Great research starts with great data.

Learn More
More >
Patent Analysis of

Recovering stranded data

Updated Time 12 June 2019

Patent Registration Data

Publication Number

US10152399

Application Number

US14/888338

Application Date

30 July 2013

Publication Date

11 December 2018

Current Assignee

HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

Original Assignee (Applicant)

HEWLETT-PACKARD DEVELOPMENT COMPANY, L.P.

International Classification

G06F11/20,G06F12/02

Cooperative Classification

G06F11/2097,G06F11/203,G06F11/2035,G06F12/0246,G06F11/2025

Inventor

WHEELER, ANDREW R.,LESARTRE, GREGG B.

Patent Images

This patent contains figures and images illustrating the invention and its embodiment.

US10152399 Recovering stranded data 1 US10152399 Recovering stranded data 2 US10152399 Recovering stranded data 3
See all images <>

Abstract

A system and method for recovering stranded data from a non-volatile memory is provided. An example of a method includes copying data from a non-volatile memory (NVM) in a home node over a sideband interface and writing the data to a target memory region, wherein the target memory region is in a fail-over node.

Read more

Claims

1. A method for recovering stranded data, comprising:

in response to detecting a failure of a home node, copying data from a non-volatile memory (NVM) in the home node over a sideband interface across a sideband bus interconnecting a management device of the home node to a management device of a fail-over node; and writing the data to a target memory region, wherein the target memory region is in the fail-over node.

2. The method of claim 1, further comprising writing the data to a second NVM in the fail-over node.

3. The method of claim 1, further comprising writing the data to a virtual memory area in the fail-over node.

4. The method of claim 1, further comprising accessing the NVM in the home node from a management subsystem.

5. The method of claim 1, further comprising accessing the NVM when main system power is off to the home node.

6. The method of claim 1, further comprising providing a backup power in case all power has failed in the home node.

7. The method of claim 1, further comprising reactivating processes in the target memory region.

8. The method of claim 1, further comprising:

migrating a plurality of memory stripes from a corresponding plurality of NVMs in the home node to the fail-over node; detecting if any of the plurality of memory stripes comprises missing or defective data; and rebuilding the missing or defective data.

9. The method of claim 1, wherein the writing of the data to the target memory region in the fail-over node is through a system management device of the fail-over node.

10. The method of claim 1, wherein the sideband interface comprises a serial presence detect interface.

11. The method of claim 1 further comprising:

prior to the failure of the home node, accessing data in the nonvolatile memory in the home node via a memory controller, wherein the copying of the data from the non-volatile memory (NVM) in the home node over the sideband interface across the sideband bus interconnecting bus interconnecting the management device of the home node to the management device of the failover node is independent of the memory controller.

12. The method of claim 1, wherein the management device of the home node resides on a dual in-line memory module (DIMM).

13. The method of claim 12, wherein the DIMM further comprises volatile memory, a nonvolatile memory controller for controlling the NVM, and a DIMM controller for reading and writing data to the volatile memory, wherein the copying of the data from the NVM in the home node over the sideband interface across the sideband bus interconnecting the management device of the home node to the management device of the fail-over node further comprises propagating the data being copied from the nonvolatile memory in the home node across the nonvolatile memory controller and across the DIMM controller.

14. The method of claim 1, wherein the sideband bus comprises a system management bus of a management network through which communications from a management system are communicated.

15. A computing system, comprising:

a home node, comprising:

a processor; a memory controller coupled to the processor of the home node; a main network interface coupled to the processor of the home node, and a network; a non-volatile memory (NVM) coupled to the memory controller of the home node; and a system management device, coupled to the memory controller of the home node, the processor of the home node, and a system management network;a fail-over node, comprising:

a processor; a memory controller coupled to the processor of the fail-over node; a main network interface coupled to the processor of the fail-over node, and to the network; a target memory region coupled to the memory controller of the fail-over node; and a system management device, coupled to the memory controller of the fail-over node, the processor of the fail-over node, and the system management network; and a system management processor provided in the system management device of the fail-over node or another system device connected to the home node across the system management network, wherein the system management processor is to access data stored in the NVM of the home node through the system management device in the home node, and transfer the data to the target memory region of the fail-over node through the system management device of the fail-over node across the system management network.

