초록 ▼

A computer implemented method for providing homogeneous recovery in a redundant memory system. The method includes receiving a notification that a memory channel has failed, where the memory channel is one of a plurality of memory channels in a memory system. New operations are blocked from starting

A computer implemented method for providing homogeneous recovery in a redundant memory system. The method includes receiving a notification that a memory channel has failed, where the memory channel is one of a plurality of memory channels in a memory system. New operations are blocked from starting on the memory channels in response to the notification, and any pending operations on the memory channels are completed in response to the notification. A recovery operation is performed on the memory channels in response to the completing. The new operations are started on at least a first subset of the memory channels in response to the recovery operation completing. The memory system is configured to operate with the first subset of the memory channels.

대표청구항 ▼

1. A computer implemented method for performing recovery, the method comprising: receiving a notification that a memory channel has failed, the memory channel one of a plurality of memory channels in a memory system;preventing new operations from starting on the memory channels based on the notifica

1. A computer implemented method for performing recovery, the method comprising: receiving a notification that a memory channel has failed, the memory channel one of a plurality of memory channels in a memory system;preventing new operations from starting on the memory channels based on the notification;shutting down the failing memory channel and ignoring any pending stores and fetches in the failing memory channel;based on shutting down the failing memory channel, completing any in-progress fetches only on a portion of the memory channels, the portion of the memory channels consisting of non-failing channels;performing a recovery operation on the memory channels based on the completing of any in-progress fetches, the recovery operation comprising resetting the memory channels and performing data calibration on at least a second subset of the memory channels in the memory system, wherein any other memory channels in the memory system that are not in the second subset are idle during the performing of the data calibration;retrying any pending stores that were issued prior to receiving notification of the failing memory channel after performing the recovery operation; andallowing the new operations to start on at least a first subset of the memory channels based on completion of the recovery operation, the memory system configured to operate with the first subset of the memory channels. 2. The method of claim 1, wherein there are five memory channels in the memory system, the memory system is capable of operating with any four of the five memory channels, and the first subset includes four of the memory channels. 3. The method of claim 1, further comprising starting the new operations on all of the memory channels in the memory system. 4. The method of claim 1, the recovery operation further comprising performing clock calibration on at least a third subset of the memory channels in the memory system while any other memory channels in the memory system that are not in the third subset are idle. 5. The method of claim 4, the recovery operation further comprising transmitting a failure alert to a memory controller. 6. The method of claim 1, the recovery operation further comprising performing lane repair on the failing memory channel.