US20050268161A1 - Storage-device activation control for a high-availability storage system - Google Patents
Storage-device activation control for a high-availability storage system Download PDFInfo
- Publication number
- US20050268161A1 US20050268161A1 US11/173,453 US17345305A US2005268161A1 US 20050268161 A1 US20050268161 A1 US 20050268161A1 US 17345305 A US17345305 A US 17345305A US 2005268161 A1 US2005268161 A1 US 2005268161A1
- Authority
- US
- United States
- Prior art keywords
- storage
- data
- drives
- disk
- drive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/2053—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where persistent mass storage functionality or persistent mass storage control functionality is redundant
- G06F11/2094—Redundant storage or storage space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/008—Reliability or availability analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/1658—Data re-synchronization of a redundant component, or initial sync of replacement, additional or spare unit
- G06F11/1662—Data re-synchronization of a redundant component, or initial sync of replacement, additional or spare unit the resynchronized component or unit being a persistent storage device
Definitions
- This invention relates to improved techniques for controlling and/or monitoring storage devices in a high-availability storage system.
- Some computer systems are dedicated storage systems. These storage systems typically include one or more arrays of rotating magnetic disks for secondary, non-volatile storage of data.
- a storage system may include an enclosure, power supply, cooling fans, and disk array controller(s).
- JBOD Just a Bunch Of Disks
- a JBOD is an array of disk drives that are specially designed to improve control, performance, and fault tolerance of such a disk-array storage system.
- FIG. 1 shows an example of a conventional computer network 10 having a central computer 20 for controlling the system and for central processing.
- a central computer i.e., server
- the central computer 20 controls and monitors multiple storage systems, such as storage system 30 , storage system 32 , and storage system 34 .
- FIG. 2 shows a block diagram of the basic components of a typical storage system, in particular, storage system 30 . It includes an input/output (I/O) unit 52 for sending/receiving data and control information to/from the central computer 20 , other storage systems, and other network devices.
- I/O input/output
- a disk array controller 54 is coupled to the I/O unit 52 and to a disk array 60 .
- One or more data and control lines connect the disk array controller 54 to the disk array 60 .
- a storage system may include multiple controllers and multiple disk arrays.
- all disk drives in an array are powered by a power supply.
- the supply of power to the drive is not controllable or selectable.
- RAID Redundant Array of Independent (or Inexpensive) Disks
- RAID was designed as a means for improving storage subsystem capacity.
- MTBF mean time before failure
- RAID schemes are classified into five basic levels (although other levels may exist):
- the fault-tolerant redundant arrays have an additional disk in the array. This is the “check” disk.
- This disk acts as the replacement disk when one disk in the array fails. The data on a failed disk are conventionally reconstructed; then the reconstructed data are written onto the replacement disk. This places the replacement disk in exactly the same state as the failed disk.
- MTBF is short for “mean time between failures” or “mean time before failure.” Typically, MTBF ratings are measured in hours and indicate the sturdiness of hard disk drives, printers, and virtually any other component.
- Typical inexpensive disk drives for personal computers have MTBF ratings of about 300,000 hours. This means that of all the drives tested, one failure occurred every 300,000 hours of testing. However, this measure is only a statistical model based upon test drives and estimated operation time of failed drives returned to the factory.
- the theoretical MTBF of a disk drive represents the steady state failure rate of a large population of drives in volume manufacture. This is the expected time after the initial burn-in phase that it will take a hardware component to fail due to normal wear and tear.
- Theoretical MTBF of a computer decreases in proportion to the number of components that make up the computer. Therefore, larger configurations containing many disk drives, by definition, have a lower overall MTBF.
- the overall MTBF of a disk drive subsystem is in direct proportion to the number of disks in the array.
- a 10-drive configuration MTBF is one-tenth the MTBF of a single drive, or 30,000 hours, and a 100-drive configuration is reduced to 3,000 hours.
- Some large systems include 1000-drive (or more) storage configurations, which are likely to require that a failed drive be replaced every one to two weeks (on average).
- the MTBF is intended to give a statistical model of the failure times of a large population of drives.
- the MTBF is not a good measure for the actual time before a given drive fails.
- One reason is the collection of disk drives used by an installation is not always representative of a large random sample (as assumed by the statistical model).
- Another reason that MTBF is not a good measure for the actual time before a given drive fails is a lack of empirical data of about drives in actual service.
- an array of drives in an installation may have a higher risk for drive failure than is represented by a theoretical MTBF calculation. Furthermore, these sequential drives are more likely to fail at approximately the same time because their inherent flaws are similar.
- the basis of the MTBF calculation for a disk drive is the measured failure rate in a testing facility. Often the calculation is based upon failure data of similar components in previous models. This facility may be part of the manufacturing process, such as a “burn-in” step. It may also be independent of the manufacturing process, such a dedicated testing laboratory. Both options only estimate how the drive is actually used in the field.
- Drive manufacturers typically guess at the actual operating life of a drive model by knowing how many drive models were sold, knowing how many were returned after they failed, and comparing the manufacture date to the returned date. This is only a guess. This does not accurately measure the actual life and use of a drive.
- Typical high-availability storage systems include a fault-tolerant redundant array of storage devices, such as disk drives. Such systems are designed to withstand the failure of X number drives without a loss of data. When a drive fails, the data is reconstructed from the redundancy information on the remaining drives. After X number of drives have failed but before a conventional manual replacement of such failed drives, the data is highly vulnerable to loss if another drive fails.
- An example of the storage-device activation control described herein is implemented with one or more inactive (un-powered) drives physically installed in the storage system, but not part of the present fault-tolerant redundant array of disk drives.
- one of the inactive drives is activated (powered-on) and it replaces the failed disk and becomes part of the present array. With the newly activated disk included, the data is reconstructed and the original fault-tolerance level is restored. Since a new disk quickly and automatically (without human intervention) replaces the failed disk in the array, the risk of data loss (based upon another drive failing before the first failure is remedied) is greatly reduced.
- the storage-device activation control described herein is implemented so that it tracks the actual in-service time of the storage devices (such as disk drives).
- Field-derived, empirical statistical data about actual in-service time of storage devices is collected and transmitted to a central data collection system. Using this actual data as a basis, a much more accurate MTBF may be calculated than the MTBF conventionally calculated.
- FIG. 1 illustrates, at a high-level, a conventional computer network that includes multiple storage systems.
- FIG. 2 is a block diagram of the basic components of a conventional storage system.
