Microway “Screamer 533”
Manufacturer: Microway, Inc.
Price: $2,995 US 500MHz and 433MHz available at lower prices.
Reviewer: Bradley Willson
This story is proof positive that one has to be careful what they wish for, because the wish might come true. It all started when I joked with Marjorie Richardson of Linux Journal about reviewing a “Screamer 500”. The next item in my e-mail was a response stating that Carlie Fairchild had contacted Microway and had convinced them to send me a machine for review. My response was, “You're kidding, right?” Naturally, I was very pleased to find out it was true. The icing on the cake came when I called Ann Fried (pronounced “freed”) at Microway. She decided it would be better to have me review the new 533MHz machine instead of the 500MHz model. The idea of having that much “horsepower” behind the keyboard brought back memories of my 1970 Mustang and the feeling of being pressed into the seat back under acceleration. The only things missing were the roar of the engine and the smell of burnt rubber.
It is not the intent of this article to compare the Microway Screamer to other DEC Alpha-based computers. This article is about the profound differences between Intel 32bit Linux and Alpha 64bit Linux. I chose the Screamer because of Microway's advertisement in Linux Journal. Their ad provided the most information about the Alpha. Mainly this article is about having more fun with a computer than should be legal, while getting a glimpse of the future of computing.
As a teenager, I thoroughly enjoyed racing against anyone that would pull alongside (State Highway Patrol was excluded, of course). Computers were not of interest to me then. Years passed, the hot rod was replaced by an econo-box commuter, and I discovered a new way to race. My first 286 was constantly tweaked to gain performance, then it was upgraded to a 386 and so on. Now the old 286 case sports an AMD 5x86 133. The green flag drops, the race between the AMD 133 and the Screamer 533 begins. My hot-rod Mustang was never a match for a Top-Fuel dragster, and the same is true for my computer pitted against a 533MHz DEC Alpha, but the fun part was getting to drive the dragster.
Vrrrmmm, Vvvrrrrmmm, sputter, sputter, my office box fires up in DOS. Type linux at the C:\ prompt and Linux boots. I read 66.56 BogoMIPS from the scrolling screen. After I log in and enter startx I'm ready to go to work. Next I turn on the Screamer, wait about 4 minutes for the boot sequence to complete, read 1063.26 BogoMIPS from the startup messages. Immediately I can see the difference in speed. Parts of the boot messages are not readable because they scroll by so fast. I log into the Screamer and enter startx. The XFree86 configuration messages flash by so fast that they appear as a blur. Literally everything runs profoundly faster on the Screamer. Emacs appears within two seconds after menu selection. xfig is ready to use by the time I move my finger off the mouse button. Both of these applications take a few seconds to launch on my machine.
I needed an application that would level the playing field and could be timed using “time” on both machines, so I wrote a bash script to append several instances of the phrase “The quick brown fox jumped over the lazy dog's back” to a file (see Listing 1). The task was repeated 100,000 times, creating a 5.2MB file on each machine. My 133 churned for 5 minutes and 12.98 seconds before completing the task (see Listing 2). The Screamer completed the execution in a mere 18.89 seconds (see Listing 3). I used the 4.9 minutes I got back from the Alpha to run a few more tests on it.
Even though it is a crude benchmark test, it exercised the CPU and the storage hardware of both machines. Several factors like IDE vs SCSI, memory and running daemons have an effect on the outcome, so your results will likely vary from these, but you will be able to gauge your machine's performance to the Screamer's.
Microway builds an industrial-grade computer, starting with the case. The all-steel construction shows thoughtful engineering. Even the drive bay face-plates are made of steel. The side access panel makes working on the internals easy. Once inside, there is plenty of room to move around. Adding and removing storage devices is quick and easy thanks to the rail mount system. There is ample room between the drives and the motherboard and installed cards so you won't need a shoe-horn to install or remove a drive. The only problem I could foresee was that using the lowest two drive bays requires removal of the rivets that connect the card support rack to the drive support rack. Once done, it is left up to the user to provide the means to reconnect the racks. There are five fans to help the Screamer keep its cool while it crunches data. However, even with all those blades spinning, the Screamer is a quiet performer.
