Re: Silicon Image 3112A SATA trouble

From: Jens Axboe (axboe_at_suse.de)
Date: 11/30/03

  • Next message: Jeff Garzik: "Re: Silicon Image 3112A SATA trouble" 
    Date:	Sun, 30 Nov 2003 19:22:32 +0100
To: Jeff Garzik <jgarzik@pobox.com>

    On Sun, Nov 30 2003, Jeff Garzik wrote:
    > Jens Axboe wrote:
    > >On Sun, Nov 30 2003, Vojtech Pavlik wrote:
    > >
    > >>On Sun, Nov 30, 2003 at 06:10:06PM +0100, Jens Axboe wrote:
    > >>
    > >>
    > >>>On Sun, Nov 30 2003, Jeff Garzik wrote:
    > >>>
    > >>>>Bartlomiej Zolnierkiewicz wrote:
    > >>>>
    > >>>>>On Sunday 30 of November 2003 17:51, Jens Axboe wrote:
    > >>>>>
    > >>>>>>>Tangent: My non-pessimistic fix will involve submitting a single
    > >>>>>>>sector
    > >>>>>>>DMA r/w taskfile manually, then proceeding with the remaining
    > >>>>>>>sectors in
    > >>>>>>>another r/w taskfile. This doubles the interrupts on the affected
    > >>>>>>>chipset/drive combos, but still allows large requests. I'm not
    > >>>>>>>terribly
    > >>>>>>
    > >>>>>>Or split the request 50/50.
    > >>>>>
    > >>>>>
    > >>>>>We can't - hardware will lock up.
    > >>>>
    > >>>>Well, the constraint we must satisfy is
    > >>>>
    > >>>> sector_count % 15 != 1
    > >>>
    > >>> (sector_count % 15 != 1) && (sector_count != 1)
    > >>>
    > >>>to be more precise :)
    > >>
    > >>I think you wanted to say:
    > >>
    > >> (sector_count % 15 != 1) || (sector_count == 1)
    > >
    > >
    > >Ehm no, I don't think so... To my knowledge, sector_count == 1 is ok. If
    > >not, the hardware would be seriously screwed (ok it is already) beyond
    > >software fixups.
    >
    >
    > Now that you've kicked my brain into action, yes, sector_count==1 is ok.
    > It's all about limiting the data FIS... and with sector_count==1
    > there is no worry about the data FIS in this case.

    Ah, my line wasn't completely clear (to say the least)... So to clear
    all doubts:

            if ((sector_count % 15 == 1) && (sector_count != 1))
                    errata path

    Agree? 

    -- 
Jens Axboe
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/
  • Next message: Jeff Garzik: "Re: Silicon Image 3112A SATA trouble"

    Relevant Pages

    • Re: 2.9test9-mm1 and DAO ATAPI cd-burning corrupt
      ... > now the capacity gets set correctly and everything seems to work just ... > also mount the disk read-write, write a 10MB file to it, and umount ... Jens Axboe ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: [PATCH] blk queue io tracing support
      ... > Wouldn't it be better to pass out the highest precision available here ... This isn't msec precision, it's usec. ... Jens Axboe ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: A problem about DIRECT IO on ext3
      ... >> same alignment as the ... >> Jens Axboe ... > your system's hard/soft block size? ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)
    • Re: 2.9test9-mm1 and DAO ATAPI cd-burning corrupt
      ... >>primary key to knowing what the problem is. ... Jens Axboe ... send the line "unsubscribe linux-kernel" in ... More majordomo info at http://vger.kernel.org/majordomo-info.html ...
      (Linux-Kernel)
    • Re: Silicon Image 3112A SATA trouble
      ... Playing with readahead or other hdparm ... > but I can find only BLKSECTGET, ... Jens Axboe ... send the line "unsubscribe linux-kernel" in ...
      (Linux-Kernel)