Systems, methods and apparatus for fabric delta merge operations to enhance NVMeoF stream writes

• US 10,664,396 B2
• Filed: 10/04/2017
• Issued: 05/26/2020
• Est. Priority Date: 10/04/2017
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Guim Bernat, Francesc, Doshi, Kshitij, Sen, Sujoy
• Primary Examiner(s): Mercado, Ramon A.
• Application Number:
  US15/724,311
• Publication Number:
  US 20190102299A1
• Time in Patent Office: 965 Days
• CPC Class Codes: G06F 12/0653 with centralised address assignment
• CPC Class Codes: G06F 12/0813 with a network or matrix configuration
• CPC Class Codes: G06F 12/0868 Data transfer between cache memory and other subsystems, e.g. storage devices or host systems
• CPC Class Codes: G06F 2212/205 Hybrid memory, e.g. using both volatile and non-volatile memory
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0631 by allocating resources to storage systems
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: G06F 3/0688 Non-volatile semiconductor memory arrays
• CPC Class Codes: G06F 9/5005 to service a request
• CPC Class Codes: G06F 9/5011 the resources being hardware resources other than CPUs, Servers and Terminals

Abstract

A method and apparatus for performing a data transfer, which include a selection a data transfer operation mode, based on telemetry data, from a first operation mode where a first type of data is transferred from a memory of a computing system to one or more shared storage devices, and a second operation mode where a second type of data is transferred from the memory to the one or more shared storage devices, the first type of data being associated with a first range of address space of the one or more shared storage devices, the second type of data being associated with a second range of address space of the one or more shared storage devices different from the first range of address space. Furthermore, a data transfer from the memory to the one or more shared storage devices in the selected data transfer operation mode may be included.

Claims

1. A computing system, comprising:

one or more processors configured to

perform a data transfer of a first type of data from a memory to one or more shared storage devices in a first operation mode of the one or more processors, the first type of data being associated with a first range of address space of the one or more shared storage devices, the one or more shared storage devices being disaggregate from the computing system,

perform a data transfer of a second type of data from the memory to the one or more shared storage devices in a second operation mode of the one or more processors, the second type of data being associated with a second range of address space of the one or more shared storage devices different from the first range of address space, and

switch between the first operation mode and the second operation mode based on telemetry data associated with at least one of the computing system or the one or more shared storage devices; and

wherein the first operation mode is performed when a first data transfer criteria is met, and

the first data transfer criteria is met when the telemetry data associated with at least one of the computing system or the one or more shared storage devices, indicates a utilization less than or equal to a first threshold utilization.

2. The computing system of claim 1,

wherein the memory comprises a delta structure configured to facilitate a lookup of device identification information of the one or more shared storage devices.

3. The computing system of claim 1,

wherein the one or more processors are configured to

assign a first priority level to the first range of address space of the one or more shared storage devices, and

assign a second priority level to the second range of address space of the one or more share storage devices.

4. The computing system of claim 2, wherein the one or more processors are configured to determine a capacity level of the delta structure based on at least one of a number of transactions within the delta structure or a cumulative size of the transactions within the delta structure.

5. The computing system of claim 4, wherein the one or more processors are configured to adapt a rate at which data is transferred in the second mode of operation based on the capacity level of the delta structure.

6. The computing system of claim 2, wherein the one or more processors are configured to determine whether a write transaction and another write transaction in the delta structure target a common device identifier of the one or more shared storage devices.

7. The computing system of claim 6, wherein the one or more processors are configured to merge the write transaction with the other write transaction in response to determining the write transaction and the other write transaction in the delta structure target the common device identifier of the one or more shared storage devices.

8. The computing system of claim 6, wherein the one or more processors are configured to append the write transaction to a tail of the delta structure when the write transaction and the other write transaction in the delta structure target the common device identifier of the one or more shared storage devices and the write transaction specifies non-blending.

9. A method for performing a data transfer over a networked storage architecture, the method comprising:

performing a data transfer of a first type of data from a memory of a computing system to one or more shared storage devices in a first operation mode, the first type of data being associated with a first range of address space of the one or more shared storage devices, the one or more shared storage devices being disaggregate from the computing system;

performing a data transfer of a second type of data from the memory to the one or more shared storage devices in a second operation mode, the second type of data being associated with a second range of address space of the one or more shared storage devices different from the first range of address space; and

switching between the first operation mode and the second operation mode based on telemetry data associated with at least one of the computing system or the one or more shared storage devices;

wherein the first operation mode is performed when a first data transfer criteria is met, and the first data transfer criteria is met when the telemetry data associated with at least one of the computing system or the one or more shared storage devices, indicates a utilization less than or equal to a first threshold utilization.

10. The method of claim 9, wherein the memory is a first in-first out (FIFO) buffer memory comprising a delta structure.

11. The method of claim 9,

wherein the first operation mode is a first delta merge operation mode for the first type of data, and

the second operation mode is a second delta merge operation mode for the second type of data.

12. The method of claim 9, wherein the first range of address space of the one or more shared storage devices comprises the second range of address space of the one or more shared storage devices.

13. The method of claim 9,

wherein the second operation mode is performed when a second data transfer criteria is met, and

the second data transfer criteria is met when the telemetry data associated with at least one of the computing system or the one or more shared storage devices indicates a utilization greater than or equal to the second threshold utilization.

14. The method of claim 9, further comprising:

acquiring the telemetry data associated with at least one of the computing system or the one or more shared storage devices at a predetermined interval; and

modifying the predetermined interval at which telemetry data associated with at least one of the computing system or the one or more shared storage devices is acquired, based on at least one of a time-averaged telemetry data level or a slope of a telemetry data signal meeting a predetermined interval update criteria.

15. The method of claim 10, further comprising:

determining whether a write transaction and another write transaction in the delta structure target a common device identifier of the one or more shared storage devices.

16. The method of claim 15, further comprising:

appending the write transaction to a tail of the delta structure in response to determining the write transaction and the other write transaction in the delta structure target different device identifiers of the one or more shared storage devices.

17. A method for performing a data transfer over a networked storage architecture, the method comprising:

selecting a data transfer operation mode from a plurality of data transfer operation modes based on telemetry data, the plurality of data transfer operation modes including a first operation mode in which a first type of data is transferred from a memory of a computing system to one or more shared storage devices, and a second operation mode in which a second type of data is transferred from the memory to the one or more shared storage devices, the first type of data being associated with a first range of address space of the one or more shared storage devices, the second type of data being associated with a second range of address space of the one or more shared storage devices different from the first range of address space, the one or more shared storage devices being disaggregate from the computing system, and

performing a data transfer from the memory to the one or more shared storage devices in the selected data transfer operation mode.

18. The method of claim 17, wherein the memory is a first in-first out (FIFO) buffer memory comprising a delta structure.

19. The method of claim 18, further comprising:

determining a capacity level of the delta structure based on at least one of a number of transactions within the delta structure or a cumulative size of the transactions within the delta structure; and

adapting a rate at which data is transferred in the second operation mode based on the capacity level of the delta structure.