Computing system with data protection mechanism with soft information and method of operation thereof
A computing system includes: a data block including a data; a storage engine, coupled to the data block, configured to process data, as hard information or soft information, through channels including a failed channel and a remaining channel, calculate an aggregated output from a hard decision from the remaining channel, calculate a selected magnitude from a magnitude from the remaining channel with an error detected, calculate an extrinsic soft information based on the aggregated output and the selected magnitude, and decode the failed channel with a scaled soft metric based on the extrinsic soft information.
1. A computing system comprising:
a data block including a data;
a storage engine, coupled to the data block, configured to:
process the data, as hard information or soft information, through channels including a failed channel and remaining channels each including a different redundant array of independent disks (RAID) stripe of the data,
calculate an aggregated output from a hard decision from the remaining channels,
calculate a selected magnitude from a magnitude from the remaining channels with an error detected by determining a minimum log likelihood ratio (LLR) of the remaining channels as the magnitude,
calculate an extrinsic soft information based on the aggregated output and the selected magnitude, and
decode the failed channel with a scaled soft metric based on the extrinsic soft information; and
a host interface bus, coupled to the storage engine, configured to transfer the data including transferring the data corrected from the failed channel and the data from the remaining channels.
2. The system as claimed in claim 1 wherein the storage engine is further configured to calculate the scaled soft metric with a soft metric, based on the hard information or the soft information, of the failed channel.
3. The system as claimed in claim 1 wherein the storage engine is further configured to calculate the scaled soft metric with a decoded output of the failed channel.
4. The system as claimed in claim 1 wherein the storage engine is further configured to calculate a decoded output of the failed channel based on the scaled soft metric.
5. The system as claimed in claim 1 wherein the storage engine is further configured to decoding a further channel with information from the failed channel successfully decoded.
6. The system as claimed in claim 1 wherein the storage engine is further configured to calculate the extrinsic soft information based on combining the aggregated output as a sign and the selected magnitude.
7. The system as claimed in claim 1 wherein the storage engine is further configured to calculate the scaled soft metric based on the extrinsic soft information and a soft metric of the failed channel.
8. The system as claimed in claim 1 wherein the storage engine is further configured to calculate the selected magnitude based on selecting a minimum from the magnitude from the remaining channel with the error detected.
9. The system as claimed in claim 1 wherein the storage engine is further configured to decode the failed channel with a sector redundancy.
10. The system as claimed in claim 1 wherein the storage engine is further configured to decode the failed channel with a first protection.
11. A method of operation of a computing system comprising:
processing data, as hard information or soft information, through channels including a failed channel and remaining channels each including a different redundant array of independent disks (RAID) stripe of the data;
calculating an aggregated output from a hard decision from the remaining channels;
calculating a selected magnitude from a magnitude from the remaining channels with an error detected by determining a minimum log likelihood ratio (LLR) of the remaining channels as the magnitude;
calculating an extrinsic soft information based on the aggregated output and the selected magnitude;
decoding the failed channel with a scaled soft metric based on the extrinsic soft information; and
transferring the data corrected from the failed channel and the data from the remaining channels through a host interface bus.
12. The method as claimed in claim 11 wherein decoding the failed channel includes calculating the scaled soft metric with a soft metric, based on the hard information or the soft information, of the failed channel.
13. The method as claimed in claim 11 wherein decoding the failed channel includes calculating the scaled soft metric with a decoded output of the failed channel.
14. The method as claimed in claim 11 wherein decoding the failed channel includes calculating a decoded output based on the scaled soft metric.
15. The method as claimed in claim 11 further comprising decoding a further channel with information from the failed channel successfully decoded.
16. The method as claimed in claim 11 wherein calculating the extrinsic soft information includes combining the aggregated output as a sign and the selected magnitude.
17. The method as claimed in claim 11 further comprising calculating the scaled soft metric based on the extrinsic soft information and a soft metric of the failed channel.
18. The method as claimed in claim 11 wherein calculating the selected magnitude includes selecting a minimum from the magnitude from the remaining channel with the error detected.
19. The method as claimed in claim 11 wherein decoding the failed channel includes decoding with a sector redundancy.
20. The method as claimed in claim 11 wherein decoding the failed channel includes decoding with a first protection.
21. A non-transitory computer readable medium including instructions for execution, the medium comprising:
processing data, as hard information or soft information, through channels including a failed channel and remaining channels each including a different redundant array of independent disks (RAID) stripe of the data;
calculating an aggregated output from a hard decision from the remaining channels;
calculating a selected magnitude from a magnitude from the remaining channels with an error detected by determining a minimum log likelihood ratio (LLR) of the remaining channels as the magnitude;
calculating an extrinsic soft information based on the aggregated output and the selected magnitude;
decoding the failed channel with a scaled soft metric based on the extrinsic soft information; and
transferring the data corrected from the failed channel and the data from the remaining channels through a host interface bus.
22. The medium as claimed in claim 21 wherein decoding the failed channel includes calculating the scaled soft metric with a soft metric, based on the hard information or the soft information, of the failed channel.
23. The medium as claimed in claim 21 wherein decoding the failed channel includes calculating the scaled soft metric with a decoded output of the failed channel.
24. The medium as claimed in claim 21 wherein decoding the failed channel includes calculating a decoded output based on the scaled soft metric.
25. The medium as claimed in claim 21 further comprising decoding a further channel with information from the failed channel successfully decoded.
26. The medium as claimed in claim 21 wherein calculating the extrinsic soft information includes combining the aggregated output as a sign and the selected magnitude.
27. The medium as claimed in claim 21 further comprising calculating the scaled soft metric based on the extrinsic soft information and a soft metric of the failed channel.
28. The medium as claimed in claim 21 wherein calculating the selected magnitude includes selecting a minimum from the magnitude from the remaining channel with the error detected.
29. The medium as claimed in claim 21 wherein decoding the failed channel includes decoding with a sector redundancy.
30. The medium as claimed in claim 21 wherein decoding the failed channel includes decoding with a first protection.