Re: ATA APM and NCQ support in FreeBSD atacontrol
Ian Smith wrote: I take Jonathan's point that it would be nice to have this functionality in atacontrol, though perhaps the BUGS section in ataidle(8) precludes merging that? cc'ing Bruce Cran in case he wants to add something .. ataidle is at the moment quite dumb about sending commands: it doesn't check that the drive actually supports APM/AAM before sending the commands, and that's an easy check to do. If this was being added to atacontrol I think I'd want to do quite a bit of work first to make it more robust. However I don't think the code from ataidle could ever just be merged in to atacontrol because the code styles are quite different; however since the interface to the ATA driver is quite straightforward it should be trivial to re-implement or copy the bits needed. -- Bruce ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
On Tue, 13 May 2008, Alexandre "Sunny" Kovalenko wrote: > On Mon, 2008-05-12 at 14:52 +1000, Ian Smith wrote: > > On Sun, 11 May 2008 [EMAIL PROTECTED] wrote: > > > Has any work been done recently towards adding SATA Native Command > > > Queueing as well as ATA APM and acoustic management to FreeBSD? > > > > > > I found this PR (with patch) to add APM and acoustic management control > > to > > > atacontrol. The PR was opened in May 2005 has not been changed since > > > December 2006 and is still open. > > > http://www.freebsd.org/cgi/query-pr.cgi?pr=81692&cat= > > > > > > I have not been able to find much of anything on SATA NCQ in FreeBSD > > newer > > > than 2005 or 2006 does anyone know anything newer? > > > > Jeremy has addressed the NCQ issue, about which I know nothing. > > > > As for APM and AAM, that functionality is handled by sysutils/ataidle, > > which that PR appears - on a quick glance - to pretty well duplicate. > > > > I see phk@ recently added an 'atacontrol spindown' command to HEAD and > > RELENG_7 that appears to offer similar functionality to 'ataidle -S > > standby_mins' or 'ataidle -I idle_mins', though specified in seconds > > instead. However this doesn't address acoustic management. > > > > Or is ataidle broken for SATA disks? > Does not look broken here (RELENG_7): > > RabbitsDen# ataidle /dev/ad4 > Device Info: > > Model: HTS541010G9SA00 > Serial: MP2ZM4X0JWY6WH > Firmware Rev:MBZIC60H > ATA revision:ATA-7 > LBA 48: yes > Geometry:16383 cyls, 16 heads, 63 spt > Capacity:93GB > SMART Supported: yes > SMART Enabled: yes > APM Supported: yes > APM Enabled: yes > AAM Supported: yes > AAM Enabled: yes > Current AAM: 1 > Vendor Recommends AAM: 1 > APM Value: 16638 Thanks for the confirmation Alexandre. I take Jonathan's point that it would be nice to have this functionality in atacontrol, though perhaps the BUGS section in ataidle(8) precludes merging that? cc'ing Bruce Cran in case he wants to add something .. > RabbitsDen# atacontrol list [..] > ATA channel 2: > Master: ad4 Serial ATA v1.0 > Slave: no device present Regarding the spindown thing, I always used to use APM (set in BIOS) to do that on this old laptop, until I found that I'd already consumed 25% of a new 40GB drive's 2 million Load_Cycle_Count in a year, following a thread warning about that last year, so now I run ataidle from rc.conf: ataidle_enable="YES" ataidle_device="ad0" ataidle_ad0="-P 0 0 0" but then found it necessary to again disable disk APM in rc.resume: /usr/local/sbin/ataidle -P 0 0 0 cheers, Ian ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
