Promise SATAII150 TX4: strange disk ordering

Promise SATAII150 TX4: strange disk ordering

[Eyal Lebedinsky]

I needed a 4-port SATA controller and this was was picked. It seems
to work OK, however I find that Linux (2.6.12.5 and .13-rc7) see
the disks in a different order than the labelled sockets (which do
match what the BIOS detection lists at bootup).

It is not even the reverse order:
	TX4 socket	sata_promise ata*
	1		4
	2		2
	3		1
	4		3
This order looks stable - I connected a different number of disks
on some ports and this ordering was maintained.

This is the 0x3d18 card.

I saw some mention on the list. Was this resolved as "cannot fix
driver" and introducing driver options to manually order the ports?

How can I ensure stable device names (/dev/sd*)?

-- 
Eyal Lebedinsky (eyal@eyal.emu.id.au) <http://samba.org/eyal/>
	attach .zip as .dat

RE: Promise SATAII150 TX4: strange disk ordering

[Allen Bolderoff]

> driver" and introducing driver options to manually order the ports?
> 
> How can I ensure stable device names (/dev/sd*)?
> 

I use LVM.

However - this card/driver is known to break when using more than 1
drive at a time (ie accessing 2 or 3 drives at once) 

another question -- RE: Promise SATAII150 TX4: strange disk ordering

[ha haha]

Allen,

  How about another Promise Fasttrack S150 TX4 SATA
card, its PCIID is 0x105a:0x3319? Does this card also
has similar problem? 

# lspci -n
...
05:09.0 Class 0104: 105a:3319 (rev 02)
...

 From my experience, the 2 SATA hard disks connected
through Promise SATA card (0x105a:0x3319) fails much
more often than another 2 SATA hard disks directly
connected to motherboard, as often as 4 times! I just
don't know why for a while.

 Please advice. Thanks a lot.



--- Allen Bolderoff <allen@gist.net.au> wrote:

> > driver" and introducing driver options to manually
> order the ports?
> > 
> > How can I ensure stable device names (/dev/sd*)?
> > 
> 
> I use LVM.
> 
> However - this card/driver is known to break when
> using more than 1
> drive at a time (ie accessing 2 or 3 drives at once)
> 
> 
> 
> 
> 
> -
> To unsubscribe from this list: send the line
> "unsubscribe linux-ide" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at 
> http://vger.kernel.org/majordomo-info.html
> 


__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com 

RE: Promise SATAII150 TX4: strange disk ordering

[Erik Slagter]

[-- Attachment #1: Type: text/plain, Size: 495 bytes --]

On Fri, 2005-08-26 at 12:35 +0930, Allen Bolderoff wrote:
> > driver" and introducing driver options to manually order the ports?
> > How can I ensure stable device names (/dev/sd*)?

> I use LVM.
> 
> However - this card/driver is known to break when using more than 1
> drive at a time (ie accessing 2 or 3 drives at once) 

Interesting. I am using a TX2 with two drives attached as softraid-1 (so
they are accessed at the same time all of the time) and I have no
problems at all.

[-- Attachment #2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 2115 bytes --]

Re: Promise SATAII150 TX4: strange disk ordering

[Jeff Garzik]

Eyal Lebedinsky wrote:
> I needed a 4-port SATA controller and this was was picked. It seems
> to work OK, however I find that Linux (2.6.12.5 and .13-rc7) see
> the disks in a different order than the labelled sockets (which do
> match what the BIOS detection lists at bootup).
> 
> It is not even the reverse order:
> 	TX4 socket	sata_promise ata*
> 	1		4
> 	2		2
> 	3		1
> 	4		3
> This order looks stable - I connected a different number of disks
> on some ports and this ordering was maintained.

sata_promise driver just presents the devices in the order that the 
board maker has wired each port to the chip.  What may be labelled "port 
3" on the board might be wired to the chip's port-0.  sata_promise just 
presents what it is given.