16. The computing system of claim 15, wherein the system management device in the home node detects a failure in the home node prior to transferring the data from the NVM of the home node to the target memory region.

17. The computing system of claim 15, wherein the system management device in the home node comprises a back-up power driver to power the memory controller in case of a complete failure of system power in the home node.

18. The computing system of claim 15, wherein the system management device in the home node comprises:

a processor; anda memory comprising instructions, wherein the instructions:

direct the processor of the system management device in the home node to detect a failure of the home node; access the data in the NVM; and transfer the data to a target memory region in the fail-over node.

19. The computing system of claim 15, wherein the system management network comprises a management server that monitors operation of a plurality of nodes and identifies a fail-over node for any of a plurality of nodes that fail.

20. The computing system of claim 15, wherein the system management processor is to access the data stored in the NVM of the home node over a sideband management bus connecting the system management device in the home node and the system management device in the fail-over node.

21. The computing system of claim 20, wherein the sideband management bus comprises a serial presence detect interface.

22. A tangible, non-transitory, machine-readable medium comprising instructions to direct a processor to:

detect a failure of a home node; access data in a non-volatile memory (NVM) of the home node over a sideband management bus of a management device of a memory controller in response to the failure of the home node being detected; and transfer the data across the sideband management bus to a target memory region in a fail-over node.

23. The tangible, non-transitory, machine-readable medium of claim 22, comprising instructions to reactivate processes in the fail-over node.

24. The tangible, non-transitory, machine-readable medium of claim 22, wherein the sideband management bus is connected to the management device of the memory controller by a serial presence detect interface.

Read more

Claim Tree

  • 1
    1. A method for recovering stranded data, comprising:
    • in response to detecting a failure of a home node, copying data from a non-volatile memory (NVM) in the home node over a sideband interface across a sideband bus interconnecting a management device of the home node to a management device of a fail-over node
    • and writing the data to a target memory region, wherein the target memory region is in the fail-over node.
    • 2. The method of claim 1, further comprising
      • writing the data to a second NVM in the fail-over node.
    • 3. The method of claim 1, further comprising
      • writing the data to a virtual memory area in the fail-over node.
    • 4. The method of claim 1, further comprising
      • accessing the NVM in the home node from a management subsystem.
    • 5. The method of claim 1, further comprising
      • accessing the NVM when main system power is off to the home node.
    • 6. The method of claim 1, further comprising
      • providing a backup power in case all power has failed in the home node.
    • 7. The method of claim 1, further comprising
      • reactivating processes in the target memory region.
    • 8. The method of claim 1, further comprising:
      • migrating a plurality of memory stripes from a corresponding plurality of NVMs in the home node to the fail-over node
      • detecting if any of the plurality of memory stripes comprises missing or defective data
      • and rebuilding the missing or defective data.
    • 9. The method of claim 1, wherein
      • the writing of the data to the target memory region in the fail-over node is through a system management device of the fail-over node.
    • 10. The method of claim 1, wherein
      • the sideband interface comprises
    • 11. The method of claim 1 further comprising:
      • prior to the failure of the home node, accessing data in the nonvolatile memory in the home node via a memory controller, wherein the copying of the data from the non-volatile memory (NVM) in the home node over the sideband interface across the sideband bus interconnecting bus interconnecting the management device of the home node to the management device of the failover node is independent of the memory controller.
    • 12. The method of claim 1, wherein
      • the management device of the home node resides on a dual in-line memory module (DIMM).
    • 14. The method of claim 1, wherein
      • the sideband bus comprises
  • 15
    15. A computing system, comprising:
    • a home node, comprising: a processor
    • a memory controller coupled to the processor of the home node
    • a main network interface coupled to the processor of the home node, and a network
    • a non-volatile memory (NVM) coupled to the memory controller of the home node
    • and a system management device, coupled to the memory controller of the home node, the processor of the home node, and a system management network
    • a fail-over node, comprising: a processor
    • a memory controller coupled to the processor of the fail-over node
    • a main network interface coupled to the processor of the fail-over node, and to the network
    • a target memory region coupled to the memory controller of the fail-over node
    • and a system management device, coupled to the memory controller of the fail-over node, the processor of the fail-over node, and the system management network
    • and a system management processor provided in the system management device of the fail-over node or another system device connected to the home node across the system management network, wherein the system management processor is to access data stored in the NVM of the home node through the system management device in the home node, and transfer the data to the target memory region of the fail-over node through the system management device of the fail-over node across the system management network.
    • 16. The computing system of claim 15, wherein
      • the system management device in the home node detects a failure in the home node prior to transferring the data from the NVM of the home node to the target memory region.
    • 17. The computing system of claim 15, wherein
      • the system management device in the home node comprises
    • 18. The computing system of claim 15, wherein
      • the system management device in the home node comprises:
    • 19. The computing system of claim 15, wherein
      • the system management network comprises
    • 20. The computing system of claim 15, wherein
      • the system management processor is to access the data stored in the NVM of the home node over a sideband management bus connecting the system management device in the home node and the system management device in the fail-over node.
  • 22
    22. A tangible, non-transitory, machine-readable medium comprising
    • instructions to direct a processor to: detect a failure of a home node
    • access data in a non-volatile memory (NVM) of the home node over a sideband management bus of a management device of a memory controller in response to the failure of the home node being detected
    • and transfer the data across the sideband management bus to a target memory region in a fail-over node.
    • 23. The tangible, non-transitory, machine-readable medium of claim 22, comprising
      • instructions to reactivate processes in the fail-over node.
    • 24. The tangible, non-transitory, machine-readable medium of claim 22, wherein
      • the sideband management bus is connected to the management device of the memory controller by a serial presence detect interface.
See all independent claims <>

