Re: Linux v2.6.16-rc6

Re: Linux v2.6.16-rc6

[Paul Blazejowski]

[-- Attachment #1: Type: text/plain, Size: 5444 bytes --]

On recent kernel 2.6.15.6 (or any 2.6.15.x) and latest testing
2.6.16-rc6 libata detects and sets wrong UDMA modes for one of the
SATA-1 drives. This seems to be a bug.

My setup is as follows:

ASUS A8N-SLI-Premium Nforce4 mainboard
AMD Athlon X2 CPU running SMP
GCC 3.3.6
Slackware 10.2 Linux

The drives are used in RAID1 array (dmraid), they are WDC-WD2000JD
series purchased few months apart. Sata is compiled in the kernel as
module sata_nv and functions properly, no errors or any other anomalies
were noticed but the UDMA mode detection seem wrong on the second drive.

Drive one reports ata3: dev 0 configured for UDMA/100 while drive two
ata4: dev 0 configured for UDMA/133

Below is the full snippet of libata detection from dmesg:

libata version 1.20 loaded.
sata_nv 0000:00:07.0: version 0.8
ACPI: PCI Interrupt Link [APSI] enabled at IRQ 22
ACPI: PCI Interrupt 0000:00:07.0[A] -> Link [APSI] -> GSI 22 (level,
low) -> IRQ 20
PCI: Setting latency timer of device 0000:00:07.0 to 64
ata1: SATA max UDMA/133 cmd 0x9F0 ctl 0xBF2 bmdma 0xD800 irq 20
ata2: SATA max UDMA/133 cmd 0x970 ctl 0xB72 bmdma 0xD808 irq 20
ata1: no device found (phy stat 00000000)
scsi1 : sata_nv
ata2: no device found (phy stat 00000000)
scsi2 : sata_nv
ACPI: PCI Interrupt Link [APSJ] enabled at IRQ 21
ACPI: PCI Interrupt 0000:00:08.0[A] -> Link [APSJ] -> GSI 21 (level,
low) -> IRQ 21
PCI: Setting latency timer of device 0000:00:08.0 to 64
ata3: SATA max UDMA/133 cmd 0x9E0 ctl 0xBE2 bmdma 0xC400 irq 21
ata4: SATA max UDMA/133 cmd 0x960 ctl 0xB62 bmdma 0xC408 irq 21
eth0: link up.
ieee1394: Host added: ID:BUS[0-00:1023]  GUID[00023c0091065c55]
ata3: dev 0 cfg 49:2f00 82:306b 83:7e01 84:4003 85:3068 86:3c01 87:4003
88:203f
ata3: dev 0 ATA-6, max UDMA/100, 390721968 sectors: LBA48
nv_sata: Primary device added
nv_sata: Primary device removed
nv_sata: Secondary device added
nv_sata: Secondary device removed
ata3: dev 0 configured for UDMA/100
scsi3 : sata_nv
ieee1394: Host added: ID:BUS[1-00:1023]  GUID[0011d800004f6359]
ata4: dev 0 cfg 49:2f00 82:346b 83:7f61 84:4003 85:3468 86:3c41 87:4003
88:407f
ata4: dev 0 ATA-6, max UDMA/133, 390721968 sectors: LBA48
nv_sata: Primary device added
nv_sata: Primary device removed
nv_sata: Secondary device added
nv_sata: Secondary device removed
ata4: dev 0 configured for UDMA/133
scsi4 : sata_nv
  Vendor: ATA       Model: WDC WD2000JD-60K  Rev: 08.0
  Type:   Direct-Access                      ANSI SCSI revision: 05
SCSI device sdb: 390721968 512-byte hdwr sectors (200050 MB)
SCSI device sdb: drive cache: write back
SCSI device sdb: 390721968 512-byte hdwr sectors (200050 MB)
SCSI device sdb: drive cache: write back
 sdb:<4>nv_sata: Primary device added
nv_sata: Primary device removed
nv_sata: Secondary device added
nv_sata: Secondary device removed
 sdb1 sdb2 sdb3 sdb4
sd 3:0:0:0: Attached scsi disk sdb
  Vendor: ATA       Model: WDC WD2000JD-00H  Rev: 08.0
  Type:   Direct-Access                      ANSI SCSI revision: 05
SCSI device sdc: 390721968 512-byte hdwr sectors (200050 MB)
SCSI device sdc: drive cache: write back
SCSI device sdc: 390721968 512-byte hdwr sectors (200050 MB)
SCSI device sdc: drive cache: write back
 sdc:<4>nv_sata: Primary device added
nv_sata: Primary device removed
nv_sata: Secondary device added
nv_sata: Secondary device removed
 sdc1 sdc2 sdc3 sdc4
sd 4:0:0:0: Attached scsi disk sdc

