Hi,
I am experiencing some strange behaviour. When I have heavy HDD
activity (running MythTV, for instance), I get 17 of these:
[ 90.004956] hda: dma_intr: bad DMA status (dma_stat=76)
[ 90.004963] hda: dma_intr: status=0x50 { DriveReady SeekComplete }
[ 90.004966] ide: failed opcode was:
Hi all,
Le samedi 16 février 2008 à 21:23 +0100, Borislav Petkov a écrit :
Do you want me to try the 2.6.25-rc2 ? and give my feedback
Yes, please.
Until now, there's no prob with the kernel 2.6.25-rc2.
15:14 [EMAIL PROTECTED] ~% uname -a
Linux Jupiter 2.6.25-rc2.waver.1 #1 Sun Feb 17
Hi again,
2008/2/17, Paul Fleischer [EMAIL PROTECTED]:
Hi,
I am experiencing some strange behaviour. When I have heavy HDD
activity (running MythTV, for instance), I get 17 of these:
[ 90.004956] hda: dma_intr: bad DMA status (dma_stat=76)
[ 90.004963] hda: dma_intr: status=0x50 {
On Sun, 2008-02-17 at 23:52 +0900, FUJITA Tomonori wrote:
On Sun, 17 Feb 2008 07:28:48 -0700
Matthew Wilcox [EMAIL PROTECTED] wrote:
On Sun, Feb 17, 2008 at 08:18:11AM -0600, James Bottomley wrote:
No, he means that kmap_atomic can only map a page of data. This makes
single page only
On Sun, Feb 17, 2008 at 03:16:42PM +0100, WaVeR wrote:
Hi all,
Le samedi 16 février 2008 à 21:23 +0100, Borislav Petkov a écrit :
Do you want me to try the 2.6.25-rc2 ? and give my feedback
Yes, please.
Until now, there's no prob with the kernel 2.6.25-rc2.
Cool, let me know
On Sun, 17 Feb 2008 09:02:14 -0600
James Bottomley [EMAIL PROTECTED] wrote:
On Sun, 2008-02-17 at 23:52 +0900, FUJITA Tomonori wrote:
On Sun, 17 Feb 2008 07:28:48 -0700
Matthew Wilcox [EMAIL PROTECTED] wrote:
On Sun, Feb 17, 2008 at 08:18:11AM -0600, James Bottomley wrote:
No, he
Dear Mark:
2008/2/16, Mark Lord [EMAIL PROTECTED]:
Mark Lord wrote:
Richard Liu wrote:
Thanks. By running the above data through hdparm --Istdin,
I see that the drive is indeed identifying itself as a 33MB drive.
Probably because it has been told to do so by either the factory
On Mon, 2008-02-18 at 00:11 +0900, FUJITA Tomonori wrote:
On Sun, 17 Feb 2008 09:02:14 -0600
James Bottomley [EMAIL PROTECTED] wrote:
On Sun, 2008-02-17 at 23:52 +0900, FUJITA Tomonori wrote:
On Sun, 17 Feb 2008 07:28:48 -0700
Matthew Wilcox [EMAIL PROTECTED] wrote:
On Sun,
Hello List,
Odd problem on my machines: the sata disks appear to be a lot slower
when used via ata_piix vs the ahci driver.
* dd if=/dev/sda of=/dev/null runs at roughly 50MB/s under ahci a
steady 100MB/s under ata_piix, same for hdparm
* bonnie++ -d /home/bonnietest -s 16G -r 8192 -u root
On Sun, 17 Feb 2008 16:41:42 +0100
Joris [EMAIL PROTECTED] wrote:
Hello List,
Odd problem on my machines: the sata disks appear to be a lot slower
when used via ata_piix vs the ahci driver.
I would expect that. AHCI allows the use of NCQ and unloads a ton of work
from the processor. It also
2008/2/17, Alan Cox [EMAIL PROTECTED]:
On Sun, 17 Feb 2008 16:41:42 +0100
Joris [EMAIL PROTECTED] wrote:
Hello List,
Odd problem on my machines: the sata disks appear to be a lot slower
when used via ata_piix vs the ahci driver.
I would expect that. AHCI allows the use of NCQ and
commit 8ac4ce742c66100931b6f2d7a36b0df08bc721fe (ide: fix host drivers
depending on ide_generic to probe for interfaces (take 2)) moved probing
to falconide but forgot to take care of Atari specific locking - fix it.
Cc: Geert Uytterhoeven [EMAIL PROTECTED]
Cc: Michael Schmitz [EMAIL PROTECTED]
Hi,
On Sunday 17 February 2008, Andrew Smith wrote:
One Line : Changes in 2.24 have rendered the ide handling on the Via
NanoBook unstable resulting in data loss under heavy load.
Keywords : modules, pata_via, viac82
Kernel version : 2.24
Environment : Packard Bell Easynote XS -
On Saturday 16 February 2008, Randy Dunlap wrote:
[...]
+You also need to use probe kernel paramater for ide-4drives driver
parameter
thanks, fixed in take 2
-
To unsubscribe from this list: send the line unsubscribe linux-ide in
the body of a message
On Saturday 16 February 2008, Julia Lawall wrote:
From: Julia Lawall [EMAIL PROTECTED]
The kernel.h macro DIV_ROUND_UP performs the computation (((n) + (d) - 1) /
(d)) but is perhaps more readable.
An extract of the semantic patch that makes this change is as follows:
Am I interpreting this correctly as having to choose between fast iops
with low cpu (+ hotplug) with ahci and twice the linear read speed
with ata_piix?
Some drives do weird things when NCQ is used and turn off some of their
caching in that case so it depends on the drive what happens to
No need for it nowadays so remove quirk code from ide_get_best_pio_mode()
and IDE_HFLAG_PIO_DOWNGRADE host flag.
Signed-off-by: Bartlomiej Zolnierkiewicz [EMAIL PROTECTED]
---
drivers/ide/ide-lib.c | 10 --
drivers/ide/pci/amd74xx.c |1 -
drivers/ide/pci/via82cxxx.c |1
* Change ide_match_hwif() argument from 'u8 bootable' to
'struct ide_port_info *d'.
* Move ide_match_hwif() to ide-probe.c from setup-pci.c and rename
it to ide_find_port_slot(). Update some comments while at it.
* ide_find_port() can be now just a wrapper for ide_find_port_slot().
There
All modular users have been fixed to not reference ide_hwifs[] directly.
Signed-off-by: Bartlomiej Zolnierkiewicz [EMAIL PROTECTED]
---
drivers/ide/ide.c |5 -
1 file changed, 5 deletions(-)
Index: b/drivers/ide/ide.c
===
* Add IDE_HFLAG_QD_2ND_PORT host flag to indicate the need of skipping
first ide_hwifs[] slot for the second port of QD65xx controller.
* Handle this new host flag in ide_find_port_slot().
* Convert legacy VLB host drivers to use ide_find_port().
While at it:
* Fix couple of printk()-s in
There should be no functional changes caused by this patch.
Signed-off-by: Bartlomiej Zolnierkiewicz [EMAIL PROTECTED]
---
drivers/ide/ide-generic.c | 17 +
1 file changed, 13 insertions(+), 4 deletions(-)
Index: b/drivers/ide/ide-generic.c
Richard Liu wrote:
Dear Mark:
2008/2/16, Mark Lord [EMAIL PROTECTED]:
Mark Lord wrote:
Richard Liu wrote:
Thanks. By running the above data through hdparm --Istdin,
I see that the drive is indeed identifying itself as a 33MB drive.
Probably because it has been told to do so by either the
Mark Lord wrote:
Richard Liu wrote:
..
I downloaded hdparm-8.1
and here is output information.
# ./hdparm -N /dev/sdc
/dev/sdc:
max sectors = 65134/1953525168, HPA is enabled
..
Yes, pretty much as expected there.
You can safely now try this:
./hdparm -N1953525168 /dev/sdc
If
Dear Mark:
2008/2/18, Mark Lord [EMAIL PROTECTED]:
Mark Lord wrote:
Richard Liu wrote:
..
I downloaded hdparm-8.1
and here is output information.
# ./hdparm -N /dev/sdc
/dev/sdc:
max sectors = 65134/1953525168, HPA is enabled
..
Yes, pretty much as expected there.
On Feb 17, 2008 2:18 PM, Mark Lord [EMAIL PROTECTED] wrote:
Richard Liu wrote:
Dear Mark:
2008/2/16, Mark Lord [EMAIL PROTECTED]:
Mark Lord wrote:
Richard Liu wrote:
Thanks. By running the above data through hdparm --Istdin,
I see that the drive is indeed identifying itself as a
There are no changes to the resulting drivers/ide/ide-disk.o binary file
(md5sum-s after and before the patch match).
Signed-off-by: Bartlomiej Zolnierkiewicz [EMAIL PROTECTED]
---
drivers/ide/ide-disk.c | 120 -
1 file changed, 70 insertions(+),
Signed-off-by: Bartlomiej Zolnierkiewicz [EMAIL PROTECTED]
---
drivers/ide/ide-disk.c |5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
Index: b/drivers/ide/ide-disk.c
===
--- a/drivers/ide/ide-disk.c
+++
* Factor out common code from proc_idedisk_read_smart_{thresholds,values}()
to proc_idedisk_read_smart() helper.
* Rename proc_idedisk_read_smart_thresholds() to proc_idedisk_read_st()
and proc_idedisk_read_smart_values() to proc_idedisk_read_sv().
There should be no functional changes
drivers/ide/ide.c:801:18: warning: symbol 'flags' shadows an earlier one
drivers/ide/ide.c:732:16: originally declared here
Also fix some whitespace damage while at it.
Signed-off-by: Bartlomiej Zolnierkiewicz [EMAIL PROTECTED]
---
drivers/ide/ide.c | 13 +
1 file changed, 5
Greg Freemyer wrote:
..
Very cool new functionality in [hdparm] 8.1
Looking forward to testing it this week.
Thanks for your efforts.
I assume DCO is still able to hide sectors from us?
..
I'm not sure (haven't tried it here yet).
But the way I read the ATA8 specification,
it sounds like
From 4ea313fe6a3c46a90226cf40d0e3ece4b36b48f9 Mon Sep 17 00:00:00 2001
From: Willy Tarreau [EMAIL PROTECTED]
Date: Sun, 17 Feb 2008 21:28:25 +0100
Subject: [PATCH 2/2] libata: implement support for 32-bit PIO transfers
When ATA_DFLAG_32BIT_PIO is set in ata flags, PIO transfers
will be performed
From 40a8174d27cb9d93b859bc073c8f075b9ff71578 Mon Sep 17 00:00:00 2001
From: Willy Tarreau [EMAIL PROTECTED]
Date: Sun, 17 Feb 2008 21:11:46 +0100
Subject: [PATCH 1/2] libata: implement ATA_IOC_GET_IO32/ATA_IOC_SET_IO32 ioctls
This patch implements the aforementionned ioctls and get/set the
new
Hi Jeff,
For several times I tried libata on small machines equipped with either
CompactFlash or IDE DOM (Disk-On-Module). All those machines with small
flashes (= 256 MB) were about 35-40% slower under libata than under the
plain old IDE driver. I realized that all the slower ones were running
Thus, I have implemented the 32-bit mode to bring the performance back
to the level of the old IDE driver. I jumped from 1.5 MB/s to 2.5 MB/s,
which is an important difference at this level of performance, especially
when large files are read. The 32-bit mode is enabled using the ioctl
which
On Sun, 17 Feb 2008 22:20:04 +0100
Willy Tarreau [EMAIL PROTECTED] wrote:
From 4ea313fe6a3c46a90226cf40d0e3ece4b36b48f9 Mon Sep 17 00:00:00 2001
From: Willy Tarreau [EMAIL PROTECTED]
Date: Sun, 17 Feb 2008 21:28:25 +0100
Subject: [PATCH 2/2] libata: implement support for 32-bit PIO
On Sun, Feb 17, 2008 at 10:31:34PM +, Alan Cox wrote:
Thus, I have implemented the 32-bit mode to bring the performance back
to the level of the old IDE driver. I jumped from 1.5 MB/s to 2.5 MB/s,
which is an important difference at this level of performance, especially
when large
http://bugzilla.kernel.org/show_bug.cgi?id=3615
--- Comment #16 from [EMAIL PROTECTED] 2008-02-17 17:30 ---
(In reply to comment #15)
Could you try 2.6.24 or 2.6.25-rc2 with hdc=noprobe parameter?
I'm using a different DVD drive now and I don't have any delays during boot
anymore.
37 matches
Mail list logo