This sounds like expected behavior with 3 storage nodes. In order for a write 
to successfully complete, it must be written to a quorum of storage devices. In 
the case of 3 replicas, the quorum is 2. By writing to two drives, Swift is 
providing some guarantees about the durability and availability of the data. A 
single copy is not durable, so a write to only a single drive will never return 
success to the client.

This means that you need at least 2 drives available in order to write to a 3 
replica policy.

--John




On 13 Feb 2018, at 3:21, aRaviNd wrote:

> Hi All,
>
> We have configured swift with one proxy and three storage nodes. Our setup
> contain two regions and three zones.
>
>
> ‚Äč
> When two nodes goes down we are not able to upload any files but download
> and read is working fine. Is there any requirement for minimum no of
> storage nodes required for write to work?
>
> Aravind M D


> _______________________________________________
> Mailing list: http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack
> Post to     : openstack@lists.openstack.org
> Unsubscribe : http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack

Attachment: signature.asc
Description: OpenPGP digital signature

_______________________________________________
Mailing list: http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack
Post to     : openstack@lists.openstack.org
Unsubscribe : http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack

Reply via email to