This message is from the T13 list server.
Hi Gary:
Greetings. Allow me to answer your questions one by one:
1. I do intend to propose the availability of an HPA complaince tool
that can be used by disk drive manufacturers, OEM's etc. to validate the
HPA compliance of a disk drive. Details to
This message is from the T13 list server.
Send to both T13 and T10 - Hale.
On Wed, 12 Feb 2003 09:44:11 -0700, Pat LaVarre wrote:
This message is from the T13 list server.
[...]
As was reported to t13, I'm still working offline
with Hale Landis to try and make the issue more plain.
[...]
This message is from the T13 list server.
On Wed, 12 Feb 2003 09:35:13 -0800, Mukesh Kataria wrote:
This message is from the T13 list server.
1. I do intend to propose the availability of an HPA complaince tool
that can be used by disk drive manufacturers, OEM's etc. to validate the
HPA
This message is from the T13 list server.
Hi Hale:
Your consideration is well noted and accepted that instead of a
compliance tool, we should rather report problems/issues and have them
fixed via/in the spec.
The reason to have a special tool is to tackle drives/devices which
don't seem to
This message is from the T13 list server.
Hale,
The tool was not intended to be a T13 thing, but rather something
available to folks who were interested. I talked to several folks at T13 in
Vegas who were interested in seeing it. I am glad it is still being
pursued, I personally think its
This message is from the T13 list server.
Hale,
One thing lost in the mix is DCO +/- HPA and the various combinations and
effects releated to the 28/48-bit address point and command sets. Add in
the twist of SET MAX EXTENDED and the reporting of capacity of
fabrications in the two locations,
This message is from the T13 list server.
I'll now drop t10 from this thread if noone replies online to indicate interest.
Pat LaVarre
This message is from the T13 list server.
I'll keep this brief
I wish you well.
Some OS's at a high level treat everything storage
as SCSI, so lower-level drivers must identify
their actual device and convert SCSI-2-Whatever.
I've been told Windows works this way. The higher
levels speak
This message is from the T13 list server.
Re: Fwd: why not H = C = D ModeSense6 for just the header
Pat, I don't understand your confusion
Thanks you for your interest, sorry I was unclear,
kind of everyone here to let me try again.
about determining if a device is an ATAPI or SCSI
device.
This message is from the T13 list server.
Interesting.
Thanks for saying.
Note that this description is very abbreviated and
contains errors that, for a 100k-ft view should be
acceptable.
Indeed, what you say fits what I heard before, I see
no errors, so if I'm wrong here, the 100k-ft
~$towhzpaper2[1].doc
Description: Binary data
This message is from the T13 list server.
Pete,
It has been fun, but I have been unable to renew my voting member status.
So you have one less cook in the kitchen.
Cheers,
Andre Hedrick
LAD Storage Consulting Group
On Mon, 24 Feb 2003, Mclean, Pete wrote:
This message is from the T13
This message is from the T13 list server.
No sooner than I sent that did I realize that I meant volume 3.
So
I have a question about vol *3* of ATA-7, (SATA).
If a host sets the state of the nIEN bit in the device control
register, does that get transmitted to the drive as an control
This message is from the T13 list server.
The asserting of an interupt to the host is handled by the host adapter. If
a FIS is received from the device indicating it wants to interrupt, the host
adapter either interrupts the host or not depending on the state of the nIEN
bit in its shadow
This message is from the T13 list server.
-Original Message-
From: Bennett, Barbara [mailto:[EMAIL PROTECTED]
Sent: Thursday, March 06, 2003 11:30 AM
To: INCITS_EB (E-mail); INCITS TC/TG/SG Chairs (E-mail) (E-mail)
Cc: McLean, Peter
Subject: Notification of an Approved Project Proposal
This message is from the T13 list server.
I have just put ATA/ATAPI-7 rev 2a on the FTP site as docs2003/d1532v1r2a,
d1532v2r2a, and d1532v3r2a. Both .pdf and .zip (zipped .doc). This rev
includes all of the reorganization of volume 3 agreed to at last weeks
working group meeting and the changes
Is T13 still active? I have not seen any
traffic.
gary laatsch
[EMAIL PROTECTED]
This message is from the T13 list server.
