[lkml]   [1997]   [Feb]   [11]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: Big mallocs, mmap sorrows and double buffering.
In article <> you wrote:

: Side Question : On Vaxen they had fancy IO hardware so it paid to do double
: buffering. (Ie Read first buffer, Read second buffer NO_WAIT, process
: first while second buffer is reading, Write NO_WAIT first output
: buffer, Read NO_WAIT into first input buffer, process second input
: buffer, etc. etc.) Does it pay to do this on a PC under Linux?

Sure! It is the most efficient way for all scientific tasks
requiring large amounts of memory.
I did it in pretty weird manner: process clones thread,
that reads and writes by enough large chunks to make disk IO
maximally efficient.

Linux vm manager is the dumbest one in the world 8)8)
I tested my program on SunOS-4, SunOS-5, FreeBSD and Digital Unix,
Linux's VM looks really pathetic.

Do you know, what Linus said about it? Something sort of:
(citation is not very exact 8)8)) "Linux is optimized for playing xquake,
scientific tasks are not supported." 8)8)8)

Note that the double buffering makes Linux comparable with another OSes.

Alexey Kuznetsov.

 \ /
  Last update: 2005-03-22 13:38    [W:0.020 / U:2.976 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site