All of lore.kernel.org
 help / color / mirror / Atom feed
* How dm multipath handle IO
@ 2014-03-14  8:44 Nicolas Michel
  2014-03-14  9:12 ` Akira Hayakawa
  0 siblings, 1 reply; 3+ messages in thread
From: Nicolas Michel @ 2014-03-14  8:44 UTC (permalink / raw)
  To: device-mapper development


[-- Attachment #1.1: Type: text/plain, Size: 422 bytes --]

Hello Guys,

It's a general question about how dm and particularly multipathd handle IO?
I mean, is it a transaction? Is each IO initiated from the OS get back an
acknowledgement? If it is, is there a retry mechanism?
Or are the IO sent blindingly to the block device?

If someone have some good article on it, I would be very interested in
understanding more deeply how IO are handled.

Thanks a lot,

-- 
Nicolas MICHEL

[-- Attachment #1.2: Type: text/html, Size: 568 bytes --]

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



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

* Re: How dm multipath handle IO
  2014-03-14  8:44 How dm multipath handle IO Nicolas Michel
@ 2014-03-14  9:12 ` Akira Hayakawa
  2014-03-20  6:26   ` Nicolas Michel
  0 siblings, 1 reply; 3+ messages in thread
From: Akira Hayakawa @ 2014-03-14  9:12 UTC (permalink / raw)
  To: dm-devel

Hi,

Let's google it.
Is this the article you are looking for?
https://www.kernel.org/doc/ols/2007/ols2007v2-pages-235-244.pdf

--
Akira

On 3/14/14 5:44 PM, Nicolas Michel wrote:
> Hello Guys,
> 
> It's a general question about how dm and particularly multipathd handle IO? I mean, is it a transaction? Is each IO initiated from the OS get back an acknowledgement? If it is, is there a retry mechanism?
> Or are the IO sent blindingly to the block device?
> 
> If someone have some good article on it, I would be very interested in understanding more deeply how IO are handled.
> 
> Thanks a lot,
> 
> -- 
> Nicolas MICHEL
> 
> 
> --
> dm-devel mailing list
> dm-devel@redhat.com
> https://www.redhat.com/mailman/listinfo/dm-devel
> 

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

* Re: How dm multipath handle IO
  2014-03-14  9:12 ` Akira Hayakawa
@ 2014-03-20  6:26   ` Nicolas Michel
  0 siblings, 0 replies; 3+ messages in thread
From: Nicolas Michel @ 2014-03-20  6:26 UTC (permalink / raw)
  To: device-mapper development


[-- Attachment #1.1: Type: text/plain, Size: 1049 bytes --]

Wonderfull. Thank you. I did google it but never found that doc ;)


2014-03-14 10:12 GMT+01:00 Akira Hayakawa <ruby.wktk@gmail.com>:

> Hi,
>
> Let's google it.
> Is this the article you are looking for?
> https://www.kernel.org/doc/ols/2007/ols2007v2-pages-235-244.pdf
>
> --
> Akira
>
> On 3/14/14 5:44 PM, Nicolas Michel wrote:
> > Hello Guys,
> >
> > It's a general question about how dm and particularly multipathd handle
> IO? I mean, is it a transaction? Is each IO initiated from the OS get back
> an acknowledgement? If it is, is there a retry mechanism?
> > Or are the IO sent blindingly to the block device?
> >
> > If someone have some good article on it, I would be very interested in
> understanding more deeply how IO are handled.
> >
> > Thanks a lot,
> >
> > --
> > Nicolas MICHEL
> >
> >
> > --
> > dm-devel mailing list
> > dm-devel@redhat.com
> > https://www.redhat.com/mailman/listinfo/dm-devel
> >
>
> --
> dm-devel mailing list
> dm-devel@redhat.com
> https://www.redhat.com/mailman/listinfo/dm-devel
>



-- 
Nicolas MICHEL

[-- Attachment #1.2: Type: text/html, Size: 1904 bytes --]

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



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

end of thread, other threads:[~2014-03-20  6:26 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2014-03-14  8:44 How dm multipath handle IO Nicolas Michel
2014-03-14  9:12 ` Akira Hayakawa
2014-03-20  6:26   ` Nicolas Michel

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.