Too much traffic, too little traffic, that is the question.
Offline near T10 lately I saw ... before 1841, J. F. Cooper wrote 'tis useless
talking, as each man will think for himself, and have his say agreeable to his
thoughts.
Pat LaVarre
This message is from the T13 list server.
Well, you beat me to the question!
Andre Hedrick
LAD Storage Consulting Group
On Mon, 31 Mar 2003, Gary Laatsch wrote:
Is T13 still active? I have not seen any traffic.
gary laatsch
[EMAIL PROTECTED]
Title: Serial # of an ATA drive
Hi folks,
Can someone here tell me if the serial # string returned by the IDENTIFY DEVICE command of a drive will be unique for one particular drive ?
The reason why I am asking is that the verbiage in the ATA spec 7.0 says,
6.16.17 Words (19:10): Serial
This message is from the T13 list server.
It is my experience that ATAPI devices generally have a blank field
for serial number.
I've not run across an ATA hard drive which did not meet the
standard's language of the combination of vendor/model and serial
number strings being unique when
This message is from the T13 list server.
FYI -
CompactFlash media is required to be uniquely serialized.
Steve
-Original Message-
From: Larry Barras [mailto:[EMAIL PROTECTED]
Sent: Friday, April 04, 2003 3:44 PM
To: [EMAIL PROTECTED]
Subject: RE: [t13] Serial # of an ATA drive
This message is from the T13 list server.
All:
I retract my statement regarding the unique serialization of CompactFlash
cards. Only those cards which implement a rights management scheme are
required to be uniquely serialized.
There do exist CF cards in the market which are not serialized.
Title: Serial # of an ATA drive
All,
In looking back through the minutes on this I
noticed in August 2002 (e02134r0 section 7.5.9) Curtis Stevens asked that this
be made manditory. The proposal adopted wasn't very clear other than it
provided for supported and not supported bits which I
This message is from the T13 list server.
Gary,
Is this gigabytes for dollars again? Sounds like DCO with a new label.
When are the OEM's going to give up the idea they can stuff their dirty
little secrets on the tail of the drive? No body wants a system that is
subject to being compromised
Michael,
PARTIES-2 proposal:
http://www.t13.org/docs2003/e03106r0.pdf
The orginal PARTIES spec used to be on the Phoenix
website. I don't know if it is still there or if anyone from Phoenix is
even maintaining that stuff anymore. I know the ones who used to are no
longer there. I would
This message is from the T13 list server.
Figure 33 on page 350:
The HPD1:HPD3 transition is not in SFF 8020i r2.6 and seems inconsistent
with the device diagram in Figure 34.
The transition seems to imply that the host should wait for an interrupt
before starting a DMA transfer. But in the
This message is from the T13 list server.
T13 Forum List Members:
I received official notification of my appointment as T13 Chairman from
INCITS.
We need a new vice chairman. The vice chairman's only official duty is to
fill in for the chairman in his absence. Traditionally the vice
This message is from the T13 list server.
Dear T13 Reflector Members:
I placed the Ad Hoc Meeting Minutes on the web site as document e03119r0.
Best Regards,
Dan Colegrove
[EMAIL PROTECTED]
This message is from the T13 list server.
Hi,
I hope this is the correct forum for such questions - if
the group does not field T13 implementation questions,
please let me know.
I'm writing an ATA driver for RISC OS. I've implemented a
lot of standard ATA-4 onwards features which I've not
Title: ATA-7 Write DMA Queued FUA EXT problem
T13 Reflector,
Western Digital believes there is a problem with the wording under the description paragraph for the Write DMA Queued FUA EXT command.
The description states this command shall not be released. There is a fundamental problem if
Title: ATA-7 Write DMA Queued FUA EXT problem
I am reading back through the minutes and my notes
on this. I remember this was discussed back in June of 2002 (when we voted
it into ATAPI-7). This particular case is not reflected in
theminutes (which of course doesnt mean we didnt discuss it).
Title: ATA-7 Write DMA Queued FUA EXT problem
As I think about this more some of the discussion
is coming back. I do remember discussing similar to what Mark is talking
about now. I dont remember exact details, but I remember discussing how
drives use automation and things like read from
This message is from the T13 list server.
