Gordon F. Hughes

Improved disk-drive failure warnings

Improved methods are proposed for disk-drive failure prediction. The SMART (self monitoring and reporting technology) failure prediction system is currently implemented in disk-drives. Its purpose is to predict the near-term failure of an individual hard disk-drive, and issue a backup warning to prevent data loss. Two experimental tests of SMART show only moderate accuracy at low false-alarm rates. (A rate of 0.2% of total drives per year implies that 20% of drive returns would be good drives, relative to /spl ap/1% annual failure rate of drives). This requirement for very low false-alarm rates is well known in medical diagnostic tests for rare diseases, and methodology used there suggests ways to improve SMART. Two improved SMART algorithms are proposed. They use the SMART internal drive attribute measurements in present drives. The present warning-algorithm based on maximum error thresholds is replaced by distribution-free statistical hypothesis tests. These improved algorithms are computationally simple enough to be implemented in drive microprocessor firmware code. They require only integer sort operations to put several hundred attribute values in rank order. Some tens of these ranks are added up and the SMART warning is issued if the sum exceeds a prestored limit. These new algorithms were tested on 3744 drives of 2 models. They gave 3-4 times higher correct prediction accuracy than error thresholds on will-fail drives, at 0.2% false-alarm rate. The highest accuracies achievable are modest (40%-60%). Care was taken to test will-fail drive prediction accuracy on data independent of the algorithm design data. Additional work is needed to verify and apply these algorithms in actual drive design. They can also be useful in drive failure analysis engineering. It might be possible to screen drives in manufacturing using SMART attributes. Marginal drives might be detected before substantial final test time is invested in them, thereby decreasing manufacturing cost, and possibly decreasing overall field failure rates.

Magnetization reversal in cobalt–phosphorus films

A brief review is given of preparation, structure, and magnetization reversal in Co–P thin films for digital recording. From this, a magnetization reversal theory is developed which correctly predicts a number of observed facts about Co–P. Among these are &mA0.1 (conventional theory predicts 0.64 and 0.51, respectively), avalanche and cluster reversal mechanisms, transverse ripple, and sawtooth structure in recorded bits. Limitations to high bit and track density recording are discussed. It is suggested that lower Mr/Ms remanent squareness values may alleviate these density limiting mechanisms.

Read channels for patterned media

Patterned media may alleviate thermal decay and transition noise limits on the horizon for conventional continuous film media. A system analysis of oriented patterned media for magnetic recording is presented. Gbit/sec read channels for vertical and horizontal easy axis patterned media are analyzed at 100 Gb/in/sup 2/. Encouraging bit error rates of 10/sup -9/ are predicted by channel simulation using recording physics read pulses and electronic and patterning lithography noise.

Recording head side read/write effects

Fields off the side of a recording head are derived and three dimensional side effects (side writing, erasing and reading) are evaluated. The closed-form equations are sufficiently general and simple to permit recording system calculations involving inter-track crosstalk guardbands, prior data crosstalk due to head-track misalignment, and adjacent track overwrite.

Reliability and security of RAID storage systems and D2D archives using SATA disk drives

