Scality Ecosystem & Application Partners
Scality and Cloudera.
Scality RING as the object back end for the Cloudera Data Platform. The Cloudera engines — Iceberg, Spark, Hive, Trino and Impala — query the same S3 namespace, with capacity scaling on the storage side.
the problem
Cloudera on Scality RING, using the standard S3 path.
Scality RING is the S3 back end behind Cloudera. The Hadoop ecosystem already speaks S3, so Iceberg, Spark, Hive, Trino and Impala read and write the same RING buckets. Erasure coding replaces HDFS triple replication.
- RING is the S3 back end for the Cloudera engines.
- Standard S3 path, already in the Cloudera distribution (Hadoop S3A).
- Iceberg, Spark, Hive, Trino and Impala share the same buckets.
- Erasure coding replaces HDFS triple replication.
the joint solution
F5 in front of Scality, validated for AI data delivery.
F5's Application Delivery and Security Platform handles S3 traffic at scale. Scality RING is the storage layer; ADI frames the AI data path that BIG-IP delivers traffic to. Security, traffic management and application delivery applied at the gateway, before the storage layer.
- Validated joint architecture.
- F5 BIG-IP in front of Scality RING.
- Scality ADI as the AI data layer behind the gateway.
- Security applied at the data path, not bolted on.
joint solution benefits
What the joint analytics stack delivers.
Compute and storage move independently.
Add Cloudera nodes for query performance. Add Scality nodes for capacity. Neither side waits for the other.
One copy across all engines.
Iceberg, Spark, Hive, Trino and Impala query the same RING buckets. No per-engine copies of the data.
No HDFS rebalancing windows.
Capacity grows without pausing the cluster. The analytics team stops scheduling around storage operations.
Hot, warm and cold on one platform.
Recent queries, working tables and long retention all sit on the same Scality cluster. Trino federates across them.
Joint architecture
How Cloudera runs on Scality.
Workloads flow through the partner integration and land on the Scality data layer.
Show us the workflow. We will show you the fit.