Description

CROSS-REFERENCE TO RELATED APPLICATION

This application is a United States National Stage Application of International Patent Application No. PCT/US2013/052671, filed on Jul. 30, 2013, the contents of which are incorporated by reference as if set forth in their entirety herein.

BACKGROUND

In current computing systems, the majority of main memory for a computer system is comprised of dual in line memory modules (DIMMs) based on dynamic random access memory (DRAM). DRAM provides very fast access times, is byte addressable, and has attractive price/per bit metrics compared to other memory technologies. However, DRAM is volatile, losing data once power is removed from the device. Thus, the bulk storage for a computer system often includes a hard disk drive, solid state flash memory drives, or a hybrid combination to permanently store data. New generations of memory modules are starting to become available within the computer industry that enable long term storage of data in DIMMs even after power is removed.

BRIEF DESCRIPTION OF THE DRAWINGS

Certain examples are described in the following detailed description and in reference to the drawings, in which:

FIG. 1 is a block diagram of an example of a computing system 100 that allows access to stranded data in non-volatile memory (NVM) of a failed node;

FIG. 2 is a block diagram of an example of a single node that may be used in the computing system of FIG. 1;

FIG. 3 is a schematic of a computing system showing a home node and a fail-over node;

FIG. 4 is a block diagram of a management device that can be used in a node to access data in NVM over a management or sideband bus; and

FIG. 5 is a process flow diagram illustrating a method for accessing stranded data in the NVM of a computing system.

DETAILED DESCRIPTION OF SPECIFIC EXAMPLES

Networked computing systems generally include host computing devices, or nodes, configured to provide resources such as storage, applications, databases, and the like. The host computing device may be a server such as a database server, file server, mail server, print server, web server, or some other type of server configured to provide services to client devices within a network.

Although new types of memory modules allow persistent data storage after power is removed from a node, a failure of a given server or node (the “home” node), can result in the persistent data no longer being accessible by other consumers of the data. As used herein, this data has become “stranded” and remains “captive” in the memory module. Techniques described herein relate generally to accessing data that is stranded in the non-volatile memory (NVM) of a computing system, such as the failed node. In one example, a sideband interface connected to the DIMM controller on the memory module allows data to be read (extracted) and written (loaded) through a management subsystem. For example, the standard Serial Presence Detect (SPD) interface on an industry standard DIMM module may be used. During the operation of this technique, the management subsystem and portions of the memory modules operate off stand-by power. This way, data can be extracted when the failed node's main power is off, for example, due to a node failure.

