I'm talking subsystem NQN. Host NQN should not be relevant. Per default Host
NQN of the clients is generated randomly (you can set it via the
configuration file).
On Wed, 26 Jun 2019 16:22:18 +
David Crespi wrote:
We’re talking host nqn right, not subsystem nqn?
David
714-476-2692
We’re talking host nqn right, not subsystem nqn?
David
714-476-2692
> On Jun 26, 2019, at 09:17, Jonas Pfefferle wrote:
>
> There can only be 1 NQN in the whole system. For multiple storage classes
> just use different ip/port combinations with the same NQN. e.g. start a NVMf
> server on
There can only be 1 NQN in the whole system. For multiple storage classes
just use different ip/port combinations with the same NQN. e.g. start a NVMf
server on node 1 with storage class 1 with NQN X and start a server on node
2 with storage class 2 with NQN X. You can start another server on
Sorry Jonas but I’m still confused.
I started off doing this by having each storage class 1 connected to it’s own
subsystem,
with a single namespace. This is where I was seeing the correct IP address of
that subsystem,
but the wrong controller name. It was the controller name of the storage
Yep. I wanted to use crail-store for temp results storage, storage class 2,
AND the shuffle data, with
storage class 1.
Regards,
David
From: Jonas Pfefferle
Sent: Wednesday, June 26, 2019 7:51:43 AM
To: dev@crail.apache.org; David Crespi
I’m a bit confused now. If it only ever handles 1 namespace, then multiple
datanodes are useless.
Or are you saying only 1 namespace for type-1? If you’re not saying only one
for type-1, how do you
mix types if limited to 1 namespace?
Regards,
David
I forgot to add: Namespace has to be 1 for the moment. This is a limitation
in how the namenode handles storage tier metadata (essentially it only
stores ip/port). You can set it on the server side however it will not be
respected by the client, i.e. the client will always use namespace id 1.