Track-dependent decoding

Patent metadata

Field	Value
Publication number	US-9412410-B1
Application number	US-201514946580-A
Country	US
Kind code	B1
Filing date	Nov 19, 2015
Priority date	Nov 19, 2015
Publication date	Aug 9, 2016
Grant date	Aug 9, 2016

Abstract

In one embodiment, a tape drive includes a magnetic head having a plurality of read sensors, each read sensor being configured to read data simultaneously, a controller, and logic integrated with and/or executable by the controller. The logic is configured to read, using the plurality of read sensors, encoded data from a plurality of tracks of a magnetic tape medium simultaneously. The logic is also configured to perform track-dependent erasure decoding on the encoded data based on detection of one or more time-varying signal quality issues associated with at least one of the plurality of tracks read simultaneously from the magnetic tape medium.

First claim

What is claimed is:

1. A tape drive, comprising:
a magnetic head having a plurality of read sensors, each read sensor being configured to read data simultaneously; and
a controller and logic integrated with and/or executable by the controller, the logic being configured to:
read, using the plurality of read sensors, encoded data from a plurality of tracks of a magnetic tape medium simultaneously; and
perform track-dependent erasure decoding on the encoded data based on detection of one or more time-varying signal quality issues associated with at least one of the plurality of tracks read simultaneously from the magnetic tape medium.

2. The tape drive as recited in claim 1 , wherein the one or more time-varying signal quality issues is determined based on side information about reliability of detected bytes within C1 codewords of each simultaneously-read track.

3. The tape drive as recited in claim 2 , wherein the side information comprises read or write channel performance of at least one read or write channel falling below a predetermined threshold based on statistics monitored by firmware of the tape drive.

4. The tape drive as recited in claim 3 , wherein the statistics monitored for the read channel include exponentially averaged mean squared error (MSE) or signal-to-noise ratio (SNR) for each simultaneously read track.

5. The tape drive as recited in claim 2 , wherein the side information comprises C1 decoder performance falling below a predetermined threshold based on statistics accumulated for the C1 decoder during C1 decoding of the encoded data.

6. The tape drive as recited in claim 5 , wherein the statistics accumulated for the C1 decoder comprise a number of uncorrectable C1 codewords for each track, and wherein the C1 decoder determines an uncorrectable C1 codeword in response to more than a correctable number of C1 byte errors being present in the C1 codeword.

7. The tape drive as recited in claim 6 , wherein the C1 decoder performance falls below the predetermined threshold for a specific track in response to detection of at least one uncorrectable C1 codeword read from the specific track.

8. The tape drive as recited in claim 6 , wherein the C1 decoder performance falls below the predetermined threshold for a specific track in response to detection of more than a predetermined number (N) of uncorrectable C1 codewords within a preset number (M) of most recently decoded C1 codewords for the specific track.

9. The tape drive as recited in claim 2 , wherein the side information comprises a number of run-length limited (RLL) error detection flags per C1 codeword, and wherein track-dependent erasure decoding is performed on the encoded data for a specific track in response to a determination of more than an allowable number of RLL error detection flags in a single C1 codeword read from the specific track.

10. The tape drive as recited in claim 1 , wherein the logic configured to perform track-dependent erasure decoding on the encoded data is configured to:
calculate an erasure coefficient for each byte in a particular C1 codeword read using a specific track, each erasure coefficient being a measure of a reliability of an associated decoded byte;
sum all erasure coefficients for the particular C1 codeword to produce a sum of erasure coefficients;
determine whether the sum of erasure coefficients is greater than a predetermined configurable coefficient threshold; and
perform track-dependent erasure decoding on the encoded data for the specific track in response to a determination that the sum is greater than the predetermined configurable threshold.

11. The tape drive as recited in claim 1 , wherein the logic configured to perform track-dependent erasure decoding on the encoded data is configured to:
perform C1 decoding of the encoded data to produce a plurality of C1 codewords;
determine a probability that any of the plurality of C1 codewords individually includes a number of C1 byte errors that exceeds a predetermined threshold of C1 byte errors;
enable erasure pointers for C2 decoding in response to a determination that the probability is greater than a threshold probability;
insert an erasure pointer in place of each C1 codeword of the plurality of C1 codewords for which the probability is greater than the threshold probability to produce a plurality of erasure-enabled C1 codewords; and
perform C2 decoding on the plurality of erasure-enabled C1 codewords using C2 error-and-erasure decoding.

12. The tape drive as recited in claim 11 , wherein erasure pointers are enabled only on a set of tracks having a highest relative probability that a C1 codeword read from that track includes C1 byte errors exceeding the predetermined threshold of C1 byte errors.

13. A method, comprising:
reading, using a plurality of read sensors of a magnetic head, encoded data from a plurality of tracks of a magnetic tape medium simultaneously; and
performing track-dependent erasure decoding on the encoded data based on detection of one or more time-varying signal quality issues associated with at least one of the plurality of tracks read simultaneously from the magnetic tape medium.

14. The method as recited in claim 13 , wherein the performing track-dependent erasure decoding on the encoded data comprises:
performing C1 decoding of the encoded data to produce a plurality of C1 codewords;
determining a probability that any of the plurality of C1 codewords individually includes a number of C1 byte errors that exceeds a predetermined threshold of C1 byte errors;
enabling erasure pointers for C2 decoding in response to a determination that the probability is greater than a threshold probability;
inserting an erasure pointer in place of each C1 codeword of the plurality of C1 codewords for which the probability is greater than the threshold probability to produce a plurality of erasure-enabled C1 codewords; and
performing C2 decoding on the plurality of erasure-enabled C1 codewords using C2 error-and-erasure decoding.

15. The method as recited in claim 14 , wherein erasure pointers are enabled only on a set of tracks having a highest relative probability that a C1 codeword read from that track includes C1 byte errors exceeding the predetermined threshold of C1 byte errors.

16. The method as recited in claim 13 , wherein the one or more time-varying signal quality issues is determined based on side information about reliability of detected bytes within C1 codewords of each simultaneously-read track.

17. The method as recited in claim 16 , wherein the side information is selected from a group consisting of:
read channel performance of at least one read channel falling below a predetermined threshold based on read channel statistics monitored by firmware;
write channel performance of at least one write channel falling below a predetermined threshold based on write channel statistics monitored by the firmware; and
C1 decoder performance falling below a predetermined threshold based on statistics accumulated for the C1 decoder during C1 decoding of the encoded data,
wherein the read channel statistics include exponentially averaged mean squared error (MSE) or signal-to-noise ratio (SNR) for each simultaneously read track,
wherein the statistics accumulated for the C1 decoder comprise a number of uncorrectable C1 codewords for each track, and
wherein the C1 decoder determines an uncorrectable C1 codeword in response to more than a correctable number of C1 byte errors being present in the C1 codeword.

18. The method as recited in claim 17 , wherein the C

Assignees

• IBM

Inventors

• Bentley Steven R
• Cideciyan Roy D
• Furrer Simeon
• Tanaka Keisuke

Classifications

• G11B5/00826 Primary

  comprising a plurality of single poles or gaps or groups thereof operative at the same time · CPC title

• G11B5/00813

  magnetic tapes · CPC title

• G11B5/29

  Structure or manufacture of unitary devices formed of plural heads for more than one track {(G11B5/33, G11B5/49 and subgroups take precedence; in thin film structure G11B5/31)} · CPC title

• G11B20/10388 Primary

  control of the read or write heads, e.g. tracking errors, defocus or tilt compensation · CPC title

• G11B20/1833

  by adding special lists or symbols to the coded information (G11B20/1806, G11B20/1866 take precedence) · CPC title