Does FUA mean access the media ONLY for the single command that
requests FUA or for all data currently in the write cache
(basically combining the effect of some writes followed by a FLUSH
CACHE) or is it something far more complex (and therefore more
This message is from the T13 list server.
Only the FUA command's data would be affected. Since a FLUSH command already affects
all commands in the write cache and FLUSH adversely affects performance, the FUA
command gives us the ability to target specific requests as non-cacheable so we can
This message is from the T13 list server.
On Mon, 16 Jun 2003 09:06:33 -0600, [EMAIL PROTECTED]
wrote:
This message is from the T13 list server.
Just as a point of reference - - - here is the last proposal revision:
http://t13.org/docs2002/e01141r2.pdf
Thanks Jim.
OK, the proposed
This message is from the T13 list server.
As I asked in the previous email, I don't see a proposal for the
WRITE DMA QUEUED FUA command. But looking at the ATA/ATAPI-7
description (both the general description of O/Q and the command
description) I don't see a problem. Basically this command is a
This message is from the T13 list server.
The last paragraph of section 4.20 in ATAPI-7 clearly states that WRITE DMA
QUEUED FUA EXT (could we make this name longer) is unique. It also goes
on to state regardless of the state of any cache. That is the best case I
found for our discussions. In
This message is from the T13 list server.
Hale,
Yes, SATA-II is proposing adding 2 new opcodes for Queued DMA reads and
writes with an FUA bit. As expected, the question at hand is not clear
there either. They (SATA) do state in a FUA Read condition, that is dirty
cache exists with the
This message is from the T13 list server.
Hale,
IIRC when Nina from Microsoft intoduced this monster, many issues came up.
The worst was FUA would ram to the front of the cache queue and basically
NUKE all outstanding tags. This was a major mess.
Corrections requested.
Andre Hedrick
LAD
This message is from the T13 list server.
All the operating systems I've ever seen have locks to ensure that you
don't issue multiple I/Os simultaneously to the same range of sectors on
a disk.
-Costa
This message is from the T13 list server.
I'm curious why there are no comments about the question of the
origin of the WRITE DMA QUEUED FUA command (where is the proposal?).
And why no comments on QUEUED EXT commands with large sector counts.
Is this because all these discussions must take
This message is from the T13 list server.
On Tue, Jun 17 2003, Constantine Sapuntzakis wrote:
This message is from the T13 list server.
All the operating systems I've ever seen have locks to ensure that you
don't issue multiple I/Os simultaneously to the same range of sectors on
a
This message is from the T13 list server.
Agreed. What I said was wrong - the locks in the buffer cache don't
ensure anything. You can definitely write code at user and kernel
level that ends up issuing simultaneous requests to the same sectors on
a disk. And the disk driver doesn't really
This message is from the T13 list server.
Curtis and Hale,
Also, to expand upon this. I think Hale's point is the proposal put
forth by Nita didn't contain the QUEUE FUA or QUEUE FUA EXT commands and he
was wondering where they were added or how they were proposed. My memory was
this was
This message is from the T13 list server.
It seems to me that the essence of what was requested has been captured.
However the original comment to this thread related to a released Write
request that may contain LBAs that when written would then overwrite data
that from a system point of view
This message is from the T13 list server.
Gary
As I recall, there were some inacuracies in the proposals as made to the
committee. There were many revisions. The only new FUA commands that make
sense are the queued ones. All others could be followed by flush cache.
This message is from the T13 list server.
Before I go out and spend my hard earned $$ on the official EDD
specification available from ANSI and Global Engineering, can someone
tell me if the differences between the last T13 Draft (d1484r3 BIOS
Enhanced Disk Drive Services - 2 (EDD-2)) and the
This message is from the T13 list server.
It should warn explicitly that the host shall ensure that any released
commands with overlapping LBAs to an upcoming FUA are serviced before
issuing the FUA.
We have faced similar situation when we discussed AV command set
specification. And we T13
This message is from the T13 list server.
All modern HDD's have a buffer for write cache that is used to stack up
write data from both queued and unqueued write commands. A write command
followed by a flush cache command will likely not move the data from the
last write command to the media
This message is from the T13 list server.
Yep it is called DATABASE access.
