Guy Watkins wrote:
} -Original Message-
} From: [EMAIL PROTECTED] [mailto:linux-raid-
} [EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED]
} Sent: Thursday, July 12, 2007 1:35 PM
} To: [EMAIL PROTECTED]
} Cc: Tejun Heo; [EMAIL PROTECTED]; Stefan Bader; Phillip Susi; device-mapper
}
Guy Watkins wrote:
} -Original Message-
} From: [EMAIL PROTECTED] [mailto:linux-raid-
} [EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED]
} Sent: Thursday, July 12, 2007 1:35 PM
} To: [EMAIL PROTECTED]
} Cc: Tejun Heo; [EMAIL PROTECTED]; Stefan Bader; Phillip Susi; device-mapper
}
} -Original Message-
} From: [EMAIL PROTECTED] [mailto:linux-raid-
} [EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED]
} Sent: Thursday, July 12, 2007 1:35 PM
} To: [EMAIL PROTECTED]
} Cc: Tejun Heo; [EMAIL PROTECTED]; Stefan Bader; Phillip Susi; device-mapper
} development; [EMAIL
[EMAIL PROTECTED] wrote:
On Wed, 11 Jul 2007 18:44:21 EDT, Ric Wheeler said:
[EMAIL PROTECTED] wrote:
On Tue, 10 Jul 2007 14:39:41 EDT, Ric Wheeler said:
All of the high end arrays have non-volatile cache (read, on power loss, it is a
promise that it will get all of your data out to
On Wed, 11 Jul 2007 18:44:21 EDT, Ric Wheeler said:
> [EMAIL PROTECTED] wrote:
> > On Tue, 10 Jul 2007 14:39:41 EDT, Ric Wheeler said:
> >
> >> All of the high end arrays have non-volatile cache (read, on power loss,
> >> it is a
> >> promise that it will get all of your data out to permanent
On Wed, 11 Jul 2007 18:44:21 EDT, Ric Wheeler said:
[EMAIL PROTECTED] wrote:
On Tue, 10 Jul 2007 14:39:41 EDT, Ric Wheeler said:
All of the high end arrays have non-volatile cache (read, on power loss,
it is a
promise that it will get all of your data out to permanent storage). You
[EMAIL PROTECTED] wrote:
On Wed, 11 Jul 2007 18:44:21 EDT, Ric Wheeler said:
[EMAIL PROTECTED] wrote:
On Tue, 10 Jul 2007 14:39:41 EDT, Ric Wheeler said:
All of the high end arrays have non-volatile cache (read, on power loss, it is a
promise that it will get all of your data out to
} -Original Message-
} From: [EMAIL PROTECTED] [mailto:linux-raid-
} [EMAIL PROTECTED] On Behalf Of [EMAIL PROTECTED]
} Sent: Thursday, July 12, 2007 1:35 PM
} To: [EMAIL PROTECTED]
} Cc: Tejun Heo; [EMAIL PROTECTED]; Stefan Bader; Phillip Susi; device-mapper
} development; [EMAIL
[EMAIL PROTECTED] wrote:
On Tue, 10 Jul 2007 14:39:41 EDT, Ric Wheeler said:
All of the high end arrays have non-volatile cache (read, on power loss, it is a
promise that it will get all of your data out to permanent storage). You don't
need to ask this kind of array to drain the cache. In
[EMAIL PROTECTED] wrote:
On Tue, 10 Jul 2007 14:39:41 EDT, Ric Wheeler said:
All of the high end arrays have non-volatile cache (read, on power loss, it is a
promise that it will get all of your data out to permanent storage). You don't
need to ask this kind of array to drain the cache. In
Ric Wheeler wrote:
>> Don't those thingies usually have NV cache or backed by battery such
>> that ORDERED_DRAIN is enough?
