My Hardware: Mainboard: GA-879A-UD3 The relevant output from lspci (disc controllers):
00:11.0 SATA controller: ATI Technologies Inc SB700/SB800 SATA Controller [AHCI mode] (rev 40) 00:14.1 IDE interface: ATI Technologies Inc SB700/SB800 IDE Controller (rev 40) 04:00.0 SATA controller: JMicron Technology Corp. JMB362/JMB363 Serial ATA Controller (rev 03) 04:00.1 IDE interface: JMicron Technology Corp. JMB362/JMB363 Serial ATA Controller (rev 03) 06:00.0 SATA controller: JMicron Technology Corp. JMB362/JMB363 Serial ATA Controller (rev 02) 06:00.1 IDE interface: JMicron Technology Corp. JMB362/JMB363 Serial ATA Controller (rev 02) Used discs: Seagate ST31000524NS Firmware SN11 (according to smartctl --all), currently no FW upgrade available Western DIgital WD1003FBYX Both disc types are 24/7 discs according to their manufactures. Everytime I will talk about kernel compilation, I use the .config from the original ubuntu 10.10 server kernel and create .deb files using kernel-package. All of the issues above are the same that happened to me with the Seagate discs which I bought in the first place in combination with the mentioned mainboard. I already had a working system on those 4 discs, but connected through an PCI-E SAS controller, working like a charm. As the controller was only for testing purposes, I connected my 4 discs directly to the mainboard. Thats where all the problems begun you are describing above. I couldn't boot my system anymore, but each time, when I booted with RIP-Linux or knoppix the installed linux raid + lvm2 signatures were found and usable. No errors were reported to dmesg. Simply booting the system was not possible. As the data on the discs were not to important, I decided to install from scratch... So I booted with my ubuntu 10.10 server cd. When the installer came to the partition manager, the errors you're describing all occurred on console ALT+F4. When I hit the reset button, the mainboard's bios did not recognize the discs anymore and hung while trying to enumerate the connected discs. After a hard reboot (pulled the cable) the bios at least worked again. So I made an bios upgrade. Same problem as before. By the time I destroyed my filesystem voluntarily as I thought, that this might have something to do with a signature, the initial SAS controller had written to the discs. I tried with Ubuntu 10.04 Server - exactly the same... So every time I booted a recent Ubuntu version, 64 or 32 bit, the partition manager could not read the discs and the mainboard was not able to enumerate after soft-reset. Everytime I booted with a non Ubuntu distro, I had no problems, I concluded, that this might be an ubuntu issue, so I decided to setup the new Debian Squeeze. Worked like a charm to me. But as usual, debian is outdated by the time it's released, so I installed the ubuntu 10.10 server kernel to my debian system and guess: Yes, same problem as above.... Next step was to use the ubuntu kernel sources, compile them in debian, and boot them -> worked Now I got the vanilla kernel 2.6.37 (current stable), compiled and booted -> worked Now I knew, that's an Ubuntu Kernel issue. 2 weeks later and having returning 3 of 4 hard discs as I thought they might have a failure (transportation etc...) I decided to buy the 4 Western Digital 1TB discs to have a comparison. Setup Ubuntu 10.10 Server works perfectly. Now I setted up Ubuntu 10.10 Server to an old 160GB WD disc Next I plugged in the Seagate discs and got instantly the errors from above, so I compiled a recent stable vanilla kernel, in a native ubuntu environment and rebootet. All my Seagate discs were connected at that time of the reboot, and the system rebooted with my vanilla kernel without having any errors or performance issues. So I started my raid and lvm2, formated the /root partition on the lvm2, mounted it and all the other lvm2 partitions to the fs tree, and installed a ubuntu-minimal with debootstrap, chrooted, installed mdadm and lvm2, installed my vanilla kernel, setted up grub2 and bootet. Voila, my system's booting and running on the Seagate discs. 3 weeks have passed, since I started. But it was all worth the effort. Felix -- You received this bug notification because you are a member of Ubuntu Bugs, which is subscribed to Ubuntu. https://bugs.launchpad.net/bugs/550559 Title: hdd problems, failed command: READ FPDMA QUEUED -- ubuntu-bugs mailing list ubuntu-bugs@lists.ubuntu.com https://lists.ubuntu.com/mailman/listinfo/ubuntu-bugs
