Hi,
during a stress test (sunix-next kernel 3.18 rc3) i got some strange errors
on 2 devices with a port multiplier (only one hdd is connected):
[141223.041206] ata1: illegal qc_active transition (00000001->40000001)
[141223.049907] ata1.00: failed to read SCR 1 (Emask=0x40)
[141223.055189] ata1.01: failed to read SCR 1 (Emask=0x40)
[141223.060543] ata1.15: exception Emask 0x2 SAct 0x0 SErr 0x400001 action
0x6 frozen
[141223.068152] ata1.15: SError: { RecovData Handshk }
[141223.073135] ata1.00: exception Emask 0x100 SAct 0x1 SErr 0x0 action 0x6
frozen
[141223.080515] ata1.00: failed command: WRITE FPDMA QUEUED
[141223.085892] ata1.00: cmd 61/08:00:00:c9:d3/00:00:1a:00:00/40 tag 0 ncq
4096 out
[141223.085892] res 40/00:04:00:c9:d3/00:00:1a:00:00/40 Emask
0x100 (unknown error)
[141223.101543] ata1.00: status: { DRDY }
[141223.105342] ata1.01: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6
frozen
[141223.112794] ata1.15: hard resetting link
[141223.679395] ata1.15: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
[141223.689560] ata1.00: hard resetting link
[141224.259793] ata1.00: SATA link up 3.0 Gbps (SStatus 123 SControl 320)
[141224.291129] ata1.01: hard resetting link
[141224.670056] ata1.01: SATA link down (SStatus 0 SControl 320)
[141224.681979] ata1.00: configured for UDMA/133
[141224.709013] ata1: EH complete
I did the same test with NCQ disabled and this error did not happen again.
Has someone an idea why this could happen?
Tobias
Am Montag, 29. Dezember 2014 21:22:07 UTC+1 schrieb arete74:
>
> hi,
>
> 2014-12-29 11:33 GMT+01:00 <[email protected] <javascript:>>:
>
>> Hi,
>>
>> these are my test results for the hdd speed with the Marvel PMP
>> MV88SM9602:
>>
>> Driver information:
>>
>> hdparm -I /dev/sda
>>
>> /dev/sda:
>>
>> ATA device, with non-removable media
>> Model Number: WD10JPVT-00MS8T0
>> Serial Number: WD-WXB1A1356953
>> Firmware Revision:
>> Standards:
>> Supported: 9 8 7 6
>> Likely used: 9
>> 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: 1953525168
>> device size with M = 1024*1024: 953869 MBytes
>> device size with M = 1000*1000: 1000204 MBytes (1000 GB)
>> Capabilities:
>> LBA, IORDY(can be disabled)
>> Queue depth: 32
>> Standby timer values: spec'd by standard, with device specific
>> minimum
>> R/W multiple sector transfer: Max = 16 Current = 0
>> AdvancedPM level: unknown setting (0x0060)
>> 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:
>> * NOP cmd
>> * READ BUFFER cmd
>> * WRITE BUFFER cmd
>> * Host Protected Area feature set
>> * Look-ahead
>> * Write cache
>> * Power Management feature set
>> Security Mode feature set
>> * SMART feature set
>> * FLUSH CACHE EXT cmd
>> * Mandatory FLUSH CACHE cmd
>> * Device Configuration Overlay feature set
>> * 48-bit Address feature set
>> SET MAX security extension
>> * SET FEATURES subcommand required to spinup after power up
>> Power-Up In Standby feature set
>> * Adv. Power Management feature set
>> * DOWNLOAD MICROCODE cmd
>> * General Purpose Logging feature set
>> * SMART self-test
>> * SMART error logging
>> Security:
>> Master password revision code = 65534
>> supported
>> not enabled
>> not locked
>> not frozen
>> not expired: security count
>> supported: enhanced erase
>> 178min for SECURITY ERASE UNIT. 178min for ENHANCED SECURITY
>> ERASE UNIT.
>> Checksum: correct
>>
>> Speed tests (reading):
>>
>> # hdparm -tT /dev/sda
>>
>> /dev/sda:
>> Timing buffer-cache reads: 348 MB in 0.51 seconds = 695658 kB/s
>> Timing buffered disk reads: 294 MB in 3.00 seconds = 100205 kB/s
>> #
>>
>> time dd if=tempfile of=/dev/null bs=1M count=1024
>> 1024+0 records in
>> 1024+0 records out
>> real 0m 18.84s
>> user 0m 0.03s
>> sys 0m 5.68s
>>
>> Writing:
>>
>> time dd if=/dev/zero of=tempfile bs=1M count=1024 conv=fsync,notrunc
>> 1024+0 records in
>> 1024+0 records out
>> real 1m 33.33s
>> user 0m 0.02s
>> sys 0m 6.21s
>>
>> If you need some special test (we don't use raid for example) ask - i'll
>> perform these tests if possible.
>>
>>
> Is possible have this tests with same hd , but without PMP?
>
> regards
> Gerardo Di Iorio
>
> Tobias
>>
>>
>>
>> Am Donnerstag, 25. Dezember 2014 12:01:34 UTC+1 schrieb Tobias Andresen:
>>
>>> Yes, thats right. Forgot this to mention. Our custom A20 board has
>>> always a port multiplier on it.