>
> All of the high end arrays have non-volatile cache (read, on power loss,
> it is a promise that it will get all of your data out to permanent
> storage). You don't need
[EMAIL PROTECTED] wrote:
> On Tue, 10 Jul 2007 14:39:41 EDT, Ric Wheeler said:
>
>> All of the high end arrays have non-volatile cache (read, on power loss, it
>> is a
>> promise that it will get all of your data out to permanent storage). You
>> don't
>> need to ask this kind of array to
On Tue, 10 Jul 2007 14:39:41 EDT, Ric Wheeler said:
> All of the high end arrays have non-volatile cache (read, on power loss, it
> is a
> promise that it will get all of your data out to permanent storage). You
> don't
> need to ask this kind of array to drain the cache. In fact, it might
Tejun Heo wrote:
[ cc'ing Ric Wheeler for storage array thingie. Hi, whole thread is at
http://thread.gmane.org/gmane.linux.kernel.device-mapper.devel/3344 ]
I am actually on the list, just really, really far behind in the thread ;-)
Hello,
[EMAIL PROTECTED] wrote:
but when you
Tejun Heo wrote:
[ cc'ing Ric Wheeler for storage array thingie. Hi, whole thread is at
http://thread.gmane.org/gmane.linux.kernel.device-mapper.devel/3344 ]
I am actually on the list, just really, really far behind in the thread ;-)
Hello,
[EMAIL PROTECTED] wrote:
but when you
On Tue, 10 Jul 2007 14:39:41 EDT, Ric Wheeler said:
All of the high end arrays have non-volatile cache (read, on power loss, it
is a
promise that it will get all of your data out to permanent storage). You
don't
need to ask this kind of array to drain the cache. In fact, it might just
[EMAIL PROTECTED] wrote:
On Tue, 10 Jul 2007 14:39:41 EDT, Ric Wheeler said:
All of the high end arrays have non-volatile cache (read, on power loss, it
is a
promise that it will get all of your data out to permanent storage). You
don't
need to ask this kind of array to drain the
Ric Wheeler wrote:
Don't those thingies usually have NV cache or backed by battery such
that ORDERED_DRAIN is enough?
All of the high end arrays have non-volatile cache (read, on power loss,
it is a promise that it will get all of your data out to permanent
storage). You don't need to ask
On Thu, Jul 05 2007, Tejun Heo wrote:
> Hello, Jens.
>
> Jens Axboe wrote:
> > On Mon, May 28 2007, Neil Brown wrote:
> >> I think the implementation priorities here are:
> >>
> >> 1/ implement a zero-length BIO_RW_BARRIER option.
> >> 2/ Use it (or otherwise) to make all dm and md modules handle
On Thu, Jul 05 2007, Tejun Heo wrote:
Hello, Jens.
Jens Axboe wrote:
On Mon, May 28 2007, Neil Brown wrote:
I think the implementation priorities here are:
1/ implement a zero-length BIO_RW_BARRIER option.
2/ Use it (or otherwise) to make all dm and md modules handle
barriers
Hello, Jens.
Jens Axboe wrote:
> On Mon, May 28 2007, Neil Brown wrote:
>> I think the implementation priorities here are:
>>
>> 1/ implement a zero-length BIO_RW_BARRIER option.
>> 2/ Use it (or otherwise) to make all dm and md modules handle
>>barriers (and loop?).
>> 3/ Devise and
Hello, Jens.
Jens Axboe wrote:
On Mon, May 28 2007, Neil Brown wrote:
I think the implementation priorities here are:
1/ implement a zero-length BIO_RW_BARRIER option.
2/ Use it (or otherwise) to make all dm and md modules handle
barriers (and loop?).
