linux-kernel - Re: Abysmal PATA IDE performance

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Thu, 9 Nov 2006 15:17:00 +0000
From:	"Alessandro Suardi" <alessandro.suardi@...il.com>
To:	Stephen.Clark@...lark.us
Cc:	"Arjan van de Ven" <arjan@...radead.org>,
	"\"\\\"J.A.\\\" Magallón\"" <jamagallon@....com>,
	"Björn Steinbrink" <B.Steinbrink@....de>,
	"Mark Lord" <lkml@....ca>,
	linux-kernel <linux-kernel@...r.kernel.org>,
	alan@...rguk.ukuu.org.uk
Subject: Re: Abysmal PATA IDE performance

On 11/9/06, Stephen Clark <Stephen.Clark@...lark.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@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/