- FIG. 3 is a block diagram of the basic components of a storage system implementing storage-device activation control for a high-availability storage system.
- FIG. 4 is a flow diagram of a methodological implementation of a storage-device activation control for a high-availability storage system.
- FIG. 5 illustrates, at a high-level, a computer network with a storage system implementing storage-device activation control for a high-availability storage system and a data collection system for receiving empirical data sent by such storage system.
- FIG. 6 is a flow diagram of another methodological implementation of storage-device activation control for a high-availability storage system.
- each exemplary storage-device activation control is described herein in the context of “disk drives.” Those of ordinary skill in the art understand and appreciate that each exemplary storage-device activation control may be implemented with any variety of secondary, non-volatile storage devices. Therefore, references herein to disk drives are applicable to any similar secondary, non-volatile storage devices.
- Examples of an “activation status” of a storage device may be either active (powered on) or inactive (powered off).
- the “field-derived, empirical statistical data about the actual in-service time of a storage device” is described herein. By way of example, this refers to data about the actual in-service time of a storage device (such as a disk drive) that is measured in the field. This terminology distinguishes itself from data derived in a testing facility because such data is not field-derived and is not related to actual in-service time. This terminology also distinguishes itself from data derived from statistical models for similar reasons.
- FIG. 3 shows a block diagram of the basic components of an exemplary storage system 100 that implements the exemplary storage-device activation control.
- the storage system 100 includes a disk array controller 112 coupled to a disk array 120 .
- the disk array controller may be composed of several basic computer components, such as an input/output (I/O) unit, bus adapters, etc.
- the I/O unit is for sending/receiving data and control information to/from other network devices.
- One or more data and control lines (such as line 130 in FIG. 3 ) connect the disk array controller 112 to the disk array 120 .
- the disk array 120 includes a set of disk drives 120 a - j.
- a storage system implementing a storage-device activation control may include multiple controllers and multiple JBODs.
- a storage system implementing a storage-device activation control typically have other conventional computer components, such as a CPU, system memory, one or more buses, other I/O systems, communications, and the like.
- the storage system 100 in FIG. 3 includes a power supply 116 , which supplies power to the drives 120 a - j via power and control lines 142 .
- the power and control lines 142 are shown separate from data and control line(s) 130 , but such lines may be within the same conduit and perhaps share the same wiring where appropriate.
- the disk array controller 112 is operatively coupled to power switch control (PSC) 114 , which may also be called the power-switch controller. With direction from the disk array controller 112 , the PSC 114 selectively controls the activation and deactivation of specific drives 120 a - j of the disk array 120 via the operatively coupled power and control lines 142 . Each drive of drives 120 a - j has an associated power activation switch 140 a - j , which switchably couples each drive to the power supply 116 .
- PSC power switch control
- Switches 140 a - j may be any electronically controllable switches.
- the switches are a solid-state electronic component (such as a FET). Such switches may be part of a drive's internal circuitry or they may be external to the drive.
- the disk drives 120 a - j in the disk array 120 are selectively powered on (“activated”) or off (“deactivated”) by the PSC 114 under direction from the disk array controller 112 .
- Switches 140 a , 140 b , 140 c , 140 e , 140 g , and 140 i are closed and thus allowing power to flow to their associated drives ( 120 a , 120 b , 120 c , 120 e , 120 g , and 120 i ). Therefore, these drives are active. Since these drives are active, their lifespan is decreasing each second and they will eventually fail. Their MTBF is an estimate of that lifespan, but the actual lifespan of each drive is unknown.
- these six drives ( 120 a , 120 b , 120 c , 120 e , 120 g , and 120 i ) form an active RAID of 5+1 (which is five disks of data and one disk of redundancy parity data). Electricity is flowing through its circuitry and its parts are moving. Its lifespan is decreasing.
- Switches 140 d , 140 f , 140 h , and 140 i are open and thus no power is flowing to their associated drives ( 120 d, 120 f , 120 h , and 120 i ). Therefore, these drives are inactive. No electricity is flowing through the circuitry of these drives. No parts are moving in these drives. Since these drives are inactive, their lifespan is unchanged and unaffected.
- the disk array controller 112 instructs the PSC 114 to activate one of the inactive drives (such drive 120 h ).
- the newly activated drive 120 h replaces just-failed drive 120 c within the RAID of 5+1 disks. Therefore, a minimum amount of time is spent with a danger of data loss before the failed drive is replaced in the RAID with a new active drive.
- FIG. 4 shows a methodological implementation of an exemplary storage-device activation control performed by a storage system (or a portion thereof), such as storage system 100 of FIG. 3 .
- This methodological implementation may be performed in software, hardware, or a combination thereof.
- the disk array controller 112 receives an indication of a drive failure and an identification of which drive that failed.
- the drive is a member of a fault-tolerant redundancy array of drives.
- the disk array controller 112 activates one of a set of inactive drives. For example, it may direct the PSC 114 to activate drive 120 h. The PSC does this by switching the drive's associated switch, which is switch 140 h, from an open position to a closed position.
- the disk array controller 112 reconstructs the fault-tolerant redundancy array so that the newly activated drive 120 h replaces the failed drive.
- the data arrangement of the redundant array is reconstructed with drive 120 h as part of the array. The process ends at 216 .
- FIG. 5 shows a high-level view of a storage system 180 coupled to a data collection system 190 via a network link 185 .
- Storage system 180 includes the same basic components of storage system 100 of FIG. 3 .
- the storage system 180 illustrated in FIG. 5 implements a data tracking system of an exemplary storage-device activation control.
- the disk array controller 112 dynamically controls the activation of drives and monitors their failures, it can track the actual operational life of a drive from initial activation to eventual failure. This is an empirical measurement of drive life and how it was actually used in the field. This is not a statistical estimation or model.
- the storage system After the storage system has collected empirical data regarding the drives' lifespan, it can transmit that data to a data collection system 190 via a network link 185 , such as the Internet.
- the storage system may provide various types of information about a drive, such as:
- An array manufacturer may host the data collection system 190 . It will use the field-derived, empirical data about actual in-service time of storage devices (such as a drives) to accurately calculate the MTBF. Since the MTBF calculation will be based upon measurements of actual in-service time in the field, the MTBF will accurately estimate the lifespan of a drive. Such a MTBF calculation may be termed an AMTBF (for Actual MTBF) calculation.
- AMTBF for Actual MTBF
- FIG. 6 shows a methodological implementation of exemplary data tracking of an exemplary storage-device activation control performed by a storage system (or a portion thereof), such as storage system 100 of FIG. 3 and storage system 180 of FIG. 5 .