lspci -vvv 

00:07.0 RAID bus controller: nVidia Corporation CK804 Serial ATA
Controller (rev f3) (prog-if 85)
        Subsystem: ASUSTeK Computer Inc.: Unknown device 815a
        Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop-
ParErr- Stepping- SERR- FastB2B-
        Status: Cap+ 66Mhz+ UDF- FastB2B+ ParErr- DEVSEL=fast >TAbort-
<TAbort- <MAbort- >SERR- <PERR-
        Latency: 0 (750ns min, 250ns max)
        Interrupt: pin A routed to IRQ 20
        Region 0: I/O ports at 09f0 [size=8]
        Region 1: I/O ports at 0bf0 [size=4]
        Region 2: I/O ports at 0970 [size=8]
        Region 3: I/O ports at 0b70 [size=4]
        Region 4: I/O ports at d800 [size=16]
        Region 5: Memory at d2002000 (32-bit, non-prefetchable)
[size=4K]
        Capabilities: [44] Power Management version 2
                Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA
PME(D0-,D1-,D2-,D3hot-,D3cold-)
                Status: D0 PME-Enable- DSel=0 DScale=0 PME-

00:08.0 RAID bus controller: nVidia Corporation CK804 Serial ATA
Controller (rev f3) (prog-if 85)
        Subsystem: ASUSTeK Computer Inc. K8N4-E Mainboard
        Control: I/O+ Mem+ BusMaster+ SpecCycle- MemWINV- VGASnoop-
ParErr- Stepping- SERR- FastB2B-
        Status: Cap+ 66Mhz+ UDF- FastB2B+ ParErr- DEVSEL=fast >TAbort-
<TAbort- <MAbort- >SERR- <PERR-
        Latency: 0 (750ns min, 250ns max)
        Interrupt: pin A routed to IRQ 21
        Region 0: I/O ports at 09e0 [size=8]
        Region 1: I/O ports at 0be0 [size=4]
        Region 2: I/O ports at 0960 [size=8]
        Region 3: I/O ports at 0b60 [size=4]
        Region 4: I/O ports at c400 [size=16]
        Region 5: Memory at d2001000 (32-bit, non-prefetchable)
[size=4K]
        Capabilities: [44] Power Management version 2
                Flags: PMEClk- DSI- D1- D2- AuxCurrent=0mA
PME(D0-,D1-,D2-,D3hot-,D3cold-)
                Status: D0 PME-Enable- DSel=0 DScale=0 PME-


Cheers!

Paul B.

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 191 bytes --]

Re: Linux v2.6.16-rc6

[Lee Revell]

On Sun, 2006-03-12 at 13:45 -0500, Paul Blazejowski wrote:
> On recent kernel 2.6.15.6 (or any 2.6.15.x) and latest testing
> 2.6.16-rc6 libata detects and sets wrong UDMA modes for one of the
> SATA-1 drives. This seems to be a bug.
> 
> My setup is as follows:
> 
> ASUS A8N-SLI-Premium Nforce4 mainboard
> AMD Athlon X2 CPU running SMP
> GCC 3.3.6
> Slackware 10.2 Linux
> 
> The drives are used in RAID1 array (dmraid), they are WDC-WD2000JD
> series purchased few months apart. Sata is compiled in the kernel as
> module sata_nv and functions properly, no errors or any other anomalies
> were noticed but the UDMA mode detection seem wrong on the second drive.
> 
> Drive one reports ata3: dev 0 configured for UDMA/100 while drive two
> ata4: dev 0 configured for UDMA/133

This bug report is still somewhat unclear.

What are the correct modes you expect to see?

Lee

Re: Linux v2.6.16-rc6

[Paul Blazejowski]

[-- Attachment #1: Type: text/plain, Size: 4120 bytes --]

On Sun, 2006-03-12 at 16:46 -0500, Lee Revell wrote:
> On Sun, 2006-03-12 at 13:45 -0500, Paul Blazejowski wrote:
> > On recent kernel 2.6.15.6 (or any 2.6.15.x) and latest testing
> > 2.6.16-rc6 libata detects and sets wrong UDMA modes for one of the
> > SATA-1 drives. This seems to be a bug.
> > 
> > My setup is as follows:
> > 
> > ASUS A8N-SLI-Premium Nforce4 mainboard
> > AMD Athlon X2 CPU running SMP
> > GCC 3.3.6
> > Slackware 10.2 Linux
> > 
> > The drives are used in RAID1 array (dmraid), they are WDC-WD2000JD
> > series purchased few months apart. Sata is compiled in the kernel as
> > module sata_nv and functions properly, no errors or any other anomalies
> > were noticed but the UDMA mode detection seem wrong on the second drive.
> > 
> > Drive one reports ata3: dev 0 configured for UDMA/100 while drive two
> > ata4: dev 0 configured for UDMA/133
> 
> This bug report is still somewhat unclear.
> 
> What are the correct modes you expect to see?
> 
> Lee
> 
> 

I belive the modes should say DMA100 because UDMA133 would be mode ATA-7
and DMA100 ATA-6 mode. This is the info i get from hdparm -I on the ata3
drive: DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 *udma5

while on the ata4 one:  DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3
udma4 udma5 *udma6

The thing is that the older drive is the one with the mode being set at
133 while the newer with mode 100. I belive they come from the same
factory but do carry different firmware revisons.

