Reliability Specifications
Oracle 6.4 TB NVMe SSD reliability specifications are listed in the following table.
|
|
Uncorrectable Bit Error Rate (UBER)
|
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.
< 1 sector per 1017 bits read
|
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).
|
Data Retention
|
The time period for retaining data in the NAND at maximum
rated endurance. Three months power-off retention once storage
drive reaches rated write endurance at 40°C.
|
Endurance Rating
|
-
Up to
34.61
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.
|
Temperature Sensor
|
Internal temperature sensor with an accuracy of +/- 2°C over
a range of -10°C to +85°C, which can be monitored using NVMe
Health Log.
The sensor has an accuracy of +/- 3°C over a range of -20°C
to 125°C. SMBUS temperature sensor is not reported in NVMe
Health Log.
Drive provides out-of-band access to temperature by means of
SMBUS.
|
Out-of-Band Management (SMBUS)
|
Provides out-of-band management by means of SMBUS interface.
This requires 3.3V auxiliary voltage.
SMBUS access includes the VPD page and temperature sensor.
|
Hot-Plug Support
|
Supports PCIe presence detect and link-up detect.
Device advanced power loss protection provides robust data
integrity. During IOs, the storage drive integrated monitoring
enables the integrity of already committed data on the media and
commits acknowledged writes to the media.
|
|
Related Information