3/ Devise and implement appropriate
Jens Axboe wrote:
> On Sat, Jun 02 2007, Tejun Heo wrote:
>> Hello,
>>
>> Jens Axboe wrote:
Would that be very different from issuing barrier and not waiting for
its completion? For ATA and SCSI, we'll have to flush write back cache
anyway, so I don't see how we can get performance
Jens Axboe wrote:
On Sat, Jun 02 2007, Tejun Heo wrote:
Hello,
Jens Axboe wrote:
Would that be very different from issuing barrier and not waiting for
its completion? For ATA and SCSI, we'll have to flush write back cache
anyway, so I don't see how we can get performance advantage by
} -Original Message-
} From: [EMAIL PROTECTED] [mailto:linux-raid-
} [EMAIL PROTECTED] On Behalf Of Jens Axboe
} Sent: Saturday, June 02, 2007 10:35 AM
} To: Tejun Heo
} Cc: David Chinner; [EMAIL PROTECTED]; Phillip Susi; Neil Brown; linux-
} [EMAIL PROTECTED];
Jens Axboe wrote:
On Fri, Jun 01 2007, Bill Davidsen wrote:
Jens Axboe wrote:
On Thu, May 31 2007, Bill Davidsen wrote:
Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
On Fri, Jun 01 2007, Bill Davidsen wrote:
> Jens Axboe wrote:
> >On Thu, May 31 2007, Bill Davidsen wrote:
> >
> >>Jens Axboe wrote:
> >>
> >>>On Thu, May 31 2007, David Chinner wrote:
> >>>
> >>>
> On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
>
>
On Sat, Jun 02 2007, Tejun Heo wrote:
> Hello,
>
> Jens Axboe wrote:
> >> Would that be very different from issuing barrier and not waiting for
> >> its completion? For ATA and SCSI, we'll have to flush write back cache
> >> anyway, so I don't see how we can get performance advantage by
> >>
Hello,
Jens Axboe wrote:
>> Would that be very different from issuing barrier and not waiting for
>> its completion? For ATA and SCSI, we'll have to flush write back cache
>> anyway, so I don't see how we can get performance advantage by
>> implementing separate WRITE_ORDERED. I think
Hello,
Jens Axboe wrote:
Would that be very different from issuing barrier and not waiting for
its completion? For ATA and SCSI, we'll have to flush write back cache
anyway, so I don't see how we can get performance advantage by
implementing separate WRITE_ORDERED. I think zero-length
On Sat, Jun 02 2007, Tejun Heo wrote:
Hello,
Jens Axboe wrote:
Would that be very different from issuing barrier and not waiting for
its completion? For ATA and SCSI, we'll have to flush write back cache
anyway, so I don't see how we can get performance advantage by
implementing
On Fri, Jun 01 2007, Bill Davidsen wrote:
Jens Axboe wrote:
On Thu, May 31 2007, Bill Davidsen wrote:
Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
On Thu, May 31 2007, David Chinner
Jens Axboe wrote:
On Fri, Jun 01 2007, Bill Davidsen wrote:
Jens Axboe wrote:
On Thu, May 31 2007, Bill Davidsen wrote:
Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
} -Original Message-
} From: [EMAIL PROTECTED] [mailto:linux-raid-
} [EMAIL PROTECTED] On Behalf Of Jens Axboe
} Sent: Saturday, June 02, 2007 10:35 AM
} To: Tejun Heo
} Cc: David Chinner; [EMAIL PROTECTED]; Phillip Susi; Neil Brown; linux-
} [EMAIL PROTECTED];
Jens Axboe wrote:
On Thu, May 31 2007, Phillip Susi wrote:
Jens Axboe wrote:
No Stephan is right, the barrier is both an ordering and integrity
constraint. If a driver completes a barrier request before that request
and previously submitted requests are on STABLE storage, then it
Neil Brown wrote:
On Friday June 1, [EMAIL PROTECTED] wrote:
On Thu, May 31, 2007 at 02:31:21PM -0400, Phillip Susi wrote:
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
behaviour
[EMAIL PROTECTED] wrote:
> On Fri, 01 Jun 2007 16:16:01 +0900, Tejun Heo said:
>> Don't those thingies usually have NV cache or backed by battery such
>> that ORDERED_DRAIN is enough?
>
> Probably *most* do, but do you really want to bet the user's data on it?
Thought we were talking about
On Fri, 01 Jun 2007 16:16:01 +0900, Tejun Heo said:
> Don't those thingies usually have NV cache or backed by battery such
> that ORDERED_DRAIN is enough?
Probably *most* do, but do you really want to bet the user's data on it?
