Re: do i need to give up on this setup

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



The controller is crap, and is expected to have serious issues no
matter what drives are on the controller.

Given the green's don't seem to have any reallocated blocks, I am
guessing the controller is 90%+ of the problem, and right now may be
all of the problem.  If you lose all of the disks on the marvell
controller at roughly the same time, that is the controller bug and
not a disk issue.  It also does not seem to be caused by a disk issue,
the controller just seems to have a race condition when multiple
operations are being done at the same time the controller just
"crashes" and stops responding to all drives on that controller.

On Tue, Oct 6, 2020 at 6:29 AM antlists <antlists@xxxxxxxxxxxxxxx> wrote:
>
> On 06/10/2020 11:53, Roger Heflin wrote:
> > When the card has an
> > issue all of the ports seem to stop responding to commands.  I am
> > guessing the firmware on the card somehow crashes or gets into some
> > sort of endless loop.  I reported it to marvel, they blamed the OS'es
> > ACHI drivers,even though the AHCI drivers worked perfectly fine with
> > the built in AMD ports.
>
> So we've got the crap drives on the crap controllers ... would it make
> any difference if you put the Greens on the motherboard, and the Caviars
> on the Marvell? Caviars I believe are good quality drives that might
> take enough load off the Marvell to enable it to work sort-of okay ...
>
> Oh - and replace the Greens pretty soon - I don't know how they compare
> against other drives quality-wise, but they are optimised in a raid
> anti-pattern.
>
> Cheers,
> Wol



[Index of Archives]     [Linux RAID Wiki]     [ATA RAID]     [Linux SCSI Target Infrastructure]     [Linux Block]     [Linux IDE]     [Linux SCSI]     [Linux Hams]     [Device Mapper]     [Device Mapper Cryptographics]     [Kernel]     [Linux Admin]     [Linux Net]     [GFS]     [RPM]     [git]     [Yosemite Forum]


  Powered by Linux