Any number of computing devices may be nodes in the system, such as workstations, servers, network attached storage, and the like. One example of a node that can be used in a computing system is a blade server, which is a server computer having a modular design optimized to minimize the use of physical space. Whereas a standard rack mount server can function with a power cord and network cable, a blade server has many components removed for the purpose of saving space, minimizing power consumption and other considerations, while still having all the functional components to be considered a computer. A multi-slot chassis can hold multiple blade server cartridges and provide shared resources such as power, cooling, networking, various interconnects, and management.

Each node typically includes memory, such as dual in-line memory modules (DIMMs), single in-line memory modules (SIMMs), and the like. As used herein, any reference to a DIMM includes a memory module having any package type. Emerging memory modules that may be used in the DIMMs in nodes may include DRAM, NVM, or combinations of both. NVM can include any number of memory technologies, such as flash memory, phase change memory, spin transfer torque ram, and resistive ram. An NVM memory module could also take the form of a DRAM module having a battery backup.

The use of persistent storage directly in the CPU's directly addressable main memory address space allows many novel system architectures and programming models to be enabled, such as fast power down and restart modes, or more local storage of data. Further, shared storage systems using NVM can enable high availability of the data in the case of a component failure, for example, by storing multiple copies of the data, or by using techniques such as RAID that can reconstitute the data in case of a component failure (such as a processor).

The ability to access data that is stranded as a result of a node failure, such as a CPU or power loss, guards against node failures, but not against DIMM failures. However, the techniques discussed herein are compatible with a system that RAIDs data across multiple DIMMs on the server. This solution can then separately migrate each of the RAID stripes to allow continued operation. If just a DIMM fails, the server can rebuild. If both the server and a DIMM fails, the failover server could rebuild after migration.

FIG. 1 is a block diagram of an example of a computing system 100 that allows access to stranded data in non-volatile memory (NVM) of a failed node. The computing system 100 can have a main bus 102, based on any number of technologies, such as PCI, Infiniband, PCI-Express, HyperTransport®, NuBus, etc., Ethernet, and the like. In some examples, the main bus 102 could also take the form of a switched fabric. The main bus 102 can connect any number of units, including one or more server nodes 104 that may have DIMM, or other structures, that include NVM 106. Long term storage may be provide by one or more solid state disk drive (SSDD) storage nodes 108, which may also include NVM 106. Long term storage may also be provided by one or more disk nodes 110, which may include hard drives, NVM 106, or combinations thereof.

The computing system 100 can have a router 112 to provide access to one or more client devices 114. The client devices can include networks, such as LANs, WANs, or the Internet, or user devices that can access the computing system 100.

A management system 116 can be coupled to the other units in the computing system 100, such as the server nodes 104, the SSDD storage nodes 108, and the Disk nodes 110 through a management, or sideband, bus 118. The management system 116, or devices in the individual units 104, 108, and 110, can detect failures of a unit that may strand data in a home node. The management system 116 can then read the stranded data out from NVM 106 in the home node, for example, over the management bus 118, and write the data to a target node. The data may be written to NVM 106 in the target node, in which a DIMM in the failed node is directly copied to a DIMM in the target node. In other examples, the data may be written to a virtual memory. Any rebuilding of data, for example, recreating data from RAID striped memory may be carried out during the data transfer. Once the data is in the target node, the processes that were operational in the home node before failure can be restarted.

The block diagram of FIG. 1 is not intended to indicate that the computing system 100 is to include all of the components shown in FIG. 1. Further, the computing system 100 may include any number of additional components not shown in FIG. 1, depending on the details of the specific implementation.

FIG. 2 is a block diagram of an example of a single node 200 that may be used in the computing system 100 of FIG. 1. Like numbered items are as described with respect to FIG. 1. The node 200 includes a processor 202 to control operations and perform tasks, such as computation and data access for clients. The processor 202 can be a single core processor, a multi-core processor, a computing cluster, or any number of other configurations. The processor 202 can be implemented as a complex instruction set computer (CISC) or a reduced instruction set computer (RISC) processors, x86 Instruction set compatible processors, multi-core, or any other microprocessor or central processing unit (CPU).