	Jeff

Re: Promise SATAII150 TX4: strange disk ordering

[Eyal Lebedinsky]

Jeff Garzik wrote:
> Eyal Lebedinsky wrote:
> 
>> I needed a 4-port SATA controller and this was was picked. It seems
>> to work OK, however I find that Linux (2.6.12.5 and .13-rc7) see
>> the disks in a different order than the labelled sockets (which do
>> match what the BIOS detection lists at bootup).
>>
>> It is not even the reverse order:
>>     TX4 socket    sata_promise ata*
>>     1        4
>>     2        2
>>     3        1
>>     4        3
>> This order looks stable - I connected a different number of disks
>> on some ports and this ordering was maintained.
> 
> 
> sata_promise driver just presents the devices in the order that the
> board maker has wired each port to the chip.  What may be labelled "port
> 3" on the board might be wired to the chip's port-0.  sata_promise just
> presents what it is given.
> 
>     Jeff

Seeing how people trust these number, the confusion is risky. I may
remove the wrong raid disk when it is reported offline and lose the
lot.

If we know the wiring (I assume this is stable for each board) why
not arrange the logical ports accordingly? Much more user friendly.

Thanks

-- 
Eyal Lebedinsky (eyal@eyal.emu.id.au) <http://samba.org/eyal/>
	attach .zip as .dat

Re: Promise SATAII150 TX4: strange disk ordering

[Thorild Selen]

allen@gist.net.au (Allen Bolderoff) writes:
> However - this card/driver is known to break when using more than 1
> drive at a time (ie accessing 2 or 3 drives at once) 

I only have experience with the SATA150 TX4 (which uses the same
driver), but it quite obviously breaks somewhere between 2.6.10 and
2.6.11. Several people have been reporting problems with sata_promise,
using several disks simultaneously with a kernel later than 2.6.10.

Moving the entire SCSI/libata code from 2.6.10 into a more recent
kernel (i tried 2.6.12.3) works fine, and appears to fix the bug. So
the bug should be in SCSI/libata somewhere (but I guess this was
obvious anyway...).

It would be great indeed if someone with a system that exhibits the
problem and some time to spare could try moving SCSI/libata code piece
by piece from 2.6.10 and 2.6.11 to try to pinpoint which change
introduced the problem. (Does anyone have any better ideas?)

(The changes in sata_promise between 2.6.10 and 2.6.11 are very small
-- the only significant changes appear to be some added PCI ids, a
writel() added in pdc_interrupt(), and the addition and handling of
the pci_dev_busy flag -- but I assume that the bug could as well hide
elsewhere in the SCSI/libata code.)


Thorild Selén
Datorföreningen Update / Update Computer Club, Uppsala, SE

Re: Promise SATAII150 TX4: strange disk ordering

[Brad Campbell]

Thorild Selen wrote:
> allen@gist.net.au (Allen Bolderoff) writes:
>> However - this card/driver is known to break when using more than 1
>> drive at a time (ie accessing 2 or 3 drives at once) 
> 
> I only have experience with the SATA150 TX4 (which uses the same
> driver), but it quite obviously breaks somewhere between 2.6.10 and
> 2.6.11. Several people have been reporting problems with sata_promise,
> using several disks simultaneously with a kernel later than 2.6.10.

In one machine, I'm using 15 disks on 4 SATA150TX4 cards with 2.6.11.7 and have been now for over 4 
months.. it's working perfectly.. not so much as a glitch.

My other box is still running 2.6.10-pre10 with 12 disks on 3 SATA150TX4 cards and the same.. no 
glitches

Brad
-- 
"Human beings, who are almost unique in having the ability
to learn from the experience of others, are also remarkable
for their apparent disinclination to do so." -- Douglas Adams

Re: Promise SATAII150 TX4: strange disk ordering

[Thorild Selen]

Brad Campbell writes:
 > In one machine, I'm using 15 disks on 4 SATA150TX4 cards with
 > 2.6.11.7 and have been now for over 4 months.. it's working
 > perfectly.. not so much as a glitch.

Is this a single-processor system without hyperthreading or the like?
In that case, it could be that the problem only appears on SMP/HT
systems, which would be interesting to know.

(I was hit by the bug on a single-processor Xeon system, but with HT
enabled. I never thought of testing if disabling HT would make the bug
disappear or not. And now that the system is up and running again, I
don't really have the possibility to experiment with it.)