> The problem is that the interface between the host and a storage
Jens Axboe wrote:
On Thu, May 31 2007, Bill Davidsen wrote:
Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
IOWs, there are two
On Fri, Jun 01 2007, Tejun Heo wrote:
> Jens Axboe wrote:
> > On Thu, May 31 2007, David Chinner wrote:
> >> On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
> >>> On Thu, May 31 2007, David Chinner wrote:
> IOWs, there are two parts to the problem:
>
> 1 - guaranteeing
On Fri, Jun 01, 2007 at 03:59:51PM +1000, Neil Brown wrote:
> On Friday June 1, [EMAIL PROTECTED] wrote:
> > On Thu, May 31, 2007 at 02:31:21PM -0400, Phillip Susi wrote:
> > > David Chinner wrote:
> > > >That sounds like a good idea - we can leave the existing
> > > >WRITE_BARRIER behaviour
[ cc'ing Ric Wheeler for storage array thingie. Hi, whole thread is at
http://thread.gmane.org/gmane.linux.kernel.device-mapper.devel/3344 ]
Hello,
[EMAIL PROTECTED] wrote:
> but when you consider the self-contained disk arrays it's an entirely
> different story. you can easily have a few gig
On Fri, Jun 01 2007, Neil Brown wrote:
> On Friday June 1, [EMAIL PROTECTED] wrote:
> > On Thu, May 31, 2007 at 02:31:21PM -0400, Phillip Susi wrote:
> > > David Chinner wrote:
> > > >That sounds like a good idea - we can leave the existing
> > > >WRITE_BARRIER behaviour unchanged and introduce a
On Friday June 1, [EMAIL PROTECTED] wrote:
> On Thu, May 31, 2007 at 02:31:21PM -0400, Phillip Susi wrote:
> > David Chinner wrote:
> > >That sounds like a good idea - we can leave the existing
> > >WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
> > >behaviour that only
On Friday June 1, [EMAIL PROTECTED] wrote:
On Thu, May 31, 2007 at 02:31:21PM -0400, Phillip Susi wrote:
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
behaviour that only guarantees
On Fri, Jun 01 2007, Neil Brown wrote:
On Friday June 1, [EMAIL PROTECTED] wrote:
On Thu, May 31, 2007 at 02:31:21PM -0400, Phillip Susi wrote:
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and introduce a new
[ cc'ing Ric Wheeler for storage array thingie. Hi, whole thread is at
http://thread.gmane.org/gmane.linux.kernel.device-mapper.devel/3344 ]
Hello,
[EMAIL PROTECTED] wrote:
but when you consider the self-contained disk arrays it's an entirely
different story. you can easily have a few gig of
On Fri, Jun 01 2007, Tejun Heo wrote:
Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
IOWs, there are two parts to the problem:
1 - guaranteeing I/O ordering
2 -
On Fri, Jun 01, 2007 at 03:59:51PM +1000, Neil Brown wrote:
On Friday June 1, [EMAIL PROTECTED] wrote:
On Thu, May 31, 2007 at 02:31:21PM -0400, Phillip Susi wrote:
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and
Jens Axboe wrote:
On Thu, May 31 2007, Bill Davidsen wrote:
Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
IOWs, there are two
On Fri, 01 Jun 2007 16:16:01 +0900, Tejun Heo said:
Don't those thingies usually have NV cache or backed by battery such
that ORDERED_DRAIN is enough?
Probably *most* do, but do you really want to bet the user's data on it?
The problem is that the interface between the host and a storage
[EMAIL PROTECTED] wrote:
On Fri, 01 Jun 2007 16:16:01 +0900, Tejun Heo said:
Don't those thingies usually have NV cache or backed by battery such
that ORDERED_DRAIN is enough?
Probably *most* do, but do you really want to bet the user's data on it?