On Mon, 2008-05-12 at 14:52 +1000, Ian Smith wrote: > On Sun, 11 May 2008 [EMAIL PROTECTED] wrote: > > Has any work been done recently towards adding SATA Native Command > > Queueing as well as ATA APM and acoustic management to FreeBSD? > > > > I found this PR (with patch) to add APM and acoustic management control to > > atacontrol. The PR was opened in May 2005 has not been changed since > > December 2006 and is still open. > > http://www.freebsd.org/cgi/query-pr.cgi?pr=81692&cat= > > > > I have not been able to find much of anything on SATA NCQ in FreeBSD newer > > than 2005 or 2006 does anyone know anything newer? > > Jeremy has addressed the NCQ issue, about which I know nothing. > > As for APM and AAM, that functionality is handled by sysutils/ataidle, > which that PR appears - on a quick glance - to pretty well duplicate. > > I see phk@ recently added an 'atacontrol spindown' command to HEAD and > RELENG_7 that appears to offer similar functionality to 'ataidle -S > standby_mins' or 'ataidle -I idle_mins', though specified in seconds > instead. However this doesn't address acoustic management. > > Or is ataidle broken for SATA disks? Does not look broken here (RELENG_7): RabbitsDen# ataidle /dev/ad4 Device Info: Model: HTS541010G9SA00 Serial: MP2ZM4X0JWY6WH Firmware Rev: MBZIC60H ATA revision: ATA-7 LBA 48: yes Geometry: 16383 cyls, 16 heads, 63 spt Capacity: 93GB SMART Supported:yes SMART Enabled: yes APM Supported: yes APM Enabled:yes AAM Supported: yes AAM Enabled:yes Current AAM:1 Vendor Recommends AAM: 1 APM Value: 16638 RabbitsDen# atacontrol list ATA channel 0: Master: no device present Slave: no device present ATA channel 1: Master: no device present Slave: no device present ATA channel 2: Master: ad4 Serial ATA v1.0 Slave: no device present ATA channel 3: Master: no device present Slave: no device present ATA channel 4: Master: no device present Slave: no device present ATA channel 5: Master: no device present Slave: no device present atacontrol: ioctl(IOCATADEVICES): Device not configured RabbitsDen# uname -a FreeBSD RabbitsDen.RabbitsLawn.verizon.net 7.0-STABLE FreeBSD 7.0-STABLE #1: Sun May 11 20:31:21 EDT 2008 [EMAIL PROTECTED]:/usr/src/sys/i386/compile/TPX60 i386 RabbitsDen# > > cheers, Ian > > ___ > freebsd-stable@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-stable > To unsubscribe, send any mail to "[EMAIL PROTECTED]" -- Alexandre "Sunny" Kovalenko (Олександр Коваленко) ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
On Mon, May 12, 2008 at 07:54:58AM -0600, Scott Long wrote:
> Mark Kirkwood wrote:
>> Jeremy Chadwick wrote:
>>>
>>> I am too, but PRs that are 2 years old which include patches for severe
>>> bugs that affect reliability of RAID is (in my opinion) not acceptable.
>>> I've been spanked over saying this before ("you don't understand how
>>> open source works"), but necessity easily supercedes idealism.
>>>
>>> Linux's libata has evolved very quickly and very well, and has multiple
>>> eyes familiar with the code (in the case the author takes vacation,
>>> etc.). It has the upper hand here.
>>>
>>>
>> Linux has more eyes period, which helps a lot. In addition Linux has more
>> commercial sponsorship - having said that, I've no idea if libdata
>> development has had any such sponsorship...
>>
>> However. I do agree that we (that is FreeBSD) need more folks brave enough
>> to help Soren out with the (S)ATA layer - that means people like you or me
>> deciding to get our hands dirty with this code...
>>
>
> I'm working on adding ATA/SATA support to CAM.
! Wow... I had no idea you were working on such! Ideally that'd be the
best implementation. Thanks a ton for working on it!
If you need someone to test patches (I figure they'll be for -CURRENT,
but our test boxes run RELENG_7), let me know and I'll be more than
happy to give them a shot.
--
| Jeremy Chadwickjdc at parodius.com |
| Parodius Networking http://www.parodius.com/ |
| UNIX Systems Administrator Mountain View, CA, USA |
| Making life hard for others since 1977. PGP: 4BD6C0CB |
___
freebsd-stable@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
Mark Kirkwood wrote:
Jeremy Chadwick wrote:
I am too, but PRs that are 2 years old which include patches for severe
bugs that affect reliability of RAID is (in my opinion) not acceptable.
