Data processing: measuring – calibrating – or testing – Measurement system in a specific environment – Mechanical measurement system
Reexamination Certificate
1999-01-28
2001-11-06
Hoff, Marc S. (Department: 2857)
Data processing: measuring, calibrating, or testing
Measurement system in a specific environment
Mechanical measurement system
C073S578000
Reexamination Certificate
active
06314377
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Technical Field
The present invention relates in general to an improved information storage system. In particular, the present invention relates to a method and system for preventing read/write errors caused by drive assembly vibration. More particularly, the present invention relates to strategically arranging drive assemblies within a storage array so as to minimize the negative impact on drive assembly performance caused by inherent drive assembly vibration. Still more particularly, the present invention relates to a method and system for determining the vibration level of individual drive assemblies and thereafter installing drive assemblies with relatively higher vibration levels at predetermined locations within a storage array frame such that adjacent drive assemblies are minimally affected, thereby minimizing drive assembly read/write failures and the effects thereof.
2. Description of the Related Art
Generally, a digital data storage system consists of one or more storage devices that store data on storage media such as magnetic or optical data storage disks. In disk storage systems, the storage devices typically utilize a magnetic or optical medium to preserve the data. The most common data storage device has one or more generally circular disks formed from a non-magnetic substrate with a ferromagnetic coating. The disks rotate or spin, and a pivoting arm having electromagnetic transducers is utilized to read from, and write to, the disks. Both surfaces (upper and lower) of a disk can be utilized. Such a magnetic storage device is commonly referred to as a head disk assembly (HDA), and is usually packaged in a modular enclosure so that it may be easily installed in and removed from a computer system. Many computer systems utilize multiple HDAs for greater storage capability, or for fault tolerance, such as in a Redundant Array of Independent Disks (RAID) system.
A HDA is an electromechanical device that reads from and writes to disks. The main components of an HDA include a spindle on which the disk is mounted, a drive motor that spins the disk when the drive is in operation, one or more read/write heads, a second motor that positions the read/write head(s) over the disk, and controller circuitry that synchronizes read/write activities and transfers information to and from the computer. This controller circuitry, often referred to as a HDA controller, is a special purpose integrated circuit and other associated circuitry that directs and controls reading from and writing to a computer's disk drive. An HDA controller handles such tasks as positioning the read/write head, mediating between the drive and the microprocessor, and controlling the transfer of information to and from memory.
A number of known data storage systems incorporate certain techniques and devices to predict storage device failures, along with other techniques and devices to quickly recover from device failures. As discussed below, however, these systems may not be completely adequate for use in certain applications.
Predictive failure analysis (PFA) is commonly utilized in disk drive controllers and has become an industry standard as a diagnostic tool. Typically, PFA is implemented via the microcode utilized to control local disk drive operations conducted via the disk drive controller. The controller will detect that either a failure has occurred or that a disk drive failure is imminent. In response to detecting an existing or imminent error, the microcode will respond by posting an error signal. The disk drive user or the system itself may respond by taking the drive off-line or by taking data recovery action to retrieve data that was lost or compromised by the failure.
Another method of addressing drive read/write errors that is closely related to PFA is a method known as Data Recovery Procedure (DRP). An example implementation of DRP during a read operation, for example, would be if the head (the sensor) is positioned too far off the track center and the resulting poorer signal to noise ratio then causes the disk drive not being able to decode the read-back signal which then triggers the DRP. The DRP is usually a collection of operations intended to alleviate the error conditions. In the example above, one possible DRP response would be to reposition the head. DRP is therefore geared to data recovery and is invoked in-stream with the user operations (reads and writes).
Although PFA and DRP are effective in detecting and recovering from disk drive failures, they fail to address and remedy a disk drive vibration as significant cause of many such failures. Vibrations can cause problems that are addressed currently in two ways: (1) a measurement of the inherent radial vibration of a drive, referred to as root mean square of spindle runout or ACRMS, to ensure that the vibration level does not exceed a particular specified value; and (2) encoding this ACRMS information within the disk drive control circuitry thereby permitting a feedback circuit to counteract repeatable (in sync with spindle) non-uniformities within the servo controller of an individual disk drive assembly.
Although ACRMS is utilized for addressing the vibration levels of individual disk drive assemblies, the interference caused by the vibration of a first drive on other surrounding drives, such as often occurs within storage array systems such as RAID systems remains unaddressed. Currently, disk drives that have acceptable ACRMS levels, are placed into a storage array during manufacturing in a random manner. If a disk drive (referred to interchangeably as a “drive assembly”) that has a relatively high (yet still within specification requirements) is placed in a drive location where it is not isolated to the greatest extent possible, or where the mounting is not as solid as it would be in another location in the frame, the vibration may cause errors on adjacent disk drives. This problem of “contaminating” good drives is well known in the field of storage arrays.
Based on the foregoing, it can be appreciated that a need exists for an improved method and system for allocating the relative locations of drive assemblies within a multiple drive array that would account for individual, inherent vibration levels of each drive assembly. Such a method and system, if implemented, would be useful by ensuring that drive assemblies with higher vibration levels are installed at locations within a particular multiple drive array frame that provide greater structural support and damping such that the negative effects of inter-drive vibration are minimized.
SUMMARY OF THE INVENTION
It is therefore an object of the invention to provide a method and system for improving an information storage system.
It is another object of the invention to provide a method and system for preventing read/write errors caused by drive assembly vibration.
It is still another object of the invention to provide a method and system for strategically arranging drive assemblies within a storage array so as to minimize the negative impact on drive assembly performance caused by inherent drive assembly vibration.
It is yet another object of the present invention to provide a method and system for determining the vibration level of individual drive assemblies and installing drive assemblies with relatively higher vibration levels at locations within a storage array such that adjacent drive assemblies are minimally affected, thereby minimizing drive assembly read/write failures and the effects thereof.
The above and other objects are achieved as is now described. A method and system are disclosed for strategically arranging drive assemblies within a multiple drive array. The multiple drive array includes a plurality of drive locations for installing the drive assemblies, each of the drive assemblies having inherent vibration levels during operation. First, a vibration classification is assigned to each drive location among a plurality of drive locations within a multiple drive array. The vibration classification corresponds to a range of measura
Ottesen Hal Hjalmar
Smith Gordon James
Bracewell & Patterson LLP
Hoff Marc S.
International Business Machines - Corporation
Pretlow Demetrius
LandOfFree
Optimal location of drive assemblies within a multiple drive... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Optimal location of drive assemblies within a multiple drive..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optimal location of drive assemblies within a multiple drive... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2572398