Andre Hedrick
LAD Storage Consulting Group
On Tue, 17 Jun 2003, Jens Axboe wrote:
This message is from the T13 list server.
On Tue, Jun 17 2003, Constantine Sapuntzakis wrote:
This message is from the T13
This message is from the T13 list server.
Gary,
They did get discussed because Tony G. and I wanked the issue just before
the subject change started into the weed write and write wong.
Recall I ranted about FUA needed to be identical to ordered operations in
tag command queue if FUA was set.
This message is from the T13 list server.
Steve,
This totally nukes and destroys write ordered operations.
Example is the down/commit block on a journalled operation.
Taking an FUA command to platter and blasting past the queue cache will
destroy every bit of the security designed into any
This message is from the T13 list server.
I assume Mark V and others have conversed at some sub-t13 board level about
this since I havent seen any MS commants on this and it was their proposal
that started it. I haven't really seen any comments about it from other
drive folks either.
Did we
This message is from the T13 list server.
Andre, I get the feeling your using drugs (again?)!
Give me a scenario that you perceive will fail using FUA on queued or non-queued
commands, then we can have a useful discussion. Just blowing smoke, as you've done
below, does nothing to resolve
This message is from the T13 list server.
I have not been present at any of the discussions, but Out-Of-Order
writes are inherently dangerous to ANY file system - not only to
journaling. Now that we have Flush Cache as a mandatory command, why
don't we simply issue the Flush Cache to force
This message is from the T13 list server.
My (humble?) opinion is that FUA is necessary and is not dangerous as long as a disk
drive properly deals with outstanding requests.
First off a flush is very slow, affecting system benchmark scores by as much as 5%.
The more interesting fact is that
This message is from the T13 list server.
I really don't think the issue is one of implementation... It looks to me
like there are some concerns about usage and the possibility of unexpected
outcomes. MS clearly stated that they understood several of the unexpected
outcomes and still needed
This message is from the T13 list server.
All,
I wanted to get this note out on the August T13 meeting.
Date: August 19th - 21st
Location: Boulderado Hotel downtown Boulder
2115 Thirteenth Street
Boulder, CO 80302
Phone: 303-442-4344
Fax: 303-442-4378
This message is from the T13 list server.
Someone requested the FUA command for a specific purpose. That purpose is
to immediately execute the write without the performance hit of a flush
cache. That is the way the command should work. Any driver writer that
issues the FUA command with
This message is from the T13 list server.
Gary
The wording you propose would defeat the purpose of the command. I do
not know if you were there for the discussion. The purpose of the FUA was
to cause critical data to be committed to the media, regardless of what is
in the que. If you
This message is from the T13 list server.
Curtis,
I was there for the discussions. I disagree it would defeat the
purpose. If no overlapping everred occurred, it wouldn't be a problem.
This is an exception case and would only be a problem (speed) in the case of
the mentioned overlap.
This message is from the T13 list server.
With my own eyes I have only seen drives faking good status for seek immediate and
write behind, never for flush. But I'm curious now:
How do people prove that a drive whose firmware we did not write has not lied about
flushing?
Do people actually
This message is from the T13 list server.
Imbedded response below:
On Tuesday, June 24, 2003, at 11:02 AM, Pat LaVarre wrote:
This message is from the T13 list server.
With my own eyes I have only seen drives faking good status for seek
immediate and write behind, never for flush. But I'm
This message is from the T13 list server.
Subject: RE: [t13] flush I said because flush I meant
From: Harlan Andrews [mailto:[EMAIL PROTECTED]
Educational, thanks.
other means (such as standby immediate)
to force data to the media ...
Rumour tells me Win write cache stays dirty thru
This message is from the T13 list server.
Kindly offline now I hear Win 2K/ XP do at least sometimes send Ata flush Atapi sync
cache to writeable disks before hibernate/ suspend.
I can't easily reconcile the idea of any particular kind of Win always sending those
commands with my memory of
This message is from the T13 list server.
Kindly offline I hear we might find more folk interested in how reliably Win flushes
cache near the ntdev portion of:
http://www.osronline.com/page.cfm?name=ListServer
-Original Message-
From: Pat LaVarre
Sent: Tue
This message is from the T13 list server.
