Skip to main content
Pure Technical Services

Pure as-a-Service Catalog

Currently viewing public documentation. Please login to access the full scope of documentation.

Block Storage Service

//Block Service
  Ultra Premium Performance Capacity

 

Highest-performance block storage service for mission-critical, I/O intensive, low-latency workloads. High-performance block storage service for mission-critical low-latency or throughput workloads. Cost-effective general performance block storage service for mission-critical low-latency or throughput workloads Cost-effective capacity-optimized block storage service for Tier2 workloads.
Performance
Latency
sub-ms sub-ms sub-ms 3-5 ms
Min IOPS/TiB*
2000 1000 300 100
Max Read Performance
18GB/Sec 18GB/Sec 18GB/Sec 3.2GB/Sec
Max Write Performance
6GB/Sec 6GB/Sec 6GB/Sec 1.4GB/Sec
Suggested Use Cases
Ideal for workloads that require the highest IOPS/TiB performance and in-memory DBSAP HANA, Oracle, VoltDB, Couchbase. Ideal for a broad range of workloads that require high IOPS/TiB performance, such as database, virtual machines, and SQL.

Ideal for a broad range of Tier1 workloads with no IOPS/TiB requirements, such as databases, virtual machines, SQL, hybrid and multi-cloud, containers, and test/dev.

Tier2 Database and virtual machines, archive stores, test/dev, snapshot consolidation/retention.

* IOPS/TiB: The defines the minimum ratio of Input-Output Operations (IOPS) per every Effective Used TiB of capacity.  This is often referred to as I/O Density.   IOPS/TiB are based on a 70:30 Read / Write mixed workload with an average of 4:1 DRR using a 16K I/O size and a workload concurrency of 60%.  Remote replication may impact front end host performance. All IOPS/TiB numbers provided should be used as reference points for scaling.  

†Max Read and Max Write Performance: These are max bandwidth numbers at 4:1 and assume either 100% reads or 100% writes at 512K block size.

The service offers tremendous burst performance headroom and most customer workloads will be able to drive significantly more performance.  Pure as-a-Service can also support custom performance requirements that are higher than what is quoted in the service catalog.

 

Unified Fast File and Object (UFFO) Service

//UFFO Service
  Ultra Premium

 

UFFO scale-out file and fast object storage service that is designed to deliver ultra-fast read and write. UFFO scale-out file and fast object storage service that is designed to deliver premium fast read and write.
Performance
Max Read Performance
96MB/TiB 43MB/TiB
Max Write Performance
35MB/TiB 15MB/TiB
Suggested Use Cases
Rapid Restore, Artificial Intelligence, Analytics, EDA, HPC, Software development, Code & artifact repository with ultra-high read and write requirements.

Rapid Restore, Artificial Intelligence, Analytics, EDA, HPC, Software development, Code & artifact repository. Custom and COTS (Splunk, Vertica EON) S3 app support Rapid Restore (CommVault, Veeam).


Max Read and Max Write Performance:  Units of measure MB/TiB - The defines the minimum ratio of read or write bandwidth available per every Effective Used TiB. All MB//TiB numbers provided should be used as reference points for scaling. These are conservative minimum bandwidth numbers assuming a DRR of 1.5:1 and a workload of either 100% reads or 100% writes with a 512K block size. The UFFO service is a bandwidth optimized service that provides NFS, SMB, and S3 Protocols.  Remote replication may impact front end host performance.  All performance numbers referenced are using NFSv3. 

The service offers tremendous burst performance headroom and most customer workloads will be able to drive significantly more performance.   Pure as-a-Service can also support custom performance requirements that are higher than what is quoted in the service catalog.