Re: very degraded RAID5, or increasing capacity by adding discs

[Bill Davidsen <davidsen@tmr.com>]

Louis-David Mitterrand wrote:
> On Tue, Oct 09, 2007 at 01:48:50PM +0400, Michael Tokarev wrote:
>   
>> There still is - at least for ext[23].  Even offline resizers
>> can't do resizes from any to any size, extfs developers recommend
>> to recreate filesystem anyway if size changes significantly.
>> I'm too lazy to find a reference now, it has been mentioned here
>> on linux-raid at least this year.  It's sorta like fat (yea, that
>> ms-dog filesystem) - when you resize it from, say, 501Mb to 999Mb,
>> everything is ok, but if you want to go from 501Mb to 1Gb+1, you
>> have to recreate almost all data structures because sizes of
>> all internal fields changes - and here it's much safer to just
>> re-create it from scratch than trying to modify it in place.
>> Sure it's much better for extfs, but the point is still the same.
>>     
>
> I'll just mention that I once resized a multi-Tera ext3 filesystem and 
> it took 8hours +, a comparable XFS online resize lasted all of 10 
> seconds! 

Because of the different way these file systems do things, there is no 
comparable resize, at least in terms of work to be done. For many 
systems R/W operations are more common than resize, so the F/S type is 
selected to optimize that. ;-)

-- 
bill davidsen <davidsen@tmr.com>
  CTO TMR Associates, Inc
  Doing interesting things with small computers since 1979