- This methodological implementation may be performed in software, hardware, or a combination thereof.
- a storage system gathers and stores field-derived, empirical data about actual in-service time of storage devices (such as disk drives) from block 310 .
- the storage system occasionally sends such data to a data collection system (such as system 190 in FIG. 5 ).
- the storage system may send the data on a regular timed basis, based upon a user instruction to do so, based upon instructions from a data collection system, when a drive fails, or other such triggering event.
- the collected data is used to calculate AMTBF (actual MTBF) of the storage device associated with that data.
- AMTBF actual MTBF
- the in-service data can also be used to predict the future failure of units that have either not accumulated in-service time as quickly or were deployed at a later time. The enables predictive replacement of drives that are nearing their expected life.
- an exemplary storage-activation control device may intelligently choose to power down one or more existing active drives in a redundant array. If it is determined that a portion of available storage space is unnecessary, the control may choose to deactivate a number of storage devices equivalent to the portion of unnecessary storage space. Conversely, if additional storage space is needed, the control may activate inactive devices to provide such additional storage space.
- Exemplary characteristics of the exemplary storage-device activation control may include, but are not limited to, the following:
- Examples of benefits of the exemplary storage-device activation control may include, but are not limited to, the following:
Abstract
Implementations of this invention provide improved technology for storage-device activation control in high-availability storage systems and tracking of in-service data statistics of storage-devices. Typical high-availability storage systems include a fault-tolerant redundant array of storage devices, such as disk drives. The invention may be implemented with one or more inactive (un-powered) drives physically installed in the storage system, but not part of the present fault-tolerant redundant array of disk drives. When a drive fails, one of the inactive drives is activated (powered-on) and it replaces the failed disk and becomes part of the present array. With the newly activated disk included, the data is reconstructed and the original fault-tolerance level is restored. Furthermore, the invention may be implemented so that it tracks the actual in-service time of the storage devices (such as disk drives). Field-derived, empirical data about actual in-service time of storage devices is collected and transmitted to a central data collection system. Using this actual data as a basis, a much more accurate MTBF may be calculated than the MTBF conventionally calculated.
Description
- This application is a divisional of and claims priority to U.S. patent application Ser. No. 09/792,443, filed Feb. 23, 2001, the disclosure of which is incorporated by reference herein.
- This invention relates to improved techniques for controlling and/or monitoring storage devices in a high-availability storage system.
- Some computer systems are dedicated storage systems. These storage systems typically include one or more arrays of rotating magnetic disks for secondary, non-volatile storage of data. Typically, a storage system may include an enclosure, power supply, cooling fans, and disk array controller(s).
- These disk arrays are sometimes colloquially called “Just a Bunch Of Disks” or alternatively “Just a Box Of Disks” (JBOD). A JBOD is an array of disk drives that are specially designed to improve control, performance, and fault tolerance of such a disk-array storage system.
-
FIG. 1 shows an example of aconventional computer network 10 having acentral computer 20 for controlling the system and for central processing. Of course, such a central computer (i.e., server) may be composed of many interconnected computers. In addition to other functions, thecentral computer 20 controls and monitors multiple storage systems, such asstorage system 30,storage system 32, andstorage system 34. -
FIG. 2 shows a block diagram of the basic components of a typical storage system, in particular,storage system 30. It includes an input/output (I/O)unit 52 for sending/receiving data and control information to/from thecentral computer 20, other storage systems, and other network devices. Adisk array controller 54 is coupled to the I/O unit 52 and to adisk array 60. One or more data and control lines connect thedisk array controller 54 to thedisk array 60. Of course, a storage system may include multiple controllers and multiple disk arrays. - In a conventional storage system (like the one illustrated in
FIG. 2 ), all disk drives in an array are powered by a power supply. Typically, the supply of power to the drive is not controllable or selectable. - Redundant Array of Independent Disks (RAID)
- A common high-availability storage solution is a Redundant Array of Independent (or Inexpensive) Disks (RAID). RAID is a high-availability storage system that employs two or more drives in combination.
- RAID was designed as a means for improving storage subsystem capacity. However, there was a problem with this implementation. The resulting “mean time before failure” (MTBF) of the array was actually reduced due to the probability of any one drive of the array failing. As a result of this finding, the RAID developers proposed multiple levels of RAID to provide a balance of performance and data protection.
- Conventionally, RAID schemes are classified into five basic levels (although other levels may exist):
-
- a first level in which the same data are stored on two disks (“mirrored” disks);
- a second level in which data are bit-interleaved across a group of disks, including check disks on which redundant bits are stored using a Hamming code;
- a third level in which each group has only a single check disk (sometimes called a “parity” disk), on which parity bits are stored;
- a fourth level that uses block interleaving and a single check disk per group; and
- a fifth level that uses block interleaving and distributes the parity information evenly over all disks in a group, so that the writing of parity information is not concentrated on a single check disk.
- For RAID levels 2-5, the fault-tolerant redundant arrays have an additional disk in the array. This is the “check” disk. This disk acts as the replacement disk when one disk in the array fails. The data on a failed disk are conventionally reconstructed; then the reconstructed data are written onto the replacement disk. This places the replacement disk in exactly the same state as the failed disk.
- MTBF
- MTBF is short for “mean time between failures” or “mean time before failure.” Typically, MTBF ratings are measured in hours and indicate the sturdiness of hard disk drives, printers, and virtually any other component.
- Typical inexpensive disk drives for personal computers have MTBF ratings of about 300,000 hours. This means that of all the drives tested, one failure occurred every 300,000 hours of testing. However, this measure is only a statistical model based upon test drives and estimated operation time of failed drives returned to the factory.
- The theoretical MTBF of a disk drive represents the steady state failure rate of a large population of drives in volume manufacture. This is the expected time after the initial burn-in phase that it will take a hardware component to fail due to normal wear and tear.
- Calculating Theoretical MTBFs.
- Most discussions of a computer's MTBF focus on its disk drives' MTBFs for several reasons. Primarily, components with moving parts (such as disk drive actuators and motors) typically have significantly lower MTBFs than non-moving components (such as memory chips or main CPU boards). Because a computer's theoretical MTBF is most influenced by the MTBF of the least reliable component as well as the sheer number of components, disk drive MTBFs typically dominate the overall computer system's theoretical MTBF.