If you have partitions on different devices that you can spare and
feel a little risky, you can try running badblocks -w (WARNING: this
will destroy any data on the disk/partition!) on several disks
simultaneously.  That appears to be the simplest way to quickly
reproduce the bug.


Thorild Selén
Datorföreningen Update / Update Computer Club, Uppsala, SE

Re: Promise SATAII150 TX4: strange disk ordering

[Brad Campbell]

Thorild Selen wrote:
> Brad Campbell writes:
>  > In one machine, I'm using 15 disks on 4 SATA150TX4 cards with
>  > 2.6.11.7 and have been now for over 4 months.. it's working
>  > perfectly.. not so much as a glitch.
> 
> Is this a single-processor system without hyperthreading or the like?
> In that case, it could be that the problem only appears on SMP/HT
> systems, which would be interesting to know.
> 
> (I was hit by the bug on a single-processor Xeon system, but with HT
> enabled. I never thought of testing if disabling HT would make the bug
> disappear or not. And now that the system is up and running again, I
> don't really have the possibility to experiment with it.)
> 
> If you have partitions on different devices that you can spare and
> feel a little risky, you can try running badblocks -w (WARNING: this
> will destroy any data on the disk/partition!) on several disks
> simultaneously.  That appears to be the simplest way to quickly
> reproduce the bug.

These 15 drives are in a RAID-6 that gets thrashed from time to time quite hard.. so there is almost 
*always* simultaneous IO to them.. But it is certainly a UP machine (both of them are).
This one has 15 drives RAID-6, the other has 10 drives RAID-5 and 3 drives RAID-5 (two on the 
Promise ctrlr and one on the on-board VIA)

No free partitions to spare, sorry.. all md's are pretty full.
However I did all sorts of badblocks/dd/bonnie runs when I was burning in the box and never had an 
issue at all.

-- 
"Human beings, who are almost unique in having the ability
to learn from the experience of others, are also remarkable
for their apparent disinclination to do so." -- Douglas Adams

Re: Promise SATAII150 TX4: strange disk ordering

[Ian Oliver]

In article <17173.49068.154562.170503@Psilocybe.Update.UU.SE>, Thorild 
Selen wrote:
> In that case, it could be that the problem only appears on SMP/HT
> systems, which would be interesting to know.

I have the problem (maybe!) with a TX2plus/PDC20375 on kernel 2.6.10 
(Ubuntu Hoary) on an Ahtlon system (so no HT or SMP)

See http://bugzilla.ubuntu.com/show_bug.cgi?id=13046

Regards

Ian

Re: Promise SATAII150 TX4: strange disk ordering

[Tyler]

First thing you can try Ian, is a vanilla kernel, to rule out ubuntu's 
custom kernel.  I would suggest trying the vanilla kernel, and the -mm tree.

Tyler.

Ian Oliver wrote:

>In article <17173.49068.154562.170503@Psilocybe.Update.UU.SE>, Thorild 
>Selen wrote:
>  
>
>>In that case, it could be that the problem only appears on SMP/HT
>>systems, which would be interesting to know.
>>    
>>
>
>I have the problem (maybe!) with a TX2plus/PDC20375 on kernel 2.6.10 
>(Ubuntu Hoary) on an Ahtlon system (so no HT or SMP)
>
>See http://bugzilla.ubuntu.com/show_bug.cgi?id=13046
>
>Regards
>
>Ian
>
>
>
>-
>To unsubscribe from this list: send the line "unsubscribe linux-ide" in
>the body of a message to majordomo@vger.kernel.org
>More majordomo info at  http://vger.kernel.org/majordomo-info.html
>
>  
>

Re: Promise SATAII150 TX4: strange disk ordering

[Ian Oliver]

In article <4315F787.3030003@dtbb.net>, Tyler wrote:
> First thing you can try Ian, is a vanilla kernel, to rule out ubuntu's 
> custom kernel.  I would suggest trying the vanilla kernel, and the -mm tree.

Sadly, it's too late for tinkering now as I've had to switch to a hardware 
configuration that works. However, guilt at not sticking with it may prompt me 
to try recreating the setup at some point.

Regards

Ian