ATA_PIIX - soft resetting port, port is slow to respond, machine "freezes" for a few seconds

ATA_PIIX - soft resetting port, port is slow to respond, machine "freezes" for a few seconds

[Tomasz Chmielewski]

I just upgraded from 2.6.18 distributed with Debian to 2.6.22.6.

I compiled ATA_PIIX directly in the kernel.

 From time to time, the machine "freezes" for a couple of seconds, and 
I'm getting the following logs (pasted below).

I didn't have anything like that with the old IDE.

The machine runs a 2 GB Transcend IDE flash disk.

Any ideas what it might be?


ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x2 frozen
ata1.00: cmd ca/00:10:47:64:1d/00:00:00:00:00/e0 tag 0 cdb 0x0 data 8192 out
res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
ata1: port is slow to respond, please be patient (Status 0xd0)
ata1: device not ready (errno=-16), forcing hardreset
ata1: soft resetting port
ata1.00: configured for MWDMA2
ata1: EH complete
ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x2 frozen
ata1.00: cmd ca/00:10:47:64:1d/00:00:00:00:00/e0 tag 0 cdb 0x0 data 8192 out
res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
ata1: port is slow to respond, please be patient (Status 0xd0)
ata1: device not ready (errno=-16), forcing hardreset
ata1: soft resetting port
ata1.00: configured for MWDMA2
ata1: EH complete
ata1.00: limiting speed to MWDMA1:PIO4
ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x2 frozen
ata1.00: cmd ca/00:10:47:64:1d/00:00:00:00:00/e0 tag 0 cdb 0x0 data 8192 out
res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
ata1: port is slow to respond, please be patient (Status 0xd0)
ata1: device not ready (errno=-16), forcing hardreset
ata1: soft resetting port
ata1.00: configured for MWDMA1
ata1: EH complete
sd 0:0:0:0: [sda] 3985632 512-byte hardware sectors (2041 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: disabled, read cache: enabled, doesn't 
support DPO or FUA
sd 0:0:0:0: [sda] 3985632 512-byte hardware sectors (2041 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: disabled, read cache: enabled, doesn't 
support DPO or FUA


-- 
Tomasz Chmielewski
http://wpkg.org

Re: ATA_PIIX - soft resetting port, port is slow to respond, machine "freezes" for a few seconds

[Joris]

Hello Tomasz,


This appears remarkably simelar to what I'm experiencing, altough I'm
getting that on sata ports.
I'm currently at a loss on what caused this, but if there's two of us... ;-)
See: http://marc.info/?l=linux-ide&m=118812690407577&w=2

What kind of hardware are you running?


Kind regards,
Joris

Re: ATA_PIIX - soft resetting port, port is slow to respond, machine "freezes" for a few seconds

[Tomasz Chmielewski]

Joris schrieb:
> Hello Tomasz,
> 
> 
> This appears remarkably simelar to what I'm experiencing, altough I'm
> getting that on sata ports.
> I'm currently at a loss on what caused this, but if there's two of us... ;-)
> See: http://marc.info/?l=linux-ide&m=118812690407577&w=2
> 
> What kind of hardware are you running?

It's a dual core Xeon.

Root filesystem starts off a 2 GB Transcend IDE flash disk, and there is 
a 4-disk RAID-10 array behind a hardware RAID, with LVM on it.

I noticed it doesn't soft reset anymore once the kernel said:

