On 4/16/07, Rodrigo Severo <rodrigo@xxxxxxxxxxxxxxxxxxx> wrote:
On 4/15/07, Rodrigo Severo <rodrigo@xxxxxxxxxxxxxxxxxxx> wrote: > > I have this cheap SATA addon card with an ULI chipset. > > A have a linear raid over 3 disks one PATA, hda and two SATAs, sda and sdb. > > When copying data to the raid device I get log messages like the following: > > Apr 15 10:54:20 [kernel] ata1.00: exception Emask 0x0 SAct 0x0 SErr > 0x0 action 0x2 frozen > Apr 15 10:54:20 [kernel] ata1.00: cmd > 35/00:00:df:90:0e/00:04:0b:00:00/e0 tag 0 cdb 0x0 data 524288 out > Apr 15 10:54:20 [kernel] res > 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout) > Apr 15 10:54:27 [kernel] ata1: port is slow to respond, please be > patient (Status 0xd0) > Apr 15 10:54:48 [kernel] ata1: port failed to respond (30 secs, Status 0xd0) > Apr 15 10:54:48 [kernel] ata1: soft resetting port > Apr 15 10:54:48 [kernel] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300) > Apr 15 10:54:48 [kernel] ATA: abnormal status 0xD0 on port 0x9007 > - Last output repeated 6 times - > Apr 15 10:54:48 [kernel] ata1.00: configured for UDMA/133 > Apr 15 10:54:48 [kernel] ata1: EH complete > Apr 15 10:54:48 [kernel] SCSI device sda: 488397168 512-byte hdwr > sectors (250059 MB) > Apr 15 10:54:48 [kernel] sda: Write Protect is off > Apr 15 10:54:48 [kernel] SCSI device sda: write cache: enabled, read > cache: enabled, doesn't support DPO or FUA > > All references I found to this kind of message where related to some > driver issue and not hardware problems. Can this be the case? In search for a solution for this issue I bought a new HD to replace the one presenting the problem above. Now I have a SAMSUNG HD400LJ in place of the previous ST3250820AS. The problem remains the same. When I put a Maxtor 6L300S0 to perform the same hole as the Samsung or the Seagate, I couldn't trigger the exception. I bet this happened because Maxtor is immune to this issue and the Samsung (which seems to be affected) was barely used.
Now with kernel 2.6.21-rc6, addon board reattached and cables changed I still get messages like the following every 10 minutes or so under high load: Apr 16 13:03:27 [kernel] ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x2 frozen Apr 16 13:03:27 [kernel] ata1.00: cmd 35/00:00:91:fd:06/00:04:0b:00:00/e0 tag 0 cdb 0x0 data 524288 out Apr 16 13:03:27 [kernel] res 40/00:00:00:00:00/00:00:00:00:00/00 Emask 0x4 (timeout) Apr 16 13:03:35 [kernel] ata1: port is slow to respond, please be patient (Status 0xd0) Apr 16 13:03:58 [kernel] ata1: port failed to respond (30 secs, Status 0xd0) Apr 16 13:03:58 [kernel] ata1: soft resetting port Apr 16 13:03:58 [kernel] ata1: SATA link up 1.5 Gbps (SStatus 113 SControl 300) Apr 16 13:03:58 [kernel] ata1.00: configured for UDMA/133 Apr 16 13:03:58 [kernel] ata1: EH complete Apr 16 13:03:58 [kernel] SCSI device sda: 781422768 512-byte hdwr sectors (400088 MB) Apr 16 13:03:58 [kernel] sda: Write Protect is off Apr 16 13:03:58 [kernel] SCSI device sda: write cache: enabled, read cache: enabled, doesn't support DPO or FUA Is this expected behavior? Rodrigo Severo - To unsubscribe from this list: send the line "unsubscribe linux-ide" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