I also tried the drives on sata_sil (sil3114) controller and they show
the same modes being detected:

sata_sil 0000:05:0a.0: Applying R_ERR on DMA activate FIS errata fix
ata5: SATA max UDMA/100 cmd 0xF9402080 ctl 0xF940208A bmdma 0xF9402000
irq 23
ata6: SATA max UDMA/100 cmd 0xF94020C0 ctl 0xF94020CA bmdma 0xF9402008
irq 23
ata7: SATA max UDMA/100 cmd 0xF9402280 ctl 0xF940228A bmdma 0xF9402200
irq 23
ata8: SATA max UDMA/100 cmd 0xF94022C0 ctl 0xF94022CA bmdma 0xF9402208
irq 23
ata5: SATA link up 1.5 Gbps (SStatus 113)
ata5: dev 0 cfg 49:2f00 82:306b 83:7e01 84:4003 85:3068 86:3c01 87:4003
88:203f
ata5: dev 0 ATA-6, max UDMA/100, 390721968 sectors: LBA48
ata5: dev 0 configured for UDMA/100
scsi5 : sata_sil
ata6: SATA link up 1.5 Gbps (SStatus 113)
ata6: dev 0 cfg 49:2f00 82:346b 83:7f61 84:4003 85:3468 86:3c41 87:4003
88:207f
ata6: dev 0 ATA-6, max UDMA/133, 390721968 sectors: LBA48
ata6: dev 0 configured for UDMA/100
scsi6 : sata_sil
ata7: SATA link down (SStatus 0)
scsi7 : sata_sil
ata8: SATA link down (SStatus 0)
scsi8 : sata_sil
  Vendor: ATA       Model: WDC WD2000JD-60K  Rev: 08.0
  Type:   Direct-Access                      ANSI SCSI revision: 05
SCSI device sdb: 390721968 512-byte hdwr sectors (200050 MB)
sdb: Write Protect is off
sdb: Mode Sense: 00 3a 00 00
SCSI device sdb: drive cache: write back
SCSI device sdb: 390721968 512-byte hdwr sectors (200050 MB)
sdb: Write Protect is off
sdb: Mode Sense: 00 3a 00 00
SCSI device sdb: drive cache: write back
 sdb: sdb1 sdb2 sdb3 sdb4
sd 5:0:0:0: Attached scsi disk sdb
  Vendor: ATA       Model: WDC WD2000JD-00H  Rev: 08.0
  Type:   Direct-Access                      ANSI SCSI revision: 05
SCSI device sdc: 390721968 512-byte hdwr sectors (200050 MB)
sdc: Write Protect is off
sdc: Mode Sense: 00 3a 00 00
SCSI device sdc: drive cache: write back
SCSI device sdc: 390721968 512-byte hdwr sectors (200050 MB)
sdc: Write Protect is off
sdc: Mode Sense: 00 3a 00 00
SCSI device sdc: drive cache: write back
 sdc: sdc1 sdc2 sdc3 sdc4
sd 6:0:0:0: Attached scsi disk sdc

I also see a difference with the transfer rates from hdparm -Tt:

ata3 drive (mode UDMA100) shows:

Timing buffered disk reads:  172 MB in  3.00 seconds =  57.30 MB/sec

while ata4 drive (mode UDMA133) shows:

Timing buffered disk reads:  118 MB in  3.03 seconds =  38.96 MB/sec

At this point is this due to drive capabilites in regards to modes
supported, broken drive? or libata code bug? I am trying to be as clear
as possible, anything else i should provide?

Thanks,

Paul B.

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 191 bytes --]

Re: Linux v2.6.16-rc6

[Jeff Garzik]

Paul Blazejowski wrote:
> sata_sil 0000:05:0a.0: Applying R_ERR on DMA activate FIS errata fix

sata_sil

> ata5: SATA max UDMA/100 cmd 0xF9402080 ctl 0xF940208A bmdma 0xF9402000
> irq 23
> ata6: SATA max UDMA/100 cmd 0xF94020C0 ctl 0xF94020CA bmdma 0xF9402008
> irq 23
> ata7: SATA max UDMA/100 cmd 0xF9402280 ctl 0xF940228A bmdma 0xF9402200
> irq 23
> ata8: SATA max UDMA/100 cmd 0xF94022C0 ctl 0xF94022CA bmdma 0xF9402208
> irq 23

host max udma5

> ata5: dev 0 ATA-6, max UDMA/100, 390721968 sectors: LBA48
> ata5: dev 0 configured for UDMA/100

dev max udma5, configured for udma5

> ata6: dev 0 ATA-6, max UDMA/133, 390721968 sectors: LBA48
> ata6: dev 0 configured for UDMA/100

dev max udma6, configured for host maximum udma5

Everything looks correct.