Information storage reliability and security is addressed by using personal computer disk drives in enterprise-class nearline and archival storage systems. The low cost of these serial ATA (SATA) PC drives is a tradeoff against drive reliability design and demonstration test levels, which are higher in the more expensive SCSI and Fibre Channel drives. This article discusses the tradeoff between SATA which has the advantage that fewer higher capacity drives are needed for a given system storage capacity, which further reduces cost and allows higher drive failure rates, and the use of additional storage system redundancy and drive failure prediction to maintain system data integrity using less reliable drives. RAID stripe failure probability is calculated using typical ATA and SCSI drive failure rates, for single and double parity data reconstruction failure, and failure due to drive unrecoverable block errors. Reliability improvement from drive failure prediction is also calculated, and can be significant. Todays SATA drive specifications for unrecoverable block errors appear to allow stripe reconstruction failure, and additional in-drive parity blocks are suggested as a solution. The possibility of using low cost disks data for backup and archiving is discussed, replacing higher cost magnetic tape. This requires significantly better RAID stripe failure probability, and suitable drive technology alternatives are discussed. The failure rate of nonoperating drives is estimated using failure analysis results from ≈4000 drives. Nonoperating RAID stripe failure rates are thereby estimated. User data security needs to be assured in addition to reliability, and to extend past the point where physical control of drives is lost, such as when drives are removed from systems for data vaulting, repair, sale, or discard. Today, over a third of resold drives contain unerased user data. Security is proposed via the existing SATA drive secure-erase command, or via the existing SATA drive password commands, or by data encryption. Finally, backup and archival disc storage is compared to magnetic tape, a technology with a proven reliability record over the full half-century of digital data storage. In contrast, tape archives are not vulnerable to tape transport failure modes. Only failure modes in the archived tapes and reels will make data unrecoverable.

Disposal of Disk and Tape Data by Secure Sanitization

User data is often unprotected on disk and tape drives or not erased when no longer needed, creating data security vulnerabilities that many computer users are unaware of. Federal and state laws require data sanitization, which comprises a variety of data eradication methods. Secure sanitization refers to methods meeting those federal and state laws. Companies that fail to meet these laws can be subject to fines of

Carbon overcoat and the process dependence on its microstructure and wear characteristics

5 million, and individuals can be imprisoned for up to 10 years. Physical destruction of storage devices offers the highest security. But executing the disk drive internal secure-erase command also offers a higher security level than external-block-overwrite software, according to federal guideline NIST 800-88. Recent disk drives with internal full disk encryption now implement an enhanced secure-erase command that takes only milliseconds to complete.

Thin film recording head efficiency and noise

Carbon films prepared by DC magnetron sputtering as an overcoat for rigid-disk thin film media are studied. The tribological or wear performance shows a strong dependence on the sputtering process. The microstructure of the carbon films was evaluated using transmission electron microscopy, scanning tunneling microscopy, and Raman scattering. The results show that the films with better wear performance have a more uniform grain size distribution with a higher percentage (2-3%) of SP bonded carbon atoms and have a homogeneous work function distribution as compared to the films with poor wear performance. Atomic resolution images show disorder of the carbon atoms on the surface; however, some hexagonal patterns extending over about 10 AA are visible. >

Read channels for pre-patterned media, with trench playback

Analytic formulas for thin film recording head efficiency and thermal noise are presented. Paton’s transmission line model is replaced by two‐dimensional eddy currents in four regions: the coil region, the gap region, and two permeable pole regions. Predicted efficiencies are lower, and close to actual thin film heads. Basically, a four‐region solution is needed because the gap region is a reluctive load on the coil region’s pole reluctance, which lowers the predicted efficiency substantially below that of the unloaded Paton two region (coil and pole) transmission line. Paton efficiency formulas seem to often predict either too high an efficiency, or too low a permeability. For typical head dimensions, the four region efficiency formulas reduces to hand calculator simplicity. Eddy currents in the drive coils and conductive (permalloy) poles can cause the impedance phase angle θ of these heads to hover closer to 45° than to a purely inductive 90° (eddy currents in a permeable, plane slab have 45° average phase angle). Such eddy currents can give an unusual impedance Z( f), and can raise the real part of the head impedance (‖Z‖cos θ) an order of magnitude higher than the dc resistance, and thereby similarly raise the mean‐square thermal noise from the head. Magnetic field formulas from the four‐region eddy current equations are used to calculate this impedance and the excess noise factor.

Wise drives [hard disk drive]

In this paper, the trench media can produce significant playback signals, since the maximum trench depth is comparable to the bit size a lithographic minimum feature size requirement. By DC magnetizing the trenches, their signal is a repeatable signal polarity pulse (bit writing must not switch the trench media).