Clarence wrote::
>> Why have you used b:0, and therefor completely disableing smartdrvs read
>> ahead capabilities ?
>
>A) Because that was the point of the test. Compare cache software under
> the SAME conditions. Some can't/won't readahead.
IMHO you should point out that you didn't use readahead. A test with max
readahead (and possibly cache size) on all of them would also be
interesting - or atleast write what the max is for each.
>B) The test is a REAL test. It runs MUCH faster without readahead.
> Readahead collects stuff you don't want/don't need in the cache.
> And that's not even the worst part. You have to wait for the disk
> to turn to get that stuff. The platter takes 16 milliseconds to make
> a full revolution or about 1/2 to 1 mSec a sector. Why wait ?
>and
>C) The only time readahead improves things is when you are loading a LARGE
> file _on a 100% defragged and compacted drive_ for the first time.
Sorry that's incorrect. The gain is *very* - no make that *enormous* - if
you have read-ahead and read only a small ammount of data from a file at a
time in the program. I did a test with and without SmartDrive when reading
a 10MB (IIRC, might have been more) file and reading 1 characther at a time
from it (going to the extreme I know). I got tried of waiting after around
1 hour without the read-ahead. With read-ahead (using the max of 56K) it
took less than 5 minutes. (And there we see the effect of the ammounts of
calls).
Now why did I test this? Because the teacher said that increasing the read
the program does to 8K would make it much faster (which happens to be
true), but the biggest diffrence I could see was with read-ahead or not.
Of course I maxed out SmartDrive (I always do) at around 36.5MB
//Bernie
