Comment 105 for bug 285892

I'm still seeing the problem in the most recent build of Natty as well:

2.6.38-8-generic #42-Ubuntu SMP Mon Apr 11 03:31:24 UTC 2011 x86_64 x86_64 x86_64 GNU/Linux
ext4 / partition for the whole drive (minus a bit of swap)

This is on a new (to me) box that was happily running Windows 7 prior to me installing Natty Beta2.

Hopefully relevant hardware information:

SAMSUNG Spinpoint F1 HD753LJ 750GB hard drive.
Intel Core i7-920 processor
JMicron Technology Corp. JMB362/JMB363 Serial ATA Controller (rev 03)
nVidia Corporation G92 [GeForce 9800 GT] (rev a2) (with the proprietary driver installed)

It happens if I set the SATA controller either in IDE or AHCI mode in the BIOS.

I've also tried the vanilla mainline kernel (2.6.38-02063803-generic #201104150912 SMP Fri Apr 15 09:15:15 UTC 2011 x86_64 x86_64 x86_64 GNU/Linux from http://kernel.ubuntu.com/~kernel-ppa/mainline/v2.6.38.3-natty/) and had the same failures.

NCQ seems to be supported everywhere that matters:

[ 3.181549] ata1.00: ATA-7: SAMSUNG HD753LJ, 1AA01114, max UDMA7
[ 3.181551] ata1.00: 1465149168 sectors, multi 16: LBA48 NCQ (depth 0/32)
...
[ 5.427976] ahci 0000:02:00.0: version 3.0
[ 5.427984] ahci 0000:02:00.0: PCI INT A -> GSI 19 (level, low) -> IRQ 19
[ 5.455655] ahci 0000:02:00.0: AHCI 0001.0000 32 slots 2 ports 3 Gbps 0x3 impl SATA mode
[ 5.455661] ahci 0000:02:00.0: flags: 64bit ncq pm led clo pmp pio slum part
[ 5.455668] ahci 0000:02:00.0: setting latency timer to 64
[ 5.456043] scsi6 : ahci
[ 5.456267] scsi7 : ahci
[ 5.456348] ata7: SATA max UDMA/133 abar m8192@0xf7dfe000 port 0xf7dfe100 irq 19
[ 5.456353] ata8: SATA max UDMA/133 abar m8192@0xf7dfe000 port 0xf7dfe180 irq 19

Here's the error that I see:

[ 190.934060] ata1.00: exception Emask 0x0 SAct 0x0 SErr 0x0 action 0x6 frozen
[ 190.934065] ata1.00: failed command: FLUSH CACHE EXT
[ 190.934073] ata1.00: cmd ea/00:00:00:00:00/00:00:00:00:00/a0 tag 0
[ 190.934074] res 40/00:00:01:4f:c2/00:00:00:00:00/00 Emask 0x4 (timeout)
[ 190.934077] ata1.00: status: { DRDY }
[ 190.934087] ata1.00: hard resetting link
[ 191.283287] ata1.01: hard resetting link
[ 196.822167] ata1.00: link is slow to respond, please be patient (ready=0)
[ 200.953882] ata1.00: SRST failed (errno=-16)
[ 200.953889] ata1.00: hard resetting link
[ 201.303204] ata1.01: hard resetting link
[ 206.842098] ata1.00: link is slow to respond, please be patient (ready=0)

What's odd is that the box seemed ok until I started copying my data over to it, now it's essentially unusable.

I can consistently lock up the drive by running a SMART scan on it (smartctl --test=short /dev/sda), so if someone needs a way to consistently repeat the error, there you go.