Whilst your point is valid, it's not the biggest reason. NAT is so popular because it is EASY. Without NAT you have to have a REAL router and you then have to setup a REAL router, telling it which IP's you have attached to each interface, probably some subnetting. You can bet your average user has no idea how to setup a real router, but with NAT they can just plug in and go
Or maybe, just maybe the project is a ALPHA status and is very new and has only been active for 2 weeks so no one has had a chance to write any documentation?
The point he was making was that there is no way to know if something is compatible with linux and so not in the list, or if it's simply that no one had added it to the list because they didn't know of the lists existance, or haven't tested it with linux to discover if it's compatible
I'm hanging out for a SQL pluging. Being able to "SELECT filename FROM filesystem WHERE size > 1000000" would be fantatstic (note very basic example). Not to mention meta data plugins that can index your media files and store that data in the filesystem (again with SQL access)
Tumwater is derivled from the Linderhurst, so thats probably where you got it from. It should also be mentioned that the reason this PCIe problem cropped up is that the PCIe spec was changed at a very late stage and Intel had already built the chips
Both Xeon and Itanium suffer the same woes, this gives them a good chance to correct both at the same time, although it will take a massive engineering effort on their part.
Intel are going to have to drop their shared bus architecture and move to a point to point system like AMD or memory performance will suffer greatly, otherwise you can only run your memory at your FSB speed and adding more procs just means they all get less mem bandwidth. This is going to become more pronounced with the introduction of Dual Core CPU's. Also since Xeons are build on the core of the desktop CPU's they will also have to change to follow suit (assuming Intel are going to move to a P2P architecture). At that time one would assume we would be talking about the P5 and one would also have to assume Intel would move the memory controllers onto the CPU's like AMD have.
That is quite a lot of work for Intel to do when they are also talking about dual cores. It's a lot of tech to get right all at the same time, especially given the delays involved with the Nocona launch and the associated motherboards. Itwould give them some rather nice options though, rather than using Hypertransport they could use PCI-E to join CPU's and have controllers on the CPU like the Opterons. Also because the CPU's are joined with a serial bus you can move them onto riser cards and make the most of the real estate in the chassis meaning you should be able to pack more CPU's in a smaller space.
The thing here though is that at some level the CPU's need to talk the same language, at least for initialisation at boot, although we are presuambly talking about 2 completly new cores so ever that is within the realm of possibility.
The multiple-PHD Admin certainly knows it, and has likely been voicing his concerns for some time. Unfortuantly the way the word works is that if it ain't broke, don't fix it. I imagine said admin(s) will now get the money they require to resolve the problem properly, otherwise Oxford risk more students doing this in 12 months time and looking even more silly
The difference is that the address bus can be expanded to 64bit without the software ever knowing or caring, and I seriously doubt a current Athlon64 is going to be required to run the latest and greatest software in 12 years time
I think the general point being made is that in recent years Intel has had a number of recalls. One only needs think of the P3 1.13, the i820 MTH, and now this. The biggest of course being the i820 MTH as they had been selling thefor several months before Intel admitted there was something wrong with them.
When was the last AMD recall you can remember? Now AMD is a lot smaller than Intel and they don't make nearly the number of chipsets, but it does indicate that AMD take more care before they release a product and don't just throw it out into the market for the market to test.
And following the same theme, what are the chances there is any redundancy in this system? What happens if the server fails? I bet there isn't any replication to another server in a different location. In fact there probably isn't even a UPS and RAID array on the machine hosting this
A blog is not at all like a book. A book is a tangible item that cannot (easily) be copied or backed up. A blog is a collection of text in a DB of some kind, backing up a database is a simple thing to do.
The Hypertansport link isn't what makes Opterons good in this situation (although it helps), it the on-chip memory controllers and the fact that there are 2 of them that makes them so fast
For the record. Only AMD64 based CPU's currently have support for this on x86. Intel and Transmeta's next generation chips will also support it. No previous CPU's will.
He's not talking about data loos but redundancy. Presumably buying Oracle you want the thing to be solid, so using a single IDE drive and no redundant power means a single hardware failure will bring the DB down
They have 50 and 30watt version of the opteron, it would seem likely that this system uses one of these rather than the standard parts as a 300watt PSU would be very much struggling otherwise
Slashdot Mirror
It had nothing to do with big balls (well not much) and a lot more to do with big money. These guys had WAY more money than anyone else
Whilst your point is valid, it's not the biggest reason. NAT is so popular because it is EASY.
Without NAT you have to have a REAL router and you then have to setup a REAL router, telling it which IP's you have attached to each interface, probably some subnetting. You can bet your average user has no idea how to setup a real router, but with NAT they can just plug in and go
Or maybe, just maybe the project is a ALPHA status and is very new and has only been active for 2 weeks so no one has had a chance to write any documentation?
Why shouldn't an admin have that right?
