Problem with ahci and a external sata disk

Problem with ahci and a external sata disk

[Jose Alberto Reguero]

When I try to make a ext3 fs in the disk I got a lot of erros:

Disk:

Feb 18 22:10:44 jar kernel: ata4: irq_stat 0x02400000, PHY RDY changed
Feb 18 22:10:44 jar kernel: ata4: hard resetting link
Feb 18 22:10:56 jar kernel: ata4: SATA link up 3.0 Gbps (SStatus 123 SControl 
300)
Feb 18 22:10:56 jar kernel: ata4.00: ATA-6: Seagate FreeAgent Pro, 3.AFM, max 
UDMA/133
Feb 18 22:10:56 jar kernel: ata4.00: 1465149168 sectors, multi 0: LBA48
Feb 18 22:10:56 jar kernel: ata4.00: configured for UDMA/133
Feb 18 22:10:56 jar kernel: ata4: EH complete
Feb 18 22:10:56 jar kernel: scsi 3:0:0:0: Direct-Access     ATA      Seagate 
FreeAgen 3.AF PQ: 0 ANSI: 5
Feb 18 22:10:56 jar kernel: sd 3:0:0:0: [sdd] 1465149168 512-byte hardware 
sectors (750156 MB)
Feb 18 22:10:56 jar kernel: sd 3:0:0:0: [sdd] Write Protect is off
Feb 18 22:10:56 jar kernel: sd 3:0:0:0: [sdd] Write cache: enabled, read 
cache: enabled, doesn't support DPO or FUA
Feb 18 22:10:56 jar kernel: sd 3:0:0:0: [sdd] 1465149168 512-byte hardware 
sectors (750156 MB)
Feb 18 22:10:56 jar kernel: sd 3:0:0:0: [sdd] Write Protect is off
Feb 18 22:10:56 jar kernel: sd 3:0:0:0: [sdd] Write cache: enabled, read 
cache: enabled, doesn't support DPO or FUA
Feb 18 22:10:56 jar kernel:  sdd: sdd1
Feb 18 22:10:56 jar kernel: sd 3:0:0:0: [sdd] Attached SCSI disk
Feb 18 22:10:56 jar kernel: sd 3:0:0:0: Attached scsi generic sg4 type 0

Errors:

Feb 18 22:12:48 jar kernel: ata4.00: exception Emask 0x0 SAct 0x0 SErr 0x0 
action 0x2
Feb 18 22:12:48 jar kernel: ata4.00: irq_stat 0x40000001
Feb 18 22:12:48 jar kernel: ata4.00: cmd ca/00:00:65:2d:00/00:00:00:00:00/e0 
tag 0 dma 131072 out
Feb 18 22:12:48 jar kernel:          res 51/84:00:64:2e:00/00:00:00:00:00/e0 
Emask 0x10 (ATA bus error)
Feb 18 22:12:48 jar kernel: ata4.00: status: { DRDY ERR }
Feb 18 22:12:48 jar kernel: ata4.00: error: { ICRC ABRT }
Feb 18 22:12:48 jar kernel: ata4: hard resetting link

Feb 18 22:12:48 jar kernel: ata4.00: configured for UDMA/133Feb 18 22:12:48 
jar kernel: ata4: EH complete                                                       
Feb 18 22:12:48 jar kernel: sd 3:0:0:0: [sdd] 1465149168 512-byte hardware 
sectors (750156 MB)                                                                  
Feb 18 22:12:48 jar kernel: sd 3:0:0:0: [sdd] Write Protect is off              
Feb 18 22:12:48 jar kernel: sd 3:0:0:0: [sdd] Write cache: enabled, read 
cache: enabled, doesn't support DPO or FUA                                             
Feb 18 22:12:49 jar kernel: ata4.00: exception Emask 0x0 SAct 0x0 SErr 0x0 
action 0x2                                                                           
Feb 18 22:12:49 jar kernel: ata4.00: irq_stat 0x40000001                        
Feb 18 22:12:49 jar kernel: ata4.00: cmd ca/00:00:4f:06:28/00:00:00:00:00/e0 
tag 0 dma 131072 out                                                               
Feb 18 22:12:49 jar kernel:          res 51/84:00:4e:07:28/00:00:00:00:00/e0 
Emask 0x10 (ATA bus error)
Feb 18 22:12:49 jar kernel: ata4.00: status: { DRDY ERR }
Feb 18 22:12:49 jar kernel: ata4.00: error: { ICRC ABRT }
Feb 18 22:12:49 jar kernel: ata4: hard resetting link

