32bit variables on >2T arrays

32bit variables on >2T arrays

[Mario 'BitKoenig' Holbe]

[-- Attachment #1: Type: text/plain, Size: 580 bytes --]

Hello again :)

there seems to be another (minor) 32bit-issue...

md7 : active raid10 sdh1[5] sdg1[3] sdf1[1] sdc1[0] sde1[4] sdd1[2]
      4395406848 blocks 512K chunks 2 near-copies [6/6] [UUUUUU]
      [>....................]  check =  0.6% (28034560/4395406848) finish=4.7min speed=254624K/sec
      bitmap: 0/131 pages [0KB], 16384KB chunk

the time-to-finish calculation seems to be quite optimistic :)


Mario
-- 
What I need is an exact list of specific unknown problems we might encounter.
                                -- Manager, Lykes Lines Shipping

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 481 bytes --]

Re: 32bit variables on >2T arrays

[Mario 'BitKoenig' Holbe]

[-- Attachment #1: Type: text/plain, Size: 603 bytes --]

On Sun, May 03, 2009 at 04:13:00PM +0200, Mario 'BitKoenig' Holbe wrote:
> there seems to be another (minor) 32bit-issue...
>       [>....................]  check =  0.6% (28034560/4395406848) finish=4.7min speed=254624K/sec

A little later it normalizes...

      [=>...................]  check =  6.1% (269385216/4395406848) finish=266.0min speed=258429K/sec

seems like it broke the 32bit barrier :)
4395406848 - 269385216 < 2^32


Mario
-- 
"Why are we hiding from the police, daddy?"      | J. E. Guenther
"Because we use SuSE son, they use SYSVR4."      | de.alt.sysadmin.recovery

[-- Attachment #2: Digital signature --]
[-- Type: application/pgp-signature, Size: 481 bytes --]

Re: 32bit variables on >2T arrays

[NeilBrown]

On Mon, May 4, 2009 12:13 am, Mario 'BitKoenig' Holbe wrote:
> Hello again :)
>
> there seems to be another (minor) 32bit-issue...
>
> md7 : active raid10 sdh1[5] sdg1[3] sdf1[1] sdc1[0] sde1[4] sdd1[2]
>       4395406848 blocks 512K chunks 2 near-copies [6/6] [UUUUUU]
>       [>....................]  check =  0.6% (28034560/4395406848)
> finish=4.7min speed=254624K/sec
>       bitmap: 0/131 pages [0KB], 16384KB chunk
>
> the time-to-finish calculation seems to be quite optimistic :)

Thanks.

I've just posted as series of patches which includes a fix for
this as well as the other issues you identified.

Thanks for helping to improve md!

NeilBrown