I've been spanked over saying this before ("you don't understand how
open source works"), but necessity easily supercedes idealism.
Linux's libata has evolved very quickly and very well, and has multiple
eyes familiar with the code (in the case the author takes vacation,
etc.). It has the upper hand here.
Linux has more eyes period, which helps a lot. In addition Linux has
more commercial sponsorship - having said that, I've no idea if libdata
development has had any such sponsorship...
However. I do agree that we (that is FreeBSD) need more folks brave
enough to help Soren out with the (S)ATA layer - that means people like
you or me deciding to get our hands dirty with this code...
I'm working on adding ATA/SATA support to CAM.
Scott
___
freebsd-stable@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
Mark Kirkwood wrote: Linux has more eyes period, which helps a lot. In addition Linux has more commercial sponsorship - having said that, I've no idea if libdata development has had any such sponsorship... As I know the most of active libata developers have full-time job in Linux companies, e.g. in Red Hat. -- WBR, Andrey V. Elsukov ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
Jeremy Chadwick wrote:
I am too, but PRs that are 2 years old which include patches for severe
bugs that affect reliability of RAID is (in my opinion) not acceptable.
I've been spanked over saying this before ("you don't understand how
open source works"), but necessity easily supercedes idealism.
Linux's libata has evolved very quickly and very well, and has multiple
eyes familiar with the code (in the case the author takes vacation,
etc.). It has the upper hand here.
Linux has more eyes period, which helps a lot. In addition Linux has
more commercial sponsorship - having said that, I've no idea if libdata
development has had any such sponsorship...
However. I do agree that we (that is FreeBSD) need more folks brave
enough to help Soren out with the (S)ATA layer - that means people like
you or me deciding to get our hands dirty with this code...
best wishes
Mark
___
freebsd-stable@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
On Mon, May 12, 2008 at 03:36:50AM -0400, [EMAIL PROTECTED] wrote:
> On Mon, May 12, 2008 03:23, Jeremy Chadwick wrote:
> > On Mon, May 12, 2008 at 03:16:10AM -0400, [EMAIL PROTECTED] wrote:
> >> ataidle is easy enough to find, I won't deny, but why make users do the
> >> google search and install a port when there is (what looks to me) a
> >> fairly simple patch that can be added to the base system. Either way it
> >> would be good to get the PR closed one way or the other considering the
> >> backlog...
> >
> > There are a "decent" number of PRs pertaining to ATA/SATA stuff in
> > FreeBSD, some going back over 2 years which fix very severe bugs in RAID
> > (see my Common Issues list for examples).
>
> Where is this list? I did a quick search but couldn't find it.
http://wiki.freebsd.org/JeremyChadwick/Commonly_reported_issues
> > Your cries are heard by some, but I'm left believing Soren is just super
> > busy with real life. I consider this even more justification that the ATA
> > layer in FreeBSD needs additional eyes familiar with it, and not just a
> > single person.
>
> No argument here. Soren does an incredible job maintaining ATA as it is
> and I am very grateful that he has put as much of his time into the
> project as he has. (Thanks Soren!)
I am too, but PRs that are 2 years old which include patches for severe
bugs that affect reliability of RAID is (in my opinion) not acceptable.
I've been spanked over saying this before ("you don't understand how
open source works"), but necessity easily supercedes idealism.
Linux's libata has evolved very quickly and very well, and has multiple
eyes familiar with the code (in the case the author takes vacation,
etc.). It has the upper hand here.