- Theoretical MTBF of a computer decreases in proportion to the number of components that make up the computer. Therefore, larger configurations containing many disk drives, by definition, have a lower overall MTBF.
- A system's overall theoretical MTBF is calculated from the theoretical MTBFs of the components that make up the system:
- where
- N=MTBF of each component
- x=the number of components in the configuration
- The overall MTBF of a disk drive subsystem is in direct proportion to the number of disks in the array. For example, the MTBF of a disk drive subsystem consisting of two disk drives with identical 300,000 hour MTBFs is:
- =150,000 hours, which is exactly half the MTBF of each disk drive
- Similarly, a 10-drive configuration MTBF is one-tenth the MTBF of a single drive, or 30,000 hours, and a 100-drive configuration is reduced to 3,000 hours. Some large systems include 1000-drive (or more) storage configurations, which are likely to require that a failed drive be replaced every one to two weeks (on average).
- Actual Time Before Failure Compared to MTBF
- The MTBF is intended to give a statistical model of the failure times of a large population of drives. The MTBF is not a good measure for the actual time before a given drive fails. One reason is the collection of disk drives used by an installation is not always representative of a large random sample (as assumed by the statistical model). Another reason that MTBF is not a good measure for the actual time before a given drive fails is a lack of empirical data of about drives in actual service.
- Non-Representative Samples.
- Installations typically purchase drives in bulk. They are likely to receive drives with sequential serial numbers because the drives were collectively shipped right from the assembly line of a factory to the large installations.
- Often problems that cause a drive to fail are inadvertently introduced during the manufacturing process. The induction of dust particles and other particulate matter is a common cause of ultimate drive failures. It is typical for such problems to be introduced to a collection of sequentially manufactured drives.
- Therefore, an array of drives in an installation may have a higher risk for drive failure than is represented by a theoretical MTBF calculation. Furthermore, these sequential drives are more likely to fail at approximately the same time because their inherent flaws are similar.
- Lack of Empirical Data.
- The basis of the MTBF calculation for a disk drive is the measured failure rate in a testing facility. Often the calculation is based upon failure data of similar components in previous models. This facility may be part of the manufacturing process, such as a “burn-in” step. It may also be independent of the manufacturing process, such a dedicated testing laboratory. Both options only estimate how the drive is actually used in the field.
- Drive manufacturers typically guess at the actual operating life of a drive model by knowing how many drive models were sold, knowing how many were returned after they failed, and comparing the manufacture date to the returned date. This is only a guess. This does not accurately measure the actual life and use of a drive.
- Conventionally, there is no technique to accurately measure how drives are used in the field; therefore, it is difficult, at best, to determine the accuracy of the artificial failure rates estimated by development engineering.
- Described herein is an improved technology for storage-device activation control in high-availability storage systems and tracking such activations. Typical high-availability storage systems include a fault-tolerant redundant array of storage devices, such as disk drives. Such systems are designed to withstand the failure of X number drives without a loss of data. When a drive fails, the data is reconstructed from the redundancy information on the remaining drives. After X number of drives have failed but before a conventional manual replacement of such failed drives, the data is highly vulnerable to loss if another drive fails.
- An example of the storage-device activation control described herein is implemented with one or more inactive (un-powered) drives physically installed in the storage system, but not part of the present fault-tolerant redundant array of disk drives. When a drive fails, one of the inactive drives is activated (powered-on) and it replaces the failed disk and becomes part of the present array. With the newly activated disk included, the data is reconstructed and the original fault-tolerance level is restored. Since a new disk quickly and automatically (without human intervention) replaces the failed disk in the array, the risk of data loss (based upon another drive failing before the first failure is remedied) is greatly reduced.
- Furthermore, another example of the storage-device activation control described herein is implemented so that it tracks the actual in-service time of the storage devices (such as disk drives). Field-derived, empirical statistical data about actual in-service time of storage devices is collected and transmitted to a central data collection system. Using this actual data as a basis, a much more accurate MTBF may be calculated than the MTBF conventionally calculated.
- The same numbers are used throughout the drawings to reference like elements and features.
-
FIG. 1 illustrates, at a high-level, a conventional computer network that includes multiple storage systems. -
FIG. 2 is a block diagram of the basic components of a conventional storage system. -
FIG. 3 is a block diagram of the basic components of a storage system implementing storage-device activation control for a high-availability storage system. -
FIG. 4 is a flow diagram of a methodological implementation of a storage-device activation control for a high-availability storage system. -
FIG. 5 illustrates, at a high-level, a computer network with a storage system implementing storage-device activation control for a high-availability storage system and a data collection system for receiving empirical data sent by such storage system. -
FIG. 6 is a flow diagram of another methodological implementation of storage-device activation control for a high-availability storage system. - The following description sets forth one or more specific embodiments of a storage-device activation control for a high-availability storage system that incorporates elements recited in the appended claims. The embodiments are described with specificity in order to meet statutory requirements, such as written description, enablement, and best-mode. However, the description itself is not intended to limit the scope of this patent. Rather, the inventors have contemplated that the claimed invention might also be embodied in other ways, in conjunction with other present or future technologies.
- Described herein are examples the storage-device activation control for a high-availability storage system. Each example may be referred to as an “exemplary storage-device activation control.”) Those of ordinary skill in the art understand and appreciate that an exemplary storage-device activation control may be implemented on any computer system (or network) with one or more arrays of storage devices. Therefore, references herein to storage systems are applicable to any similar computer system (or network) with at least one array of storage devices.
- Furthermore, each exemplary storage-device activation control is described herein in the context of “disk drives.” Those of ordinary skill in the art understand and appreciate that each exemplary storage-device activation control may be implemented with any variety of secondary, non-volatile storage devices. Therefore, references herein to disk drives are applicable to any similar secondary, non-volatile storage devices.
- Examples of an “activation status” of a storage device may be either active (powered on) or inactive (powered off). The “field-derived, empirical statistical data about the actual in-service time of a storage device” is described herein. By way of example, this refers to data about the actual in-service time of a storage device (such as a disk drive) that is measured in the field. This terminology distinguishes itself from data derived in a testing facility because such data is not field-derived and is not related to actual in-service time. This terminology also distinguishes itself from data derived from statistical models for similar reasons.
