some IDE trays are bad (was Re: SW-RAID 1 and kernel 2.4.18)

some IDE trays are bad (was Re: SW-RAID 1 and kernel 2.4.18)

[Louis-David Mitterrand]

On Tue, Nov 26, 2002 at 02:56:41PM +0100, SCHEP. - Schepke, Arnt wrote:
> Hi, i have a running software raid 1. This consist of two ide devices hda
> and hdc. The root filesystem is running on this raid array. The harddiscs
> are installed in removable frames. 
                   ^^^^^^^^^^^^^^^^^

That is the issue.

> The system seems to work correctly. But i get some errors. In the file
> messages i found: 
> 
> linux kernel: hdc: dma_intr: status=0x51 { DriveReady SeekComplete Error } 
> linux kernel: hdc: dma_intr: error=0x84 { DriveStatusError BadCRC }

I've just had the same problem. My setup: 4 Maxtor 160G connected to a
Promise 133TX2 card, one of them was in an Icy Dock removable rack, the
three remaining were directly connected to the IDE cable. 

The tray-connected disk would always give us the BadCRC error upon
resynching with the raid5 array. That kind of error is typical of bad
cabling.

It seems the additionnal connectors and cable-length in these IDE trays
is too much to bear for picky/sensitive ATA133 drives. In any case the
BadCRC disappeared the moment the drive was directly connected the IDE
ribbon.

hdparm -t /dev/md1 gives me over 100MB/s on IDE raid5. Incredible! Over
twice what a top-of-the-line 15k scsi drive gives me.

-- 
    PHEDRE: Comme il ne respirait qu'une retraite prompte !
            Et combien sa rougeur a redoublé ma honte !
                                          (Phèdre, J-B Racine, acte 3, scène 1)
-
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: some IDE trays are bad (was Re: SW-RAID 1 and kernel 2.4.18)

[Maurice Hilarius]

With regards to your message at 09:01 AM 12/3/02, Louis-David Mitterrand. 
Where you stated:
>On Tue, Nov 26, 2002 at 02:56:41PM +0100, SCHEP. - Schepke, Arnt wrote:
> > Hi, i have a running software raid 1. This consist of two ide devices hda
> > and hdc. The root filesystem is running on this raid array. The harddiscs
> > are installed in removable frames.
>                    ^^^^^^^^^^^^^^^^^
>
>That is the issue.
>
><<snip>>
>I've just had the same problem. My setup: 4 Maxtor 160G connected to a
>Promise 133TX2 card, one of them was in an Icy Dock removable rack, the
>three remaining were directly connected to the IDE cable.
>
>The tray-connected disk would always give us the BadCRC error upon
>resynching with the raid5 array. That kind of error is typical of bad
>cabling.
That type of error is also typical of Promise and other inferior IDE cards.
using IDE ports on motherboards, and using 3Ware cards we rarely see this 
issue.
Using Promise we frequently see it.
Also, cables are important, I agree. Yellow Teflon/TPE cables make a big 
difference.
The cheap grey ones are not suitable for this type of use.



With our best regards,

Maurice W. Hilarius       Telephone: 01-780-456-9771
Hard Data Ltd.               FAX:       01-780-456-9772
11060 - 166 Avenue        mailto:maurice@harddata.com
Edmonton, AB, Canada      http://www.harddata.com/
    T5X 1Y3

Ask me about NAS and near-line storage

Re: some IDE trays are bad (was Re: SW-RAID 1 and kernel 2.4.18)

[Gregory Leblanc]

On Tue, 2002-12-03 at 08:01, Louis-David Mitterrand wrote:
> On Tue, Nov 26, 2002 at 02:56:41PM +0100, SCHEP. - Schepke, Arnt wrote:
> > The system seems to work correctly. But i get some errors. In the file
> > messages i found: 
> > 
> > linux kernel: hdc: dma_intr: status=0x51 { DriveReady SeekComplete Error } 
> > linux kernel: hdc: dma_intr: error=0x84 { DriveStatusError BadCRC }
> 
> I've just had the same problem. My setup: 4 Maxtor 160G connected to a
> Promise 133TX2 card, one of them was in an Icy Dock removable rack, the
> three remaining were directly connected to the IDE cable. 
> 
> The tray-connected disk would always give us the BadCRC error upon
> resynching with the raid5 array. That kind of error is typical of bad
> cabling.
> 
> It seems the additionnal connectors and cable-length in these IDE trays
> is too much to bear for picky/sensitive ATA133 drives. In any case the
> BadCRC disappeared the moment the drive was directly connected the IDE
> ribbon.

It's probably far more the quality of the connectors and such than the
length of the cables.  

> hdparm -t /dev/md1 gives me over 100MB/s on IDE raid5. Incredible! Over
> twice what a top-of-the-line 15k scsi drive gives me.

Are you saying that a RAID 5 array gives you better performance than a
single disk?  Make sense to me.  I'd be far more interested in a real
benchmark, rather than hdparm.  Across given runs on a single disk, I've
found it to be reasonably reliable, but from one disk to another, not
necessarily.  
	Greg

-- 
Gregory Leblanc <gleblanc@linuxweasel.com>

Re: some IDE trays are bad (was Re: SW-RAID 1 and kernel 2.4.18)

[Maurice Hilarius]

With regards to your message at 03:10 PM 12/3/02, Gregory Leblanc. Where 
you stated:
>It's probably far more the quality of the connectors and such than the
>length of the cables.
Actually in my experience it is both.
Also the fact that adding more connectors does attenuate a signal.
However we have used the "Icy Dock" trays on occasion,  and I found the 
order of importance for success and failure, in order of impact were:
1) RAID card. HPT were worst, Promise 2nd, and 3Ware best.
2) Cables. The inexpensive grey 80 wire cables are not adequate for this use.
3) Canisters. Icy dock are about typical of any of them. The circuit board 
used to manage the hot-swap does have some impact on the connection, but it 
simply seems to be mostly a matter of more connectors and/or longer cabling 
makes it more sensitive.
Timing issues also creep up.
I have seen a case where a Promise ATA133 card would not negotiate full 
speed with the drives when in a 32 bit, 5V slot, but would succeed when in 
a 64 bit 3.3V slot on the same motherboard.
Even though the cards are only 32 bit.

> > hdparm -t /dev/md1 gives me over 100MB/s on IDE raid5. Incredible! Over
> > twice what a top-of-the-line 15k scsi drive gives me.
I would not consider hdparm to be a reliable test for this type of situation.
bonnie++, using a file size at least 2X real system memory is more 
representative of reality.



With our best regards,

Maurice W. Hilarius       Telephone: 01-780-456-9771
Hard Data Ltd.               FAX:       01-780-456-9772
11060 - 166 Avenue        mailto:maurice@harddata.com
Edmonton, AB, Canada      http://www.harddata.com/
    T5X 1Y3

Ask me about NAS and near-line storage