News Column

Researchers Submit Patent Application, "Reconstructive Error Recovery Procedure (Erp) Using Reserved Buffer", for Approval

June 3, 2014



By a News Reporter-Staff News Editor at Information Technology Newsweekly -- From Washington, D.C., VerticalNews journalists report that a patent application by the inventors Katagiri, Takashi (Yokohama-shi, JP); Nylander-Hill, Pamela R. (Tucson, AZ), filed on November 14, 2012, was made available online on May 22, 2014.

The patent's assignee is International Business Machines Corporation.

News editors obtained the following quote from the background information supplied by the inventors: "The present invention relates to data storage, and more particularly, to reading data from tape using a reconstructive error recovery procedure (ERP) to reduce backhitches during error burst scenarios.

"Tape and optical storage devices use very powerful error correction codes, such as product codes or concatenated codes, in conjunction with interleaving to provide a very high degree of data integrity. These error correction schemes typically use two error correction codes (ECCs) as component codes. Two important burst-error performance measures for tape storage systems protected by these schemes are: 1) lateral width of an erroneous stripe which is still capable of being corrected (this is also known as 'broken track correction' capability), and 2) longitudinal width of an erroneous stripe that is still capable of being corrected. A 'broken' track generally refers to a track that cannot be read correctly due to a problem on the media itself and/or a problem with the readback channel, e.g., as a channel that does not detect data correctly because of alignment or some systematic problem with the head.

"When a tape drive reads data from a tape, or when a tape drive writes data to a tape, a unit of data that is read or written is referred to as a 'data set.' The data set is encoded using interleaved sets of codewords that are organized into an ECC-encoded matrix of size M bytes.times.N bytes (M.times.N) and then written to tape as shown in FIG. 1, according to the prior art. There are two levels of encoding within this matrix 150. The first level of encoding utilizes the matrix rows 102. Each row 102 of the matrix contains C1-ECC row parity 106, which adds p-bytes of C1-ECC to the n-bytes of user data (e.g., N=n+p bytes). The second level of encoding, C2-ECC column parity 108, adds q-bytes of C2-ECC to each matrix column 104. For example, if q=12, then adding 12 bytes of C2-ECC would add 12 rows to the matrix 150 (e.g., M=m+q bytes).

"When the data set is read from the tape in a high error rate condition, C1/C2 ECC is not capable of correcting the read data. For example, in some approaches, C1-encoding is capable of correcting 10 bytes of error, and C2-encoding is capable of correcting 20 bytes of error. If the error bytes exceed this correction power, then data cannot be read from the tape. In this scenario, the tape drive will then attempt ERP to read the data set from the tape again with a different hardware setting (e.g., changing the tape speed). ERP repeats until C1/C2-encoding is able to correct the data or until the ERP retry count exceeds a threshold. If the retry count exceeds the threshold, then the tape drive will report a permanent error for the read operation.

"There are several problems with this conventional approach. First, if the error rate is consistently high, C1 and C2 cannot correct the data and the tape drive fails to read the data set, which is extremely undesirable. Second, in areas of tape where the error rate is high due to media damage, marginal writing, data written in older formats, etc., the drive may fail to read. Third, extended recovery involves multiple backhitches necessary to reread data from the tape which degrades host performance and can also further damage media.

"Accordingly, it would be beneficial to have a data recovery procedure that increases the efficiency of reading stored data from the tape."

As a supplement to the background information on this patent application, VerticalNews correspondents also obtained the inventors' summary information for this patent application: "In one embodiment, a system for reading data from a medium includes logic adapted for reading a data set from a medium one or more times, the data set including a plurality of portions which combine together to wholly form the data set, wherein during each read of the data set, settings are changed in an attempt to better read the data set from the medium, logic adapted for storing all portions of the data set to a reserved data buffer after a first reading of the data set from the medium, logic adapted for storing one or more of the portions of the data set to the reserved data buffer after subsequent readings of the data set from the medium when the one or more portions are correctable using C1-error correction code (ECC), logic adapted for aggregating the one or more portions of the data set in the reserved data buffer to form an assembled data set, wherein each of the one or more portions are correctable using C1-ECC, logic adapted for determining whether C2-ECC is capable of correcting all errors in the assembled data set, logic adapted for correcting any remaining errors in the assembled data set using C2-ECC to form a reconstructed data set and sending the reconstructed data set to a host when C2-ECC is capable of correcting all errors in the assembled data set, and logic adapted for rereading the data set from the medium using a different setting in an error recovery procedure (ERP) when an error in the assembled data set is not correctable using C2-ECC.

