6.7.1-rc1 - SATA controler trouble

[SeppDK]

im having speed issues with disks on my new sata controller, i have pulled every other PCI card out but the controller,

in the hopes that my setup would work correctly if i keept it simple.

 

i can see a couple of errors in the syslog, but the one that worries me the most is this:

 

Jun  3 22:16:25 Tower kernel: ata18.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen
Jun  3 22:16:25 Tower kernel: ata18.00: failed command: WRITE DMA
Jun  3 22:16:25 Tower kernel: ata18.00: cmd ca/00:08:40:10:00/00:00:00:00:00/e0 tag 29 dma 4096 out
Jun  3 22:16:25 Tower kernel:         res 40/00:01:01:4f:c2/00:00:00:00:00/00 Emask 0x4 (timeout)
Jun  3 22:16:25 Tower kernel: ata18.00: status: { DRDY }
Jun  3 22:16:25 Tower kernel: ata18: hard resetting link
Jun  3 22:16:25 Tower kernel: ata18: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
Jun  3 22:16:25 Tower kernel: ata18.00: configured for UDMA/133
Jun  3 22:16:25 Tower kernel: ata18: EH complete
Jun  3 22:16:56 Tower kernel: ata17.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen
Jun  3 22:16:56 Tower kernel: ata17.00: failed command: WRITE DMA
Jun  3 22:16:56 Tower kernel: ata17.00: cmd ca/00:08:40:10:00/00:00:00:00:00/e0 tag 12 dma 4096 out
Jun  3 22:16:56 Tower kernel:         res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
Jun  3 22:16:56 Tower kernel: ata17.00: status: { DRDY }
Jun  3 22:16:56 Tower kernel: ata17: hard resetting link
Jun  3 22:16:56 Tower kernel: ata18.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen
Jun  3 22:16:56 Tower kernel: ata18.00: failed command: WRITE DMA
Jun  3 22:16:56 Tower kernel: ata18.00: cmd ca/00:08:f8:e3:2e/00:00:00:00:00/e0 tag 4 dma 4096 out
Jun  3 22:16:56 Tower kernel:         res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
Jun  3 22:16:56 Tower kernel: ata18.00: status: { DRDY }
Jun  3 22:16:56 Tower kernel: ata18: hard resetting link
Jun  3 22:16:56 Tower kernel: ata18: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
Jun  3 22:16:56 Tower kernel: ata17: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
Jun  3 22:16:56 Tower kernel: ata18.00: configured for UDMA/133
Jun  3 22:16:56 Tower kernel: ata18.00: device reported invalid CHS sector 0
Jun  3 22:16:56 Tower kernel: ata18: EH complete
Jun  3 22:16:56 Tower kernel: ata17.00: configured for UDMA/133
Jun  3 22:16:56 Tower kernel: ata17.00: device reported invalid CHS sector 0
Jun  3 22:16:56 Tower kernel: ata17: EH complete
Jun  3 22:17:27 Tower kernel: ata18.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen
Jun  3 22:17:27 Tower kernel: ata18.00: failed command: WRITE DMA
Jun  3 22:17:27 Tower kernel: ata18.00: cmd ca/00:08:f8:e3:2e/00:00:00:00:00/e0 tag 5 dma 4096 out
Jun  3 22:17:27 Tower kernel:         res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
Jun  3 22:17:27 Tower kernel: ata18.00: status: { DRDY }
Jun  3 22:17:27 Tower kernel: ata18: hard resetting link
Jun  3 22:17:27 Tower kernel: ata18: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
Jun  3 22:17:27 Tower kernel: ata18.00: configured for UDMA/133
Jun  3 22:17:27 Tower kernel: ata18.00: device reported invalid CHS sector 0
Jun  3 22:17:27 Tower kernel: ata18: EH complete
Jun  3 22:18:22 Tower kernel: sdl: sdl1 sdl2 sdl3
Jun  3 22:18:26 Tower kernel: ata17.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen
Jun  3 22:18:26 Tower kernel: ata17.00: failed command: WRITE DMA EXT
Jun  3 22:18:26 Tower kernel: ata17.00: cmd 35/00:08:40:68:e0/00:00:e8:00:00/e0 tag 15 dma 4096 out
Jun  3 22:18:26 Tower kernel:         res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout)
Jun  3 22:18:26 Tower kernel: ata17.00: status: { DRDY }
Jun  3 22:18:26 Tower kernel: ata17: hard resetting link
Jun  3 22:18:26 Tower kernel: ata17: SATA link up 6.0 Gbps (SStatus 133 SControl 300)
Jun  3 22:18:26 Tower kernel: ata17.00: configured for UDMA/133
Jun  3 22:18:26 Tower kernel: ata17.00: device reported invalid CHS sector 0
Jun  3 22:18:26 Tower kernel: ata17: EH complete

 

 

is there any way to fix this?