--
| Jeremy Chadwickjdc at parodius.com |
| Parodius Networking http://www.parodius.com/ |
| UNIX Systems Administrator Mountain View, CA, USA |
| Making life hard for others since 1977. PGP: 4BD6C0CB |
___
freebsd-stable@freebsd.org mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-stable
To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
On Mon, May 12, 2008 03:23, Jeremy Chadwick wrote: > On Mon, May 12, 2008 at 03:16:10AM -0400, [EMAIL PROTECTED] wrote: > >> On Mon, May 12, 2008 00:52, Ian Smith wrote: >> >>> On Sun, 11 May 2008 [EMAIL PROTECTED] wrote: >>> I found this PR (with patch) to add APM and acoustic management control to atacontrol. The PR was opened in May 2005 has not been changed since December 2006 and is still open. http://www.freebsd.org/cgi/query-pr.cgi?pr=81692&cat= >>> >>> As for APM and AAM, that functionality is handled by >>> sysutils/ataidle, which that PR appears - on a quick glance - to >>> pretty well duplicate. >>> >>> I see phk@ recently added an 'atacontrol spindown' command to HEAD >>> and RELENG_7 that appears to offer similar functionality to 'ataidle >>> -S >>> standby_mins' or 'ataidle -I idle_mins', though specified in seconds >>> instead. However this doesn't address acoustic management. >>> >>> Or is ataidle broken for SATA disks? >>> >> >> I think the idea was to put the ability to control it where people see >> it first. I expected to be able to control NCQ, APM, and acoustic >> management from atacontrol considering it listed whether they were >> enabled or not. > > Well, atacontrol(8) does let you control many things, but most pertain > to ataraid(4). Otherwise, it acts purely as an ATA/SATA information > utility; maybe it should be renamed atainfo(8)? That would probably confuse more existing users than it would help new ones. I don't think it would be worth renaming it unless the raid functionality was moved to a separate command, which would be a pointless bunch of work. > The expectation that the tool should be able to control those things is > legitimate, but if this is something you absolutely *need*, then I would > recommend going with Linux instead. Their libata has support for all of > the above, and has userland applications to control said features. Nope, I'm happy with FreeBSD. This is more of a minor quirk than anything else for me. I figured I would see if anything had changed since the last mailing list messages I found where well over a year old. >> ataidle is easy enough to find, I won't deny, but why make users do the >> google search and install a port when there is (what looks to me) a >> fairly simple patch that can be added to the base system. Either way it >> would be good to get the PR closed one way or the other considering the >> backlog... > > There are a "decent" number of PRs pertaining to ATA/SATA stuff in > FreeBSD, some going back over 2 years which fix very severe bugs in RAID > (see my Common Issues list for examples). Where is this list? I did a quick search but couldn't find it. > Your cries are heard by some, but I'm left believing Soren is just super > busy with real life. I consider this even more justification that the ATA > layer in FreeBSD needs additional eyes familiar with it, and not just a > single person. No argument here. Soren does an incredible job maintaining ATA as it is and I am very grateful that he has put as much of his time into the project as he has. (Thanks Soren!) Jonathan Stewart ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
On Mon, May 12, 2008 at 03:16:10AM -0400, [EMAIL PROTECTED] wrote: > On Mon, May 12, 2008 00:52, Ian Smith wrote: > > On Sun, 11 May 2008 [EMAIL PROTECTED] wrote: > > > >> I found this PR (with patch) to add APM and acoustic management control > >> to atacontrol. The PR was opened in May 2005 has not been changed since > >> December 2006 and is still open. > >> http://www.freebsd.org/cgi/query-pr.cgi?pr=81692&cat= > >> > >> I have not been able to find much of anything on SATA NCQ in FreeBSD > >> newer than 2005 or 2006 does anyone know anything newer? > > > > As for APM and AAM, that functionality is handled by sysutils/ataidle, > > which that PR appears - on a quick glance - to pretty well duplicate. > > > > I see phk@ recently added an 'atacontrol spindown' command to HEAD and > > RELENG_7 that appears to offer similar functionality to 'ataidle -S > > standby_mins' or 'ataidle -I idle_mins', though specified in seconds > > instead. However this doesn't address acoustic management. > > > > Or is ataidle broken for SATA disks? > > I think the idea was to put the ability to control it where people see it > first. I expected to be able to control