Skip to main content
Pure Technical Services

Evergreen//One Service Catalog

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

Block Storage Service

//Block Service
  Ultra Premium Performance Capacity
Expected Performance *
Latency
sub-ms sub-ms sub-ms 3-5 ms
Bandwidth per TiB

(effective used)

32 MB/s (R/W Throughput) or 2000 IOPS (@16KiB IO) 16 MB/s (R/W Throughput) or 1000 IOPS (@16KiB IO) 8 MB/s (R/W Throughput) or 500 IOPS (@16KiB IO) 1.6 MB/s (R/W Throughput) or 100 IOPS (@16KiB IO)
Max Read Performance

(As high as, per unit)

50 GB/s 50 GB/s 18 GB/s 9 GB/s
Pre-Reduced or Encrypted (PRE) Charge
PRE rates are 2x of the standard rate. PRE rates applies if DRR<2:1 and if Pure has to ship additional capacity due to PRE Refer to EULA and Evergreen//One program description.  PRE rates are 2x of the standard rate. PRE rates applies if DRR<2:1 and if Pure has to ship additional capacity due to PRE Refer to EULA and Evergreen//One program description. PRE rates are 2x of the standard rate. PRE rates applies if DRR<2:1 and if Pure has to ship additional capacity due to PRE Refer to EULA and Evergreen//One program description. N/A
Suggested Use Cases
In Memory DB SAP HANA, Oracle, VoltDB, Couchbase. Ideal for a broad range of //Block performance workloads with ultra IOPS/TiB requirements. Ideal for a broad range of //Block performance workloads with premium IOPS/TiB requirements.

Ideal for a broad range of Tier1 workloads: Cassandra, MongoDB, MariaDB. VDI, Vmware, Oracle, Microsoft SQL Server, SAP, HyperV, Epic. Hybrid and multi cloud, contrainers, media libraries, short term storage, Migrate to cloud, DR to cloud, test/dev.

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


* Based on the the average reads/writes as measured in terms of MB/sper TiB and IOPS/TiB (IOPS = average IO size divided by 16KiBk) of the applicable Reserve Commitment, or the Effective Used for all Evergreen One customers, average and reported over the prior month. The workload characteristics are up to a 50/50 read/write, DRR=4:1, block size=16k, and concurrency=60%. However this is not a run-time metric and actual IOPS/TiB may vary based on the characteristics of the workload. Pure only evaluates underlying equipment based on the assumed workload characteristics. The performance can be achieved when used with block workloads only. Quote numbers assume FC (or NVME-OF) "DMA" Direct Memory Addressing performance from the host. iSCSI numbers will be lower.  

The service offers tremendous burst performance headroom and most customer workloads will be able to drive significantly more performance.  Evergreen//One 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 Performance
Description
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. UFFO scale-out file and fast object storage service that is designed to deliver consistent read and write.
Performance
 
Max Blended Performance / TiB
130 MB/s  (R/W Throughput) 50 MB/s (R/W Throughput) 20 MB/s (R/W Throughput)
Pre-Reduced or Encrypted (PRE) Charge
N/A N/A N/A
Suggested Use Cases
Artificial Intelligence, High-speed Analytics, EDA, HPC, Software development, Code & artifact repository, High Performance S3, Rapid Restore (CommVault, Veeam) Analytics, Software development, Code & artifact repository. Custom and COTS (Splunk, Vertica EON) S3 app support Rapid Restore (CommVault, Veeam) Rapid Restore (CommVault, Veeam), Software development, Code & Artifact repository

**70/30 read/write @ 512KB 

NOTE: UFFO Subscriptions initiated prior to June 8th, 2022, delivered on the 15-blade chassis system will continue to be measured and deliver the performance agreements under which they were entered.  UFFO Ultra: 96 MB/s per TiB for reads and 35 MB/s per TiB for writes.  UFFO Premium: 43 MB/s per TiB for reads and 15 MB/s per TiB for writes


 

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