Keith Roberts wrote:
On Wed, 12 Jan 2011, compdoc wrote:
To: 'CentOS mailing list' centos@centos.org From: compdoc compdoc@hotrodpc.com Subject: Re: [CentOS] Kernel Errors Present
Bad sectors get reallocated automatically, so you might not find any with testing. You need to see how many have been reallocated.
<snip> Maybe, but I'd fsck -C -c /dev/.... ^^ - check for bad blocks, put them in the table
mark
On Wed, 12 Jan 2011, m.roth@5-cent.us wrote:
To: CentOS mailing list centos@centos.org From: m.roth@5-cent.us Subject: Re: [CentOS] Kernel Errors Present...
Keith Roberts wrote:
On Wed, 12 Jan 2011, compdoc wrote:
To: 'CentOS mailing list' centos@centos.org From: compdoc compdoc@hotrodpc.com Subject: Re: [CentOS] Kernel Errors Present
Bad sectors get reallocated automatically, so you might not find any with testing. You need to see how many have been reallocated.
<snip> Maybe, but I'd fsck -C -c /dev/.... ^^ - check for bad blocks, put them in the table
I could do that soon
But I don't want to use DMA on this drive (/dev/hde) anyway.
In the BIOS I turn DMA off for /dev/hda and /dev/hdc, but they still show up in /proc/ide/.../settings as using_dma 1.
So is the kernel ignoring the BIOS DMA settings?
32-bit transfer mode is on in the BIOS though.
Keith
----------------------------------------------------------------- Websites: http://www.karsites.net http://www.php-debuggers.net http://www.raised-from-the-dead.org.uk
All email addresses are challenge-response protected with TMDA [http://tmda.net] -----------------------------------------------------------------
In the BIOS I turn DMA off for /dev/hda and /dev/hdc, but they still show up in /proc/ide/.../settings as using_dma 1.
say HUH? IDE PIO modes are like 3-7 MBytes/sec and require 100% CPU utilization during the transfer phase. why in dogs name would you be doing this in 2011 ?
On Wed, 12 Jan 2011, John R Pierce wrote:
To: centos@centos.org From: John R Pierce pierce@hogranch.com Subject: Re: [CentOS] Kernel Errors Present...
In the BIOS I turn DMA off for /dev/hda and /dev/hdc, but they still show up in /proc/ide/.../settings as using_dma 1.
say HUH? IDE PIO modes are like 3-7 MBytes/sec and require 100% CPU utilization during the transfer phase. why in dogs name would you be doing this in 2011 ?
I'm only using 40 wire IDE cables, and from past experience I don't trust DMA 100%
I'd rather transfer data slower with hopefully more stability.
I will build a new machine at some time, using SATA and possibly PCI express.
But this will have to do for now :)
Keith
----------------------------------------------------------------- Websites: http://www.karsites.net http://www.php-debuggers.net http://www.raised-from-the-dead.org.uk
All email addresses are challenge-response protected with TMDA [http://tmda.net] -----------------------------------------------------------------
On 01/12/11 2:47 PM, Keith Roberts wrote:
I'm only using 40 wire IDE cables, and from past experience I don't trust DMA 100%
40 wire supports DMA modes up to Ultra/DMA 33 (as in 33Mbyte/sec). UDMA 66+ require the 80 wire shielded cables (and both drives on the same cable have to support it).
The only time I've had any problems with DMA, something has been very badly broken with the hardware.
Use the modern, 80 wire cables, and trust the technology - it's come a long way.
On Wed, 12 Jan 2011, compdoc wrote:
What model is the drive?
=== START OF INFORMATION SECTION === Model Family: Western Digital Caviar family Device Model: WDC WD400BB-00GFA0 Serial Number: WD-WMAKA1241735 Firmware Version: 09.01B09 User Capacity: 40,020,664,320 bytes Device is: In smartctl database [for details use: -P show] ATA Version is: 5 ATA Standard is: Exact ATA specification draft version not indicated Local Time is: Wed Jan 12 22:44:01 2011 GMT SMART support is: Available - device has SMART capability. SMART support is: Enabled
Keith
----------------------------------------------------------------- Websites: http://www.karsites.net http://www.php-debuggers.net http://www.raised-from-the-dead.org.uk
All email addresses are challenge-response protected with TMDA [http://tmda.net] -----------------------------------------------------------------
Gosh that's an old drive. Seems its capable of some speed, tho:
Data transfer rate (buffer to host) Mode 5 Ultra ATA4 100 MB/s Mode 4 Ultra ATA4 66.6 MB/s Mode 2 Ultra ATA4 33.3 MB/s Mode 2 DMA4 16.6 MB/s Mode 4 PIO4 16.6 MB/s
John Pierce is right - if you don't use a dma mode, the cpu has a lot more work.
SMART says your drive is good, but it still could be failing. Or the cabling is wrong - very common if there's both a master and slave present, but even possible if only one drive is attached.
The ide port on the mainboard could be failing as well. Also, but not as likely - how the drive is defined in the bios, or how other things are set in there. (if you have always used the defaults, then nothing to worry about)
-
compdoc -
John R Pierce -
Keith Roberts -
m.roth＠5-cent.us