Constantine Sapuntzakis raised this issue a couple of months ago and
yesterday at the T13 meeting we came up with a correction to the Host
Side Packet DMA state diagrams that appear in ATA/ATAPI-5, 6 and the
current draft of 7.
The correction has two
This message is from the T13 list server.
Curtis,
When you say state information, I assume you are referring to
information which is vital to prevent damage to system structures due
to a power failure. You are correct in that there is very little
warning of a power failure. In fact, I
This message is from the T13 list server.
I am sending this as a test. I haven't been able to get onto the T13
List Server yet although I have been trying to reply to this thread for
a while. I apologize if I reawaken the issue. For those who were not
at the T13 meeting this week, the
This message is from the T13 list server.
Subject: RE: [t13] hmmm.. no comments?
Once upon a time I saw a fua write implementation that received the write data into
cache, flushed the whole cache, and then copied status in.
This meets the added restriction that the data must be to the
This message is from the T13 list server.
Yes, that implementation satisfied the FUA criteria.
I am not going to comment on how good of an implementation decision that
method is, but it should not be considered out of spec.
Nathan
-Original Message-
From: [EMAIL PROTECTED]
This message is from the T13 list server.
I hope it is more than a removal of the sentence.
The command, as defined, has no Tag Value and the Sector Count value comes
from the Sector Count register (like legacy extended commands) and not from
the Features Register like all the rest of the
This message is from the T13 list server.
From what I have been following on that I first got the
impression that the new FUA command is about writing
data to the medium with a higher priority than cached data
which was written via normal write. Sounds dangerous, but disk write
can always be
This message is from the T13 list server.
The command has no tag because it is not supposed to release. FUA means
that the command will not complete until the data is committed to media.
The wording allows the drive to dump the entire cache to the media, but the
original intention was NOT to
This message is from the T13 list server.
Since I started the hmmm.. no comments message thread and now there
seems to be some confusion about the FUA commands, let me try an
explaination...
First, it seems that Microsoft proposed four new commands, WRITE DMA
FUA, WRITE DMA EXT FUA, WRITE
This message is from the T13 list server.
Hale,
I don't understand your interest of a disk drive cache
algorithm. The only behavior the host can assume about a disk cache is
that it doesn't change the behavior of the drive. Once the drive has
signaled the completion of a transfer, it
This message is from the T13 list server.
On Fri, 27 Jun 2003 09:13:02 -0700, Nathan Obr wrote:
This message is from the T13 list server.
Hale,
I don't understand your interest of a disk drive cache
algorithm. The only behavior the host can assume about a disk cache is
that it doesn't change the
This message is from the T13 list server.
On Friday, June 27, 2003, at 09:13 AM, Nathan Obr wrote:
Because the FUA commands do not affect the internal queuing or
write ordering of the disk, FUA commands are no more of a data
integrity
problem for the host then normal write and queued write
This message is from the T13 list server.
On Fri, 27 Jun 2003 13:44:26 -0700, Nathan Obr wrote:
I do assume that drive manufacturers will do the right thing, but that
is only because they have for years.
Are you sure? What is the definition of right thing? Is it some
test Microsoft uses for
This message is from the T13 list server.
Harlan,
Not could completely destroy data, it will.
Simple proof is a journalling FS and FUA is issued on the down block of
the journal. This is more than local single host and device ownership.
Apply this to a global filesystem where the only
This message is from the T13 list server.
Hale,
The 'right thing' for the disk drive behavior that I was
referring to is the assumption that after a write to the disk, any read
from the same address any time after the write, will produce the same
data. The presence or absence of a cache
This message is from the T13 list server.
Nathan,
Sweet! This is what I like to hear.
Andre Hedrick
LAD Storage Consulting Group
On Sun, 29 Jun 2003, Nathan Obr wrote:
Andre,
Microsoft did not deem it all important to jump the queue. FUA
does not jump the queue. FUA doesn't have
This message is from the T13 list server.
On Sun, 29 Jun 2003, Nathan Obr wrote:
This message is from the T13 list server.
Hale,
The 'right thing' for the disk drive behavior that I was
referring to is the assumption that after a write to the disk, any read
from the same address
This message is from the T13 list server.
Dan,
I am no longer employed by Network Appliance, Inc.
The previous Alternate will become the new Principal.