Thought we were talking about high-end
Neil Brown wrote:
On Friday June 1, [EMAIL PROTECTED] wrote:
On Thu, May 31, 2007 at 02:31:21PM -0400, Phillip Susi wrote:
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
behaviour
Jens Axboe wrote:
On Thu, May 31 2007, Phillip Susi wrote:
Jens Axboe wrote:
No Stephan is right, the barrier is both an ordering and integrity
constraint. If a driver completes a barrier request before that request
and previously submitted requests are on STABLE storage, then it
On Fri, 1 Jun 2007, Tejun Heo wrote:
but one
thing we should bear in mind is that harddisks don't have humongous
caches or very smart controller / instruction set. No matter how
relaxed interface the block layer provides, in the end, it just has to
issue whole-sale FLUSH CACHE on the device to
Stefan Bader wrote:
> 2007/5/30, Phillip Susi <[EMAIL PROTECTED]>:
>> Stefan Bader wrote:
>> >
>> > Since drive a supports barrier request we don't get -EOPNOTSUPP but
>> > the request with block y might get written before block x since the
>> > disk are independent. I guess the chances of this
Jens Axboe wrote:
> On Thu, May 31 2007, David Chinner wrote:
>> On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
>>> On Thu, May 31 2007, David Chinner wrote:
IOWs, there are two parts to the problem:
1 - guaranteeing I/O ordering
2 - guaranteeing blocks are
On Thu, May 31, 2007 at 02:31:21PM -0400, Phillip Susi wrote:
> David Chinner wrote:
> >That sounds like a good idea - we can leave the existing
> >WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
> >behaviour that only guarantees ordering. The filesystem can then
> >choose
On Thu, May 31 2007, [EMAIL PROTECTED] wrote:
> On Thu, 31 May 2007, Jens Axboe wrote:
>
> >On Thu, May 31 2007, Phillip Susi wrote:
> >>David Chinner wrote:
> >>>That sounds like a good idea - we can leave the existing
> >>>WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
>
On Thu, 31 May 2007, Jens Axboe wrote:
On Thu, May 31 2007, Phillip Susi wrote:
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
behaviour that only guarantees ordering. The filesystem can then
On Thu, May 31 2007, Phillip Susi wrote:
> David Chinner wrote:
> >That sounds like a good idea - we can leave the existing
> >WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
> >behaviour that only guarantees ordering. The filesystem can then
> >choose which to use where
On Thu, May 31 2007, Phillip Susi wrote:
> Jens Axboe wrote:
> >No Stephan is right, the barrier is both an ordering and integrity
> >constraint. If a driver completes a barrier request before that request
> >and previously submitted requests are on STABLE storage, then it
> >violates that
Jens Axboe wrote:
No Stephan is right, the barrier is both an ordering and integrity
constraint. If a driver completes a barrier request before that request
and previously submitted requests are on STABLE storage, then it
violates that principle. Look at the code and the various ordering
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
behaviour that only guarantees ordering. The filesystem can then
choose which to use where appropriate
So what if you want a synchronous write,
David Chinner wrote:
you are understanding barriers to be the same as syncronous writes. (and
therefor the data is on persistant media before the call returns)
No, I'm describing the high level behaviour that is expected by
a filesystem. The reasons for this are below
You say no, but
On Thu, May 31 2007, Bill Davidsen wrote:
> Jens Axboe wrote:
> >On Thu, May 31 2007, David Chinner wrote:
> >
> >>On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
> >>
> >>>On Thu, May 31 2007, David Chinner wrote:
> >>>
> IOWs, there are two parts to the problem:
>
Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
IOWs, there are two parts to the problem:
1 - guaranteeing I/O ordering
2 - guaranteeing blocks are
Neil Brown wrote:
On Monday May 28, [EMAIL PROTECTED] wrote:
There are two things I'm not sure you covered.
First, disks which don't support flush but do have a "cache dirty"
status bit you can poll at times like shutdown. If there are no drivers
which support these, it can be ignored.