NCQ, APM, and acoustic management > from atacontrol considering it listed whether they were enabled or not. Well, atacontrol(8) does let you control many things, but most pertain to ataraid(4). Otherwise, it acts purely as an ATA/SATA information utility; maybe it should be renamed atainfo(8)? The expectation that the tool should be able to control those things is legitimate, but if this is something you absolutely *need*, then I would recommend going with Linux instead. Their libata has support for all of the above, and has userland applications to control said features. > ataidle is easy enough to find, I won't deny, but why make users do the > google search and install a port when there is (what looks to me) a fairly > simple patch that can be added to the base system. Either way it would be > good to get the PR closed one way or the other considering the backlog... There are a "decent" number of PRs pertaining to ATA/SATA stuff in FreeBSD, some going back over 2 years which fix very severe bugs in RAID (see my Common Issues list for examples). Your cries are heard by some, but I'm left believing Soren is just super busy with real life. I consider this even more justification that the ATA layer in FreeBSD needs additional eyes familiar with it, and not just a single person. -- | Jeremy Chadwickjdc at parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB | ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
On Mon, May 12, 2008 00:52, Ian Smith wrote: > On Sun, 11 May 2008 [EMAIL PROTECTED] wrote: > >> I found this PR (with patch) to add APM and acoustic management control >> to atacontrol. The PR was opened in May 2005 has not been changed since >> December 2006 and is still open. >> http://www.freebsd.org/cgi/query-pr.cgi?pr=81692&cat= >> >> I have not been able to find much of anything on SATA NCQ in FreeBSD >> newer than 2005 or 2006 does anyone know anything newer? > > As for APM and AAM, that functionality is handled by sysutils/ataidle, > which that PR appears - on a quick glance - to pretty well duplicate. > > I see phk@ recently added an 'atacontrol spindown' command to HEAD and > RELENG_7 that appears to offer similar functionality to 'ataidle -S > standby_mins' or 'ataidle -I idle_mins', though specified in seconds > instead. However this doesn't address acoustic management. > > Or is ataidle broken for SATA disks? I think the idea was to put the ability to control it where people see it first. I expected to be able to control NCQ, APM, and acoustic management from atacontrol considering it listed whether they were enabled or not. ataidle is easy enough to find, I won't deny, but why make users do the google search and install a port when there is (what looks to me) a fairly simple patch that can be added to the base system. Either way it would be good to get the PR closed one way or the other considering the backlog... Jonathan Stewart ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
Jeremy Chadwick wrote: No. ata(4) driver currently doesn't support/use NCQ. Thanks for this information -- I had no idea! I'll add this to my Common Issues page, although it's not so much an "issue" but more so a feature. I was always under the impression that AHCI included automatic support for negotiation and use of extensions like NCQ and TCQ: http://en.wikipedia.org/wiki/Native_Command_Queuing http://www.seagate.com/content/docs/pdf/whitepaper/D2c_tech_paper_intc-stx_sata_ncq.pdf AHCI has standart method to determine presence of NCQ support. But FreeBSD's driver needs some code to work with NCQ. Soren said to me that he is going to work with NCQ support after merging PM support, but I don't know about current status. -- WBR, Andrey V. Elsukov ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
On Mon, May 12, 2008 at 09:27:13AM +0400, Andrey V. Elsukov wrote: > Jeremy Chadwick wrote: >> I believe NCQ is supported, assuming that your controller is operating >> in AHCI mode and your disk supports NCQ. This mainly applies to Intel >> ICHx controllers, but there are others which support it as well. >> There's also NCQ support in non-AHCI drivers like hptmv(4), rr232x(4), >> hptrr(4), and mpt(4) with SATA disks. > > No. ata(4) driver currently doesn't support/use NCQ. Thanks for this information -- I had no idea! I'll add this to my Common Issues page, although it's not so much an "issue" but more so a feature. I was always under the impression that AHCI included automatic support for negotiation and use of extensions like NCQ and TCQ: http://en.wikipedia.org/wiki/Native_Command_Queuing http://www.seagate.com/content/docs/pdf/whitepaper/D2c_tech_paper_intc-stx_sata_ncq.pdf -- | Jeremy Chadwickjdc at parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB | ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
