Nicolas Alvarez wrote:
> http://apcmag.com/why_i_quit_kernel_developer_con_kolivas.htm

Heh. """Hardware driven innovation cannot be afforded by the market any 
more. There is no money in it. There will be no market for it. Computers 
are boring."""  Yeah, right. Because nobody gets excited about OLPC, or 
a PS3, or a new graphics processing pipeline design, or SSDDs, or 
hardware RAID, or multi-touch screens, or virtualization, or ....

This guy's starting to sound like that Alan Kay interview.

"""Computers of today may be 1,000 times faster than they were a decade 
ago, yet the things that matter are slower."""  Yeah, because with 
uptimes of months or years, the length of time it takes to boot is of 
supreme importance.

"""Money was pouring into development from all these big names into 
developing Linux's performance in these areas.""" Ding ding ding!

He tinkers with Linux scheduling. I wonder if he realizes that UNIX 
scheduling has always sucked ass compared to anything contemporary. The 
scheduling tables in the mainframe I worked on actually had to be 
compressed in memory (in the sense of sparse, I guess) because they'd 
otherwise take up too much core. And UNIX at the time was saying "let's 
nuke him if he's compute bound, and otherwise bump him up." I still 
don't know if they even have the concept of a minquan.  Sheesh. But it 
certainly sounds like he was getting it working much better. :-)

-- 
Darren New / San Diego, CA, USA (PST)

Post a reply to this message