The processor 202 can be coupled to an internal bus 204 within the node 200 for communications with other units. The internal bus 204 can include any number of different types, such as PCI, ISA, PCI-Express, HyperTransport®, NuBus, and the like. Further, the internal bus 204 may be the same type as the system bus 102, or may be a different type. A network interface device 206 may be used to couple the internal bus 204 to the system bus 206. The network interface device 206 can include an Ethernet interface, or any number of other types of other interfaces or switches configured to isolate the internal bus 204 from the system bus 102, while allowing communications.

A number of different units can be included in the node 200 to provide storage for data or programs. The storage units can include a disk subsystem 208, a memory subsystem 210, and the like. The disk subsystem 208 can include a disk controller 212 that controls the reading and writing of data to any combinations of disk drives 214 and memory, such as NVM DIMMs 216.

The memory subsystem 210 can include both non-volatile and volatile random access memory, such as SRAM, DRAM, zero capacitor RAM, SONOS, eDRAM, EDO RAM, DDR RAM, RRAM, PRAM, etc. Further the memory subsystem 210 can include read only memory, such as Mask ROM, PROM, EPROM, EEPROM, and the like. The memory subsystem 210 can include a memory controller 218 that controls access to memory, such as DRAM DIMMs 220 and NVM DIMMs 222.

As described above, a failure of the node 200 may trap data in the NVM DIMMs 222 in the memory subsystem 210 or the NVM DIMMs 216 in the disk subsystem 208. In examples described herein, the data can be accessed and transferred to a different node through the sideband bus 118. To facilitate the transfer, the memory controller 218 may have a management device 224 capable of accessing the NVM DIMMs 222. In the event of a total power failure in the node 200, the management device 224 can provide sufficient power to the memory controller 218 and the NVM DIMMs 222 to access the data. Similarly, the disk controller 212 can have a management device 226 capable of providing similar functions, allowing access to the data in the NVM DIMMs 216 in the disk subsystem 208.

The block diagram of FIG. 2 is not intended to indicate that the node 200 is to include all of the components shown in FIG. 1. For example, a server node may not have the disk subsystem 208. Further, the node 200 may include any number of additional components not shown in FIG. 1, depending on the details of the specific implementation. For example, the node 200 may include man-machine interfaces, such as a display interface, a keyboard interface, a pointing device interface, and the like.

FIG. 3 is a schematic of a computing system 300 showing a home node 302 and a fail-over node 304. Like numbered items are as described with respect to FIG. 1. In this example, each of the nodes 302 and 304, have a processor 306, which can be any number of types, as described with respect to the processor 202 in FIG. 2. Each processor 306 is coupled to an I/O device 308, for example, to an internal bus. The I/O device 308 provides an interface between each node 302 and 304, and the system bus 102, which may be a local or datacenter network. Each processor 306 is also coupled to a memory controller 310, which is used, in this example, to control one or more hybrid DIMMs 312. Each hybrid DIMM 312 can include a hybrid DIMM controller 314, which can be used to read and write data to DRAM 316. Each hybrid DIMM 312 can also include an NVM controller 318 that is used to control NVM 320 on the hybrid DIMM 312. Each of the nodes 302 and 304 also includes a system management device 322 that can be used to interface with a management network 118. Further, each of the hybrid DIMMs 312 includes a management device 324 that interfaces with the system management device 322, allowing access to persistent data through the management network 118.

During normal operation, the loads and stores to the persistent memory, such as NVM 320, come via the memory controller 310 attached to the processor 306. Other nodes may access this data via the system bus (datacenter network) 102. If the home node 302 fails in any way, the directly attached hybrid DIMMs 312 would no longer be available via the datacenter network 102. Unless this data was somehow replicated in another manner, the data is stranded and vital information could be lost without physically removing the hybrid DIMMs 312.

As described in examples herein, if the home node 302 fails, a management processor, for example, located in the system management device 322, in the management system 116, or in other system devices, notes the failure and begins the process of “reintegration”. Through the use of the management network 118, system management processors read the contents from the home node 302 and write the contents to the failover node 304. Once the data has been successfully copied, existing methods can be used to restart processes and applications running from the point of failure. Such methods may include reference workload migration, active/passive high availability, or check-pointing schemes, among others. It can be noted that the failover node 304 does not need to be specified before the failure event. The management system 116 can assign an appropriate target as the failover node 304 after a failure on the home node 302 just prior to instigating the data copy operation.

