Re: [gentoo-user] hdparm HDIO_SET_DMA failed
On Sat, 14 May 2005, Volker Armin Hemmann wrote: is this not deafault? Not on my system. m16 sets to 16 ;) but: is m16 not the default setting? Again not on my system. I don't know, if there is any combination today, that makes probs, but not using -u is wasting performance. Don't complain about stuttering sound and video-hangs, if you have not tried -u1 I use it... why? default is 256.. why changing it? Again it's not the default on my machine... Best regards Peter K -- gentoo-user@gentoo.org mailing list
Re: [gentoo-user] hdparm HDIO_SET_DMA failed
On Fri, 13 May 2005, Peter Gordon wrote: My understanding is that the kernel will automagically configure DMA as appropriate if you build support for the IDE controller statically, but hdparm is needed to initialize DMA stuff if you build your IDE controller's driver as a module. I'm not certain though. I tend to build everything into the kernel, and I've not needed to use hdparm. There's a whole lot more one can do with hdparm. What the kernel _can_ do is enable dma only. hdparm is used to set other performance enhancing options. My '/etc/conf.d/hdparm' contains 'hda_args=-d1A1m16u1a64' which means: -d1 - enables dma for this drive (to ensure dma is set). -A1 - enables the IDE drive's read-lookahead feature. -m1 - set sector count to 16. This reads 16 sectors per interrupt instead of one. Some drives run slower with this. -u1 - set interrupt-unmask for the drive. Can be dangerous with some drive/controller combinations. Allows the kernel to service other i/o interrupts, afaicu. -a64 - set sector count for filesystem read-ahead to 64 sectors. A cache-mechanism. http://gentoo-wiki.com/HOWTO_Use_hdparm_to_improve_IDE_device_performance Best regards Peter K -- gentoo-user@gentoo.org mailing list
Re: [gentoo-user] hdparm HDIO_SET_DMA failed
My understanding is that the kernel will automagically configure DMA as appropriate if you build support for the IDE controller statically, but hdparm is needed to initialize DMA stuff if you build your IDE controller's driver as a module. I'm not certain though. I tend to build everything into the kernel, and I've not needed to use hdparm. There's a whole lot more one can do with hdparm. What the kernel _can_ do is enable dma only. hdparm is used to set other performance enhancing options. My '/etc/conf.d/hdparm' contains 'hda_args=-d1A1m16u1a64' which means: -d1 - enables dma for this drive (to ensure dma is set). -A1 - enables the IDE drive's read-lookahead feature. -m1 - set sector count to 16. This reads 16 sectors per interrupt instead of one. Some drives run slower with this. -u1 - set interrupt-unmask for the drive. Can be dangerous with some drive/controller combinations. Allows the kernel to service other i/o interrupts, afaicu. -a64 - set sector count for filesystem read-ahead to 64 sectors. A cache-mechanism. Thanks Peter. Is your -u1 a typo? - Grant -- gentoo-user@gentoo.org mailing list
Re: [gentoo-user] hdparm HDIO_SET_DMA failed
On Sat, 14 May 2005, Grant wrote: Thanks Peter. Is your -u1 a typo? No. That option works fine, afaict, with my drive/chipset combination (maxtor/ich5). Best regards Peter K -- gentoo-user@gentoo.org mailing list
Re: [gentoo-user] hdparm HDIO_SET_DMA failed
Peter Karlsson wrote: On Sat, 14 May 2005, Grant wrote: Thanks Peter. Is your -u1 a typo? No. That option works fine, afaict, with my drive/chipset combination (maxtor/ich5). Best regards Peter K Nice... Any idea how to pull this off with S/ATA? -- [Name ] :: [Matan I. Peled] [Location ] :: [Israel] [Public Key] :: [0xD6F42CA5] [Keyserver ] :: [keyserver.kjsl.com] encrypted/signed plain text preferred signature.asc Description: OpenPGP digital signature
Re: [gentoo-user] hdparm HDIO_SET_DMA failed
Quoting Grant [EMAIL PROTECTED]: Actually, is hdparm supposed to be used when specific IDE support is not included in the kernel? It sounds like the kernel optimally configures your device if that support is included. hdparm sounds like it does the same thing. My understanding is that the kernel will automagically configure DMA as appropriate if you build support for the IDE controller statically, but hdparm is needed to initialize DMA stuff if you build your IDE controller's driver as a module. I'm not certain though. I tend to build everything into the kernel, and I've not needed to use hdparm. -- () The ASCII Ribbon Campaign - against HTML Email, /\ vCards, and proprietary formats. --- Peter A. Gordon (codergeek42) E-Mail: [EMAIL PROTECTED] GPG Public Key ID: 0x109DBECE GPG Key Fingerprint (SHA1): E485 E2F7 11CE F9B2 E3D9 C95D 208F B732 109D BECE Encrypted and/or Signed correspondence preffered. Notice: This message not is not GPG-signed, because it is sent through a webmail interface. --- -- gentoo-user@gentoo.org mailing list
Re: [gentoo-user] hdparm HDIO_SET_DMA failed
Actually, is hdparm supposed to be used when specific IDE support is not included in the kernel? It sounds like the kernel optimally configures your device if that support is included. hdparm sounds like it does the same thing. My understanding is that the kernel will automagically configure DMA as appropriate if you build support for the IDE controller statically, but hdparm is needed to initialize DMA stuff if you build your IDE controller's driver as a module. I'm not certain though. I tend to build everything into the kernel, and I've not needed to use hdparm. Ok, thanks Peter. Maybe I'll only use hdparm for the system that doesn't have IDE chipset support in the kernel: IDE interface: Intel Corporation 82801AA IDE (rev 02) - Grant -- gentoo-user@gentoo.org mailing list
[gentoo-user] hdparm HDIO_SET_DMA failed
Hello, I've been setting up hdparm on my systems and 3 out of 4 have returned this when trying to set DMA: HDIO_SET_DMA failed: Operation not permitted but subsequent attempts have executed without error. 'hdparm -i /dev/hda' does show the * character beside a udma mode in each instance. Does anyone know what that error is about? This is pretty minor really. - Grant -- gentoo-user@gentoo.org mailing list
Re: [gentoo-user] hdparm HDIO_SET_DMA failed
Grant wrote: HDIO_SET_DMA failed: Operation not permitted Does the kernel you built for those have support for the appropriate IDE controller chipset? You can get this information with `lspci | grep IDE'. (lspci is part of the sys-apps/pciutils package.) For example on my system I have a VIA 82CXXX IDE controller: :00:07.1 IDE interface: VIA Technologies, Inc. \ VT82C586A/B/VT82C686/A/B/VT823x/A/C PIPC Bus Master IDE (rev 06) So I set CONFIG_BLK_DEV_VIA82CXXX=y in kernel configuration. For the 2.6 kernel series you should choose the appropriate option: Device Drivers - ATA/ATAPI/MFM/RLL support - Enhanced IDE/MFM/RLLdisk/cdrom/tape/floppy support - PCI IDE chipset support - Generic PCI bus-master DMA support - * Your IDE Controller chipset Hope that helps! -- () The ASCII Ribbon Campaign - against HTML Email, /\ vCards, and proprietary formats. --- Peter A. Gordon (codergeek42) E-Mail: [EMAIL PROTECTED] GPG Public Key ID: 0x109DBECE GPG Key Fingerprint (SHA1): E485 E2F7 11CE F9B2 E3D9 C95D 208F B732 109D BECE Encrypted and/or Signed correspondence preffered. GPG Public Key available upon request or from pgp.mit.edu's public key server. --- signature.asc Description: OpenPGP digital signature