Given that the recption machine is very often in the public view why would you want the hunk of the month set as her background?
Shadows and fonts are fine, but anything that gives the user the ability to offend other employees or customers should be disabled
Yeah, just like those damn flying cars and cold fusion. As always don't count your chickens before they hatch
Thats just downright mean :-)
The point he was making was that there is no way to know if something is compatible with linux and so not in the list, or if it's simply that no one had added it to the list because they didn't know of the lists existance, or haven't tested it with linux to discover if it's compatible
No what would be really elegant is if there was an NDIS interface written into the linux kernel so you could nativly load NDIS drivers in linux.
I'm hanging out for a SQL pluging. Being able to "SELECT filename FROM filesystem WHERE size > 1000000" would be fantatstic (note very basic example). Not to mention meta data plugins that can index your media files and store that data in the filesystem (again with SQL access)
Tumwater is derivled from the Linderhurst, so thats probably where you got it from. It should also be mentioned that the reason this PCIe problem cropped up is that the PCIe spec was changed at a very late stage and Intel had already built the chips
It depends what they got. If the got a SQL and Exchange CAL with that then it's not nearly so bad. If they got Office too then it's great
Nothing's stopping them, but it seems like a lot of work when they are going to have to redesign the cores anyway
Both Xeon and Itanium suffer the same woes, this gives them a good chance to correct both at the same time, although it will take a massive engineering effort on their part.
Intel are going to have to drop their shared bus architecture and move to a point to point system like AMD or memory performance will suffer greatly, otherwise you can only run your memory at your FSB speed and adding more procs just means they all get less mem bandwidth. This is going to become more pronounced with the introduction of Dual Core CPU's. Also since Xeons are build on the core of the desktop CPU's they will also have to change to follow suit (assuming Intel are going to move to a P2P architecture). At that time one would assume we would be talking about the P5 and one would also have to assume Intel would move the memory controllers onto the CPU's like AMD have.
That is quite a lot of work for Intel to do when they are also talking about dual cores. It's a lot of tech to get right all at the same time, especially given the delays involved with the Nocona launch and the associated motherboards. Itwould give them some rather nice options though, rather than using Hypertransport they could use PCI-E to join CPU's and have controllers on the CPU like the Opterons. Also because the CPU's are joined with a serial bus you can move them onto riser cards and make the most of the real estate in the chassis meaning you should be able to pack more CPU's in a smaller space.
The thing here though is that at some level the CPU's need to talk the same language, at least for initialisation at boot, although we are presuambly talking about 2 completly new cores so ever that is within the realm of possibility.
Just for the record, while USB is theoretically faster, in the real world Firewire will destroy USB2 in data transfer tests
The multiple-PHD Admin certainly knows it, and has likely been voicing his concerns for some time. Unfortuantly the way the word works is that if it ain't broke, don't fix it. I imagine said admin(s) will now get the money they require to resolve the problem properly, otherwise Oxford risk more students doing this in 12 months time and looking even more silly
The difference is that the address bus can be expanded to 64bit without the software ever knowing or caring, and I seriously doubt a current Athlon64 is going to be required to run the latest and greatest software in 12 years time
This might be viable, except AMD64 doesn't have "Hyper-Threading" so it can't actually run 2 threads simultaneously.
Just to be picky ;-), isn't the xscale an Intel chip that is just compatible with the ARM instruction set?
I don't think ARM had anything to do with it, in fact I'm pretty sure it's Intels attempt to take market share off ARM.
I think the general point being made is that in recent years Intel has had a number of recalls. One only needs think of the P3 1.13, the i820 MTH, and now this. The biggest of course being the i820 MTH as they had been selling thefor several months before Intel admitted there was something wrong with them.
When was the last AMD recall you can remember? Now AMD is a lot smaller than Intel and they don't make nearly the number of chipsets, but it does indicate that AMD take more care before they release a product and don't just throw it out into the market for the market to test.
And following the same theme, what are the chances there is any redundancy in this system? What happens if the server fails? I bet there isn't any replication to another server in a different location. In fact there probably isn't even a UPS and RAID array on the machine hosting this
A blog is not at all like a book. A book is a tangible item that cannot (easily) be copied or backed up. A blog is a collection of text in a DB of some kind, backing up a database is a simple thing to do.
The Hypertansport link isn't what makes Opterons good in this situation (although it helps), it the on-chip memory controllers and the fact that there are 2 of them that makes them so fast
For the record. Only AMD64 based CPU's currently have support for this on x86. Intel and Transmeta's next generation chips will also support it. No previous CPU's will.
He's not talking about data loos but redundancy. Presumably buying Oracle you want the thing to be solid, so using a single IDE drive and no redundant power means a single hardware failure will bring the DB down
They have 50 and 30watt version of the opteron, it would seem likely that this system uses one of these rather than the standard parts as a 300watt PSU would be very much struggling otherwise