Tony Aiello
Technical Director
Network Appliance, Inc.
495 E. Java Drive
Sunnyvale, CA 94089
408.622.6515
[EMAIL PROTECTED]
The senior
This message is from the T13 list server.
On Sun, 29 Jun 2003 23:25:48 -0700, Nathan Obr wrote:
This message is from the T13 list server.
The 'right thing' for the disk drive behavior that I was
referring to is the assumption that after a write to the disk, any read
from the same address any
This message is from the T13 list server.
Hugh,
There seems to be some confusion about how FUA works.
Some people seem to think that FUA requests get promoted in the queue.
Others (myself included) believe that FUA should simply delay return
until that request AND ALL other requests ahead of
This message is from the T13 list server.
Harlan,
FUA doesn't have any relevance to a queue.
FUA can return before other requests which were ahead of the
queue have been flushed to the media. Only the FUA command/data itself
has to be on the media before it can return.
This message is from the T13 list server.
Hello,
Who requested this change/addition? Why?
I believe someone said MS requested it to be able to write the directory
without having to flush cache. If that is the case, there will be overlap
between each directory write (which will use the FUA
This message is from the T13 list server.
HISTORY of FUA as I saw it:
The original FUA proposal was requested by MS over a year ago. Most (98%)
of this was discussed, the proposal amended (to include the QUEUED version
of the commands) and adopted back in June of 2002. Mark Vallis brought up
This message is from the T13 list server.
Hiya,
I spotted a couple of typos in the T13 spec. Do I report them on this
group, or do I e-mail someone in particular?
I'm afraid I don't have them in front of me, so I can't replicate them
all here for this e-mail. A few are included:
One of them
Gary,
No need for such info. We have been assured (by Nathan) that FUA does NOT imply queue promotion.
The drive MUST still maintain data integrity.
...Harlan
On Saturday, July 5, 2003, at 4:48 PM, Gary Laatsch wrote:
I know we beat FUA to death and it probably got closed at the meetings
Wow! The latest e-mails regarding FUA adds a whole new
spin on the meaning of flush cache that as a drive firmware engineer I had
never considered.
So now I must ask,
Does flush mean down the toilet? Or
onto the media?
Paul J.
This message is from the T13 list server.
Please plan on attending the T-13 add hoc meeting July 31st and Aug.1st,
2003
Planned review of the ATA 7, (Serial ATA) Vol 3
Hosted by Seagate Technology @
At Seagate Technology
This message is from the T13 list server.
Tony,
It seems wrong to me. Can someone explain the rational for that
behavior.
I don't think current devices actually work that way. Surely we don't
want that behavior, do we ?
Regards,
Harlan
On Wednesday, July 9, 2003, at 12:11PM, Tony
This message is from the T13 list server.
What causes a PCI bus SATA controller to stop responding in the
middle of a command? Specifically, in the middle of a READ DMA
command, what would cause the drive status to change to FDH or FFH
and then cause the controller and drive(s) to ignore a Soft
This message is from the T13 list server.
On Thu, 10 Jul 2003 09:31:15 +0200, Jens Axboe wrote:
This message is from the T13 list server.
[...] It worries me more than
just a little bit that the people here discussing flush cache usage is
not even aware of how that affects tcq as worded in the
This message is from the T13 list server.
resend
did not see this returned on the reflector.
[EMAIL PROTECTED],
Product Planning, Seagate Technology
389 Disc Drive. Longmont, Co 80503
720-684-1333 ph
720-684-1031 fax
303-589-8263 Cel
- Forwarded by Marc A Noblitt/Seagate on 07/10/2003 12:18
This message is from the T13 list server.
resend
[EMAIL PROTECTED],
Product Planning, Seagate Technology
389 Disc Drive. Longmont, Co 80503
720-684-1333 ph
720-684-1031 fax
303-589-8263 Cel
- Forwarded by Marc A Noblitt/Seagate on 07/10/2003 12:26 PM -
This message is from the T13 list server.
Please plan on attending the T-13 add hoc meeting July 31st and Aug.1st,
2003
Planned review of the ATA 7, (Serial ATA) Vol 3
Hosted by Seagate Technology @
601 - 700 of 1830 matches
Mail list logo