- Storage System Implementing Exemplary Storage-Device Activation Control
-
FIG. 3 shows a block diagram of the basic components of anexemplary storage system 100 that implements the exemplary storage-device activation control. Thestorage system 100 includes adisk array controller 112 coupled to adisk array 120. The disk array controller may be composed of several basic computer components, such as an input/output (I/O) unit, bus adapters, etc. The I/O unit is for sending/receiving data and control information to/from other network devices. - One or more data and control lines (such as
line 130 inFIG. 3 ) connect thedisk array controller 112 to thedisk array 120. Thedisk array 120 includes a set ofdisk drives 120 a-j. - Although only one controller and one JBOD are shown in
FIG. 3 , a storage system implementing a storage-device activation control may include multiple controllers and multiple JBODs. A storage system implementing a storage-device activation control typically have other conventional computer components, such as a CPU, system memory, one or more buses, other I/O systems, communications, and the like. - The
storage system 100 inFIG. 3 includes apower supply 116, which supplies power to thedrives 120 a-j via power andcontrol lines 142. The power andcontrol lines 142 are shown separate from data and control line(s) 130, but such lines may be within the same conduit and perhaps share the same wiring where appropriate. - The
disk array controller 112 is operatively coupled to power switch control (PSC) 114, which may also be called the power-switch controller. With direction from thedisk array controller 112, thePSC 114 selectively controls the activation and deactivation ofspecific drives 120 a-j of thedisk array 120 via the operatively coupled power andcontrol lines 142. Each drive ofdrives 120 a-j has an associated power activation switch 140 a-j, which switchably couples each drive to thepower supply 116. - Switches 140 a-j may be any electronically controllable switches. In the exemplary storage system, the switches are a solid-state electronic component (such as a FET). Such switches may be part of a drive's internal circuitry or they may be external to the drive. Unlike a conventional storage system (such as
storage system 30 illustrated inFIGS. 1 and 2 ), thedisk drives 120 a-j in thedisk array 120 are selectively powered on (“activated”) or off (“deactivated”) by thePSC 114 under direction from thedisk array controller 112. -
Switches - For example, assume that these six drives (120 a, 120 b, 120 c, 120 e, 120 g, and 120 i) form an active RAID of 5+1 (which is five disks of data and one disk of redundancy parity data). Electricity is flowing through its circuitry and its parts are moving. Its lifespan is decreasing.
-
Switches - For example, if a drive fails (such as
drive 120 c), thedisk array controller 112 instructs thePSC 114 to activate one of the inactive drives (such drive 120 h). Thus, the newly activateddrive 120 h replaces just-faileddrive 120 c within the RAID of 5+1 disks. Therefore, a minimum amount of time is spent with a danger of data loss before the failed drive is replaced in the RAID with a new active drive. - Methodological Implementation of Exemplary Storage-Device Activation Control
-
FIG. 4 shows a methodological implementation of an exemplary storage-device activation control performed by a storage system (or a portion thereof), such asstorage system 100 ofFIG. 3 . This methodological implementation may be performed in software, hardware, or a combination thereof. - At 210 of
FIG. 4 , thedisk array controller 112 receives an indication of a drive failure and an identification of which drive that failed. The drive is a member of a fault-tolerant redundancy array of drives. At 212, thedisk array controller 112 activates one of a set of inactive drives. For example, it may direct thePSC 114 to activate drive 120 h. The PSC does this by switching the drive's associated switch, which isswitch 140 h, from an open position to a closed position. - At 214, the
disk array controller 112 reconstructs the fault-tolerant redundancy array so that the newly activateddrive 120 h replaces the failed drive. The data arrangement of the redundant array is reconstructed withdrive 120 h as part of the array. The process ends at 216. - Exemplary Data Tracking System of Exemplary Storage-Device Activation Control
-
FIG. 5 shows a high-level view of astorage system 180 coupled to adata collection system 190 via anetwork link 185.Storage system 180 includes the same basic components ofstorage system 100 ofFIG. 3 . Thestorage system 180 illustrated inFIG. 5 implements a data tracking system of an exemplary storage-device activation control. - Since the
disk array controller 112 dynamically controls the activation of drives and monitors their failures, it can track the actual operational life of a drive from initial activation to eventual failure. This is an empirical measurement of drive life and how it was actually used in the field. This is not a statistical estimation or model. - After the storage system has collected empirical data regarding the drives' lifespan, it can transmit that data to a
data collection system 190 via anetwork link 185, such as the Internet. The storage system may provide various types of information about a drive, such as: -
- brand;
- model;
- serial number;
- components and features (e.g., number of cylinders, platters, segments, etc.);
- in-service timespan (which may include day and time of activation and failure);
- type of failure;
- usage patterns during that lifespan, during each day, during an average day, etc.
- An array manufacturer may host the
data collection system 190. It will use the field-derived, empirical data about actual in-service time of storage devices (such as a drives) to accurately calculate the MTBF. Since the MTBF calculation will be based upon measurements of actual in-service time in the field, the MTBF will accurately estimate the lifespan of a drive. Such a MTBF calculation may be termed an AMTBF (for Actual MTBF) calculation. - Methodological Implementation of Exemplary Data Tracking
-
FIG. 6 shows a methodological implementation of exemplary data tracking of an exemplary storage-device activation control performed by a storage system (or a portion thereof), such asstorage system 100 ofFIG. 3 andstorage system 180 ofFIG. 5 . This methodological implementation may be performed in software, hardware, or a combination thereof. - At 312 of
FIG. 6 , a storage system gathers and stores field-derived, empirical data about actual in-service time of storage devices (such as disk drives) fromblock 310. At 314, the storage system occasionally sends such data to a data collection system (such assystem 190 inFIG. 5 ). The storage system may send the data on a regular timed basis, based upon a user instruction to do so, based upon instructions from a data collection system, when a drive fails, or other such triggering event. - At 316, the collected data is used to calculate AMTBF (actual MTBF) of the storage device associated with that data. The process ends at 318.
- The in-service data can also be used to predict the future failure of units that have either not accumulated in-service time as quickly or were deployed at a later time. The enables predictive replacement of drives that are nearing their expected life.
- Alternative Implementation of Storage-Device Activation Control
- Rather than powering up a drive to replace a failed drive in a redundant array, an alternative implementation of an exemplary storage-activation control device may intelligently choose to power down one or more existing active drives in a redundant array. If it is determined that a portion of available storage space is unnecessary, the control may choose to deactivate a number of storage devices equivalent to the portion of unnecessary storage space. Conversely, if additional storage space is needed, the control may activate inactive devices to provide such additional storage space.
