____/ [H]omer on Saturday 01 September 2007 02:09 : \____
> Verily I say unto thee, that Roy Schestowitz spake thusly:
>> Those Dang DPCs Clogging the MMCSS [or "Why Vista Scheduling is Broken"]
>> ,----[ Quote ]
>> | Critical optimizations such as zero-copy aside, there is no excusable
>> | reason why processing IP packets should so damagingly affect the system.
>> | [...]
>> | Putting aside the larger problem for the moment, there are several issues
>> | with this solution. It prioritizes multimedia playback over networking
>> | performance, which, as the resulting clamor has shown, is not everyone's
>> | personal policy preference. It is almost assuredly a layering violation.
>> | It picks a fixed and hard-coded packet limit (ten per millisecond), which
>> | won't scale across different hardware—think significantly faster
>> | processors or substantially slower networking drivers. It ignores the
>> | commonality of GigE. And, finally, the solution is complicated, as the
>> | convoluted description and resulting bugs in the implementation
>> | demonstrate.
> IOW after more than twenty years, Microsoft /still/ can't do a decent
> kernel, and /still/ can't do networking.
Entire city of Vista users can't access the internet
,----[ Quote ]
| Lundis Energi blamed Microsoft because Vista has got a bug and it isn't going
| to change the configuration of the server just to cope with the flaw.
Some will blame Linux for Vista's bugs. Wait and watch. This story has only
just emerged and it's being translated and brought to English press.
~~ Best of wishes
Roy S. Schestowitz | Open syntax, Open API's, Open Source
http://Schestowitz.com | GNU/Linux | PGP-Key: 0x74572E8E
Mem: 515500k total, 444028k used, 71472k free, 4160k buffers
http://iuron.com - next generation of search paradigms