Previous page

Next page

Locate page in Contents

Print this page

Recommended Configuration

The table below lists two of the recommended configurations for deploying Parallels Cloud Storage clusters.

Metadata Server

Chunk Server

Total Number of Servers

3
(can be shared with chunk servers and clients)

5-9
(can be shared with metadata servers and clients)

5 or more
(depending on the number of clients and chunk servers and whether they share roles)

5
(can be shared with chunk servers and clients)

10 or more
(can be shared with metadata servers and clients)

5 or more
(depending on the number of clients and chunk servers and whether they share roles)

Clients

1 or more

You can include any number of clients in the cluster. For example, if you have 5 servers with Parallels Cloud Server, you can configure them all to act as clients.

You can share servers acting as clients with chunk and metadata servers. For example, you can have 5 physical servers and configure each of them to simultaneously act as an MDS server, a chunk server, and a client.

Even though new clusters are configured to have 1 replica for each data chunk by default, you need to configure each data chunk to have at least 3 replicas to provide high availability for your data.

In total, at least 9 machines running Parallels Cloud Storage are recommended per cluster. Smaller clusters will work as fine but will not provide the significant performance advantages over direct-attached storage (DAS) or improved recovery times.

Notes:

1. For large clusters, it is critically important to configure proper failure domains to improve data availability. For more information, see Configuring Failure Domains .

2. In small and medium clusters, MDS servers consume little resources and do not require being set up on dedicated Hardware Nodes.

3. A small cluster is 3 to 5 machines, a medium cluster is 6 to 15-20 machines, and a large cluster is 15-20 machines and more.

4. Time should be synchronized on all servers in the cluster via NTP. Doing so will make it easier for the support department to understand cluster logs (migrations, failovers, etc.). For more details, see http://kb.sp.parallels.com/en/3197 .

Top of page Feedback