- Other than abstract efficiency reasons, it is desirable to only have just enough storage devices active in a redundant array to satisfy the storage needs of the present and the near future. Why? Doing so, minimizes costs by doing the following:
-
- increasing the effective lifespan of a storage device by deactivating it when not needed;
- decreasing cooling costs by reducing the number of devices generating heat; and
- decreasing power costs by reducing the number of devices drawing electricity.
Exemplary Characteristics of Exemplary Storage-Device Activation Control
- Exemplary characteristics of the exemplary storage-device activation control, may include, but are not limited to, the following:
-
- automated control by a storage system of its storage devices;
- automated activation control of storage devices so that such device may be selectively powered on or off;
- tracking of time-in-service type statistics by individual storage device;
- central data collection and reporting system to collect and analyze the in-service statistics of storage devices; and
- failure prediction by analyzing actual field failure statistics of like mechanisms.
Examples of Benefits of Exemplary Storage-Device Activation Control
- Examples of benefits of the exemplary storage-device activation control, may include, but are not limited to, the following:
-
- online and available spare storage devices reduce the time a redundancy array will exist in a non-redundant state (or in a state of lesser redundancy); in such a state, data loss may occur if another storage device fails;
- keeping the online and available spare storage devices in a powered down (inactive) state optimizes their life expectancy, thereby preventing the conventional device-failure recovery situation (e.g., like with RAID) where redundancy is re-established using an active storage device which has already seen most if its functional life;
- keeping the storage devices of unused redundancy arrays in a powered down state reduces power consumption; reduces acoustic levels, reduces thermal levels, and optimizes life expectancy of the devices;
- failure prediction (based upon field-derived, empirical data about actual in-service time of storage devices) enables the preventative replacement of storage devices, thus avoiding exposure to loss of redundancy that occurs when storage devices are allowed to fail while in service;
- failure prediction also enables supply chain optimization for manufacturers and distributors by predicting demand for replacement units prior to failure;
- failure prediction further enables predictive shipment of replacement devices, thereby reducing the reliance on expensive express delivery shipments.
- Although the invention has been described in language specific to structural features and/or methodological steps, it is to be understood that the invention defined in the appended claims is not necessarily limited to the specific features or steps described. Rather, the specific features and steps are disclosed as preferred forms of implementing the claimed invention.
Claims (3)
1. A data tracking method comprising:
obtaining field-derived, empirical statistical data about actual in-service time of storage devices;
collecting such data;
transmitting the collected data to a remote data collection system via a telecommunications network, wherein the obtaining is performed remotely from the data collection system.
2. A method as recited in claim 1 , wherein the obtaining comprises:
monitoring in-service statistics of storage devices as such devices are actually used;
recording such statistics to produce the field-derived, empirical data about actual in-service time of storage devices.
3. A computer-readable medium having computer-executable instructions that, when executed by a computer, performs acts comprising:
obtaining field-derived, empirical statistical data about actual in-service time of storage devices;
collecting such data;
transmitting the collected data to a remote data collection system via a telecommunications network, wherein the obtaining is performed remotely from the data collection system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US11/173,453 US20050268161A1 (en) | 2001-02-23 | 2005-07-01 | Storage-device activation control for a high-availability storage system |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/792,443 US6986075B2 (en) | 2001-02-23 | 2001-02-23 | Storage-device activation control for a high-availability storage system |
US11/173,453 US20050268161A1 (en) | 2001-02-23 | 2005-07-01 | Storage-device activation control for a high-availability storage system |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/792,443 Division US6986075B2 (en) | 2001-02-23 | 2001-02-23 | Storage-device activation control for a high-availability storage system |
Publications (1)
Publication Number | Publication Date |
---|---|
US20050268161A1 true US20050268161A1 (en) | 2005-12-01 |
Family
ID=25156893
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/792,443 Expired - Lifetime US6986075B2 (en) | 2001-02-23 | 2001-02-23 | Storage-device activation control for a high-availability storage system |
US11/173,453 Abandoned US20050268161A1 (en) | 2001-02-23 | 2005-07-01 | Storage-device activation control for a high-availability storage system |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/792,443 Expired - Lifetime US6986075B2 (en) | 2001-02-23 | 2001-02-23 | Storage-device activation control for a high-availability storage system |
Country Status (1)
Country | Link |
---|---|
US (2) | US6986075B2 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070217815A1 (en) * | 2006-03-17 | 2007-09-20 | Fujitsu Limited | Suspected place identifying apparatus and processing method |
Families Citing this family (43)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7426534B2 (en) * | 2001-12-19 | 2008-09-16 | International Business Machines Corporation | Method and system for caching message fragments using an expansion attribute in a fragment link tag |
US7210004B2 (en) * | 2003-06-26 | 2007-04-24 | Copan Systems | Method and system for background processing of data in a storage system |
US7210005B2 (en) * | 2002-09-03 | 2007-04-24 | Copan Systems, Inc. | Method and apparatus for power-efficient high-capacity scalable storage system |
GB0221638D0 (en) * | 2002-09-17 | 2002-10-30 | Ibm | Device system and method for predictive failure analysis |
US20140200907A1 (en) | 2013-01-16 | 2014-07-17 | American Health Data Institute, Inc. | Method of optimizing healthcare services consumption |
US11335446B2 (en) * | 2002-12-06 | 2022-05-17 | Quality Healthcare Intermediary, Llc | Method of optimizing healthcare services consumption |
JP4651913B2 (en) * | 2003-02-17 | 2011-03-16 | 株式会社日立製作所 | Storage system |
