Predicting solid state drive reliability

Patent metadata

Field	Value
Publication number	US-10078455-B2
Application number	US-201615002216-A
Country	US
Kind code	B2
Filing date	Jan 20, 2016
Priority date	Jan 20, 2016
Publication date	Sep 18, 2018
Grant date	Sep 18, 2018

Abstract

Aspects extend to methods, systems, and computer program products for predicting solid state drive reliability. Aspects of the invention can be used to predict and/or to configure a data center to minimize one or more of: SSD capacity degradation (how much storage an SSD has left), SSD performance degradation (reduced read/write latency/throughput), and SSD failure. Models and data center considerations can be based on device level SSD related operations, such as, for example, read, write, erase. Operations decisions can be made for a data center based on SSD specific features, such as, for example, remaining capacity, write amplification factor, etc. Dependence and/or causality of various different data center factors can be leveraged. The impact of the various data center factors on different SSD failure modes and capacity/performance degradation can be quantified to drive SSD design, SSD provisioning, and SSD operations.

First claim

What is claimed:

1. A method comprising:
receiving a Solid State Drive (SSD) configuration indicating the configuration of one or more Solid State Drives (SSDs) within a data center;
observing a plurality of factors related to Solid State Drive (SSD) functionality in another data center;
deriving a relationship between each of a plurality of observed factors and the Solid State Drive (SSD) configuration, each relationship quantifying a causal impact on Solid State Drive (SSD) reliability;
inferring existence of at least one unobserved latent variable related to Solid State Drive (SSD) functionality based on the observed plurality of factors;
deriving an additional relationship between the unobserved latent variable and the Solid State Drive (SSD) configuration quantifying an additional causal impact on Solid State Drive (SSD) reliability;
determining a Solid State Drive (SSD) optimization based on the Solid State Drive (SSD) configuration, data center factors for the data center, the derived relationships, and the derived additional relationship; and
applying the optimization to the one or more Solid State Drives (SSDs) to optimize Solid State Drive (SSD) reliability at the data center.

2. The method of claim 1 , wherein receiving a Solid State Drive (SSD) configuration comprises receiving a hypothetical Solid State Drive (SSD) configuration for a data center.

3. The method of claim 1 , wherein deriving a relationship between each of a plurality of observed factors and Solid State Drive (SSD) configuration comprises deriving a relationship between two or more of: a multi-factor Solid State Drive (SSD) dependency model, a multi-factor Solid State Drive (SSD) design support model, a multi-factor Solid State Drive (SSD) provisioning support model, and a multi-factor Solid State Drive (SSD) operational support model, and Solid State Drive (SSD) functionality.

4. The method of claim 1 , wherein deriving a relationship between each of a plurality of observed factors and Solid State Drive (SSD) configuration comprises deriving a relationship between two or more of: Solid State Drive (SSD) failure symptoms, Solid State Drive (SSD) capacity degradation, Solid State Drive (SSD) performance degradation, and Solid State Drive (SSD) failure, and Solid State Drive (SSD) functionality.

5. The method of claim 1 , wherein deriving a relationship between each of a plurality of observed factors and Solid State Drive (SSD) configuration comprises deriving a relationship between two or more of: facility features of a physical facility for the data center, hardware features of hardware that is to interoperate with the one or more Solid State Drives (SSDs) within the data center, device features for the one or more Solid State Drives (SSDs), workload features of workloads using the one or more Solid State Drives (SSDs), environmental features of the environment within the data center, and policy features of management policies associated with the data center, and Solid State Drives (SSD) functionality.

6. The method of claim 1 , wherein determining a Solid State Drive (SSD) optimization comprises predicting one or more of: a probability of Solid State Drive (SSD) failure, a probability of Solid State Drive (SSD) capacity degradation, and a probability of Solid State Drive (SSD) performance degradation for the one or more Solid State Drives (SSDs) over a specified period of time operating within the data center.