Feb 18 22:12:49 jar kernel: ata4.00: configured for UDMA/133
Feb 18 22:12:49 jar kernel: ata4: EH complete
Feb 18 22:12:49 jar kernel: sd 3:0:0:0: [sdd] 1465149168 512-byte hardware 
sectors (750156 MB)
Feb 18 22:12:49 jar kernel: sd 3:0:0:0: [sdd] Write Protect is off
Feb 18 22:12:49 jar kernel: sd 3:0:0:0: [sdd] Write cache: enabled, read 
cache: enabled, doesn't support DPO or FUA
Feb 18 22:12:50 jar kernel: ata4.00: exception Emask 0x0 SAct 0x0 SErr 0x0 
actio
n 0x2
Feb 18 22:12:50 jar kernel: ata4.00: irq_stat 0x40000001
Feb 18 22:12:50 jar kernel: ata4.00: cmd ca/00:00:4f:08:60/00:00:00:00:00/e0 
tag 0 dma 131072 out
Feb 18 22:12:50 jar kernel:          res 51/84:00:4e:09:60/00:00:00:00:00/e0 
Emask 0x10 (ATA bus error)
Feb 18 22:12:50 jar kernel: ata4.00: status: { DRDY ERR }
Feb 18 22:12:50 jar kernel: ata4.00: error: { ICRC ABRT }
Feb 18 22:12:50 jar kernel: ata4: hard resetting link

Jose Alberto

Re: Problem with ahci and a external sata disk

[Tejun Heo]

Jose Alberto Reguero wrote:
> When I try to make a ext3 fs in the disk I got a lot of erros:

Can you please try 2.6.25-rc4 and see whether it behaves any
differently.  The initial errors should be about the same but EH should
slow the PHY to 1.5Gbps quickly and that seems to solve many PHY related
problems on eSATA connectors.

Thanks.

-- 
tejun

Re: Problem with ahci and a external sata disk

[Jose Alberto Reguero]

El Jueves, 6 de Marzo de 2008, Tejun Heo escribió:
> Jose Alberto Reguero wrote:
> > When I try to make a ext3 fs in the disk I got a lot of erros:
>
> Can you please try 2.6.25-rc4 and see whether it behaves any
> differently.  The initial errors should be about the same but EH should
> slow the PHY to 1.5Gbps quickly and that seems to solve many PHY related
> problems on eSATA connectors.
>
> Thanks.

I try with kernel 2.6.25-rc4 but when the limiting speed to 1.5g the device 
can't recover.
I try whith the option:
options libata force=4:1.5g
and works, but the speed is limited until:
ata4.00: limiting speed to UDMA/33:PIO4
and still have some errors.

Do you know what Transfer mode   I must try in  libata force to not have 
erros?

Thanks.

Jose Alberto

hdparm -I

Re: Problem with ahci and a external sata disk

[Jose Alberto Reguero]

El Viernes, 7 de Marzo de 2008, Jose Alberto Reguero escribió:
> El Jueves, 6 de Marzo de 2008, Tejun Heo escribió:
> > Jose Alberto Reguero wrote:
> > > When I try to make a ext3 fs in the disk I got a lot of erros:
> >
> > Can you please try 2.6.25-rc4 and see whether it behaves any
> > differently.  The initial errors should be about the same but EH should
> > slow the PHY to 1.5Gbps quickly and that seems to solve many PHY related
> > problems on eSATA connectors.
> >
> > Thanks.
>
> I try with kernel 2.6.25-rc4 but when the limiting speed to 1.5g the device
> can't recover.
> I try whith the option:
> options libata force=4:1.5g
> and works, but the speed is limited until:
> ata4.00: limiting speed to UDMA/33:PIO4
> and still have some errors.
>
> Do you know what Transfer mode   I must try in  libata force to not have
> erros?
>
> Thanks.
>
> Jose Alberto
>

