lkml.org 
[lkml]   [1996]   [Apr]   [23]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
SubjectRe: IDE Disk speed enhancements
Date
J.J. Burgess wrote:
>
> My question is do 2 simultaneous 256k IDE requests to ide0 & ide1 get any
> chance of any parallelism, or does each request continue until completion?

If the hardware is capable of it, Linux will overlap I/O on
the IDE interfaces (up to four interfaces at once).

> Is it possible to issue 2 simultaneous disk transfers, especially on 2
> channel Triton DMA controllers?

The ATA (IDE) specs do not permit overlapped disk transfers within
a single interface. But, as already noted, requests to disks on
separate interfaces can be overlapped. Linux has done this since
kernel revision 1.1.76 or so.

The same treatment applies, regardless of whether PIO or (triton) DMA
is being used on any given interface. (the Triton chipset counts as
two interfaces, ide0 and ide1).

IDE tapes using the latest ATAPI enhancements can overlap operation
with an IDE disk on the same interface under Linux. Some cdroms may
also have this capability, but not yet with Linux.

> Thinking about it, this could be a direct consequence of the limit imposed
> be ll_rw_blk.c of 240-something blocks in any one transfer in a single
> request. Hence 128k is the biggest amount of data any of the lower layers
> have to work with hence md only issues commands which go to a single
> drive. (I know 128k+ stripes are a little silly, but the way things change
> with computers, this may also change)

As it turns out, 128kB is also the per-request limit for ATA/IDE disks.

-ml
the Linux IDE guy


\
 
 \ /
  Last update: 2005-03-22 13:37    [W:3.220 / U:0.000 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site