The last SGI system listed (SGI 2200 2X 400 MHz R12K) is for a single processor system - notice the "1" in the column labeled "CPU". The results for that system are 319/343, which beat the fastest Intel results of 304/314 for the Intel VC820 (1 GHz Pentium III).
[...] and linux clusters can be built that outperform the o2000 line for a fraction of the price
Clustering is a very important technology, that works very well for some applications. But there are some very important, real world applications that will be very difficult (if not impossible) to implement in a clustered environment.
A real world example: A travel reservation company uses a 32 processor Origin 2000 with 16 GBs of memory. They load all of the data (flight schedules, hotel availability, rental car data - about 8 GBs) into a shared memory area, where processes running on all 32 processors can access them directly.
Imagine how difficult that would be to implement in a clustered environment, with the data spread across the system memory of multiple machines. Just finding all the flights from Austin to San Jose would be a nightmare, then you have to worry about locking, etc.
Clustering is great, but it is not the best solution for all problems.
Of course, solutions like this for general websites aren't very appropriate yet for public websites, as they require IE 5.0. But the technology is very exciting.
There are several other examples on this site that utilize client-side XML processing to dynamically change the way data is displayed - sorting a baseball roster by name or batting averages, or even calculating and displaying statistics on the client.
The only thing that isn't consistent with this is their statement about continuing to support their MIPs systems at least until 2006, but I suppose that can be put down to not wanting to abandon their old customer base. That makes sense, as long as they don't spend too much money in this area of diminishing returns.
No one is going to buy a new Origin 2000 unless they feel confident that SGI will continue to support them for the lifetime of the system - thus the reassurance that IRIX will continue to exist until at least 2006.
I can't offer "significant proof" yet, as the SGI 1400 doesn't appear on the external SGI web page. But it is not a Visual Workstation 320/540 without graphics - the 1400 is a new hardware configuration. As a previous poster mentioned, it has the standard Intel-based server options - integrated SCSI, redundant power supplies, etc.
How do I know this - well, I work for SGI.:) There's a couple 1400s in my lab 100 feet away.
I can't offer "significant proof" yet, as the SGI 1400 doesn't appear on the external SGI web page. But it is not a Visual Workstation 320/540 without graphics - the 1400 is a new hardware configuration. As a previous poster mentioned, it has the standard Intel-based server options - integrated SCSI, redundant power supplies, etc. How do I know - I work there.:) There's a couple 1400s in my lab 100 feet away.
You are not going to beat an SGI Origin 200 at price/performance on an application like this. This system was designed for exactly this type of continous, high throughput data serving. SGI already uses Clariion in their Fibre Channel solutions, and has a very solid Gigabit ethernet adapter available. SGI's XFS filesystem has a 64-bit journaled architecture which can address filesystems in the thousands of TBs.
The O200 starts at $10-12K, so you could use FailSafe to have redundant services available.
Slashdot Mirror
The last SGI system listed (SGI 2200 2X 400 MHz R12K) is for a single processor system - notice the "1" in the column labeled "CPU". The results for that system are 319/343, which beat the fastest Intel results of 304/314 for the Intel VC820 (1 GHz Pentium III).
SGI and Intergraph to Form Strategic Alliance
The SGI 1600SW runs at 1600x1024 as well.
Clustering is a very important technology, that works very well for some applications. But there are some very important, real world applications that will be very difficult (if not impossible) to implement in a clustered environment.
A real world example: A travel reservation company uses a 32 processor Origin 2000 with 16 GBs of memory. They load all of the data (flight schedules, hotel availability, rental car data - about 8 GBs) into a shared memory area, where processes running on all 32 processors can access them directly.
Imagine how difficult that would be to implement in a clustered environment, with the data spread across the system memory of multiple machines. Just finding all the flights from Austin to San Jose would be a nightmare, then you have to worry about locking, etc.
Clustering is great, but it is not the best solution for all problems.
IE 5.0 does this pretty well already using XML/XSL.
Here's an interesting example:
XSL Sample
Which is from the following article:
Choosing between XSL and CSS
Of course, solutions like this for general websites aren't very appropriate yet for public websites, as they require IE 5.0. But the technology is very exciting.
There are several other examples on this site that utilize client-side XML processing to dynamically change the way data is displayed - sorting a baseball roster by name or batting averages, or even calculating and displaying statistics on the client.
The only thing that isn't consistent with this is their statement about continuing to support their MIPs systems at least until 2006, but I suppose that can be put down to not wanting to abandon their old customer base. That makes sense, as long as they don't spend too much money in this area of diminishing returns.
No one is going to buy a new Origin 2000 unless they feel confident that SGI will continue to support them for the lifetime of the system - thus the reassurance that IRIX will continue to exist until at least 2006.
How do I know this - well, I work for SGI. :) There's a couple 1400s in my lab 100 feet away.
I can't offer "significant proof" yet, as the SGI 1400 doesn't appear on the external SGI web page. But it is not a Visual Workstation 320/540 without graphics - the 1400 is a new hardware configuration. As a previous poster mentioned, it has the standard Intel-based server options - integrated SCSI, redundant power supplies, etc. How do I know - I work there. :) There's a couple 1400s in my lab 100 feet away.
You are not going to beat an SGI Origin 200 at price/performance on an application like this. This system was designed for exactly this type of continous, high throughput data serving. SGI already uses Clariion in their Fibre Channel solutions, and has a very solid Gigabit ethernet adapter available. SGI's XFS filesystem has a 64-bit journaled architecture which can address filesystems in the thousands of TBs.
The O200 starts at $10-12K, so you could use FailSafe to have redundant services available.