2007/5/30, Phillip Susi <[EMAIL PROTECTED]>:
Stefan Bader wrote:
>
> Since drive a supports barrier request we don't get -EOPNOTSUPP but
> the request with block y might get written before block x since the
> disk are independent. I guess the chances of this are quite low since
> at some point a
On Thu, May 31 2007, David Chinner wrote:
> On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
> > On Thu, May 31 2007, David Chinner wrote:
> > > IOWs, there are two parts to the problem:
> > >
> > > 1 - guaranteeing I/O ordering
> > > 2 - guaranteeing blocks are on persistent
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
> On Thu, May 31 2007, David Chinner wrote:
> > IOWs, there are two parts to the problem:
> >
> > 1 - guaranteeing I/O ordering
> > 2 - guaranteeing blocks are on persistent storage.
> >
> > Right now, a single barrier I/O is
On Thu, May 31 2007, David Chinner wrote:
> IOWs, there are two parts to the problem:
>
> 1 - guaranteeing I/O ordering
> 2 - guaranteeing blocks are on persistent storage.
>
> Right now, a single barrier I/O is used to provide both of these
> guarantees. In most cases, all we really
On Wed, May 30 2007, Phillip Susi wrote:
> >That would be the exactly how I understand Documentation/block/barrier.txt:
> >
> >"In other words, I/O barrier requests have the following two properties.
> >1. Request ordering
> >...
> >2. Forced flushing to physical medium"
> >
> >"So, I/O barriers
On Wed, May 30 2007, Phillip Susi wrote:
That would be the exactly how I understand Documentation/block/barrier.txt:
In other words, I/O barrier requests have the following two properties.
1. Request ordering
...
2. Forced flushing to physical medium
So, I/O barriers need to guarantee
On Thu, May 31 2007, David Chinner wrote:
IOWs, there are two parts to the problem:
1 - guaranteeing I/O ordering
2 - guaranteeing blocks are on persistent storage.
Right now, a single barrier I/O is used to provide both of these
guarantees. In most cases, all we really need
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
IOWs, there are two parts to the problem:
1 - guaranteeing I/O ordering
2 - guaranteeing blocks are on persistent storage.
Right now, a single barrier I/O is used to provide
On Thu, May 31 2007, David Chinner wrote:
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
IOWs, there are two parts to the problem:
1 - guaranteeing I/O ordering
2 - guaranteeing blocks are on persistent storage.
2007/5/30, Phillip Susi [EMAIL PROTECTED]:
Stefan Bader wrote:
Since drive a supports barrier request we don't get -EOPNOTSUPP but
the request with block y might get written before block x since the
disk are independent. I guess the chances of this are quite low since
at some point a
Neil Brown wrote:
On Monday May 28, [EMAIL PROTECTED] wrote:
There are two things I'm not sure you covered.
First, disks which don't support flush but do have a cache dirty
status bit you can poll at times like shutdown. If there are no drivers
which support these, it can be ignored.
Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
IOWs, there are two parts to the problem:
1 - guaranteeing I/O ordering
2 - guaranteeing blocks are
On Thu, May 31 2007, Bill Davidsen wrote:
Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
IOWs, there are two parts to the problem:
1 - guaranteeing I/O
David Chinner wrote:
you are understanding barriers to be the same as syncronous writes. (and
therefor the data is on persistant media before the call returns)
No, I'm describing the high level behaviour that is expected by
a filesystem. The reasons for this are below
You say no, but
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
behaviour that only guarantees ordering. The filesystem can then
choose which to use where appropriate
So what if you want a synchronous write,
Jens Axboe wrote:
No Stephan is right, the barrier is both an ordering and integrity
constraint. If a driver completes a barrier request before that request
and previously submitted requests are on STABLE storage, then it
violates that principle. Look at the code and the various ordering
On Thu, May 31 2007, Phillip Susi wrote:
Jens Axboe wrote:
No Stephan is right, the barrier is both an ordering and integrity
constraint. If a driver completes a barrier request before that request
and previously submitted requests are on STABLE storage, then it
violates that principle. Look
On Thu, May 31 2007, Phillip Susi wrote:
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
behaviour that only guarantees ordering. The filesystem can then
choose which to use where appropriate
On Thu, 31 May 2007, Jens Axboe wrote:
On Thu, May 31 2007, Phillip Susi wrote:
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
behaviour that only guarantees ordering. The filesystem can then
On Thu, May 31 2007, [EMAIL PROTECTED] wrote:
On Thu, 31 May 2007, Jens Axboe wrote:
On Thu, May 31 2007, Phillip Susi wrote:
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
behaviour that
On Thu, May 31, 2007 at 02:31:21PM -0400, Phillip Susi wrote:
David Chinner wrote:
That sounds like a good idea - we can leave the existing
WRITE_BARRIER behaviour unchanged and introduce a new WRITE_ORDERED
behaviour that only guarantees ordering. The filesystem can then
choose which to use
Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
On Thu, May 31, 2007 at 08:26:45AM +0200, Jens Axboe wrote:
On Thu, May 31 2007, David Chinner wrote:
IOWs, there are two parts to the problem:
1 - guaranteeing I/O ordering
2 - guaranteeing blocks are on persistent storage.
