In comp.os.linux.advocacy, DFS
<nospam@xxxxxxxx>
wrote
on Fri, 25 Jul 2008 01:26:57 -0400
<etdik.7413$w93.4707@xxxxxxxxxxxxxxxxxxxxxx>:
> Roy Schestowitz wrote:
>
>> "What's noteworthy about it is that Microsoft compared Singularity to
>> FreeBSD and Linux as well as Windows/XP - and almost every result
>> shows Windows losing to the two Unix variants. For example, they show
>> the number of CPU cycles needed to "create and start a process" as
>> 1,032,000 for FreeBSD, 719,000 for Linux, and 5,376,000 for
>> Windows/XP.""
>
> Do I hear a "Linux is 7.48x faster than Windows!"?
>
Do I hear an inappropriate comparison?
One might ask whether Linux is X times faster than
NTOSKRNL, perhaps, or whether Ubuntu is X times faster than
Windows Vista Home Basic. There are also issues regarding
disk speed, system configuration, and RAM available for
the benchmark, either total or free after initial boot.
(Vista throws in ReadyBoost as well, just to make things
even more interesting.)
One might as well ask whether a tire, steering wheel,
differential, or engine is faster than a '74 Pinto
or Corvair.
In any event, Singularity will eventually speed up, either
because NRE will be spent on the slow spots, or (more
likely) because microprocessor hardware will be redesigned
to help it, much like modern video cards assist Windows.
Since Singularity does not require TSS context switches,
there is great potential for speedup, though one wonders
if a hacker can wreak havoc with a little assembly glue
stuck in exactly the wrong place.
http://en.wikipedia.org/wiki/Singularity_%28operating_system%29
(Interestingly, Amiga Exec apparently had most of the
capabilities Singularity is touting. The main thing
missing was language/policy enforcement.)
--
#191, ewill3@xxxxxxxxxxxxx
/dev/signature: Not a text file
** Posted from http://www.teranews.com **
|
|