"In another embodiment, a tape drive includes a data buffer including a reserved data buffer, logic adapted for reading a data set from a medium repeatedly using different settings until either: a reconstructed data set is sent to a host and/or stored, or a maximum number of rereads has been reached, logic adapted for, after each reading of the data set, storing each row to the reserved data buffer that has no errors or errors in the row are correctable using C1-ECC unless a matching row already exists in the reserved data buffer that has fewer corrected errors therein, logic adapted for assembling the data set from the rows stored in the reserved data buffer when all rows are present in the reserved data buffer to form an assembled data set, logic adapted for correcting any remaining errors in the assembled data set using C2-ECC to form the reconstructed data set, and logic adapted for sending the reconstructed data set to the host and/or storing the reconstructed data set.

"According to another embodiment, a method for reading data from a medium includes reading a data set from a medium one or more times, the data set including a plurality of portions which combine together to wholly form the data set, wherein during each read of the data set, settings are changed in an attempt to better read the data set from the medium, storing all portions of the data set to a reserved data buffer after a first reading of the data set from the medium, storing one or more of the portions of the data set to the reserved data buffer after subsequent readings of the data set from the medium when the one or more portions are correctable using C1-ECC, aggregating the one or more portions of the data set in the reserved data buffer to form an assembled data set, wherein each of the one or more portions are correctable using C1-ECC, determining whether C2-ECC is capable of correcting all errors in the assembled data set, correcting any remaining errors in the assembled data set using C2-ECC to form a reconstructed data set and sending the reconstructed data set to a host when C2-ECC is capable of correcting all errors in the assembled data set, and rereading the data set from the medium using a different setting in an ERP when an error in the assembled data set is not correctable using C2-ECC.

"According to another embodiment, a method for reading data from a medium includes reading a data set from a medium repeatedly using different settings until either: a reconstructed data set is sent to a host and/or stored, or a maximum number of rereads has been reached, after each reading of the data set, storing each row to the reserved data buffer that has no errors or errors in the row are correctable using C1-ECC unless a matching row already exists in the reserved data buffer that has fewer corrected errors therein, assembling the data set from the rows stored in the reserved data buffer to form an assembled data set, correcting any remaining errors in the assembled data set using C2-ECC to form the reconstructed data set, and sending the reconstructed data set to the host and/or storing the reconstructed data set.

"Other aspects and embodiments of the present invention will become apparent from the following detailed description, which, when taken in conjunction with the drawings, illustrates by way of example the principles of the invention.

BRIEF DESCRIPTION OF THE SEVERAL VIEWS OF THE DRAWINGS

"FIG. 1 shows a data set matrix, according to the prior art.

"FIG. 2A illustrates a network storage system, according to one embodiment.

"FIG. 2B illustrates a simplified tape drive of a tape-based data storage system, according to one embodiment.

"FIG. 3 shows a method for reading data from a medium using a reconstructive error recovery procedure (ERP), according to one embodiment.

"FIG. 4 shows a method for reading data from a medium using a reconstructive ERP, according to one embodiment.

"FIG. 5 shows a method for reading data from a medium using a reconstructive ERP, according to one embodiment.

"FIG. 6 shows a method, according to one embodiment."

For additional information on this patent application, see: Katagiri, Takashi; Nylander-Hill, Pamela R. Reconstructive Error Recovery Procedure (Erp) Using Reserved Buffer. Filed November 14, 2012 and posted May 22, 2014. Patent URL: http://appft.uspto.gov/netacgi/nph-Parser?Sect1=PTO2&Sect2=HITOFF&u=%2Fnetahtml%2FPTO%2Fsearch-adv.html&r=386&p=8&f=G&l=50&d=PG01&S1=20140515.PD.&OS=PD/20140515&RS=PD/20140515

Keywords for this news article include: Information Technology, Information and Data Storage, International Business Machines Corporation.

Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2014, NewsRx LLC


For more stories covering the world of technology, please see HispanicBusiness' Tech Channel



Source: Information Technology Newsweekly


Story Tools






HispanicBusiness.com Facebook Linkedin Twitter RSS Feed Email Alerts & Newsletters