[root@jar Pls]# hdparm -I /dev/sdd

/dev/sdd:

ATA device, with non-removable media
        Model Number:       Seagate FreeAgent Pro
        Serial Number:      5QD3Q2AZ
        Firmware Revision:  3.AFM
Standards:
        Used: ATA/ATAPI-6 T13 1410D revision 1
        Supported: 6 5 4
Configuration:
        Logical         max     current
        cylinders       16383   0
        heads           16      0
        sectors/track   63      0
        --
        LBA    user addressable sectors:  268435455
        LBA48  user addressable sectors: 1465149168
        device size with M = 1024*1024:      715404 MBytes
        device size with M = 1000*1000:      750156 MBytes (750 GB)
Capabilities:
        LBA, IORDY(cannot be disabled)
        Standby timer values: spec'd by Vendor, with device specific minimum
        R/W multiple sector transfer: Max = 1   Current = 0
        DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 udma5 *udma6
             Cycle time: min=120ns recommended=120ns
        PIO: pio0 pio1 pio2 pio3 pio4
             Cycle time: no flow control=120ns  IORDY flow control=120ns
Commands/features:
        Enabled Supported:
           *    SMART feature set
           *    Power Management feature set
           *    Write cache
           *    48-bit Address feature set
           *    Mandatory FLUSH_CACHE
           *    FLUSH_CACHE_EXT
           *    SMART self-test
           *    WRITE_{DMA|MULTIPLE}_FUA_EXT
           *    SATA-I signaling speed (1.5Gb/s)
           *    SATA-II signaling speed (3.0Gb/s)
Integrity word not set (found 0x0000, expected 0x23a5)

I noticed that :
  R/W multiple sector transfer: Max = 1   Current = 0

It is important?

Jose Alberto

Re: Problem with ahci and a external sata disk

[Jose Alberto Reguero]

El Viernes, 7 de Marzo de 2008, Jose Alberto Reguero escribió:
> El Viernes, 7 de Marzo de 2008, Jose Alberto Reguero escribió:
> > El Jueves, 6 de Marzo de 2008, Tejun Heo escribió:
> > > Jose Alberto Reguero wrote:
> > > > When I try to make a ext3 fs in the disk I got a lot of erros:
> > >
> > > Can you please try 2.6.25-rc4 and see whether it behaves any
> > > differently.  The initial errors should be about the same but EH should
> > > slow the PHY to 1.5Gbps quickly and that seems to solve many PHY
> > > related problems on eSATA connectors.
> > >
> > > Thanks.
> >
> > I try with kernel 2.6.25-rc4 but when the limiting speed to 1.5g the
> > device can't recover.
> > I try whith the option:
> > options libata force=4:1.5g
> > and works, but the speed is limited until:
> > ata4.00: limiting speed to UDMA/33:PIO4
> > and still have some errors.
> >
> > Do you know what Transfer mode   I must try in  libata force to not have
> > erros?
> >
> > Thanks.
> >
> > Jose Alberto
>
> [root@jar Pls]# hdparm -I /dev/sdd
>
> /dev/sdd:
>
> ATA device, with non-removable media
>         Model Number:       Seagate FreeAgent Pro
>         Serial Number:      5QD3Q2AZ
>         Firmware Revision:  3.AFM
> Standards:
>         Used: ATA/ATAPI-6 T13 1410D revision 1
>         Supported: 6 5 4
> Configuration:
>         Logical         max     current
>         cylinders       16383   0
>         heads           16      0
>         sectors/track   63      0
>         --
>         LBA    user addressable sectors:  268435455
>         LBA48  user addressable sectors: 1465149168
>         device size with M = 1024*1024:      715404 MBytes
>         device size with M = 1000*1000:      750156 MBytes (750 GB)
> Capabilities:
>         LBA, IORDY(cannot be disabled)
>         Standby timer values: spec'd by Vendor, with device specific
> minimum R/W multiple sector transfer: Max = 1   Current = 0
>         DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 udma5 *udma6
>              Cycle time: min=120ns recommended=120ns
>         PIO: pio0 pio1 pio2 pio3 pio4
>              Cycle time: no flow control=120ns  IORDY flow control=120ns
> Commands/features:
>         Enabled Supported:
>            *    SMART feature set
>            *    Power Management feature set
>            *    Write cache
>            *    48-bit Address feature set
>            *    Mandatory FLUSH_CACHE
>            *    FLUSH_CACHE_EXT
>            *    SMART self-test
>            *    WRITE_{DMA|MULTIPLE}_FUA_EXT
>            *    SATA-I signaling speed (1.5Gb/s)
>            *    SATA-II signaling speed (3.0Gb/s)
> Integrity word not set (found 0x0000, expected 0x23a5)
>
> I noticed that :
>   R/W multiple sector transfer: Max = 1   Current = 0
>
> It is important?
>
> Jose Alberto
>