The schematic of FIG. 3 is not intended to indicate that all of the components must be present or that other components may not be present. For example, the management devices 324 in the hybrid DIMMs 312 may be directly interfaced to the management network 118, eliminating the system management device 322 from the nodes 302 and 304. Further, the node 200 may include disk drive, SSDs, or any number of additional components, depending on the details of the specific implementation.

FIG. 4 is a block diagram of a management device 400 that can be used in a node to access data in NVM 320 over a management or sideband bus 118. Like numbered items are as discussed with respect to FIGS. 1 and 3. The management device 400 may be an application specific integrated circuit (ASIC) mounted on a hybrid DIMM, a set of components mounted on a system mother board, a separate module within a node, or any number of other configurations.

As described herein, the management device 400 is adapted to provide access to stranded data in NVM in a failed node, in addition to other functions that may be present. The management device 400 includes a power driver 402, which is coupled to system power 404 and is adapted to provide power to the other functional blocks, for example, through a system power line 406. The management device 400 may be adapted to receive power from the main power of the node, from an emergency or standby power source, or from the system power for the network.

The management device 400 includes a processor 408, which is adapted to control the overall operation of the management device 400. The processor 408 is adapted to communicate with other nodes and a management system over the management network 118. The processor 408 is connected to various other functional blocks of the management device 400 via an internal bus 410. The protocol employed by the internal bus 410 may vary depending on system design considerations. The processor 408 may provide a full transmission control protocol/Internet protocol (TCP/IP) stack, as well as support for dynamic host configuration protocol (DHCP), secure sockets layer (SSL), transport layer security (TLS), and/or proprietary management device protocols.

A system management hub 412 can be connected to the management network 118 to allow the management device 400 to receive communications from a management system or other management devices. The system management hub 420 may be configured to allow a pass through of the management network 118 to other devices. The communications may include stranded data read from a NVM by the management device 400, and sent over the management network 118 to a management device in a fail-over node or to a management system for redirection to a fail-over node. The system management hub 412 is connected to a network interface (MC) 414 which is coupled to the processor 408 over the internal bus 410. A memory management interface 416 is coupled to the processor 408 over the internal bus 410. The memory management interface 416 can couple to drivers 418, which can be used to interface with a NVM memory controller 314 to read data from, or write data to, a NVM 320.

The management device 400 may include a memory controller 420, which is connected to other system components via the internal bus 410. The memory controller 420 is adapted to manage data flow between the processor 408 and memory resources of the management device 400. In the example shown in FIG. 4, the memory controller 420 manages a random access memory (RAM) 422 and a non-volatile memory 424. The non-volatile memory 424 may be used to store machine-readable instructions for the operation of the management device 400. The instructions may include a detection module 426 used to direct the processor 408 to detect the failure of the node, for example, by detecting the loss of main system power using a power detect interface 428 coupled to the power drivers 402. The non-volatile memory 424 may also include a data access module 430 used to direct the processor 408 to read stranded data from the NVM 320 and transfer it to another unit over the management network 118. The data access module 430 may also include instructions that direct the processor 408 to accept data sent over the management network 118 and write the data to the NVM 320, for example, if the management device 400 was located in a fail-over node. In case of a total loss of node power, including standby power, in one example, the management device may be configured to feed power from the power drivers 402 to the NVM memory controller 314 and the NVM 320 to allow data to be read from the NVM 320.

The block diagram of FIG. 4 is not intended to indicate that the management device 400 includes all of the components shown in FIG. 4. For example, a management device may not include the drivers 418, but may be directly coupled to the NVM memory controller 314. Further, the management device 400 may include any number of additional components not shown in FIG. 4, depending on the details of the specific implementation. For example, the management device 400 may include device level emergency power systems configured to provide enough power for transferring the stranded data. These systems may include batteries or capacitors, among others.

