linux-ide.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* Re: sata_promise ata exceptions (2.6.20.6)
@ 2007-04-09 10:18 Mikael Pettersson
  2007-04-09 16:01 ` Phil Dibowitz
                   ` (2 more replies)
  0 siblings, 3 replies; 20+ messages in thread
From: Mikael Pettersson @ 2007-04-09 10:18 UTC (permalink / raw)
  To: linux-ide, phil

On Sat, 07 Apr 2007 16:41:04 -0700, Phil Dibowitz wrote:
>I've recently moved to a Promise Sata controller with two SATA drives in a
>RAID1 mirror. But I get lots of ata exceptions and the kernel eventually
>slows down my drive to UDMA/33.
>
>It usually happens on ata1 (sda), but sometimes it'll kick in on ata2 (sdb).
>I can definitely cause this to happen more by increasing load on the disks.
>But even low load (checking email) causes this. Full hardware and software
>specs are below, but first, the errors:
>
>ata1.00: exception Emask 0x10 SAct 0x0 SErr 0x180100 action 0x2
>ata1.00: cmd c8/00:d0:8a:31:ae/00:00:00:00:00/e0 tag 0 cdb 0x0 data 106496 in
>         res 51/0c:0f:4b:32:ae/00:00:00:00:00/e0 Emask 0x10 (ATA bus error)
>ata1: soft resetting port
>ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
>ata1.00: configured for UDMA/133
>ata1: EH complete
>SCSI device sda: 312581808 512-byte hdwr sectors (160042 MB)
>sda: Write Protect is off
>sda: Mode Sense: 00 3a 00 00
>SCSI device sda: write cache: enabled, read cache: enabled, doesn't support
>DPO or FUA
...
>Kernel: 2.6.20.6 (PREEMT & SMP)
>SATA Controller:
>  02:04.0 RAID bus controller: Promise Technology, Inc. PDC20378 (FastTrak
>  378/SATA 378) (rev 02)
>        Subsystem: ASUSTeK Computer Inc. K8V Deluxe/PC-DL Deluxe motherboard
>        Flags: bus master, 66MHz, medium devsel, latency 96, IRQ 16
>        I/O ports at df00 [size=64]
>        I/O ports at dfa0 [size=16]
>        I/O ports at dc00 [size=128]
>        Memory at feafe000 (32-bit, non-prefetchable) [size=4K]
>        Memory at feac0000 (32-bit, non-prefetchable) [size=128K]
>        Capabilities: [60] Power Management version 2
>Drives:
>  2 x Western Digital WD1600JS-00N

I've seen reports of issues like these with second-generation
Promise SATA chips and SATAII (3Gbps) drives, but this is the
first time I've seen any issues with a first-generation chip.

1. Please try 2.6.21-rc6 plus the following two patches:
   http://user.it.uu.se/~mikpe/linux/patches/2.6/patch-sata_promise-1-separate-sata-pata-ops-2.6.21-rc6
   http://user.it.uu.se/~mikpe/linux/patches/2.6/patch-sata_promise-2-error_intr-2.6.21-rc6

   This probably won't eliminate the errors, but should improve
   the level of detail in the error messages.

2. Try with a better power supply and verify that cooling is OK.
   Also verify that the SATA data and power cables are firmly attached.

   We've seen several reports of mysterious issues that eventually
   were traced to insufficient power supplies or poorly seated
   PCI cards (but in your case the chip is integrated on the mobo).

/Mikael

^ permalink raw reply	[flat|nested] 20+ messages in thread
* Re: sata_promise ata exceptions (2.6.20.6)
@ 2007-04-16  7:42 Mikael Pettersson
  0 siblings, 0 replies; 20+ messages in thread
From: Mikael Pettersson @ 2007-04-16  7:42 UTC (permalink / raw)
  To: Tomi.Orava, phil; +Cc: linux-ide, mikpe

