| 1 |
On Mon, Dec 1, 2008 at 5:19 PM, Daniel Iliev <daniel.iliev@×××××.com> wrote: |
| 2 |
> Yes. That has crossed my mind too, but I can't figure out if there's |
| 3 |
> anything I alone can do about it. It would taint the results in a very bad |
| 4 |
> way, because it is impossible to catch by increasing the number of |
| 5 |
> repetitions. If my memory serves well its called "systematic error" in |
| 6 |
> statistics. |
| 7 |
> |
| 8 |
> I'm open to suggestions. |
| 9 |
> |
| 10 |
> |
| 11 |
> P.S. |
| 12 |
> |
| 13 |
> The way to eliminate the influence of this factor is to find |
| 14 |
> many other people to make the test and share the results. |
| 15 |
> |
| 16 |
> |
| 17 |
> |
| 18 |
> -- |
| 19 |
> Best regards, |
| 20 |
> Daniel |
| 21 |
|
| 22 |
I'm tempted to donate my system for a short bit to try it.. but at |
| 23 |
least in the case of my desktop... I pre-cache all my major software |
| 24 |
at boot time, so I don't really want to dump caches there ;) ... maybe |
| 25 |
it'll be a good use for my old amd64... but, umm... it'll need an OS |
| 26 |
and even the slightest potential of fragmented files first... maybe |
| 27 |
I'll make that happen tonight if I get bored. |
| 28 |
|
| 29 |
As a side note, SSDs are the quickest way to remove all worries where |
| 30 |
fragmentation is concerned, having negligible seek times as they do... |
| 31 |
and physically smaller platters (2.5in SAS drives, the Velociraptor, |
| 32 |
etc) at least make a small dent on worst case seek times... reducing |
| 33 |
the impact that way. |
| 34 |
|
| 35 |
-- |
| 36 |
Poison [BLX] |
| 37 |
Joshua M. Murphy |
Archives