All of lore.kernel.org
 help / color / mirror / Atom feed
* Sending reads/writes to a userspace program?
@ 2007-05-16 10:53 Nick Johnson
  2007-05-16 11:46 ` Dan Smith
  0 siblings, 1 reply; 3+ messages in thread
From: Nick Johnson @ 2007-05-16 10:53 UTC (permalink / raw)
  To: dm-devel

Does dm provide any way for a custom target type to redirect a read or
write to a userspace program? Or even for it to notify the program of
the read/write and wait until it gives the goahead, somewhat like the
way page faulting works? I'm wondering if it's possible to create a
target type that implements a 'remote' block device with blocks stored
on something like Amazon S3, keeping only a local cache of mapped
blocks, and fetching / writing blocks as needed.

-Nick Johnson

^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: Sending reads/writes to a userspace program?
  2007-05-16 10:53 Sending reads/writes to a userspace program? Nick Johnson
@ 2007-05-16 11:46 ` Dan Smith
  2008-11-21 15:10   ` Ed Cashin
  0 siblings, 1 reply; 3+ messages in thread
From: Dan Smith @ 2007-05-16 11:46 UTC (permalink / raw)
  To: device-mapper development


[-- Attachment #1.1: Type: text/plain, Size: 1054 bytes --]

NJ> Does dm provide any way for a custom target type to redirect a read or
NJ> write to a userspace program? Or even for it to notify the program of
NJ> the read/write and wait until it gives the goahead, somewhat like the
NJ> way page faulting works? 

I have been working on a userspace target, which allows you to do just
what you describe.  I have an hg tree up with some userspace tools, as
well as an out-of-body version of the kernel module:

  http://static.danplanet.com/hg/dm-userspace.ring/

I also have an actual kernel tree with dm-userspace support, from
which I could generate a patch if the above does not work well for
you.

NJ> I'm wondering if it's possible to create a target type that
NJ> implements a 'remote' block device with blocks stored on something
NJ> like Amazon S3, keeping only a local cache of mapped blocks, and
NJ> fetching / writing blocks as needed.

Yep, I have done similar things with dm-userspace.

-- 
Dan Smith
IBM Linux Technology Center
Open Hypervisor Team
email: danms@us.ibm.com

[-- Attachment #1.2: Type: application/pgp-signature, Size: 188 bytes --]

[-- Attachment #2: Type: text/plain, Size: 0 bytes --]



^ permalink raw reply	[flat|nested] 3+ messages in thread

* Re: Sending reads/writes to a userspace program?
  2007-05-16 11:46 ` Dan Smith
@ 2008-11-21 15:10   ` Ed Cashin
  0 siblings, 0 replies; 3+ messages in thread
From: Ed Cashin @ 2008-11-21 15:10 UTC (permalink / raw)
  To: dm-devel

Dan Smith <danms@us.ibm.com> writes:

> NJ> Does dm provide any way for a custom target type to redirect a read or
> NJ> write to a userspace program? Or even for it to notify the program of
> NJ> the read/write and wait until it gives the goahead, somewhat like the
> NJ> way page faulting works? 
>
> I have been working on a userspace target, which allows you to do just
> what you describe.  I have an hg tree up with some userspace tools, as
> well as an out-of-body version of the kernel module:
>
>   http://static.danplanet.com/hg/dm-userspace.ring/
>
> I also have an actual kernel tree with dm-userspace support, from
> which I could generate a patch if the above does not work well for
> you.
>
> NJ> I'm wondering if it's possible to create a target type that
> NJ> implements a 'remote' block device with blocks stored on something
> NJ> like Amazon S3, keeping only a local cache of mapped blocks, and
> NJ> fetching / writing blocks as needed.
>
> Yep, I have done similar things with dm-userspace.

The dm-userspace target is very interesting to me because it would
allow me to use block devices that were based on arbitrary and
experimental aggregations of local and remote storage coordinated by a
simple userland program.

I see in the archives that there were some attempts to get
dm-userspace into the mainline kernel by way of the development device
mapper code, but I don't think there have been recent attempts to
get dm-userspace merged.

Is there a problem with dm-userspace that is keeping it out of the
mainline?  If not, can it be resubmitted?

-- 
  Ed Cashin <ecashin@coraid.com>

^ permalink raw reply	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2008-11-21 15:10 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-05-16 10:53 Sending reads/writes to a userspace program? Nick Johnson
2007-05-16 11:46 ` Dan Smith
2008-11-21 15:10   ` Ed Cashin

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.