7. The method of claim 1 , wherein determining a Solid State Drive (SSD) optimization comprises determining an optimization for one or more of: a design decision for the one or more Solid State Drives (SSDs), a provisioning decision for the one or more Solid State Drives (SSDs), and an operational decision for the one or more Solid State Drives (SSDs).

8. The method of claim 1 , wherein determining a Solid State Drive (SSD) optimization comprises determining an optimization for one or more of: lifetime for the one or more Solid State Drives (SSDs), reliability for the one or more Solid State Drives (SSDs), capacity degradation rate for the one or more Solid State Drives (SSDs), and operating performance for the one or more Solid State Drives (SSDs).

9. A system, the system comprising:
one or more hardware processors;
system memory coupled to the one or more hardware processors, the system memory storing instructions that are executable by the one or more processors;
the one or more processors executing the instructions stored in the system memory to perform the following:
receive a Solid State Drive (SSD) configuration indicating the configuration of one or more Solid State Drives (SSDs) within a data center;
observe a plurality of factors related to Solid State Drive (SSD) functionality in another data center;
derive a relationship between each of a plurality of observed factors and the Solid State Drive (SSD) configuration, each relationship quantifying a causal impact on Solid State Drive (SSD) reliability;
infer existence of at least one unobserved latent variable related to Solid State Drive (SSD) functionality based on the observed plurality of factors;
derive an additional relationship between the unobserved latent variable and the Solid State Drive (SSD) configuration quantifying an additional causal impact on Solid State Drive (SSD) reliability;
determine a Solid State Drive (SSD) optimization based on the Solid State Drive (SSD) configuration, data center factors for the data center, the derived relationships, and the derived additional relationship; and
apply the optimization to the one or more Solid State Drives (SSDs) to optimize Solid State Drive (SSD) reliability at the data center.

10. The system of claim 9 , wherein the one or more processors executing the instructions stored in the system memory to receive a Solid State Drive (SSD) configuration comprises the one or more processors executing the instructions stored in the system memory to receive a hypothetical Solid State Drive (SSD) configuration.

11. The system of claim 9 , wherein the one or more processors executing the instructions stored in the system memory to derive a relationship between each of a plurality of observed factors and Solid State Drive (SSD) configuration comprises the one or more processors executing the instructions stored in the system memory to derive a relationship between two or more of: a multi-factor Solid State Drive (SSD) dependency model, a multi-factor Solid State Drive (SSD) design support model, a multi-factor Solid State Drive (SSD) provisioning support model, and a multi-factor Solid State Drive (SSD) operational support model, and Solid State Drive (SSD) functionality.

12. The system of claim 9 , wherein the one or more processors executing the instructions stored in the system memory to derive a relationship between each of a plurality of observed factors and Solid State Drive (SSD) configuration comprises the one or more processors executing the instructions stored in the system memory to derive a relationship between two or more of: Solid State Drive (SSD) failure symptoms, Solid State Drive (SSD) capacity degradation, Solid State Drive (SSD) performance degradation, and Solid State Drive (SSD) failure, and Solid State Drive (SSD) functionality.

13. The system of claim 9 , wherein the one or more processors executing the instructions stored in the system memory to derive a relationship between each of a plurality of observed factors and Solid State Drive (SSD) configuration comprises the one or more processors executing the instructions stored in the system memory to derive a relationship between two or more of: facility features of a physical facility for t

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Narayanan Iyswarya
• Wang Di
• Jeon Myeongjae
• Sharma Bikash
• Caulfield Laura Marie
• Govindan Sriram
• Cutler Benjamin Franklin
• Hoder Christopher W
• Bobba Jaya Naga Satish
• Liu Jie
• Khessib Badriddine

Classifications

• G06F3/0616

  in relation to life time, e.g. increasing Mean Time Between Failures [MTBF] · CPC title

• G06F3/0614 Primary

  Improving the reliability of storage systems · CPC title

• G06F3/0605 Primary

  by facilitating the interaction with a user or administrator · CPC title

• G06F3/067

  Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS] · CPC title

• G06F3/0679

  Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP] · CPC title