>>>
>>> 2014-12-25 10:59 GMT+01:00 Hans de Goede <[email protected]
>>> <javascript:>>:
>>>
>>>> Hi,
>>>>
>>>> On 25-12-14 10:48, [email protected] <javascript:> wrote:
>>>>
>>>>> I'll check this on Monday and post the results.
>>>>>
>>>>
>>>> 3.19 has this patch:
>>>>
>>>> https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.
>>>> git/commit/drivers/ata/ahci_sunxi.c?id=35c16a8f0b994461d49ce2479c6790
>>>> 3f95045159
>>>>
>>>> Which allows you to specify ahci_sunxi.enable_pmp=1 on the kernel
>>>> commandline for use with port multipliers.
>>>>
>>>> I've been running my own tests with a port multiplier, and the reason
>>>> why
>>>> the original allwinner code has the AHCI_HFLAG_NO_PMP flag is because
>>>> while port multipliers will work without it, normal disks will break if
>>>> that flag is not set. So I've added a module option which
>>>> will remove the flag when set for use with port multipliers.
>>>>
>>>> Regards,
>>>>
>>>> Hans
>>>>
>>>>
>>>>
>>>>> Am Mittwoch, 24. Dezember 2014 15:37:26 UTC+1 schrieb arete74:
>>>>>
>>>>>>
>>>>>> hi, you can report the speed transfer with sata pm?
>>>>>>
>>>>>> regards
>>>>>>
>>>>>> 2014-12-23 22:03 GMT+01:00 <[email protected] <javascript:>>:
>>>>>>
>>>>>> The A20 supports PMP, just remove the Flag AHCI_HFLAG_NO_PMP in the
>>>>>>> sunxi
>>>>>>> ahci driver.
>>>>>>> Please take a look in the Manual of the A20 (6.15.1). The SATA
>>>>>>> interface
>>>>>>> has the following specification:
>>>>>>> Comply with SATA Spec. 2.6, and AHCI Revision 1.3 specifications
>>>>>>>
>>>>>>> This includes the PMP support.
>>>>>>>
>>>>>>> We are using a Marvel PMP and it works fine - both disks are
>>>>>>> detected and
>>>>>>> work.
>>>>>>>
>>>>>>> Regards
>>>>>>>
>>>>>>> Tobias
>>>>>>>
>>>>>>> Am Dienstag, 23. Dezember 2014 11:55:58 UTC+1 schrieb bruce bushby:
>>>>>>>
>>>>>>>
>>>>>>>>
>>>>>>>> Any progress on this? I found this thread:
>>>>>>>> http://forum.lemaker.org/thread-9207-1-1-.html
>>>>>>>>
>>>>>>>> Which states:
>>>>>>>> "....the patch seems to work with the latest 3.18 kernel from
>>>>>>>> Torvalds'
>>>>>>>> git (3.18.0.-rc5) possibly with some earlier versions..."
>>>>>>>>
>>>>>>>>
>>>>>>>> 1. [ 1.735879] ata1: SATA link up 3.0 Gbps (SStatus 123
>>>>>>>> SControl
>>>>>>>> 300)
>>>>>>>> 2. [ 1.742372] ata1.15: Port Multiplier 1.2, 0x197b:0x0325
>>>>>>>> r0, 5
>>>>>>>> ports, feat 0x5/0xf
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>> But apparently it's very slow ...although no figures given. Guess
>>>>>>>> there
>>>>>>>> is also the fear of data corruption given the lack of
>>>>>>>> uptake/testing of
>>>>>>>> AllWinner PMP
>>>>>>>>
>>>>>>>>
>>>>>>>> Bruce
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>>
>>>>>>>> On Monday, 5 May 2014 22:22:48 UTC+1, hase nase wrote:
>>>>>>>>
>>>>>>>>>
>>>>>>>>> Hi,
>>>>>>>>>
>>>>>>>>> is it possible to use an sata multiplier with a A20 ? I tried it
>>>>>>>>> on a
>>>>>>>>> cubieboard, but i only got access to sda and no other connected
>>>>>>>>> drive
>>>>>>>>>
>>>>>>>>> --
>>>>>>>>
>>>>>>> You received this message because you are subscribed to the Google
>>>>>>> Groups
>>>>>>> "linux-sunxi" group.
>>>>>>> To unsubscribe from this group and stop receiving emails from it,
>>>>>>> send an
>>>>>>> email to [email protected] <javascript:>.
>>>>>>> For more options, visit https://groups.google.com/d/optout.
>>>>>>>
>>>>>>>
>>>>>>
>>>>>>
>>>>>
>>>> --
>>>> You received this message because you are subscribed to the Google
>>>> Groups "linux-sunxi" group.
>>>> To unsubscribe from this group and stop receiving emails from it, send
>>>> an email to [email protected] <javascript:>.
>>>> For more options, visit https://groups.google.com/d/optout.
>>>>
>>>
>>> --
>> You received this message because you are subscribed to the Google Groups
>> "linux-sunxi" group.
>> To unsubscribe from this group and stop receiving emails from it, send an
>> email to [email protected] <javascript:>.
>> For more options, visit https://groups.google.com/d/optout.
>>
>
>
--
You received this message because you are subscribed to the Google Groups
"linux-sunxi" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/d/optout.