On Sun, 15 Apr 2007 23:55:31 -0700, Phil Dibowitz wrote:
> Given that the last one was a hardware issue, I bought a new controller.
> Despite my bad luck, given my price-range promise still seemed to be the =
> one
> with the most good reports, so I went with that. I was going to go with a=
> 
> sil, but I couldn't find one..
> 
> Anyway, things are MUCH better now... but about once a week, I get:
> 
> ata2.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x2 frozen
> ata2.00: (port_status 0x00001000)
> ata2.00: cmd c8/00:80:9a:71:d0/00:00:00:00:00/ea tag 0 cdb 0x0 data 65536=
>  in
>          res 40/00:00:06:4f:c2/00:00:00:00:00/00 Emask 0x24 (host bus err=
> or)
> ata2: soft resetting port
> ata2: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
> ata2.00: configured for UDMA/133
> ata2: EH complete
> SCSI device sda: 312581808 512-byte hdwr sectors (160042 MB)
> sda: Write Protect is off
> sda: Mode Sense: 00 3a 00 00
> SCSI device sda: write cache: enabled, read cache: enabled, doesn't suppo=
> rt
> DPO or FUA
> 
> 
> It's the same port_status and Emask/SAct/SErr/action each time... only th=
> e
> cmd/res and data change (obviously those would change)...
> 
> Can anyone tell me what that means?

port_status 0x00001000 is "host bus timeout", which the manual
defines as the host bus being busy for more than 256 clock cycles
during an ATA I/O transfer.

I have no idea what would cause this error, and I've never
seen it myself.

As long as libata recovers and doesn't downgrade your transfer
speed it shouldn't pose too much of a problem.

/Mikael

^ permalink raw reply	[flat|nested] 20+ messages in thread
* Re: sata_promise ata exceptions (2.6.20.6)
@ 2007-04-14  9:27 Mikael Pettersson
  2007-04-14 12:46 ` Tomi Orava
  0 siblings, 1 reply; 20+ messages in thread
From: Mikael Pettersson @ 2007-04-14  9:27 UTC (permalink / raw)
  To: Tomi.Orava; +Cc: linux-ide

On Sat, 14 Apr 2007 10:13:12 +0300 (EEST), Tomi Orava wrote:
>I'm currently running with FC6 2990 kernel, which is based on
>2.6.21-rc3-git10 and contains also your 1.5Gbps limit patch and Promise
>Sata300TX4 port enumeration patch (does anybody know what might be the
>reason that port enumeration patch has not been accepted in to main line
>?).

Because that patch hasn't been submitted to linux-ide,
Jeff, or me?

I've seen fairly old discussions about the enumeration
order issue on 4-port cards, but no patches.

/Mikael

^ permalink raw reply	[flat|nested] 20+ messages in thread
* Re: sata_promise ata exceptions (2.6.20.6)
@ 2007-04-13 21:21 Mikael Pettersson
  2007-04-14  7:13 ` Tomi Orava
  2007-04-19 10:55 ` Tomi Orava
  0 siblings, 2 replies; 20+ messages in thread
From: Mikael Pettersson @ 2007-04-13 21:21 UTC (permalink / raw)
  To: Tomi.Orava, linux-ide

On Fri, 13 Apr 2007 21:36:41 +0300 (EEST), Tomi Orava wrote:
> Related to my previous tests, it seems that after I changed the order of the
> hard-disks connected to Promise Sata300TX4 the errors followed both of the
> 7200.10 disks. I swapped the power supply and the SATA-cables at the same
> time
> and still get the following kind of errors (and only with 7200.10, _never_
> with
> the older 7200.7 disks):

Thanks. This tells us that it's not a power or cabling issue, but some
kind of interface or programming incompatibility with the 7200.10 disks.

My theory is that either TBG clocking (which drives the SATA interfaces)
or SET FEATURE snooping (which adjusts internal parameters for different
PIO/(U)DMA modes) is borked for SATAII/3Gbps. I hope to have time to
investigate that soon. If you can limit transfer speeds to 1.5Gpbs then
that may provide a workaround for now.

/Mikael

^ permalink raw reply	[flat|nested] 20+ messages in thread
* Re: sata_promise ata exceptions (2.6.20.6)
@ 2007-04-09 21:33 Mikael Pettersson
  2007-04-09 22:02 ` Phil Dibowitz
  0 siblings, 1 reply; 20+ messages in thread
From: Mikael Pettersson @ 2007-04-09 21:33 UTC (permalink / raw)
  To: phil; +Cc: linux-ide