Like many other computers sold today, you can specify the options you want to buy with the base package, but the “basic” Screamer will likely keep any home user flying through code for years. The Screamer comes in two colors: black and beige. This particular box was built for the review and a series of trade-shows with these components: a 4.3GB Seagate Barracuda UW-SCSI hard-drive, a 1.44MB floppy drive, a 8x IDE Mitsumi CD-ROM, a Matrox Millennium card with 2MB, an Adaptec 2940 Ultra-Wide SCSI controller and 128MB of RAM. Of course, it also came with 2MB 9ns SRAM Cache installed. The motherboard sports 4 PCI slots (2x32bit and 2x64bit) and 2 ISA slots.
Microway generously sent a Iiyama 17'' Vision Master model MF-8617E monitor along with the Screamer. Using this monitor couldn't be easier. There are four buttons on the front panel and one of them is the power switch. You activate the on-screen menu with a single button and make menu selections with either the + or - buttons. I was impressed with its compact design. I've seen other monitors of the same display size taking up far more footprint on the desktop. This model has a maximum resolution of 1600 x 1200 non-interlaced, both 5-BNC and D-Sub mini 15 pin connections and a maximum of 19 user-definable signal settings. It is also power management and plug & play (VESA DDC1/2B) aware. At $679.00, it is a great value.
|Designing Electronics with Linux||May 22, 2013|
|Dynamic DNS—an Object Lesson in Problem Solving||May 21, 2013|
|Using Salt Stack and Vagrant for Drupal Development||May 20, 2013|
|Making Linux and Android Get Along (It's Not as Hard as It Sounds)||May 16, 2013|
|Drupal Is a Framework: Why Everyone Needs to Understand This||May 15, 2013|
|Home, My Backup Data Center||May 13, 2013|
- Linux Systems Administrator
- New Products
- Senior Perl Developer
- Technical Support Rep
- UX Designer
- Designing Electronics with Linux
- Dynamic DNS—an Object Lesson in Problem Solving
- Using Salt Stack and Vagrant for Drupal Development
- Making Linux and Android Get Along (It's Not as Hard as It Sounds)
- Have you tried Boxen? It's a
4 hours 28 min ago
- seo services in india
8 hours 59 min ago
- For KDE install kio-mtp
9 hours 24 sec ago
- Evernote is much more...
11 hours 30 sec ago
- Reply to comment | Linux Journal
19 hours 45 min ago
- Dynamic DNS
20 hours 19 min ago
- Reply to comment | Linux Journal
21 hours 18 min ago
- Reply to comment | Linux Journal
22 hours 8 min ago
- Not free anymore
1 day 2 hours ago
1 day 5 hours ago
Enter to Win an Adafruit Pi Cobbler Breakout Kit for Raspberry Pi
It's Raspberry Pi month at Linux Journal. Each week in May, Adafruit will be giving away a Pi-related prize to a lucky, randomly drawn LJ reader. Winners will be announced weekly.
Fill out the fields below to enter to win this week's prize-- a Pi Cobbler Breakout Kit for Raspberry Pi.
Congratulations to our winners so far:
- 5-8-13, Pi Starter Pack: Jack Davis
- 5-15-13, Pi Model B 512MB RAM: Patrick Dunn
- 5-21-13, Prototyping Pi Plate Kit: Philip Kirby
- Next winner announced on 5-27-13!
Free Webinar: Hadoop
How to Build an Optimal Hadoop Cluster to Store and Maintain Unlimited Amounts of Data Using Microservers
Realizing the promise of Apache® Hadoop® requires the effective deployment of compute, memory, storage and networking to achieve optimal results. With its flexibility and multitude of options, it is easy to over or under provision the server infrastructure, resulting in poor performance and high TCO. Join us for an in depth, technical discussion with industry experts from leading Hadoop and server companies who will provide insights into the key considerations for designing and deploying an optimal Hadoop cluster.
Some of key questions to be discussed are:
- What is the “typical” Hadoop cluster and what should be installed on the different machine types?
- Why should you consider the typical workload patterns when making your hardware decisions?
- Are all microservers created equal for Hadoop deployments?
- How do I plan for expansion if I require more compute, memory, storage or networking?