Stefan Bader wrote:
2007/5/30, Phillip Susi [EMAIL PROTECTED]:
Stefan Bader wrote:
Since drive a supports barrier request we don't get -EOPNOTSUPP but
the request with block y might get written before block x since the
disk are independent. I guess the chances of this are quite low since
On Fri, 1 Jun 2007, Tejun Heo wrote:
but one
thing we should bear in mind is that harddisks don't have humongous
caches or very smart controller / instruction set. No matter how
relaxed interface the block layer provides, in the end, it just has to
issue whole-sale FLUSH CACHE on the device to
On Monday May 28, [EMAIL PROTECTED] wrote:
> Neil Brown writes:
> >
>
> [...]
>
> > Thus the general sequence might be:
> >
> > a/ issue all "preceding writes".
> > b/ issue the commit write with BIO_RW_BARRIER
> > c/ wait for the commit to complete.
> > If it was
On Thu, May 31, 2007 at 02:07:39AM +0100, Alasdair G Kergon wrote:
> On Thu, May 31, 2007 at 10:46:04AM +1000, Neil Brown wrote:
> > If a filesystem cares, it could 'ask' as suggested above.
> > What would be a good interface for asking?
>
> XFS already tests:
> bd_disk->queue->ordered ==
On Thu, May 31, 2007 at 10:46:04AM +1000, Neil Brown wrote:
> If a filesystem cares, it could 'ask' as suggested above.
> What would be a good interface for asking?
XFS already tests:
bd_disk->queue->ordered == QUEUE_ORDERED_NONE
Alasdair
--
[EMAIL PROTECTED]
-
To unsubscribe from this list:
On Thu, May 31, 2007 at 10:46:04AM +1000, Neil Brown wrote:
> What if the truth changes (as can happen with md or dm)?
You get notified in endio() that the barrier had to be emulated?
Alasdair
--
[EMAIL PROTECTED]
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the
On Monday May 28, [EMAIL PROTECTED] wrote:
> On Mon, May 28, 2007 at 12:57:53PM +1000, Neil Brown wrote:
> > What exactly do you want to know, and why do you care?
>
> If someone explicitly mounts "-o barrier" and the underlying device
> cannot do it, then we want to issue a warning or reject the
On Monday May 28, [EMAIL PROTECTED] wrote:
> There are two things I'm not sure you covered.
>
> First, disks which don't support flush but do have a "cache dirty"
> status bit you can poll at times like shutdown. If there are no drivers
> which support these, it can be ignored.
There are
On Tuesday May 29, [EMAIL PROTECTED] wrote:
> Neil Brown wrote:
> > md/dm modules could keep count of requests as has been suggested
> > (though that would be a fairly big change for raid0 as it currently
> > doesn't know when a request completes - bi_endio goes directly to the
> >
On Wed, May 30, 2007 at 09:52:49AM -0700, [EMAIL PROTECTED] wrote:
> On Wed, 30 May 2007, David Chinner wrote:
> >with the barrier is on stable storage when I/o completion is
> >signalled. The existing barrier implementation (where it works)
> >provide these requirements. We need barriers to
1 - 100 of 180 matches
Mail list logo