Distributed exception handling in solid state drives
Systems and methods described herein synchronize events between various components of storage device during the processing of an exception (i.e., an internal error). The storage device can have a plurality of processors which may each coordinate operations on various domains of storage device processing tasks. An exception occurring in one domain may require input and coordination from other domains within the storage device. Each exception may have a list of predetermined steps needed for completion which are coordinated via a series of sync points placed between exception action clusters which perform a series of specific operations until data or processing from another domain is needed to continue processing. The sync points can be utilized to halt processing in one domain until the other domains are in sync and complete one or more exception action operations. In this way, a streamlined and predictable synchronization between domains may occur during an exception.
1. A device comprising:
a memory array comprising a plurality of memory devices;
a plurality of processors wherein each processor is configured to operate within one of a plurality of domains; and
exception handling logic configured to:
determine an exception occurring within one of the plurality of domains;
determine a plurality of domains associated with the exception;
generate exception data;
communicate the generated exception data to the plurality of associated domains;
establish communication with an exception scheduler; and
process the exception, wherein processing the exception comprises:
generating a first exception action cluster based on the exception data, wherein the first exception action cluster is a processed within a first domain;
generating a second exception action cluster based on the exception data, wherein the second exception action cluster is processed within a second domain;
determining a first sync point configured to pause processing in the first domain upon completion of the first exception action cluster and to resume processing when first completion requirements are met;
determining a second sync point configured to pause processing in the second domain upon completion of the second exception action cluster, and to resume processing when second completion requirements are met;
establishing exception action state data based on the generated exception action clusters;
processing the first exception action cluster and pausing at the first sync point;
processing the second exception action cluster and pausing at the second sync point, wherein:
the exception scheduler releases the first domain to continue processing when the first completion requirements of the first sync point are met; and
the exception scheduler releases the second domain to continue processing when the completion requirements of the second sync point are met.
2. The device of claim 1 , wherein a domain within the plurality of domains is selected to coordinate the processing of the exception.
3. The device of claim 2 , wherein the domain associated with the determination of the exception is selected as the coordinating domain.
4. The device of claim 1 , wherein the sync point requirement comprises one or more exception actions to be processed by at least one associated domain.
5. The device of claim 4 , wherein the exception scheduler monitors exception actions processed by all associated domains.
6. The device of claim 5 , wherein the exception action processing is monitored by determining changes in exception action state data.
7. The device of claim 6 , wherein the exception action state data is a bit vector.
8. A method of processing exceptions, comprising:
determining an exception occurring within one of a plurality of domains wherein each domain comprises at least one processor;
determining a set of one or more domains associated with the exception;
generating exception data comprising at least two or more exception action clusters for processing within each of the associated domains;
communicating the generated exception data to the associated domains;
establishing communication with an exception scheduler;
processing the exception, wherein processing the exception comprises:
generating a first exception action cluster based on the exception data, wherein the first exception action cluster is a processed within a first domain;
generating a second exception action cluster based on the exception data, wherein the second exception action cluster is processed within a second domain;
determining a first sync point configured to pause processing in the first domain upon completion of the first exception action cluster and to resume processing when first completion requirements are met;
determining a second sync point configured to pause processing in the second domain upon completion of the second exception action cluster, and to resume processing when second completion requirements are met;
establishing exception action state data based on the generated exception action clusters;
processing the first exception action cluster and pausing at the first sync point;
processing the second exception action cluster and pausing at the second sync point, wherein:
the exception scheduler configured to release the first domain to continue processing when the first completion requirements of the first sync point are met; and
the exception scheduler configured to release the second domain to continue processing when the completion requirements of the second sync point are met.
9. The method of claim 8 , wherein a notification from the exception scheduler indicates that the one or more required exception actions from the one or more associated domains have been completed.