Method for detection of soft media errors for hard drive
First Claim
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).
14 Assignments
0 Petitions
Accused Products
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.
-
Citations
18 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). - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
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). - View Dependent Claims (11, 12, 13, 14, 15)
-
-
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). - View Dependent Claims (17, 18)
-
Specification