Jeremy Chadwick wrote: I believe NCQ is supported, assuming that your controller is operating in AHCI mode and your disk supports NCQ. This mainly applies to Intel ICHx controllers, but there are others which support it as well. There's also NCQ support in non-AHCI drivers like hptmv(4), rr232x(4), hptrr(4), and mpt(4) with SATA disks. No. ata(4) driver currently doesn't support/use NCQ. -- WBR, Andrey V. Elsukov ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
On Sun, 11 May 2008 [EMAIL PROTECTED] wrote: > Has any work been done recently towards adding SATA Native Command > Queueing as well as ATA APM and acoustic management to FreeBSD? > > I found this PR (with patch) to add APM and acoustic management control to > atacontrol. The PR was opened in May 2005 has not been changed since > December 2006 and is still open. > http://www.freebsd.org/cgi/query-pr.cgi?pr=81692&cat= > > I have not been able to find much of anything on SATA NCQ in FreeBSD newer > than 2005 or 2006 does anyone know anything newer? Jeremy has addressed the NCQ issue, about which I know nothing. As for APM and AAM, that functionality is handled by sysutils/ataidle, which that PR appears - on a quick glance - to pretty well duplicate. I see phk@ recently added an 'atacontrol spindown' command to HEAD and RELENG_7 that appears to offer similar functionality to 'ataidle -S standby_mins' or 'ataidle -I idle_mins', though specified in seconds instead. However this doesn't address acoustic management. Or is ataidle broken for SATA disks? cheers, Ian ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
Re: ATA APM and NCQ support in FreeBSD atacontrol
On Sun, May 11, 2008 at 09:08:51PM -0400, [EMAIL PROTECTED] wrote: > Has any work been done recently towards adding SATA Native Command > Queueing as well as ATA APM and acoustic management to FreeBSD? > > I found this PR (with patch) to add APM and acoustic management control to > atacontrol. The PR was opened in May 2005 has not been changed since > December 2006 and is still open. > http://www.freebsd.org/cgi/query-pr.cgi?pr=81692&cat= > > I have not been able to find much of anything on SATA NCQ in FreeBSD newer > than 2005 or 2006 does anyone know anything newer? I believe NCQ is supported, assuming that your controller is operating in AHCI mode and your disk supports NCQ. This mainly applies to Intel ICHx controllers, but there are others which support it as well. There's also NCQ support in non-AHCI drivers like hptmv(4), rr232x(4), hptrr(4), and mpt(4) with SATA disks. I do see some code that explicitly disables NCQ on some nVidia chipsets, and I believe that's because the NCQ details for the nF4 chipset are unavailable; possibly Linux has them. atacontrol, on the other hand, I believe always spits out "-" as to whether or not it's enabled. I'd have to go look at the code to be sure, but I'm guessing it just says "-" no matter what. An example: Feature Support EnableValue Vendor write cacheyes yes read ahead yes yes Native Command Queuing (NCQ) yes - 31/0x1F Tagged Command Queuing (TCQ) no no 31/0x1F SMART yes yes microcode download yes yes security yes no power management yes yes advanced power management no no 0/0x00 automatic acoustic management yes no 254/0xFE128/0x80 Finally, I read a while back that NCQ on SATA does not provide a substantial improvement in overall disk I/O or under heavy load. It's not entirely marketing hype, but the benefits are like 3-4%, with added CPU utilisation. SATA TCQ is a different matter. SCSI uses TCQ, and as we all know, it works beautifully. SATA TCQ has a significantly larger queue depth than SATA NCQ (2^64 vs. 31). -- | Jeremy Chadwickjdc at parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, USA | | Making life hard for others since 1977. PGP: 4BD6C0CB | ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
ATA APM and NCQ support in FreeBSD atacontrol
Has any work been done recently towards adding SATA Native Command Queueing as well as ATA APM and acoustic management to FreeBSD? I found this PR (with patch) to add APM and acoustic management control to atacontrol. The PR was opened in May 2005 has not been changed since December 2006 and is still open. http://www.freebsd.org/cgi/query-pr.cgi?pr=81692&cat= I have not been able to find much of anything on SATA NCQ in FreeBSD newer than 2005 or 2006 does anyone know anything newer? Thanks, Jonathan Stewart ___ freebsd-stable@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-stable To unsubscribe, send any mail to "[EMAIL PROTECTED]"