I did more tests. I put:

options libata force=4:1.5g,udma0

and the ICRC errors still appear. But only writing. I try with the device at 
top speed(3G) and reading the errors don't appear.
Another thing is that when limiting the speed to 1.5G, the real read speed 
don't seem to change and is about 2 times the read speed that I have with a 
SATA-I device. Is like limiting the speed to 1.5G don't do nothing. 

I will try the disk in a SATA-I port.

Thanks.

Jose Alberto

Re: Problem with ahci and a external sata disk

[Tejun Heo]

Jose Alberto Reguero wrote:
>> I noticed that :
>>   R/W multiple sector transfer: Max = 1   Current = 0
>>
>> It is important?

Nope, it's just for PIOs.

> I did more tests. I put:
> 
> options libata force=4:1.5g,udma0
> 
> and the ICRC errors still appear. But only writing. I try with the device at 
> top speed(3G) and reading the errors don't appear.

UDMA mode shouldn't affect anything unless the drive is actually PATA
bridged over SATA and configuring lower UDMA mode makes it transfer data
slower and changes transfer pattern on the link.

> Another thing is that when limiting the speed to 1.5G, the real read speed 
> don't seem to change and is about 2 times the read speed that I have with a 
> SATA-I device. Is like limiting the speed to 1.5G don't do nothing. 

1.5Gbps means 150Mbytes/s and harddrives are yet to reach such
performance level, so 1.5 or 3.0 doesn't really make any difference
performance-wise yet.

> I will try the disk in a SATA-I port.

Can you also give a shot at shorter cable?

Thanks.

-- 
tejun

Re: Problem with ahci and a external sata disk

[Jose Alberto Reguero]

