Hybrid memory system with configurable error thresholds and failure analysis capability

A hybrid memory system comprising:

• a volatile memory (VM) subsystem;
• a non-volatile memory (NVM) subsystem;
• a hybrid memory controller including (i) a NVM controller coupled to the NVM subsystem, (ii) a communication controller, and (iii) a register set coupled to the NVM controller and to the communication controller, wherein the register set includes a first threshold register;
• and
• a VM controller through which the hybrid memory controller is coupled to the volatile memory subsystem, wherein
• the hybrid memory controller is coupled to a host computer system through the communication controller via a host interface,
• the volatile memory subsystem is coupled to the host computer system by way of the VM controller via the host interface, and
• the hybrid memory controller is operable to manage exchange of data between the nonvolatile memory subsystem and the volatile memory subsystem, and/or between the non-volatile memory subsystem and the host computer system, by:
• setting the first threshold register with a first threshold value, wherein the first threshold value corresponds to a first number of correctable symbol errors in a portion of the NVM subsystem, the portion of the NVM subsystem includes a first number of symbols, and the first number of correctable symbol errors is less than the first number of symbols, wherein a symbol is specified by a number of bits, and the first threshold register comprises a portion of the register set, and wherein the NVM controller is operable to communicate with the register set and the NVM subsystem;
• detecting a second number of correctable symbol errors in the portion of the NVM subsystem;
• determining a first symbol error value based on the detected second number of correctable symbol errors;
• and
• if the first symbol error value matches or exceeds the first threshold value, performing one or more first remediation actions,
• wherein the first number of correctable symbol errors is less than a maximum number of symbol errors that can be corrected using an error correction algorithm, such that setting the first threshold register with the threshold value corresponding to the first number of correctable symbol errors achieves a selectable error tolerance level.

A method for configuring fault tolerance in a hybrid memory system comprising a nonvolatile memory (NVM) subsystem, the method comprising:

• operating a communication controller (i) to receive configuration information from a user or a host system and to write one or more values to a register set using the configuration information, and (ii) to read a value from the register set and to deliver the value to the user or the host system, wherein the one or more values include one or more threshold values, wherein the register set comprising a first threshold register;
• managing two-way communication between the communication controller and the host system using a communication protocol via an electrical interface;
• coupling a nonvolatile memory controller (NVM controller) to the register set and to the NVM subsystem;
• setting the first threshold register with a first threshold value corresponding to a first number of correctable symbol errors in a portion of the NVM subsystem, wherein the portion of the NVM subsystem includes a first number of symbols, wherein the first number of correctable symbol errors is less than the first number of symbols, wherein a symbol is specified by a number of bits, wherein the NVM controller is operable to communicate with the register set and the NVM subsystem;
• detecting a second number of correctable symbol errors in the portion of the NVM subsystem based on an error criterion;
• determining a first symbol error value based on the detected second number of correctable symbol errors;
• and
• if the first symbol error value matches or exceeds the first threshold value, performing one or more first remediation actions,
• wherein the first number of correctable symbol errors is less than a maximum number of symbol errors that can be corrected using an error correction algorithm, such that setting the first threshold register with the threshold value corresponding to the first number of correctable symbol errors achieves a selectable error tolerance level.

A non-volatile memory (NVM) system comprising:

• one or more NVM elements;
• a NVM controller coupled to (i) the one or more NVM elements, (ii) a register set, and (iii) a host system via a communication interface, the NVM controller communicates with the host system by way of a messaging protocol and the communication interface, wherein the register set includes a first threshold register, and the NVM controller is operable to receive messaging information for setting values in the register set, the NVM controller operable to:
• set the first threshold register with a first threshold value, wherein the first threshold value corresponds to a first number of correctable symbol errors in a portion of the one or more NVM elements, wherein the NVM controller is operable to communicate with the register set and the one or more NVM elements;
• detect a second number of correctable symbol errors in the portion of the one or more NVM elements based on an error criterion;
• determine a first symbol error value based on the detected second number of correctable symbol errors;
• and
• if the first symbol error value matches or exceeds the first threshold value, perform one or more first remediation actions,
• wherein the first number of correctable symbol errors is less than a maximum number of symbol errors that can be corrected using an error correction algorithm, such that setting the first threshold register with the threshold value corresponding to the first number of correctable symbol errors achieves a selectable error tolerance level.

A method for indicating extent of copying of volatile memory data into a non-volatile memory (NVM) subsystem, comprising:

• determining a portion of the NVM subsystem necessary to write the volatile memory data from a volatile memory subsystem into the NVM subsystem;
• erasing the portion of the NVM subsystem to conduct the writing of the volatile memory data into the portion of the NVM subsystem;
• setting a first threshold register with a first threshold value, the first threshold value corresponding to a first number of correctable symbol errors in the portion of the NVM subsystem, wherein the first threshold register comprises a portion of a register set coupled to an NVM controller, wherein the NVM controller is operable to communicate with the register set and the NVM subsystem;
• detecting a second number of correctable symbol errors in the portion of the NVM subsystem;
• determining a first symbol error value based on the detected second number of correctable symbol errors;
• issuing a warning to a host system if the first symbol error value matches or exceeds the first threshold value;
• until the first symbol error value reaches a second threshold value, writing the volatile memory data into the portion of the NVM subsystem, wherein the second threshold value is greater than the first threshold value;
• determining an amount of erased NVM that has remained erased after the writing of the volatile memory data into the portion of the NVM subsystem;
• and
• indicating to the host system an extent of the writing of the volatile memory data into the NVM subsystem if the first symbol error value reaches a—the second threshold value,
• wherein the first number of correctable symbol errors is less than a maximum number of symbol errors that can be corrected using an error correction algorithm, such that setting the first threshold register with the threshold value corresponding to the first number of correctable symbol errors achieves a selectable error tolerance level.

A hybrid memory system comprising:

• a volatile memory subsystem;
• a non-volatile memory (NVM) subsystem;
• and
• a hybrid memory controller operable to indicate extent of copying of volatile memory data into the non-volatile memory (NVM) subsystem by:
• determining a portion of the NVM subsystem necessary to write the volatile memory data from the volatile memory subsystem into the NVM subsystem;
• erasing the portion of the NVM subsystem to conduct the writing of the volatile memory data into the portion of the NVM subsystem;
• setting a first threshold register with a first threshold value, wherein the first threshold value corresponds to a first number of correctable symbol errors in the portion of the NVM subsystem, the first threshold register comprises a portion of a register set coupled to an NVM controller, wherein the NVM controller is operable to communicate with the register set and the NVM subsystem;
• detecting a second number of correctable symbol errors in the portion of the NVM subsystem;
• determining a first symbol error value based on the detected second number of correctable symbol errors;
• issuing a warning to a host system if the first symbol error value matches or exceeds the first threshold value;
• until the first symbol error value reaches a second threshold value, writing the volatile memory data into the portion of the NVM subsystem, wherein the second threshold value is greater than the first threshold value and relates to a third number of correctable symbol errors in the portion of the NVM subsystem;
• determining an amount of erased NVM that has remained erased after the writing of the volatile memory data into the portion of the NVM subsystem;
• and
• indicating to the host system an extent of the writing of the volatile memory data into the NVM subsystem if the first symbol error value reaches a—the second threshold value,
• wherein the first number of correctable symbol errors is less than a maximum number of symbol errors that can be corrected using an error correction algorithm, such that setting the first threshold register with the threshold value corresponding to the first number of correctable symbol errors achieves a selectable error tolerance level.