On Mon, 9 Apr 2007 13:26:54 -0700, Phil Dibowitz wrote:
>On Mon, Apr 09, 2007 at 12:18:09PM +0200, Mikael Pettersson wrote:
>> I've seen reports of issues like these with second-generation
>> Promise SATA chips and SATAII (3Gbps) drives, but this is the
>> first time I've seen any issues with a first-generation chip.
>>
>> 1. Please try 2.6.21-rc6 plus the following two patches:
>>    http://user.it.uu.se/~mikpe/linux/patches/2.6/patch-sata_promise-1-separate-sata-pata-ops-2.6.21-rc6
>>    http://user.it.uu.se/~mikpe/linux/patches/2.6/patch-sata_promise-2-error_intr-2.6.21-rc6
>>
>>    This probably won't eliminate the errors, but should improve
>>    the level of detail in the error messages.
>
>It doesn't appear to have changed much. After a reboot, I have:
>
>ata1.00: exception Emask 0x10 SAct 0x0 SErr 0x380100 action 0x2 frozen
>ata1.00: (port_status 0x20200000)
>ata1.00: cmd c8/00:90:f2:fb:a6/00:00:00:00:00/e0 tag 0 cdb 0x0 data 73728 in
>         res 40/00:00:01:4f:c2/00:00:00:00:00/00 Emask 0x14 (ATA bus error)
...
>Any other info I can provide?

The error decodes as:
port_status 0x20200000: Drive Error during Packet Command Cycle
(the drive signalled an error to the controller)

SErr 0x380100: CRC error, Disparity error, 10B-to-8B decoding error,
non-recoverable transient data integrity error.

My conclusion is that the link between the controller and the drive
is corrupting messages. This is almost certainly a hardware problem,
and could be a broken motherboard (you wrote that you hadn't used
the mobo's Promise chip before), bad cables, bad drives, a bad power
supply, or electrical interference.

/Mikael

^ permalink raw reply	[flat|nested] 20+ messages in thread
* sata_promise ata exceptions (2.6.20.6)
@ 2007-04-07 23:41 Phil Dibowitz
  2007-04-08 10:43 ` Ansgar Knappheide
  0 siblings, 1 reply; 20+ messages in thread
From: Phil Dibowitz @ 2007-04-07 23:41 UTC (permalink / raw)
  To: linux-ide

[-- Attachment #1: Type: text/plain, Size: 4385 bytes --]

I've recently moved to a Promise Sata controller with two SATA drives in a
RAID1 mirror. But I get lots of ata exceptions and the kernel eventually
slows down my drive to UDMA/33.

It usually happens on ata1 (sda), but sometimes it'll kick in on ata2 (sdb).
I can definitely cause this to happen more by increasing load on the disks.
But even low load (checking email) causes this. Full hardware and software
specs are below, but first, the errors:

ata1.00: exception Emask 0x10 SAct 0x0 SErr 0x180100 action 0x2
ata1.00: cmd c8/00:d0:8a:31:ae/00:00:00:00:00/e0 tag 0 cdb 0x0 data 106496 in
         res 51/0c:0f:4b:32:ae/00:00:00:00:00/e0 Emask 0x10 (ATA bus error)
ata1: soft resetting port
ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
ata1.00: configured for UDMA/133
ata1: EH complete
SCSI device sda: 312581808 512-byte hdwr sectors (160042 MB)
sda: Write Protect is off
sda: Mode Sense: 00 3a 00 00
SCSI device sda: write cache: enabled, read cache: enabled, doesn't support
DPO or FUA
ata1.00: exception Emask 0x10 SAct 0x0 SErr 0x380100 action 0x2
ata1.00: cmd c8/00:a0:12:fa:bc/00:00:00:00:00/e0 tag 0 cdb 0x0 data 81920 in
         res 51/0c:1f:93:fa:bc/00:00:00:00:00/e0 Emask 0x10 (ATA bus error)
ata1: soft resetting port
ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
ata1.00: configured for UDMA/133
ata1: EH complete
SCSI device sda: 312581808 512-byte hdwr sectors (160042 MB)
sda: Write Protect is off
sda: Mode Sense: 00 3a 00 00
SCSI device sda: write cache: enabled, read cache: enabled, doesn't support
DPO or FUA
ata1.00: limiting speed to UDMA/100
ata1.00: exception Emask 0x10 SAct 0x0 SErr 0x380100 action 0x2
ata1.00: cmd c8/00:48:2a:27:ac/00:00:00:00:00/e0 tag 0 cdb 0x0 data 36864 in
         res 51/0c:27:4b:27:ac/00:00:00:00:00/e0 Emask 0x10 (ATA bus error)
ata1: soft resetting port
ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
ata1.00: configured for UDMA/100
ata1: EH complete
SCSI device sda: 312581808 512-byte hdwr sectors (160042 MB)
sda: Write Protect is off
sda: Mode Sense: 00 3a 00 00
SCSI device sda: write cache: enabled, read cache: enabled, doesn't support
DPO or FUA
ata1.00: limiting speed to UDMA/66
ata1.00: exception Emask 0x10 SAct 0x0 SErr 0x180100 action 0x2
ata1.00: cmd c8/00:f8:6a:7a:ae/00:00:00:00:00/e0 tag 0 cdb 0x0 data 126976 in
         res 51/0c:97:cb:7a:ae/00:00:00:00:00/e0 Emask 0x10 (ATA bus error)
ata1: soft resetting port
ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300)
ata1.00: configured for UDMA/66
ata1: EH complete
SCSI device sda: 312581808 512-byte hdwr sectors (160042 MB)
sda: Write Protect is off
sda: Mode Sense: 00 3a 00 00
SCSI device sda: write cache: enabled, read cache: enabled, doesn't support
DPO or FUA