El Viernes, 7 de Marzo de 2008, Jose Alberto Reguero escribió:
> El Viernes, 7 de Marzo de 2008, Jose Alberto Reguero escribió:
> > El Viernes, 7 de Marzo de 2008, Jose Alberto Reguero escribió:
> > > El Jueves, 6 de Marzo de 2008, Tejun Heo escribió:
> > > > Jose Alberto Reguero wrote:
> > > > > When I try to make a ext3 fs in the disk I got a lot of erros:
> > > >
> > > > Can you please try 2.6.25-rc4 and see whether it behaves any
> > > > differently.  The initial errors should be about the same but EH
> > > > should slow the PHY to 1.5Gbps quickly and that seems to solve many
> > > > PHY related problems on eSATA connectors.
> > > >
> > > > Thanks.
> > >
> > > I try with kernel 2.6.25-rc4 but when the limiting speed to 1.5g the
> > > device can't recover.
> > > I try whith the option:
> > > options libata force=4:1.5g
> > > and works, but the speed is limited until:
> > > ata4.00: limiting speed to UDMA/33:PIO4
> > > and still have some errors.
> > >
> > > Do you know what Transfer mode   I must try in  libata force to not
> > > have erros?
> > >
> > > Thanks.
> > >
> > > Jose Alberto
> >
> > [root@jar Pls]# hdparm -I /dev/sdd
> >
> > /dev/sdd:
> >
> > ATA device, with non-removable media
> >         Model Number:       Seagate FreeAgent Pro
> >         Serial Number:      5QD3Q2AZ
> >         Firmware Revision:  3.AFM
> > Standards:
> >         Used: ATA/ATAPI-6 T13 1410D revision 1
> >         Supported: 6 5 4
> > Configuration:
> >         Logical         max     current
> >         cylinders       16383   0
> >         heads           16      0
> >         sectors/track   63      0
> >         --
> >         LBA    user addressable sectors:  268435455
> >         LBA48  user addressable sectors: 1465149168
> >         device size with M = 1024*1024:      715404 MBytes
> >         device size with M = 1000*1000:      750156 MBytes (750 GB)
> > Capabilities:
> >         LBA, IORDY(cannot be disabled)
> >         Standby timer values: spec'd by Vendor, with device specific
> > minimum R/W multiple sector transfer: Max = 1   Current = 0
> >         DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 udma5 *udma6
> >              Cycle time: min=120ns recommended=120ns
> >         PIO: pio0 pio1 pio2 pio3 pio4
> >              Cycle time: no flow control=120ns  IORDY flow control=120ns
> > Commands/features:
> >         Enabled Supported:
> >            *    SMART feature set
> >            *    Power Management feature set
> >            *    Write cache
> >            *    48-bit Address feature set
> >            *    Mandatory FLUSH_CACHE
> >            *    FLUSH_CACHE_EXT
> >            *    SMART self-test
> >            *    WRITE_{DMA|MULTIPLE}_FUA_EXT
> >            *    SATA-I signaling speed (1.5Gb/s)
> >            *    SATA-II signaling speed (3.0Gb/s)
> > Integrity word not set (found 0x0000, expected 0x23a5)
> >
> > I noticed that :
> >   R/W multiple sector transfer: Max = 1   Current = 0
> >
> > It is important?
> >
> > Jose Alberto
>
> I did more tests. I put:
>
> options libata force=4:1.5g,udma0
>
> and the ICRC errors still appear. But only writing. I try with the device
> at top speed(3G) and reading the errors don't appear.
> Another thing is that when limiting the speed to 1.5G, the real read speed
> don't seem to change and is about 2 times the read speed that I have with a
> SATA-I device. Is like limiting the speed to 1.5G don't do nothing.
>
> I will try the disk in a SATA-I port.
>
> Thanks.
>
> Jose Alberto
> --
> 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

More tests:

When connected via USB:
[root@jar Pls]# hdparm -I /dev/sdd

/dev/sdd:

ATA device, with non-removable media
        Model Number:       ST3750640AS
        Serial Number:      5QD3Q2AZ
        Firmware Revision:  3.AFM
Standards:
        Supported: 7 6 5 4
        Likely used: 7
Configuration:
        Logical         max     current
        cylinders       16383   16383
        heads           16      16
        sectors/track   63      63
        --
        CHS current addressable sectors:   16514064
        LBA    user addressable sectors:  268435455
        LBA48  user addressable sectors: 1465149168
        device size with M = 1024*1024:      715404 MBytes
        device size with M = 1000*1000:      750156 MBytes (750 GB)
Capabilities:
        LBA, IORDY(can be disabled)
        Queue depth: 32
        Standby timer values: spec'd by Standard, no device specific minimum
        R/W multiple sector transfer: Max = 16  Current = ?
        Recommended acoustic management value: 160, current value: 0
        DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 udma5 *udma6
             Cycle time: min=120ns recommended=120ns
        PIO: pio0 pio1 pio2 pio3 pio4
             Cycle time: no flow control=240ns  IORDY flow control=120ns
Commands/features:
        Enabled Supported:
           *    SMART feature set
                Security Mode feature set
           *    Power Management feature set
           *    Write cache
           *    Look-ahead
           *    Host Protected Area feature set
           *    WRITE_BUFFER command
           *    READ_BUFFER command
           *    DOWNLOAD_MICROCODE
           *    Power-Up In Standby feature set
           *    SET_FEATURES required to spinup after power up
                SET_MAX security extension
           *    48-bit Address feature set
           *    Device Configuration Overlay feature set
           *    Mandatory FLUSH_CACHE
           *    FLUSH_CACHE_EXT
           *    SMART error logging
           *    SMART self-test
           *    General Purpose Logging feature set
           *    SATA-I signaling speed (1.5Gb/s)
           *    SATA-II signaling speed (3.0Gb/s)
           *    Native Command Queueing (NCQ)
           *    Phy event counters
                Device-initiated interface power management
           *    Software settings preservation
Security:
        Master password revision code = 65534
                supported
        not     enabled
        not     locked
        not     frozen
        not     expired: security count
        not     supported: enhanced erase
Checksum: correct

