Anyone who buys ATI by choice needs their head read. ATI's priorities are totally different from ours... low price, poor quality hardware, awful drivers, and no linux support all seem high on their list.
>I trust a board when it's "compiler stable" I use gcc for my tests.
I am running a BP6 at home, dual Celery 400's, not overclocked. Kernel compile time for kernel 2.2.11 (running 2.2.11 SMP) is:
elapsed: 169.379 user: 276.080, system: 26.96
FWIW: I was running X, but no mp3's. I doubt that playing mp3's would have done anything except extend the elapsed time for the compile.
I've been running NT, '95, and linux with no stability problems on any OS (and I admit that's unusual for '95). YMMV. What were Anandtech doing to destabilise their setup? Overclocking perhaps?
Note that when using OpenGL mode, NT is about as much slower than 95 as it is faster with software (partly due to the lousy NT drivers most cards have - OK for 2d, suck for 3d).
I quite enjoyed Metcalf's articles, but the rebuttal seemed to take itself far too seriously... in fact it could almost have been written by a thin-skinned slashdotter. Some people have no sense of humour.
I agree with your main point about making money from services and not products... however:
1. IBM sold more new mainframes this year than any previous year (about 1000, I think).
2. the fault tolerance/reliability of IBM's mainframes is really hard to beat... for instance, the CPU contains error detection hardware - if a fault is detected the CPU is shut down, the state is extracted by the OS, and the job is transparently shifted to another CPU. How many linux based systems could do that? Unix based? NT? VMS?
3. The current rush towards E-Commerce really suits said mainframes!
4. Linux has only recently started to head towards monster servers. I expect it will improve really soon, but it's not there yet... follow the links from the recent slashdot story on the PC-Week followup to the mindcraft study for details.
I use linux at home and at work (I installed and maintain our group server, which replaced a tired old SCO 3.2.4 server), but being the best solution there doesn't make it ready to replace mainframes or really large Unix or AS/400 or VMS servers.
This is similar to our experiences trying to install SCO Unixware/SCO Openserver 5 on an HP Netserver (linux wouldn't install at all - driver support is lacking).
We installed Openserver trying to work around the driver problems with NT (not NT's fault - just don't buy HP Netserver!)
The mails weren't true - they were expressing "NT beats linux? Impossible". As it turns out, for that benchmark on that hardware NT beats linux quite handily. That's why various people have been doing work on the linux kernel to do better on that benchmark, even though it is not indicative of normal loads.
It is always necessary to take benchmarks with a grain of salt *THIS* big (holds out arms). That doesn't mean Mindcraft is necessarily in Microsoft's pocket (or vice versa).
Those idiots who mailed were WAY out of line. They should have left their mail overnight before sending.
Windows NT consists of a microkernel which runs the Win32 subsystem (and the Posix and OS/2 subsystems). VAX/VMS is not based on a microkernel (afaik!). For people who consider microkernels to be more advanced than the monolithic kernels of the 60s/70s, then Win NT is more advanced.
If someone can prove than microkernels are generally superior, then the evil RMS's GNU Hurd should get a huge boost in popularity... and with as much development as linux has had over the last 5 years, should be able to match NT.
What's wrong with keeping ISA for...?
on
Cool PC Cases
·
· Score: 1
Removing ISA support gives a speed increase to the rest of the system. Some motherboards already allow disabling it.
Good riddance I say (although I'd need a new NIC and soundcard... my current ones have lasted 3 computers).
Slashdot Mirror
Anyone who buys ATI by choice needs their head read. ATI's priorities are totally different from ours... low price, poor quality hardware, awful drivers, and no linux support all seem high on their list.
>I trust a board when it's "compiler stable" I use gcc for my tests.
I am running a BP6 at home, dual Celery 400's, not overclocked. Kernel compile time for kernel 2.2.11 (running 2.2.11 SMP) is:
elapsed: 169.379 user: 276.080, system: 26.96
FWIW: I was running X, but no mp3's. I doubt that playing mp3's would have done anything except extend the elapsed time for the compile.
I've been running NT, '95, and linux with no stability problems on any OS (and I admit that's unusual for '95). YMMV. What were Anandtech doing to destabilise their setup? Overclocking perhaps?
>Too bad Quake doesn't utilize SMP.
Really? So why is Quake2 v3.19 faster on NT4 than 95 when software rendering on a dual CPU motherboard?
Both these figures are on an Abit BP6 with dual Celery 400's (not OC'd)
demo1
'95 400x300: 32.2fps, 800x600: 13.2fps
NT4 400x300: 37.3fps, 800x600: 16.2fps
crusher
'95 640x480: 13.1fps
NT4 640x480: 15.0fps
Note that when using OpenGL mode, NT is about as much slower than 95 as it is faster with software (partly due to the lousy NT drivers most cards have - OK for 2d, suck for 3d).
I quite enjoyed Metcalf's articles, but the rebuttal seemed to take itself far too seriously... in fact it could almost have been written by a thin-skinned slashdotter. Some people have no sense of humour.
I agree with your main point about making money from services and not products... however:
1. IBM sold more new mainframes this year than any previous year (about 1000, I think).
2. the fault tolerance/reliability of IBM's mainframes is really hard to beat... for instance, the CPU contains error detection hardware - if a fault is detected the CPU is shut down, the state is extracted by the OS, and the job is transparently shifted to another CPU. How many linux based systems could do that? Unix based? NT? VMS?
3. The current rush towards E-Commerce really suits said mainframes!
4. Linux has only recently started to head towards monster servers. I expect it will improve really soon, but it's not there yet... follow the links from the recent slashdot story on the PC-Week followup to the mindcraft study for details.
I use linux at home and at work (I installed and maintain our group server, which replaced a tired old SCO 3.2.4 server), but being the best solution there doesn't make it ready to replace mainframes or really large Unix or AS/400 or VMS servers.
This is similar to our experiences trying to install SCO Unixware/SCO Openserver 5 on an HP Netserver (linux wouldn't install at all - driver support is lacking).
We installed Openserver trying to work around the driver problems with NT (not NT's fault - just don't buy HP Netserver!)
The mails weren't true - they were expressing "NT beats linux? Impossible". As it turns out, for that benchmark on that hardware NT beats linux quite handily. That's why various people have been doing work on the linux kernel to do better on that benchmark, even though it is not indicative of normal loads.
It is always necessary to take benchmarks with a grain of salt *THIS* big (holds out arms). That doesn't mean Mindcraft is necessarily in Microsoft's pocket (or vice versa).
Those idiots who mailed were WAY out of line. They should have left their mail overnight before sending.
Nothing at all... but since the linux zealots beat you to it, there's little point.
Windows NT consists of a microkernel which runs the Win32 subsystem (and the Posix and OS/2 subsystems). VAX/VMS is not based on a microkernel (afaik!). For people who consider microkernels to be more advanced than the monolithic kernels of the 60s/70s, then Win NT is more advanced.
If someone can prove than microkernels are generally superior, then the evil RMS's GNU Hurd should get a huge boost in popularity... and with as much development as linux has had over the last 5 years, should be able to match NT.
Removing ISA support gives a speed increase to the rest of the system. Some motherboards already allow disabling it.
Good riddance I say (although I'd need a new NIC and soundcard... my current ones have lasted 3 computers).
Borg is quite a common Swedish name. We have a Mikael Borg here too.