Kernel: 2.6.20.6 (PREEMT & SMP)
SATA Controller:
  02:04.0 RAID bus controller: Promise Technology, Inc. PDC20378 (FastTrak
  378/SATA 378) (rev 02)
        Subsystem: ASUSTeK Computer Inc. K8V Deluxe/PC-DL Deluxe motherboard
        Flags: bus master, 66MHz, medium devsel, latency 96, IRQ 16
        I/O ports at df00 [size=64]
        I/O ports at dfa0 [size=16]
        I/O ports at dc00 [size=128]
        Memory at feafe000 (32-bit, non-prefetchable) [size=4K]
        Memory at feac0000 (32-bit, non-prefetchable) [size=128K]
        Capabilities: [60] Power Management version 2
Drives:
  2 x Western Digital WD1600JS-00N

Other Setup Details:
  3 software RAID1 mirrors (md0, 1, 2 made up of sd{a,b}1 - 3 respectively)
  md3 is an LVM physical group with 2 volumes in it. In other words:
    /dev/md0 = /boot
    /dev/md1 = swap
    /dev/md2 = LVM:
            /dev/vg00/root = /
            /dev/vg00/home = /home

The sata controller isn't brand new, but it's never been used and is
relatively new. The sata drives and cables are fresh out of the box. Any
help would be greatly appreciated.

-- 
Phil Dibowitz                             phil@ipom.com
Open Source software and tech docs        Insanity Palace of Metallica
http://www.phildev.net/                   http://www.ipom.com/

"Never write it in C if you can do it in 'awk';
 Never do it in 'awk' if 'sed' can handle it;
 Never use 'sed' when 'tr' can do the job;
 Never invoke 'tr' when 'cat' is sufficient;
 Avoid using 'cat' whenever possible" -- Taylor's Laws of Programming



[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 252 bytes --]

^ permalink raw reply	[flat|nested] 20+ messages in thread
end of thread, other threads:[~2007-04-19 10:55 UTC | newest]

Thread overview: 20+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-04-09 10:18 sata_promise ata exceptions (2.6.20.6) Mikael Pettersson
2007-04-09 16:01 ` Phil Dibowitz
2007-04-09 20:26 ` Phil Dibowitz
2007-04-10 12:49 ` Tomi Orava
2007-04-13 18:36   ` Tomi Orava
2007-04-16  6:55   ` Phil Dibowitz
2007-04-16  7:02     ` Tomi Orava
2007-04-16  7:47       ` Phil Dibowitz
  -- strict thread matches above, loose matches on Subject: below --
2007-04-16  7:42 Mikael Pettersson
2007-04-14  9:27 Mikael Pettersson
2007-04-14 12:46 ` Tomi Orava
2007-04-13 21:21 Mikael Pettersson
2007-04-14  7:13 ` Tomi Orava
2007-04-19 10:55 ` Tomi Orava
2007-04-09 21:33 Mikael Pettersson
2007-04-09 22:02 ` Phil Dibowitz
2007-04-09 22:42   ` Greg Freemyer
2007-04-07 23:41 Phil Dibowitz
2007-04-08 10:43 ` Ansgar Knappheide
2007-04-09  6:13   ` Phil Dibowitz

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).