	Jeff

Re: Linux v2.6.16-rc6

[Jan Engelhardt]

>
>I belive the modes should say DMA100 because UDMA133 would be mode ATA-7
>and DMA100 ATA-6 mode. This is the info i get from hdparm -I on the ata3
>drive: DMA: mdma0 mdma1 mdma2 udma0 udma1 udma2 udma3 udma4 *udma5
>

  UDMA4 = 66
  UDMA5 = 100
  UDMA6 = 133

Has afaics nothing to do with "ATA-5" or -6 or -7 as reported by smartctl 
"ATA version".


Jan Engelhardt
-- 

Re: Linux v2.6.16-rc6

[Jeff Garzik]

Paul Blazejowski wrote:
> sata_nv 0000:00:07.0: version 0.8

sata_nv

> ata3: SATA max UDMA/133 cmd 0x9E0 ctl 0xBE2 bmdma 0xC400 irq 21
> ata4: SATA max UDMA/133 cmd 0x960 ctl 0xB62 bmdma 0xC408 irq 21

host max udma6

> ata3: dev 0 ATA-6, max UDMA/100, 390721968 sectors: LBA48
> ata3: dev 0 configured for UDMA/100

dev max udma5, configured for max speed

> ata4: dev 0 ATA-6, max UDMA/133, 390721968 sectors: LBA48
> ata4: dev 0 configured for UDMA/133

dev max udma6, configured for max speed

Everything is correct.

	Jeff

Re: Linux v2.6.16-rc6

[Paul Blazejowski]

[-- Attachment #1: Type: text/plain, Size: 818 bytes --]

On Sun, 2006-03-12 at 17:54 -0500, Jeff Garzik wrote:
> Paul Blazejowski wrote:
> > sata_nv 0000:00:07.0: version 0.8
> 
> sata_nv
> 
> > ata3: SATA max UDMA/133 cmd 0x9E0 ctl 0xBE2 bmdma 0xC400 irq 21
> > ata4: SATA max UDMA/133 cmd 0x960 ctl 0xB62 bmdma 0xC408 irq 21
> 
> host max udma6
> 
> > ata3: dev 0 ATA-6, max UDMA/100, 390721968 sectors: LBA48
> > ata3: dev 0 configured for UDMA/100
> 
> dev max udma5, configured for max speed
> 
> > ata4: dev 0 ATA-6, max UDMA/133, 390721968 sectors: LBA48
> > ata4: dev 0 configured for UDMA/133
> 
> dev max udma6, configured for max speed
> 
> Everything is correct.
> 
> 	Jeff
> 
> 
> 

Jeff, thank you for confirming that everything looks correct. Next time
i will be buying matching drives at the same time :-).

Cheers!

Paul B.

[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 191 bytes --]

Re: Linux v2.6.16-rc6

[Bill Davidsen]

Paul Blazejowski wrote:
> On Sun, 2006-03-12 at 17:54 -0500, Jeff Garzik wrote:
>> Paul Blazejowski wrote:
>>> sata_nv 0000:00:07.0: version 0.8
>> sata_nv
>>
>>> ata3: SATA max UDMA/133 cmd 0x9E0 ctl 0xBE2 bmdma 0xC400 irq 21
>>> ata4: SATA max UDMA/133 cmd 0x960 ctl 0xB62 bmdma 0xC408 irq 21
>> host max udma6
>>
>>> ata3: dev 0 ATA-6, max UDMA/100, 390721968 sectors: LBA48
>>> ata3: dev 0 configured for UDMA/100
>> dev max udma5, configured for max speed
>>
>>> ata4: dev 0 ATA-6, max UDMA/133, 390721968 sectors: LBA48
>>> ata4: dev 0 configured for UDMA/133
>> dev max udma6, configured for max speed
>>
>> Everything is correct.
>>
>> 	Jeff
>>
>>
>>
> 
> Jeff, thank you for confirming that everything looks correct. Next time
> i will be buying matching drives at the same time :-).

Since they are the same drive modulo firmware, you might contemplate 
upgrading all to the same level. NOTE: that's just a comment, not a 
recommendation.
-- 
    -bill davidsen (davidsen@tmr.com)
"The secret to procrastination is to put things off until the
  last possible moment - but no longer"  -me