Bank-level fault management in a memory system

1. A method for bank-level fault management in a memory system having a plurality of ranks, each rank comprising a plurality of memory devices each having a plurality of banks, the method comprising:

detecting a first error in a first bank number of a first memory device of a rank;

marking the first bank number of the first memory device with a bank-level chip mark, the bank-level chip mark isolating declaration of an error condition to the first bank number;

detecting a second error in the first bank number of a second memory device of the rank;

based on determining that a non-faulty bank is available at a second bank number, steering access requests for the first bank number of the second memory device to the non-faulty bank having the second bank number; and

performing a bank-level fault management action based on the bank-level chip mark to accommodate the error condition by correcting the first error using an error-correcting code decoder.

2. The method of claim 1 , further comprising:

receiving an access request for the second bank number; and

using the error-correcting code decoder to generate recovery data associated with the non-faulty bank having the second bank number after being overwritten by data associated with the first bank number of the second memory device.

3. The method of claim 1 , wherein the non-faulty bank having the second bank number is located in the second memory device.

4. The method of claim 1 , wherein the non-faulty bank is located on a second rank.

5. The method of claim 4 , wherein the rank and the second rank are located on separate memory modules coupled to a memory buffer device that controls bank steering between the rank and the second rank.

6. The method of claim 1 , further comprising:

based on detecting a subsequent error condition at the first bank number comprising the bank-level chip mark, marking the first bank number as a faulty bank; and

supporting address range de-allocation for an address space of the faulty bank.

7. The method of claim 1 , further comprising:

overwriting in-use data storage of the second bank number with data associated with the first bank number of the second memory device based on determining that a non-faulty bank is available at a second bank number.

8. The method of claim 1 , wherein the bank-level fault management action is performed by accessing the second bank number to accommodate the second error and correcting the first error using the error-correcting code decoder in combination with accessing the first bank number and the second bank number.

9. A computer program product for bank-level fault management in a memory system having a plurality of ranks, each rank comprising a plurality of memory devices each having a plurality of banks, the computer program product comprising:

a computer readable storage medium having program instructions embodied therewith, the program instructions readable by a processing circuit to cause the processing circuit to perform a method comprising:

detecting a first error in a first bank number of a first memory device of a rank;

marking the first bank number of the first memory device with a bank-level chip mark, the bank-level chip mark isolating declaration of an error condition to the first bank number;

detecting a second error in the first bank number of a second memory device of the rank;

based on determining that a non-faulty bank is available at a second bank number, steering access requests for the first bank number of the second memory device to the non-faulty bank having the second bank number; and

performing a bank-level fault management action based on the bank-level chip mark to accommodate the error condition by correcting the first error using an error-correcting code decoder.

10. The computer program product of claim 9 , wherein the program instructions are further configured to cause the processing circuit to perform the method comprising:

receiving an access request for the second bank number; and

using the error-correcting code decoder to generate recovery data associated with the non-faulty bank having the second bank number after being overwritten by data associated with the first bank number of the second memory device.

11. The computer program product of claim 9 , wherein the non-faulty bank having the second bank number is located in the second memory device.

12. The computer program product of claim 9 , wherein the non-faulty bank is located on a second rank.

13. The computer program product of claim 12 , wherein the rank and the second rank are located on separate memory modules coupled to a memory buffer device that controls bank steering between the rank and the second rank.

14. The computer program product of claim 9 , wherein the program instructions are further configured to cause the processing circuit to perform the method comprising:

based on detecting a subsequent error condition at the first bank number comprising the bank-level chip mark, marking the first bank number as a faulty bank; and

supporting address range de-allocation for an address space of the faulty bank.

15. The computer program product of claim 9 , wherein the program instructions are further configured to cause the processing circuit to perform the method comprising:

overwriting in-use data storage of the second bank number with data associated with the first bank number of the second memory device based on determining that a non-faulty bank is available at a second bank number.

16. The computer program product of claim 9 , wherein the bank-level fault management action is performed by accessing the second bank number to accommodate the second error and correcting the first error using the error-correcting code decoder in combination with accessing the first bank number and the second bank number.