if it’s just giving a few hours’ warning before the power supply dies.

I saw a prototype FlipStart hand-held PC today. One of my friends is working for them and was showing off a prototype. I only had two or three minutes to play with it, and I didn’t have a camera with me, so I don’t have a ton to say here. All in all, it seemed decent–it’s clearly a small PC, not a big handheld, but the formfactor is okay. It fit into my shirt pocket with a millimeter or two to spare. The display seemed decent; it wasn’t outstandingly bright, but it I was right next to an open window, and it was still readable, which puts it about on par with my old Clie. The touchpad is on the right side of the unit, above the keyboard, where you can reach it with your thumb while holding the system. The mouse buttons are on the left. I was surprised, but the touchpad/button layout worked well for me. There was also a scroll wheel and a few other buttons, but I didn’t have a chance to see them in action. The keyboard is way too rubbery for me, but my contact says that it’s going to be replaced before it ships. I didn’t have a chance to test any peripherals or networking on the box; I barely had time to watch XP boot and then play around with it briefly.

The specs on the website seem to match was I saw, except for the USB ports–the specs list one USB 2.0 port, while the model I held had two mini-USB ports.

If it was shipping today, would I buy one? Probably not; I’m mostly a Mac person these days, and I wouldn’t have a whole lot of use for a pocket-sized PC. On the other hand, if it was a Mac, I’d be jumping up and down–I’d drop my Palm in an instant for it.

I was using Windows instead of OS X as my primary desktop, I’d be sorely tempted with this, because it seems to be small enough to be pocketable, while still being big enough to be usable. The keyboard’s around half-sized, which isn’t big enough to touch-type on, but it’s big enough for 3 or 4 finger typing. It’s a lot bigger then any of the built-in Palm/PocketPC keyboards that I’ve used, although the tactile feel wasn’t really any better.

DigiTimes reports that 16x DVD burners should hit the market in June, and at least a few of them will support dual-layer DVD+R disks (that’s 8.5GB, for those following along at home).

This will probably be the final round of DVD burners; there isn’t a whole lot left to do. The disks can’t spin much faster, and unless they go to double-sided burning, we’re hit the end of the road, capacity- and speed-wise. The next big upgrade will have to be one of the competing HDTV DVD standards.