Method for detection of soft media errors for hard drive

• US 9,552,247 B2
• Filed: 11/05/2014
• Issued: 01/24/2017
• Est. Priority Date: 11/05/2014
• Status: Active Grant

• Current Assignee: Dell Products LP (Dell Technologies Inc.)
• Original Assignee: Dell Products LP (Dell Technologies Inc.)
• Inventors: Jacoby, Robert B., Nguyen, Giang L.
• Primary Examiner(s): LAMARRE, GUY J
• Application Number:
  US14/533,306
• Publication Number:
  US 20160124788A1
• Time in Patent Office: 811 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 11/0727 in a storage system, e.g. in a DASD or network based storage system drivers for digital recording or reproducing units G06F3/06; circuits for error detection or correction within digital recording or reproducing units G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097
• CPC Class Codes: G06F 11/0757 by exceeding a time limit, i.e. time-out, e.g. watchdogs
• CPC Class Codes: G06F 11/0772 Means for error signaling, e.g. using interrupts, exception flags, dedicated error registers
• CPC Class Codes: G06F 11/3034 where the computing system component is a storage system, e.g. DASD based or network based digital input from or digital output to record carriers G06F3/06; digital recording or reproducing G11B20/18; for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS], H04L67/1097
• CPC Class Codes: G06F 11/3419 by assessing time
• CPC Class Codes: G06F 2201/81 Threshold

Abstract

Some embodiments are directed to a method, corresponding system, and corresponding apparatus for detecting unexpectedly high latency, due to excessive retries of a given storage device of a set of storage devices. Some embodiments may comprise a processor and associated memory. Some embodiments may monitor one or more completion time characteristics of one or more accesses between the given storage device and one or more host machines. Some embodiments may then compare the one or more completion time characteristics with a given threshold. As a result of the comparison, some embodiments may report, by the one or more host machines, at least one error associated with the given storage device. The error may be unreported by the set of storage devices.

Claims

1. A computer-implemented method for detecting unexpectedly high latency due to excessive retries, the computer-implemented method comprising, by a processor and associated memory:

monitoring, by one or more host machines external to a storage area network (SAN), one or more completion time characteristics of one or more accesses between a given storage device of a set of storage devices of the storage area network (SAN) and the one or more host machines, the one or more accesses including one or more retries, the one or more completion time characteristics including at least one of;

write latency and read latency;

comparing, by the one or more host machines, the one or more completion time characteristics with a given threshold; and

as a result of the comparison, detecting and reporting, by the one or more host machines, at least one soft error associated with the given storage device, prior to detection of or reporting of the soft error by the storage area network (SAN).

2. The computer-implemented method of claim 1, wherein the given threshold includes at least one of:

a time period, a number of accesses between the given storage device and the one or more host machines, and a numerical value.

3. The computer-implemented method of claim 1, wherein the one or more completion time characteristics is associated with a given sample time period.

4. The computer-implemented method of claim 1, wherein the one or more completion time characteristics include a ratio of queue drain time between the given storage device and at least one other storage device of the set of storage devices and zero or more of the following, associated with the one or more accesses:

peak latency for the set of storage devices;

peak latency for the given storage device; and

average latency for the given storage device.

5. The computer-implemented method of claim 4, wherein the ratio is at least one hundred to one, the given storage device has a highest queue drain time of the set of storage devices, and the at least one other storage device has a second highest queue drain time of the set of storage devices.

6. The computer-implemented method of claim 1, wherein the soft error includes at least one of the following:

soft media error, high latency error, excessive retry error, multiple retry error, and low amplitude write error.

7. The computer-implemented method of claim 1, wherein the one or more completion time characteristics include peak latency for the set of storage devices and zero or more of the following, associated with the one or more accesses:

peak latency for the given storage device;

average latency for the given storage device; and

ratio of queue drain time between the given storage device and at least one other storage device of the set of storage devices.

8. The computer-implemented method of claim 1, wherein the one or more completion time characteristics include peak latency for the given storage device and zero or more of the following, associated with the one or more accesses:

peak latency for the set of storage devices;

average latency for the given storage device; and

ratio of queue drain time between the given storage device and at least one other storage device of the set of storage devices.

9. The computer-implemented method of claim 1, wherein the one or more completion time characteristics include average latency for the given storage device and zero or more of the following, associated with the one or more accesses:

peak latency for the set of storage devices;

peak latency for the given storage device; and

ratio of queue drain time between the given storage device and at least one other storage device of the set of storage devices.

10. An information handling system (IHS) comprising:

a computing module configured to monitor, by one or more host machines external to a storage area network (SAN), one or more completion time characteristics of one or more accesses between a given storage device of a set of storage devices of the storage area network (SAN) and the one or more host machines, the one or more accesses including one or more retries, the one or more completion time characteristics including at least one of;

write latency and read latency;

the computing module further configured to compare, by the one or more host machines, the one or more completion time characteristics with a given threshold; and

a reporting module, configured to detect and report by the one or more host machines, as a result of the comparison, at least one soft error associated with the given storage device, prior to detection of or reporting of the soft error by the storage area network (SAN).

11. The IHS of claim 10, wherein the given threshold includes at least one of:

a time period, a number of accesses between the given storage device and the one or more host machines, and a numerical value.

12. The IHS of claim 10, wherein the one or more completion time characteristics is associated with a given sample time period.

13. The IHS of claim 10, wherein the one or more completion time characteristics include a ratio of queue drain time between the given storage device and at least one other storage device of the set of storage devices and zero or more of the following, associated with the one or more accesses:

peak latency for the set of storage devices;

peak latency for the given storage device; and

average latency for the given storage device.

14. The IHS of claim 13, wherein the ratio is at least one hundred to one, the given storage device has a highest queue drain time of the set of storage devices, and the at least one other storage device has a second highest queue drain time of the set of storage devices.

15. The IHS of claim 10, wherein the soft error includes at least one of the following:

soft media error, high latency error, excessive retry error, multiple retry error, and low amplitude write error.

16. A non-transitory computer readable medium having stored thereon a sequence of instructions which, when loaded and executed by a processor coupled to an apparatus, causes the apparatus to:

monitor, by one or more host machines external to a storage area network (SAN), one or more completion time characteristics of one or more accesses between a given storage device of a set of storage devices of the storage area network (SAN) and the one or more host machines, the one or more accesses including one or more retries, the one or more completion time characteristics including at least one of;

write latency and read latency;

compare, by the one or more host machines, the one or more completion time characteristics with a given threshold; and

detect and report by the one or more host machines, as a result of the comparison, at least one soft error associated with the given storage device, prior to detection of or reporting of the soft error by the storage area network (SAN).

17. The non-transitory computer readable medium of claim 16, wherein the given threshold includes at least one of:

a time period, a number of accesses between the given storage device and the one or more host machines, and a numerical value.

18. The non-transitory computer readable medium of claim 16, wherein the one or more completion time characteristics include a ratio of queue drain time between the given storage device and at least one other storage device of the set of storage devices and zero or more of the following, associated with the one or more accesses:

peak latency for the set of storage devices;

peak latency for the given storage device; and

average latency for the given storage device.