RE: RE: [Opendlm-devel] ODLM/OGFS Recovery

Don, Daniel's explanation matches our own usage of the Tru64 DLM.   Dead
man locks were almost the secondary method of detecting node failure,
since it was more likely to see an invalid lock block on some other
random pending request first.  Dead man locks were useful so we could
always detect failure even in the exception case where there was no
pending lock activity for a resource on the failed node(s), and to
prevent a failed node from immediately bouncing back up until our apps
on the other nodes had performed application recovery on the failed
nodes behalf.

My recollection is that the information re the persistent locks was not
fully replicated.  Compaq had provided a tool to dump their view of the
locks, and I'm 99.44% certain that was the case.  Unfortunately, I no
longer have access to a Tru64 cluster to confirm this.

Jack Devine
[email protected]


-----Original Message-----
From: Zickus II, Don=20
Sent: Thursday, April 29, 2004 8:49 PM
To: Devine, John T
Subject: FW: [ogfs-dev]RE: [Opendlm-devel] ODLM/OGFS Recovery


Does this ring any bells from your tru64 days?

-Don

-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Daniel
McNeil
Sent: Thursday, April 29, 2004 8:38 PM
To: [email protected]
Cc: [email protected]
Subject: RE: [ogfs-dev]RE: [Opendlm-devel] ODLM/OGFS Recovery


On Thu, 2004-04-29 at 09:18, Zickus II, Don wrote:
> Hello Stan,
>=20
> We actually used this function on trucluster.  However, its main use=20
> was _after_ detection of a failed node and even then to revalidate =20
> the lock value blocks and resources assuming you are using lock value=20
> blocks.
> =20
> I have thinking about this whole problem and wondering what everyone's

> definition of 'persistent' lock is?  Is it expected to have every=20
> resource  and its information replicated across the entire cluster or=20
> just have each  node keep track of its own resource locks?
>=20
> -Don
>=20


This is the same question I had many years ago when I first heard about
persistent locking.  As I have said before, a particular implementation
of persistent locking was used to implement a cluster file system.

>From what I remember (It has been more than 4 years since I worked
on this).  As it was explained to me, the whole point of persistent
locks was that the application did not want to keep a bunch of locks
open to be able to find out that some event has occurred which would
require an application recovery before using the lock.  Previously, the
application would keep the locks open and if it got a invalid value
block back, it would know that a recovery is required.  With
"persistent" locks, the application did not have to keep the lock open,
but would still get the invalid value block if process holding the lock
died or a node died.

Re-reading the trucluster man pages I pointed to before (like this one):
http://h30097.www3.hp.com/docs/cluster_doc/cluster_16/MAN/MAN3/0021____.
HTM

This implementation seems much more complicated than what I remember.
This looks like this DLM does keep persistent locks around if they are
invalid after the process closes them (and they get marked invalid if a
node dies).  Thus, a new lock request will see the invalid lock even
when all previous users have gone away.  I'm guessing that is what is
meant by persistent.

The more simple implementation approach I remember (as best as I can --
at least for the node death case anyway -- and it really isn't that
simple).  If a node dies, then all new persistent locks would return
invalid until the dlm_rd_validate() is made.  Also, existing dlm locks
could get marked invalid during dlm recovery.

This implementation was then used to implement CFS.  Recovery went
something like:
	running nomally
	node dies
	DLM recovery runs - non-persistent locks recover
		persistent locks return invalid
	deadman locks from dead node(s) for each file system are granted
	start file system recovery:
		surviving nodes pick one to run log replay
			id =3D dlm_attach()
			replay file system log
			if validate(id) =3D=3D MORE_RECOVERY
				re-start file system recovery
				 since there's been another death
			dlm_validate(id) - persistent locks valid now
		other surviving nodes wait for replay
	file system recovery complete
=09
	if another node dies in the middle of file system recovery
		abort current recovery and start over=20

	=09
This is simpler because persistent locks returned invalid based on
whether a node died until the validate call was made.  Every node in the
cluster did not have to replicated each lock information.

The use of persistent locks prevented surviving nodes from accessing
metadata BEFORE file system log replay had finished.  We used separate
lock domains for each file system, so file system recovery happened in
parallel.
=09

Sorry for rambling, but I think I answered the question in there
somewhere.

Daniel



-------------------------------------------------------
This SF.Net email is sponsored by: Oracle 10g
Get certified on the hottest thing ever to hit the market... Oracle 10g.

Take an Oracle 10g class now, and we'll give you the exam FREE.
http://ads.osdn.com/?ad_id=3D3149&alloc_id=3D8166&op=3Dclick
_______________________________________________
Opendlm-devel mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/opendlm-devel




-------------------------------------------------------
This SF.Net email is sponsored by: Oracle 10g
Get certified on the hottest thing ever to hit the market... Oracle 10g. 
Take an Oracle 10g class now, and we'll give you the exam FREE.
http://ads.osdn.com/?ad_id=3149&alloc_id=8166&op=click