Justin Piszcz wrote:

On Wed, 19 Dec 2007, Bill Davidsen wrote:

quoted

I'm going to try another approach, I'll describe it when I get 
results (or not).

http://home.comcast.net/~jpiszcz/align_vs_noalign/

Hardly any difference at whatsoever, only on the per char for 
read/write is it any faster..?

Am I misreading what you are doing here... you have the underlying data 
on the actual hardware devices 64k aligned by using either the whole 
device or starting a partition on a 64k boundary? I'm dubious that you 
will see a difference any other way, after all the translations take place.

I'm trying creating a raid array using loop devices created with the 
"offset" parameter, but I suspect that I will wind up doing a test after 
just repartitioning the drives, painful as that will be.

Average of 3 runs taken:

$ cat align/*log|grep ,
p63,8G,57683,94,86479,13,55242,8,63495,98,147647,11,434.8,0,16:100000:16/64,1334210,10,330,2,120,1,3978,10,312,2 

p63,8G,57973,95,76702,11,50830,7,62291,99,136477,10,388.3,0,16:100000:16/64,1252548,6,296,1,115,1,7927,20,373,2 

p63,8G,57758,95,80847,12,52144,8,63874,98,144747,11,443.4,0,16:100000:16/64,1242445,6,303,1,117,1,6767,17,359,2 


$ cat noalign/*log|grep ,
p63,8G,57641,94,85494,12,55669,8,63802,98,146925,11,434.8,0,16:100000:16/64,1353180,8,314,1,117,1,8684,22,283,2 

p63,8G,57705,94,85929,12,56708,8,63855,99,143437,11,436.2,0,16:100000:16/64,12211519,29,297,1,113,1,3218,8,325,2 

p63,8G,57783,94,78226,11,48580,7,63487,98,137721,10,438.7,0,16:100000:16/64,1243229,8,307,1,120,1,4247,11,313,2 

-- 
Bill Davidsen [off-list ref]
  "Woe unto the statesman who makes war without a reason that will still
  be valid when the war is over..." Otto von Bismark