DE10313892B4 (en) * | 2003-03-27 | 2007-04-19 | Fujitsu Siemens Computers Gmbh | Arrangement and method for exchanging mass memories |
JP4060235B2 (en) * | 2003-05-22 | 2008-03-12 | 株式会社日立製作所 | Disk array device and disk array device control method |
JP2004348464A (en) | 2003-05-22 | 2004-12-09 | Hitachi Ltd | Storage device and communication signal shaping circuit |
US7434097B2 (en) * | 2003-06-05 | 2008-10-07 | Copan System, Inc. | Method and apparatus for efficient fault-tolerant disk drive replacement in raid storage systems |
US20050210304A1 (en) * | 2003-06-26 | 2005-09-22 | Copan Systems | Method and apparatus for power-efficient high-capacity scalable storage system |
US7373559B2 (en) * | 2003-09-11 | 2008-05-13 | Copan Systems, Inc. | Method and system for proactive drive replacement for high availability storage systems |
US20060090098A1 (en) * | 2003-09-11 | 2006-04-27 | Copan Systems, Inc. | Proactive data reliability in a power-managed storage system |
JP4156499B2 (en) | 2003-11-28 | 2008-09-24 | 株式会社日立製作所 | Disk array device |
JP4497918B2 (en) | 2003-12-25 | 2010-07-07 | 株式会社日立製作所 | Storage system |
JP4634049B2 (en) | 2004-02-04 | 2011-02-16 | 株式会社日立製作所 | Error notification control in disk array system |
US7409582B2 (en) | 2004-05-06 | 2008-08-05 | International Business Machines Corporation | Low cost raid with seamless disk failure recovery |
JP4404353B2 (en) * | 2004-05-25 | 2010-01-27 | 株式会社日立製作所 | Disk array that suppresses disk failures |
EP1772804B1 (en) * | 2004-08-12 | 2011-03-23 | Hitachi, Ltd. | Storage system |
US7434090B2 (en) * | 2004-09-30 | 2008-10-07 | Copan System, Inc. | Method and apparatus for just in time RAID spare drive pool management |
JP4751153B2 (en) * | 2005-06-08 | 2011-08-17 | 株式会社日立製作所 | Storage system |
US7757015B2 (en) * | 2005-09-13 | 2010-07-13 | International Business Machines Corporation | Device, method and computer program product readable medium for determining the identity of a component |
JP2007188421A (en) * | 2006-01-16 | 2007-07-26 | Fujitsu Ltd | Electric power source supply controller, and electric power source supply control method |
US20070226536A1 (en) * | 2006-02-06 | 2007-09-27 | Crawford Timothy J | Apparatus, system, and method for information validation in a heirarchical structure |
US8707076B2 (en) | 2007-04-18 | 2014-04-22 | Dell Products L.P. | System and method for power management of storage resources |
US7472298B1 (en) * | 2008-01-31 | 2008-12-30 | International Business Machines Corporation | Storage system and method for saving energy based on storage classes with corresponding power saving policies |
JP2009294803A (en) * | 2008-06-03 | 2009-12-17 | Hitachi Ltd | Method of operating storage device, storage device and storage subsystem |
US8413029B2 (en) * | 2009-01-16 | 2013-04-02 | Lsi Corporation | Error correction capability adjustment of LDPC codes for storage device testing |
US20100199060A1 (en) * | 2009-02-04 | 2010-08-05 | Panasonic Corporation | Memory controller, nonvolatile memory module, access module, and nonvolatile memory system |
US8176208B2 (en) * | 2009-11-04 | 2012-05-08 | Hitachi, Ltd. | Storage system and operating method of storage system |
US8650435B2 (en) * | 2011-06-08 | 2014-02-11 | Dell Products L.P. | Enhanced storage device replacement system and method |
WO2014051603A1 (en) * | 2012-09-28 | 2014-04-03 | Longsand Limited | Predicting failure of a storage device |
US9939865B2 (en) | 2014-06-13 | 2018-04-10 | Seagate Technology Llc | Selective storage resource powering for data transfer management |
US9971991B2 (en) * | 2015-04-28 | 2018-05-15 | Accenture Global Services Limited | Automated, new spare parts forecasting and demand planning system |
US9766965B2 (en) * | 2015-11-25 | 2017-09-19 | Salesforce.Com, Inc. | System and method for monitoring and detecting faulty storage devices |
US10417093B2 (en) * | 2016-05-13 | 2019-09-17 | Netapp, Inc. | Methods for providing global spare data storage device management and devices thereof |
US10467172B2 (en) | 2016-06-01 | 2019-11-05 | Seagate Technology Llc | Interconnect for shared control electronics |
US9678817B1 (en) * | 2016-10-28 | 2017-06-13 | International Business Machines Corporation | Lifespan forecast for storage media devices |
US10795842B2 (en) | 2017-05-08 | 2020-10-06 | Liqid Inc. | Fabric switched graphics modules within storage enclosures |
US11119850B2 (en) | 2018-06-29 | 2021-09-14 | International Business Machines Corporation | Determining when to perform error checking of a storage unit by using a machine learning module |
US11099743B2 (en) * | 2018-06-29 | 2021-08-24 | International Business Machines Corporation | Determining when to replace a storage device using a machine learning module |
US11119662B2 (en) | 2018-06-29 | 2021-09-14 | International Business Machines Corporation | Determining when to perform a data integrity check of copies of a data set using a machine learning module |
Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5148432A (en) * | 1988-11-14 | 1992-09-15 | Array Technology Corporation | Arrayed disk drive system and method |
US5878201A (en) * | 1994-02-23 | 1999-03-02 | Mitsubishi Denki Kabushiki Kaisha | Disk system and factory automation controller and method therefor |
US5880955A (en) * | 1991-11-13 | 1999-03-09 | Fujitsu Limited | Status display system for storage device |
US5966510A (en) * | 1993-11-12 | 1999-10-12 | Seagate Technology, Inc. | SCSI-coupled module for monitoring and controlling SCSI-coupled raid bank and bank environment |
US6079029A (en) * | 1997-03-17 | 2000-06-20 | Fujitsu Limited | Device array system providing redundancy of disks from active system disks during a disk failure |
US6088768A (en) * | 1993-12-28 | 2000-07-11 | International Business Machines Corporation | Method and system for maintaining cache coherence in a multiprocessor-multicache environment having unordered communication |
US6131142A (en) * | 1990-07-13 | 2000-10-10 | Hitachi, Ltd. | Disk system and power-on sequence for the same |
US6154853A (en) * | 1997-03-26 | 2000-11-28 | Emc Corporation | Method and apparatus for dynamic sparing in a RAID storage system |
US6282670B1 (en) * | 1997-07-02 | 2001-08-28 | International Business Machines Corporation | Managing defective media in a RAID system |
US6289398B1 (en) * | 1993-03-11 | 2001-09-11 | Emc Corporation | Distributed storage array system having plurality of storage devices which each of devices including a modular control unit for exchanging configuration information over a communication link |
US6405329B1 (en) * | 1999-07-27 | 2002-06-11 | Dell Usa, L.P. | Method and apparatus for HDD time stamp benchmark and installation identification |
