Re: adding SCSI C: to IDE system
- From: "Rod Speed" <rod_speed@xxxxxxxxx>
- Date: Thu, 19 Jan 2006 09:59:57 +1100
Cruise Director <SeaFuncSpam@xxxxxxxxx> wrote
> Rod Speed wrote
>> Cruise Director <SeaFuncSpam@xxxxxxxxx> wrote
>>> It is a pity that I can't find the hard data substantiating my claim.
>>> In the past I have seen graphs of performance degrading as a
>>> function of drive fullness. I can't remember if they were academic
>>> papers or someone's benchmarking website. At any rate, it is
>>> very expensive to be provably correct on Usenet, and I already
>>> exceeded the Google search time I was willing to throw at it.
>> I dont believe that it happens or can be substantiated as happening.
> Nevertheless, I have read the papers on such.
I dont believe that either. You must have misinterpreted what they actually
said.
> Unless you've put your hands on every academic benchmarking
> paper out there, and are something of an industry professional,
> I wouldn't be so sure of yourself.
I understand how hard drives and file systems work, there
is no mechanism that could produce an effect like that.
>> There is no possible mechanism for an effect like that.
> The reasons are somewhat complex, due
> to hardware and software interactions.
Bullshit, there is no possible mechanism for an effect like that.
> The results are not. Graphs of performance degradation
> are very clear, with big dropoffs as the drives fill up.
Dont believe it. And you dont see recommendations to upgrade to bigger
drives when they are half full, and you would if it was a real effect.
Bet you're actually remembering the effect that you do get in bands of
tracks across modern drives with different sectors per track numbers.
.
- Follow-Ups:
- Re: adding SCSI C: to IDE system
- From: Cruise Director
- Re: adding SCSI C: to IDE system
- References:
- adding SCSI C: to IDE system
- From: Cruise Director
- Re: adding SCSI C: to IDE system
- From: Rod Speed
- Re: adding SCSI C: to IDE system
- From: Cruise Director
- Re: adding SCSI C: to IDE system
- From: Rod Speed
- Re: adding SCSI C: to IDE system
- From: Cruise Director
- Re: adding SCSI C: to IDE system
- From: Rod Speed
- Re: adding SCSI C: to IDE system
- From: Cruise Director
- Re: adding SCSI C: to IDE system
- From: Rod Speed
- Re: adding SCSI C: to IDE system
- From: Cruise Director
- Re: adding SCSI C: to IDE system
- From: Rod Speed
- Re: adding SCSI C: to IDE system
- From: Cruise Director
- adding SCSI C: to IDE system
- Prev by Date: Re: Single user HD benchmarks
- Next by Date: Re: ARGOSY - HD363N - Refund
- Previous by thread: Re: adding SCSI C: to IDE system
- Next by thread: Re: adding SCSI C: to IDE system
- Index(es):
Relevant Pages
|