Generation and use of system level defect tables for main memory
View Patent ↗Methods and apparatus for maintaining and utilizing system memory defect tables that store information identifying defective memory locations in memory modules. For some embodiments, the defect tables may be utilized to identify and re-map defective memory locations to non-defective replacement (spare) memory locations as an alternative to replacing an entire memory module. For some embodiments, some portion of the overall capacity of the memory module may be allocated for such replacement.
1. A method for accessing system memory having one or more memory modules, comprising:
detecting defective memory locations of the memory modules;
storing information identifying the defective memory locations in one or more system memory defect tables; and
mapping the defective memory locations identified in the system memory defect tables to replacement memory locations, wherein the step of detecting comprises:
reducing a refresh rate for refreshing rows of memory cells below an operational refresh rate specified by a manufacture of the memory modules;
identifying as marginal, memory locations of the memory modules having memory cells that fail to maintain data at the reduced refresh rate; and
storing information identifying the marginal memory locations in the system memory defect tables.
2. The method of claim 1 , further comprising maintaining the information in the system memory defect tables across reset cycles.
3. The method of claim 2 , wherein maintaining the information in the system memory defect tables across reset cycles comprises storing the system memory defect tables in non-volatile memory.
4. The method of claim 3 , wherein storing the system memory defect tables in non-volatile memory comprises storing the system memory defect tables in non-volatile memory located on the memory modules.
5. The method of claim 1 , wherein the storing and mapping are performed by operating system code.
6. The method of claim 1 , further comprising, avoiding use of a memory module if the total number of defective locations detected thereon exceeds a predetermined threshold amount.
7. The method of claim 1 , wherein mapping the defective memory locations identified in the system memory defect tables to replacement memory locations comprises generating page table entries that map virtual addresses to physical addresses of the replacement memory locations.
8. A method for identifying marginal dynamic memory cells in one or more memory modules of system memory, comprising:
a) reducing a refresh rate for refreshing rows of memory cells in the memory cells to a level below an operational refresh rate specified by a manufacturer of the memory modules;
b) identifying as marginal, memory locations of the memory modules having memory cells that fail to maintain data at the reduced refresh rate;
c) storing information identifying the marginal memory locations in one or more system memory defect tables; and
d) mapping the marginal memory locations to replacement memory locations.
9. The method of claim 8 , comprising:
repeating the operations of a) and b) to incrementally reduce the refresh rate and detecting marginal memory locations at incrementally reduced refresh rates.
10. The method of claim 8 , wherein the operations a)-d) are performed by an operating system after a system reset.
11. The method of claim 8 , further comprising maintaining information in the system memory defect tables across reset cycles.
12. A system, comprising:
one or more processing devices;
system memory addressable by the processing devices, the system memory including one or more memory modules;
one or more system memory defect tables; and
a component executable by one or more of the processing devices to detect defective memory locations of the memory modules, store information identifying the defective memory locations in one or more system memory defect tables, and map the defective memory locations identified in the system memory defect tables to replacement memory locations, the component being configured to identify memory locations as defective by reducing a refresh rate of the memory modules and storing information identifying defective memory locations having cells unable to maintain data at reduced refresh rates in the system memory defect tables including reducing the refresh rate to a level below an operational refresh rate specified by a manufacturer of the memory modules.
13. The system of claim 12 , wherein information in the system memory defect tables is maintained across reset cycles of the system.
14. The system of claim 12 , wherein the system memory defect tables are stored in non-volatile memory.
15. The system of claim 14 , wherein the system memory defect tables are stored in non-volatile memory located on the memory modules.
16. The system of claim 15 , wherein the system memory defect tables are stored in non-volatile memory located on the memory modules that are also used for serial presence detect (SPD) purposes.
17. The system of claim 12 , wherein the component is configured to map the defective memory locations identified in the system memory defect tables to replacement memory locations by generating page table entries that map virtual addresses to physical addresses of the replacement memory locations.
18. The system of claim 12 , wherein the component is configured to map defective memory locations of one memory module to replacement memory locations of another memory module.