Messages in this thread |  | | | Date | Thu, 9 Nov 2006 15:17:00 +0000 | | From | "Alessandro Suardi" <> | | Subject | Re: Abysmal PATA IDE performance |
| |
On 11/9/06, Stephen Clark <Stephen.Clark@seclark.us> wrote: > Arjan van de Ven wrote: > > >>Probably your drives are renamed. > >>Before you had (wild guess, look at your boot log messages): > >>- ata bus -> hdc,hdd > >>- sata -> sda (if you really have any sata bus...) > >> > >>Now all hdX become sdX, and PATA is detected _before_ SATA, so you names > >>probaly became: > >>- ata via libata -> sda (HD), sr0 (CDROM) > >>- sata -> sdb. > >> > >> > > > >on fedora this doesn't matter (due to mount-by-label) > > > >the bigger problem I suspect is that the sata modules aren't part of the > >initrd! > > > >you can force the issue by adding > > > >alias scsi_hostadapter1 ata_piix > > > >to the /etc/modprobe.conf file, and then recreating the initrd > >(see the mkinitrd tool, or just install the kernel rpm) > > > > > > > > > > > > > Thanks all. > > Arjan, using combined_mode=libata and making a new ramdisk increased my > xfer rate from 1.xx mb/sec to 28.xx mb/sec. > > I am curious as to why my friends dell inspiron 8200 with a 1.8ghz p4 > and the same drive using the same drive with FC6 and the standard ide > module gets 44 to 45 mb/sec.
The figures are so similar to the problem I recently posted that you might want to give a shot at unloading ehci_hcd module, then try again getting performance numbers from the IDE disk. In my case unloading ehci_hcd boosts IDE performance from 20 to 40MB/s (but of course kills USB2 disk performance).
--alessandro
"...when I get it, I _get_ it"
(Lara Eidemiller) - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
|  |