How can be so diferent that the one make with esata?

Thanks.
Jose Alberto

Re: Problem with ahci and a external sata disk

[Jose Alberto Reguero]

El Sábado, 8 de Marzo de 2008, Tejun Heo escribió:
> Jose Alberto Reguero wrote:
> >> I noticed that :
> >>   R/W multiple sector transfer: Max = 1   Current = 0
> >>
> >> It is important?
>
> Nope, it's just for PIOs.
>
> > I did more tests. I put:
> >
> > options libata force=4:1.5g,udma0
> >
> > and the ICRC errors still appear. But only writing. I try with the device
> > at top speed(3G) and reading the errors don't appear.
>
> UDMA mode shouldn't affect anything unless the drive is actually PATA
> bridged over SATA and configuring lower UDMA mode makes it transfer data
> slower and changes transfer pattern on the link.
>
> > Another thing is that when limiting the speed to 1.5G, the real read
> > speed don't seem to change and is about 2 times the read speed that I
> > have with a SATA-I device. Is like limiting the speed to 1.5G don't do
> > nothing.
>
> 1.5Gbps means 150Mbytes/s and harddrives are yet to reach such
> performance level, so 1.5 or 3.0 doesn't really make any difference
> performance-wise yet.
>
> > I will try the disk in a SATA-I port.
>
> Can you also give a shot at shorter cable?
>
> Thanks.

I have a esata 1m cable. I don't have a shorter cable.
I think I go to use only in usb mode, that appears to work well.

Thanks.
Jose Alberto

Re: Problem with ahci and a external sata disk

[Tejun Heo]

Jose Alberto Reguero wrote:
> [root@jar Pls]# hdparm -I /dev/sdd
> 
> /dev/sdd:
> 
> ATA device, with non-removable media
>         Model Number:       ST3750640AS
>         Serial Number:      5QD3Q2AZ
>         Firmware Revision:  3.AFM
>
> How can be so diferent that the one make with esata?

That's because your enclosure is emulating IDENTIFY command when
attached via SATA.  It's emulating USB mass storage device when
connected via USB but your enclosure is good enough to implement ATA
command passthrough and as hdparm issues IDENTIFY using command
passthrough, it gets to the actual drive and returns the result directly.

-- 
tejun

Re: Problem with ahci and a external sata disk

[Mark Lord]

Tejun Heo wrote:
> Jose Alberto Reguero wrote:
>> [root@jar Pls]# hdparm -I /dev/sdd
>>
>> /dev/sdd:
>>
>> ATA device, with non-removable media
>>         Model Number:       ST3750640AS
>>         Serial Number:      5QD3Q2AZ
>>         Firmware Revision:  3.AFM
>>
>> How can be so diferent that the one make with esata?
> 
> That's because your enclosure is emulating IDENTIFY command when
> attached via SATA.  It's emulating USB mass storage device when
> connected via USB but your enclosure is good enough to implement ATA
> command passthrough and as hdparm issues IDENTIFY using command
> passthrough, it gets to the actual drive and returns the result directly.
..

Hey, way cool.. that's the first enclosure I've heard of "in the wild"
that implements ATA command passthru.

Gotta remember that one ("Seagate FreeAgent Pro" USB/eSATA enclosure).