ata1.00: limiting speed to MWDMA1:PIO4


# lspci
00:00.0 Host bridge: Intel Corporation E7320 Memory Controller Hub (rev 0c)
00:00.1 Class ff00: Intel Corporation E7320 Error Reporting Registers 
(rev 0c)
00:02.0 PCI bridge: Intel Corporation E7525/E7520/E7320 PCI Express Port 
A (rev 0c)
00:03.0 PCI bridge: Intel Corporation E7525/E7520/E7320 PCI Express Port 
A1 (rev 0c)
00:1c.0 PCI bridge: Intel Corporation 6300ESB 64-bit PCI-X Bridge (rev 02)
00:1d.0 USB Controller: Intel Corporation 6300ESB USB Universal Host 
Controller (rev 02)
00:1d.1 USB Controller: Intel Corporation 6300ESB USB Universal Host 
Controller (rev 02)
00:1d.4 System peripheral: Intel Corporation 6300ESB Watchdog Timer (rev 02)
00:1d.5 PIC: Intel Corporation 6300ESB I/O Advanced Programmable 
Interrupt Controller (rev 02)
00:1d.7 USB Controller: Intel Corporation 6300ESB USB2 Enhanced Host 
Controller (rev 02)
00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev 0a)
00:1f.0 ISA bridge: Intel Corporation 6300ESB LPC Interface Controller 
(rev 02)
00:1f.1 IDE interface: Intel Corporation 6300ESB PATA Storage Controller 
(rev 02)
00:1f.3 SMBus: Intel Corporation 6300ESB SMBus Controller (rev 02)
01:00.0 Ethernet controller: Intel Corporation 82571EB Gigabit Ethernet 
Controller (rev 06)
01:00.1 Ethernet controller: Intel Corporation 82571EB Gigabit Ethernet 
Controller (rev 06)
03:02.0 RAID bus controller: LSI Logic / Symbios Logic MegaRAID (rev 01)
04:02.0 VGA compatible controller: ATI Technologies Inc Rage XL (rev 27)
04:04.0 SCSI storage controller: Adaptec AHA-2940U/UW/D / AIC-7881U (rev 01)


-- 
Tomasz Chmielewski
http://wpkg.org

Re: ATA_PIIX - soft resetting port, port is slow to respond, machine "freezes" for a few seconds

[Tomasz Chmielewski]

Joris schrieb:
> Hello,
> 
> 
> Would this be an intel motherboard?
> I'm running on an intel 3000AHLX, also with an adaptec scsi controller, hmm...

dmidecode says it's Intel:

         Vendor: Intel Corporation
         Version: SE7320SP20.86B.P.09.00.0039.092120051351
         Release Date: 09/21/2005

System Information
         Manufacturer: Acer
         Product Name: Altos G520 Altos G520

Base Board Information
         Manufacturer: Intel
         Product Name: SE7320SP2
         Version: FRU V0.01


>> I noticed it doesn't soft reset anymore once the kernel said:
>> ata1.00: limiting speed to MWDMA1:PIO4
> 
> What kind of speed are you getting after that? Perhaps this is an
> acceptable solution...
> (I already ordered an extra adaptec sata controller to work arround
> this whole mess, but it's still interesting)

Well, it's a IDE flash disk (2 GB), so you can imagine... :)

# hdparm -t /dev/sda

/dev/sda:
  Timing buffered disk reads:   28 MB in  3.19 seconds =   8.78 MB/sec

I must say I'm amazed it's so fast.


> Btw, out on a limb here: my board has specific combinations of sata
> port usage leading to a reset. Avoiding to use sata0 (sda) (unplug the
> cable) works perfectly.
> Do you have the same symptoms?

No idea, no SATA here.


-- 
Tomasz Chmielewski
http://wpkg.org

Re: ATA_PIIX - soft resetting port, port is slow to respond, machine "freezes" for a few seconds

[Tejun Heo]

Tomasz Chmielewski wrote:
> Joris schrieb:
>> Btw, out on a limb here: my board has specific combinations of sata
>> port usage leading to a reset. Avoiding to use sata0 (sda) (unplug the
>> cable) works perfectly.
>> Do you have the same symptoms?
> 
> No idea, no SATA here.

Joris, can you please post more details about the reset failure you're
seeing?