 

 

tower-diagnostics-20190604-0354.zip

[itimpi]

That type of error normally means there is a SATA (or power) cabling issue.   If it is not that then there may actually be a problem with the drive itself.

[JorgeB]

3 minutes ago, SeppDK said:

is there any way to fix this?

The problem is the controller, controllers with SATA port multipliers should be avoided.

[SeppDK]

2 minutes ago, itimpi said:

That type of error normally means there is a SATA (or power) cabling issue.   If it is not that then there may actually be a problem with the drive itself.

i have the problems with 3 drives, all conneted to the same brand new controller...

2 of the drives are also brand new.

[SeppDK]

1 minute ago, johnnie.black said:

The problem is the controller, controllers with SATA port multipliers should be avoided.

okay, what sort of controller should i get then?

i just thought that a highspeed none-raid sata controller would have been a good choise...

[JorgeB]

Any LSI with a SAS2008/2308/3008 chipset in IT mode, e.g., 9201-8i, 9211-8i, 9207-8i, 9300-8i, etc and clones, like the Dell H200/H310 and IBM M1015, these latter ones need to be crossflashed.

[SeppDK]

13 minutes ago, johnnie.black said:

Any LSI with a SAS2008/2308/3008 chipset in IT mode, e.g., 9201-8i, 9211-8i, 9207-8i, 9300-8i, etc and clones, like the Dell H200/H310 and IBM M1015, these latter ones need to be crossflashed.

so something like this, and if yes, should it be the IR or IT version?

 

https://www.ebay.co.uk/itm/9212-4i-LSI-SAS-2008-Controller-Card-4-Port-SAS-SATA-RAID-Card-6GB-PCI-E-x8-x16/401750410589?var=&hash=item5d8a30c55d&enc=AQADAAADAFjVrDbVsZ8oH%2F8PNHtt9VX4%2Fw7FZcmMuqsX8uaFEduVBAK6ATtMyEc0MaGoRmTOzAL7CaPRPj%2BzKM7tBt7rWSALSvH5twxr7HE9aVrt0hO9BqpdyBk%2BSV9GXRBH0xWfX9l1AW3DmXyoGhHR0e3NI5EKIqJEUeT2ToUp3OowvmrKiwTUEhPlHxurCpe0WKgnJSXm5vkZduL0Dh4yImvIC77pt6Pb7%2FmN3R7itJlZM85sf9b1VvMYIEoVttw8kfPNbMxuKmYnXTZs7x4wau3BUk3XBemvRGL6YG1pJ1NUSQDKM8Qm8R%2FRTksiVHq6uBZdvCttmGYg809ce6%2BTFbZXCcIputkDL3zxFZDzpdRPQoT9qiOL0qY%2BkklibOw%2BAkFwvCciEL%2B7o48agcY7QVIGx4Ft3QvN1Nd3SaajgaKTXWW1KyICECV90CrMqChrf4q5818dkJ3IADcbt5TWZG9QDZp7Hq4p4g4Z1JVE8hSatD5TzrBryK2it9dAOeBLIL%2B01x45Ho19X9rZAjLyY2SNWFhkxjDjdgKDj3edpD65kinANdi6gqIhnEcHffwbL%2BNWUm4PjJVu5593vKFBmnFl2VoFLTA5lxVGnFthYar6F9DUWr1nnAwAuqoc0%2BRO4NjZbmwquIHp8KjTz2tHjrocosaIBhQIQXCiQS88lB%2FwfHhiC3aA1T8Aky%2BYm2RP6gBLBlaYIRrBMpTJNPSpLK1mt078y3DYNzW8uiI49LTW%2BBuFN%2BgqV2QjMvkDCMMujk5OVTOJcbS3mKFcxB99dhI%2F8cX%2FWBEw4pztDjN7Um0LISMwoZp2HsOmDhIUa4rXI3tNHhWsZKev%2BzB%2FtSqqwe19OY4mKA7V%2F1pE6lz%2BDq91xzzL4Aj97EGSkZheDPf1YM2ejFFrrIchwXUvXAUnxoK22jKmnwL2O7aW5Cfr2Pbn7QDRucu030ZhoF217gyW4R%2F7GzdRGfd%2BVmmbL8to%2BjbIfjZzKUKX6j3jlKb4MEq1HjWittsIxJhI7Rorn0s31KpMKw%3D%3D&checksum=401750410589be68022160c74020bc3d1d97023e2df3&frcectupt=true

 

 

[JorgeB]

2 minutes ago, SeppDK said:

IT version?

This

[SeppDK]

On 6/4/2019 at 1:14 PM, johnnie.black said:

This

thanks, for the help

[SeppDK]

fun fact... 

i got the controler, and the text for it on ebay says max 8TB disks...

but right now i have an 10 TB disk connected, and unraid have no problems reading the disk...

[JonathanM]

That's typically a reference to the largest tested disk, we passed the last hard hurdle at 2.2TB, the next one is several years away. There may be some soft limits, but typically the hardware will just work regardless of disk size for the useful lifetime of the controller.