>> On Fri, 7 Mar 2003, Michael Sinz wrote:
>> > That is not to say that we should not look at the fact that there
>> > are hot zones in where writing happens. The fact that there are
>> > hot zones (multiple) means that there is more seeking going on than
>> > you might want (albeit it may be needed). (And each seek does
>> > cause some mechanical wear and poses potential mechanical failure)
Performance:
What is the failure rate of the log sectors on these drives?
Is even possible to tell from the Linux kernel?
If possible to tell, then maybe the journal itself should be created a little
on the large size, then when an underlying sector is re-mapped, simply quit
using that sector in the journal. This would eliminate time wasting seeks out
to the remapped sectors.
Longevity:
Even if your losing 1% of sectors/month, allocating a spare 100% of log space
as above would allow the drive to last 100 months before it was trashed and
would ensure high log speed access for the duration of that 100 months.
Greg
--
Greg Freemyer
|