Go to main content

Oracle® 6.4 TB NVMe SSD v2 User Guide

Exit Print View

Updated: July 2019
 
 

Drive Capacity and Performance

Oracle 6.4 TB NVMe SSD v2 capacity, performance, and reliability specifications are listed in the following table.

Specification
Value
Capacity
  • Usable capacity 6.4 TB

  • Unformatted capacity (total user addressable sectors in LBA mode) 12,502,446,768

Performance

Performance values vary by capacity and form factor.

Performance specifications apply to both compressible and incompressible data.

Consistently high IOPS and throughput
  • Sequential read speeds of up to 3.2 GB/s IOPS for 128KB Block Size, QD (Queue Depth) 256

  • Sequential write speeds of up to 3.0 GB/s IOPS for 128KB Block Size, QD256

  • Random read speeds of up to 694,000 Bytes/Sec IOPS for 4KB Block Size, QD256

  • Random write speeds of up to 274,000 Bytes/Sec IOPS for 4KB Block Size, QD256

Latency
  • Sequential Latency (typical) Read/Write: 7/9 μseconds

  • Random Latency (typical) Read/Write: 79/34 μseconds

  • Power On to Ready Latency (typical): 2 seconds

  • Less than 18 μsec for sequential access to the SSD.

Uncorrectable Bit Error Rate (UBER)
< 1 sector per 1017 bits read

Uncorrectable bit error rate will not exceed one sector in the specified number of bits read. In the unlikely event of a non-recoverable read error, the storage drive will report it as a read failure to the host; the sector in error is considered corrupt and is not returned to the host.

Data Retention
Three months power-off retention once storage drive reaches rated write endurance at 40°C. The time period for retaining data in the NAND at maximum rated endurance.
Endurance Rating
  • Up to 34.7 PBW (petabytes written)

    Endurance rating verification is defined to establish UBER <1E-16 at 60% upper confidence limit.

  • 2.92 Drive Writes/day (JESD219 workload)

    The number of drive writes is such that the storage drive meets the requirements according to the JESD219 standard.

Mean Time Between Failures (MTBF)
2 million hours.

Mean Time Between Failures is estimated based on Telcordia methodology and demonstrated through Reliability Demonstration Test (RDT).

Related Information