-- 
tejun

Re: ATA_PIIX - soft resetting port, port is slow to respond, machine "freezes" for a few seconds

[Tejun Heo]

Tomasz Chmielewski wrote:
> Joris schrieb:
>> Hello Tomasz,
>>
>>
>> This appears remarkably simelar to what I'm experiencing, altough I'm
>> getting that on sata ports.
>> I'm currently at a loss on what caused this, but if there's two of
>> us... ;-)
>> See: http://marc.info/?l=linux-ide&m=118812690407577&w=2
>>
>> What kind of hardware are you running?
> 
> It's a dual core Xeon.
> 
> Root filesystem starts off a 2 GB Transcend IDE flash disk, and there is
> a 4-disk RAID-10 array behind a hardware RAID, with LVM on it.
> 
> I noticed it doesn't soft reset anymore once the kernel said:
> 
> ata1.00: limiting speed to MWDMA1:PIO4

Aieee... MWDMA2 brokenness again.  cc'ing Jeff and Alan for the record.

Thanks.

-- 
tejun

Re: ATA_PIIX - soft resetting port, port is slow to respond, machine "freezes" for a few seconds

[Tomasz Chmielewski]

Tejun Heo schrieb:
> Tomasz Chmielewski wrote:
>> Joris schrieb:
>>> Hello Tomasz,
>>>
>>>
>>> This appears remarkably simelar to what I'm experiencing, altough I'm
>>> getting that on sata ports.
>>> I'm currently at a loss on what caused this, but if there's two of
>>> us... ;-)
>>> See: http://marc.info/?l=linux-ide&m=118812690407577&w=2
>>>
>>> What kind of hardware are you running?
>> It's a dual core Xeon.
>>
>> Root filesystem starts off a 2 GB Transcend IDE flash disk, and there is
>> a 4-disk RAID-10 array behind a hardware RAID, with LVM on it.
>>
>> I noticed it doesn't soft reset anymore once the kernel said:
>>
>> ata1.00: limiting speed to MWDMA1:PIO4
> 
> Aieee... MWDMA2 brokenness again.  cc'ing Jeff and Alan for the record.

BTW, is there a way to force such a device to work in MWDMA1? So that I 
could add it to the startup scripts?

It's the -X option to hdparm, right? However, I can't get it to work.

This is a part of my hdparm -I output:

Capabilities:
         LBA, IORDY(can be disabled)
         Buffer size: 2.0kB      bytes avail on r/w long: 4
         Standby timer values: spec'd by Vendor
         R/W multiple sector transfer: Max = 1   Current = 1
         DMA: not supported
         PIO: pio0 pio1 pio2 pio3 pio4
              Cycle time: no flow control=120ns  IORDY flow control=120ns


And this is a part of dmesg output when the machine seems to freeze as 
it resets the device:

(...)
ata1: soft resetting port
ata1.00: configured for MWDMA2
ata1: EH complete
sd 0:0:0:0: [sda] 3985632 512-byte hardware sectors (2041 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
ata1.00: limiting speed to MWDMA1:PIO4
ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x2 frozen
ata1.00: cmd ca/00:00:87:21:1a/00:00:00:00:00/e0 tag 0 cdb 0x0 data 
131072 out
          res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
ata1: port is slow to respond, please be patient (Status 0xd0)
ata1: device not ready (errno=-16), forcing hardreset
ata1: soft resetting port
ata1.00: configured for MWDMA1
ata1: EH complete
sd 0:0:0:0: [sda] Write cache: disabled, read cache: enabled, doesn't 
support DPO or FUA
sd 0:0:0:0: [sda] 3985632 512-byte hardware sectors (2041 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: disabled, read cache: enabled, doesn't 
support DPO or FUA


However:

# hdparm -X mdma1 /dev/sda

/dev/sda:
  setting xfermode to 33 (multiword DMA mode1)
  HDIO_DRIVE_CMD(setxfermode) failed: Input/output error


# hdparm -X 12 /dev/sda

/dev/sda:
  setting xfermode to 12 (PIO flow control mode4)
  HDIO_DRIVE_CMD(setxfermode) failed: Input/output error



-- 
Tomasz Chmielewski
http://wpkg.org