US20020073362A1 (en) * | 2000-03-31 | 2002-06-13 | Arnaout Badih Mohamad Naji | Remote evaluation of a data storage device |
US6493656B1 (en) * | 1999-02-26 | 2002-12-10 | Compaq Computer Corporation, Inc. | Drive error logging |
US6583947B1 (en) * | 1999-04-05 | 2003-06-24 | Hitachi, Ltd. | Disk array unit |
US6598174B1 (en) * | 2000-04-26 | 2003-07-22 | Dell Products L.P. | Method and apparatus for storage unit replacement in non-redundant array |
US6675129B1 (en) * | 2000-12-28 | 2004-01-06 | General Electric Company | Internet based supplier process reliability system |
US6725385B1 (en) * | 2000-09-11 | 2004-04-20 | International Business Machines Corporation | Intelligent electronic power controller |
US6782487B2 (en) * | 1999-02-01 | 2004-08-24 | Matsushita Electric Industrial Co., Ltd. | Information recording medium information recording method and information recording/reproduction system |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6088766A (en) * | 1997-10-06 | 2000-07-11 | Emc Corporation | Method for exchanging data blocks on disk storage devices utilizing disk access statistics and testing for the effect of a change |
JP2001249831A (en) * | 2000-03-07 | 2001-09-14 | Hitachi Telecom Technol Ltd | Method for monitoring operating time of storage device |
-
2001
- 2001-02-23 US US09/792,443 patent/US6986075B2/en not_active Expired - Lifetime
-
2005
- 2005-07-01 US US11/173,453 patent/US20050268161A1/en not_active Abandoned
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5148432A (en) * | 1988-11-14 | 1992-09-15 | Array Technology Corporation | Arrayed disk drive system and method |
US6131142A (en) * | 1990-07-13 | 2000-10-10 | Hitachi, Ltd. | Disk system and power-on sequence for the same |
US5880955A (en) * | 1991-11-13 | 1999-03-09 | Fujitsu Limited | Status display system for storage device |
US6289398B1 (en) * | 1993-03-11 | 2001-09-11 | Emc Corporation | Distributed storage array system having plurality of storage devices which each of devices including a modular control unit for exchanging configuration information over a communication link |
US5966510A (en) * | 1993-11-12 | 1999-10-12 | Seagate Technology, Inc. | SCSI-coupled module for monitoring and controlling SCSI-coupled raid bank and bank environment |
US6088768A (en) * | 1993-12-28 | 2000-07-11 | International Business Machines Corporation | Method and system for maintaining cache coherence in a multiprocessor-multicache environment having unordered communication |
US5878201A (en) * | 1994-02-23 | 1999-03-02 | Mitsubishi Denki Kabushiki Kaisha | Disk system and factory automation controller and method therefor |
US6079029A (en) * | 1997-03-17 | 2000-06-20 | Fujitsu Limited | Device array system providing redundancy of disks from active system disks during a disk failure |
US6154853A (en) * | 1997-03-26 | 2000-11-28 | Emc Corporation | Method and apparatus for dynamic sparing in a RAID storage system |
US6282670B1 (en) * | 1997-07-02 | 2001-08-28 | International Business Machines Corporation | Managing defective media in a RAID system |
US6782487B2 (en) * | 1999-02-01 | 2004-08-24 | Matsushita Electric Industrial Co., Ltd. | Information recording medium information recording method and information recording/reproduction system |
US6493656B1 (en) * | 1999-02-26 | 2002-12-10 | Compaq Computer Corporation, Inc. | Drive error logging |
US6583947B1 (en) * | 1999-04-05 | 2003-06-24 | Hitachi, Ltd. | Disk array unit |
US6405329B1 (en) * | 1999-07-27 | 2002-06-11 | Dell Usa, L.P. | Method and apparatus for HDD time stamp benchmark and installation identification |
US20020073362A1 (en) * | 2000-03-31 | 2002-06-13 | Arnaout Badih Mohamad Naji | Remote evaluation of a data storage device |
US6598174B1 (en) * | 2000-04-26 | 2003-07-22 | Dell Products L.P. | Method and apparatus for storage unit replacement in non-redundant array |
US6725385B1 (en) * | 2000-09-11 | 2004-04-20 | International Business Machines Corporation | Intelligent electronic power controller |
US6675129B1 (en) * | 2000-12-28 | 2004-01-06 | General Electric Company | Internet based supplier process reliability system |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070217815A1 (en) * | 2006-03-17 | 2007-09-20 | Fujitsu Limited | Suspected place identifying apparatus and processing method |
US7694179B2 (en) * | 2006-03-17 | 2010-04-06 | Fujitsu Limited | Suspected place identifying apparatus and processing method |
Also Published As
Publication number | Publication date |
---|---|
US20020162048A1 (en) | 2002-10-31 |
US6986075B2 (en) | 2006-01-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US6986075B2 (en) | Storage-device activation control for a high-availability storage system | |
US7526684B2 (en) | Deterministic preventive recovery from a predicted failure in a distributed storage system | |
US7370241B2 (en) | Device, system and method for predictive failure analysis | |
US7409582B2 (en) | Low cost raid with seamless disk failure recovery | |
US7581137B2 (en) | Storage apparatus and storage apparatus power supply failure management method | |
US8473779B2 (en) | Systems and methods for error correction and detection, isolation, and recovery of faults in a fail-in-place storage array | |
US7373559B2 (en) | Method and system for proactive drive replacement for high availability storage systems | |
US7350046B2 (en) | Managed reliability storage system and method monitoring storage conditions | |
Jiang et al. | Are disks the dominant contributor for storage failures? A comprehensive study of storage subsystem failure characteristics | |
Allen | Monitoring hard disks with smart | |
US7539907B1 (en) | Method and apparatus for determining a predicted failure rate | |
US10013321B1 (en) | Early raid rebuild to improve reliability | |
US20130179631A1 (en) | Solid-state disk (ssd) management | |
US20090161243A1 (en) | Monitoring Disk Drives To Predict Failure | |
US20060090098A1 (en) | Proactive data reliability in a power-managed storage system | |
US20180060192A1 (en) | Adaptive Failure Prediction Modeling for Detection of Data Storage Device Failures | |
US7880437B2 (en) | Quick conditioning memory backup battery | |
JP4743905B2 (en) | Flash memory storage life monitoring device | |
US8234235B2 (en) | Security and remote support apparatus, system and method | |
EP2912555B1 (en) | Hard drive backup | |
JP2007004793A (en) | Method and device for measuring code coverage for embedded processor system | |
Hunter et al. | Availability modeling and analysis of a two node cluster | |
JP6996602B1 (en) | BMC, server system, device stability determination method and program | |
JP4605374B2 (en) | Storage device testing method and apparatus | |
Li et al. | Leveraging big data to improve reliability & maintainability |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |