Re: SATA RAID5 speed drop of 100 MB/s

Jeff Garzik wrote: [trim] > Given that some drives might be better tuned for benchmarks in > non-queued mode, and that a major behavior difference is that your > drives are now NCQ-enabled, the first thing I would suggest you try is > disabling NCQ: > http://linux-ata.org/faq.html#ncq I see in

Re: SATA RAID5 speed drop of 100 MB/s

Carlo Wood wrote: Is it possible that the measurement with "hdparm -tT" returns a higher value for some setting, but that the over-all real-life performance drops? IN THEORY, RAID performance should /increase/ due to additional queued commands available to be sent to the drive. NCQ == command

Re: [PATCH 5/6] ide: add ata_dev_has_iordy() helper

On Saturday 23 June 2007, Sergei Shtylyov wrote: > Bartlomiej Zolnierkiewicz wrote: > > This one is actually arguable... > > > * Add ata_dev_has_iordy() helper. > > I thought IDE subsys make use of only 'ide_' prefixes. :-) Nope, see ide-probe.c. ;-) > > * Use it in sl82c105 host drive

Re: [PATCH 6/6] ide: add ide_pci_device_t.host_flags

On Saturday 23 June 2007, Sergei Shtylyov wrote: > Bartlomiej Zolnierkiewicz wrote: > > * Rename ide_pci_device_t.flags to ide_pci_device_t.host_flags > > and IDEPCI_FLAG_ISA_PORTS flag to IDE_HFLAG_ISA_PORTS. > > Erm, do you intend also adding device_flags field? :-O ;-) maybe 8) > > * Ad

Re: [PATCH 1/6] qd65xx: fix PIO mode selection

On Saturday 23 June 2007, Alan Cox wrote: > Possibly we should just drop support as I know of only one user and thats > purely to test the code Fine with me, please send a patch. PS Added yours "Reviewed-by:" to this patch as I still need to push it (I have other patches in the queue depending o

Re: [PATCH 1/6] qd65xx: fix PIO mode selection

Hello. Alan Cox wrote: PIO4 is a maximum PIO mode supported by a driver. Using "255" as a max_mode argument to ide_get_best_pio_mode() could result in wrong timings being used by a driver (for "pio" equal to 5) or OOPS (for "pio" values > 5 && < 255). The qdi6580 driver is somewhat hosed. T

Re: [PATCH 1/6] qd65xx: fix PIO mode selection

On Sat, 23 Jun 2007 20:02:07 +0200 Bartlomiej Zolnierkiewicz <[EMAIL PROTECTED]> wrote: > > PIO4 is a maximum PIO mode supported by a driver. Using "255" as a max_mode > argument to ide_get_best_pio_mode() could result in wrong timings being used > by a driver (for "pio" equal to 5) or OOPS (for

Re: [PATCH 5/6] ide: add ata_dev_has_iordy() helper

Bartlomiej Zolnierkiewicz wrote: This one is actually arguable... * Add ata_dev_has_iordy() helper. I thought IDE subsys make use of only 'ide_' prefixes. :-) * Use it in sl82c105 host driver so it always gets the correct info (use_iordy was incorrectly set for "pio" != 255 cases).

Re: [PATCH 6/6] ide: add ide_pci_device_t.host_flags

Bartlomiej Zolnierkiewicz wrote: * Rename ide_pci_device_t.flags to ide_pci_device_t.host_flags and IDEPCI_FLAG_ISA_PORTS flag to IDE_HFLAG_ISA_PORTS. Erm, do you intend also adding device_flags field? :-O ;-) * Add IDE_HFLAG_SINGLE flag for single channel devices. * Convert core code

Re: [PATCH 4/6] ide: make ide_get_best_pio_mode() print info if overriding PIO mode

Bartlomiej Zolnierkiewicz wrote: * Print info about overriding PIO mode in ide_get_best_pio_mode(). * Remove info about overriding PIO mode from cmd64{0,x} host drivers. * Remove no longer needed ide_pio_data_t.overridden field. Signed-off-by: Bartlomiej Zolnierkiewicz <[EMAIL PROTECTED]

Re: [PATCH] ide: Stop mapping ROMs

Bartlomiej Zolnierkiewicz wrote: Various old IDE drivers go mapping ROM devices for no apparent reason and without using the ROM mapping API we now have. They don't actually use Hm, do you mean the sysfs based aproach? I've tried that and somehow it failed to work for me -- that's because

Re: [PROBLEM]: hdparm strange behaviour for 2.6.21 and later

Hi, On Wednesday 20 June 2007, Thanos Kyritsis wrote: > On Monday 18 June 2007, Mark Lord wrote: > > Thanos Kyritsis wrote: > [snip] > > > /etc/rc.d/rc.local contains the following: > > > /usr/sbin/hdparm -q -d1 -q -u1 -q -c1 -q -k1 /dev/hda > > > /usr/sbin/hdparm -q -d1 -q -u1 -q -c1 -q -k1 /dev

Re: [PATCH 1/6] qd65xx: fix PIO mode selection

Bartlomiej Zolnierkiewicz wrote: PIO4 is a maximum PIO mode supported by a driver. Using "255" as a max_mode argument to ide_get_best_pio_mode() could result in wrong timings being used by a driver (for "pio" equal to 5) or OOPS (for "pio" values > 5 && < 255). Signed-off-by: Bartlomiej Zolnier

Re: [RFT] hpt366: reset DMA state machine on timeouts

Hello. Linas Vepstas wrote: Reset HPT36x's DMA state machine on a DMA timeout the way it's done for HPT370. drivers/ide/pci/hpt366.c | 24 +++- This worked great! I hope you meant those messages were preceeded by DMA timeouts (otherwise this code wouldn't come i

[PATCH 6/6] ide: add ide_pci_device_t.host_flags

* Rename ide_pci_device_t.flags to ide_pci_device_t.host_flags and IDEPCI_FLAG_ISA_PORTS flag to IDE_HFLAG_ISA_PORTS. * Add IDE_HFLAG_SINGLE flag for single channel devices. * Convert core code and all IDE PCI drivers to use IDE_HFLAG_SINGLE and remove no longer needed ide_pci_device_t.chann

[PATCH 4/6] ide: make ide_get_best_pio_mode() print info if overriding PIO mode

* Print info about overriding PIO mode in ide_get_best_pio_mode(). * Remove info about overriding PIO mode from cmd64{0,x} host drivers. * Remove no longer needed ide_pio_data_t.overridden field. Signed-off-by: Bartlomiej Zolnierkiewicz <[EMAIL PROTECTED]> --- drivers/ide/ide-lib.c| 10 +

[PATCH 5/6] ide: add ata_dev_has_iordy() helper

* Add ata_dev_has_iordy() helper. * Use it in sl82c105 host driver so it always gets the correct info (use_iordy was incorrectly set for "pio" != 255 cases). * Remove no longer needed ide_pio_data_t.use_iordy field. Signed-off-by: Bartlomiej Zolnierkiewicz <[EMAIL PROTECTED]> --- drivers/ide

[PATCH 2/6] atiixp: PIO mode setup fixes

* Split off exisiting atiixp_tuneproc() into atiixp_tune_pio() and then add setting device PIO mode to atiixp_tuneproc(). * Add missing ide_get_best_pio_mode() call to atiixp_tuneproc() so "pio" == 255 (autotune) is handled correctly and "pio" values > 4 && < 255 are filtered to PIO4 (previ

[PATCH 3/6] siimage: PIO mode setup fixes

* Add sil_tuneproc() wrapper for siimage_tuneproc() which also sets PIO mode on the device. * Add missing ide_get_best_pio_mode() call to sil_tuneproc() so "pio" == 255 (autotune) is handled correctly (previously PIO0 was used) and "pio" values > 4 && < 255 are filtered to PIO4 (instead of

Re: [PATCH] ide: Stop mapping ROMs

Hi, On Friday 22 June 2007, Sergei Shtylyov wrote: > Hello. > > Alan Cox wrote: > > > Various old IDE drivers go mapping ROM devices for no apparent reason and > > without using the ROM mapping API we now have. They don't actually use > > Hm, do you mean the sysfs based aproach? I've tried

[PATCH 1/6] qd65xx: fix PIO mode selection

PIO4 is a maximum PIO mode supported by a driver. Using "255" as a max_mode argument to ide_get_best_pio_mode() could result in wrong timings being used by a driver (for "pio" equal to 5) or OOPS (for "pio" values > 5 && < 255). Signed-off-by: Bartlomiej Zolnierkiewicz <[EMAIL PROTECTED]> --- d

Re: [PATCH] ide: Fix a theoretical Ooops case

On Friday 22 June 2007, Alan Cox wrote: > Found by a static analyser. It is in theory possible we dereference > dev->id when it has become invalid. Re-order to avoid this. > > Not needed for new-ide as we no longer support the crazy exabyte nest stuff > > Signed-off-by: Alan Cox <[EMAIL PROTECTED

Re: [PATCH] ide: Stop mapping ROMs

On Friday 22 June 2007, Alan Cox wrote: > Various old IDE drivers go mapping ROM devices for no apparent reason and > without using the ROM mapping API we now have. They don't actually use > the ROM they map and the new libata drivers are happy without it being > mapped so rather than port them let

Re: [PATCH] libata: Add pata_dma option so users can disable pata_dma as they can with old-ide

Hi, On Friday 22 June 2007, Alan Cox wrote: > > > I think a /sys/ "dma" attribute (pick a name) might be most appropriate, > > > or we just just implement HDIO_[GS]ET_DMA as a simpler/lazier mechanism. > > > > The problem is that libata lacks any locking needed for having this > > (and other use

Re: SATA RAID5 speed drop of 100 MB/s

Hi, On Saturday 23 June 2007, Carlo Wood wrote: > PS I'd like to do extensive testing with Bonnie++ to tune everything > there is to tune. But bonnie likes to write/read files TWICE the amount > of RAM I have. It therefore takes a LOT of time to run one test. Do you > happen to know how I can li

2.6.22-rc5 libata/ata_piix failure with older CDROM

I tried (again) to convert an Intel i815EP-chipset machine from IDE to libata, but libata still fails to initialise the CDROM on the machine. With 2.6.22-rc5, IDE says: Uniform Multi-Platform E-IDE driver Revision: 7.00alpha2 ide: Assuming 33MHz system bus speed for PIO modes; override with idebu

Re: SATA RAID5 speed drop of 100 MB/s

On Sat, Jun 23, 2007 at 03:03:33AM -0400, Jeff Garzik wrote: > Your disk configurations are quite radically different between the two > kernels (see attached diff for key highlights). > > The new behavior of the more recent kernel (551c012d7...) is that it now > fully drives your hardware :) Th

Re: how to handle pata_via when controller not in fully-pci-native mode (two irqs?)

I'm a litle confused here. Page 10 (4.2.1) so I just mask off bit 0 and bit 2 of the class prog-if byte and set it to "compatible" mode which will basically mean PCI mapped registers and two IRQs? This corresponds with the table on Page 7 (4.2.1.1).. Checked the Pegasos IDE class code and in the

Re: how to handle pata_via when controller not in fully-pci-native mode (two irqs?)

On Sat, 23 Jun 2007 10:33:46 +0100 Matt Sealey <[EMAIL PROTECTED]> wrote: > > Alan Cox wrote: > > On Sat, 23 Jun 2007 01:26:06 +0100 > > > > The simplest way is probably to load the pci class and programming > > interface bits correctly for the device to match how your IRQ setup has > > been arra

Re: how to handle pata_via when controller not in fully-pci-native mode (two irqs?)

Alan Cox wrote: > On Sat, 23 Jun 2007 01:26:06 +0100 > > The simplest way is probably to load the pci class and programming > interface bits correctly for the device to match how your IRQ setup has > been arranged. See page 78 of the VIA 8231 spec if you have it, and load > the programming class i

Re: how to handle pata_via when controller not in fully-pci-native mode (two irqs?)

On Sat, 23 Jun 2007 01:26:06 +0100 Matt Sealey <[EMAIL PROTECTED]> wrote: > There are several different ways you can set it up from having a single > IRQ (true PCI native), to using PCI register access but with IRQ routing > through a certain pair of interrupts (14/15 or 10/11) or by having real >

Re: SATA RAID5 speed drop of 100 MB/s

Jeff Garzik wrote: > Carlo Wood wrote: >> The dmesg output of 33480a0ede8dcc7e6483054279008f972bd56fd3 (thus >> "before") is: > [...] >> And the dmesg output of 551c012d7eea3dc5ec063c7ff9c718d39e77634f (thus >> "after") is: > [...] > > Your disk configurations are quite radically different between

Re: SATA RAID5 speed drop of 100 MB/s

Carlo Wood wrote: The dmesg output of 33480a0ede8dcc7e6483054279008f972bd56fd3 (thus "before") is: [...] And the dmesg output of 551c012d7eea3dc5ec063c7ff9c718d39e77634f (thus "after") is: [...] Your disk configurations are quite radically different between the two kernels (see attached diff