FIG. 5 is a process flow diagram illustrating a method 500 for accessing stranded data in the NVM of a computing system. The method 500 begins at block 502 with the detection of a failure in a node. Among other techniques, in various examples, this may be performed by a power detection system noting the loss of main system power in a node or by a management system noting the loss of communications, such as a heartbeat signal, from a node. At block 504, a management bus, or sideband channel, is used to access data stranded in NVM in the failed node. At block 506, the data is copied to a failover node, for example, into a NVM or a virtual memory space. At block 508, node processes are reactivated using techniques described herein.

It is to be understood that the process flow diagram of FIG. 5 that any number of additional steps not shown in FIG. 5 may be included within the method 500, depending on the details of the specific implementation. For example, data lost from a RAID stripe, due to a failed DIMM in a node, may be recreated from data in stripes stored in other DIMMs.

The presently described technical examples may be susceptible to various modifications and alternative forms and have been shown only for illustrative purposes. For example, the present techniques support both reading and writing operations to a NVM in a node. Furthermore, it is to be understood that the present techniques are not intended to be limited to the particular technical examples disclosed herein. Indeed, the scope of the appended claims is deemed to include all alternatives, modifications, and equivalents that are apparent to persons skilled in the art to which the disclosed subject matter pertains.

Read more
PatSnap Solutions

Great research starts with great data.

Use the most comprehensive innovation intelligence platform to maximise ROI on research.

Learn More

Citation

Patents Cited in This Cited by
Title Current Assignee Application Date Publication Date
Cluster failover from physical node to virtual node DELL PRODUCTS L.P. 14 November 2003 19 May 2005
Node removal using remote back-up system memory INTERNATIONAL BUSINESS MACHINES CORPORATION 31 October 2003 05 May 2005
在故障转移和故障回复环境中使用虚拟拷贝 国际商业机器公司 03 January 2008 11 November 2009
System and method for failure recovery and load balancing in a cluster network DELL PRODUCTS L.P. 16 July 2004 19 January 2006
Non-volatile memory with network fail-over MICRO MEMORY LLC 14 April 2004 17 February 2005
See full citation <>

More like this

Title Current Assignee Application Date Publication Date
Improving storage cache performance by using compressibility of the data as a criteria for cache insertion INTEL CORPORATION 18 February 2016 06 October 2016
Convertible leaf memory mapping SANDISK TECHNOLOGIES LLC 14 September 2016 04 May 2017
System and method for flash read cache with adaptive pre-fetch QUALCOMM INCORPORATED 29 September 2016 04 May 2017
Cluster computing service assurance apparatus and method INTEL CORPORATION,CHEN, XIAODONG,WO, BINGGANG 25 March 2015 29 September 2016
Implementing automatic switchover NETAPP, INC. 24 October 2016 27 April 2017
발명의 명칭 메모리 시스템 가부시끼가이샤 도시바 16 February 2011 20 June 2013
Memory node with cache for emulated shared memory computers TEKNOLOGIAN TUTKIMUSKESKUS VTT OY 22 December 2016 06 July 2017
System and method for direct write to MLC memory SANDISK TECHNOLOGIES LLC 14 September 2016 26 May 2017
Data processing method and apparatus for cluster file system SHENZHEN CHINA BLOG IMFORMATION TECHNOLOGY CO., LTD. 09 November 2016 01 June 2017
Dynamic mirroring NETAPP, INC. 25 April 2016 08 December 2016
Memory storage windows in a memory system MEMORY TECHNOLOGIES LLC 20 December 2016 06 July 2017
Fault tolerant computing HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP 31 July 2015 09 February 2017
Migrating data using dual-port non-volatile dual in-line memory modules HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP 30 April 2015 03 November 2016
Non-disruptive controller replacement in a cross-cluster redundancy configuration NETAPP, INC. 12 November 2015 19 May 2016
Processing method and device for memory page in memory HUAWEI TECHNOLOGIES CO.,LTD. 25 September 2015 21 July 2016
Computing method and apparatus with persistent memory INTEL CORPORATION 09 November 2015 16 June 2016
Memory persistence from a volatile memory to a non-volatile memory HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP 18 September 2015 23 March 2017
Method and apparatus for shared virtual memory to manage data coherency in a heterogeneous processing system INTEL CORPORATION 03 May 2017 11 January 2018
Fault tolerant automatic dual in-line memory module refresh INTEL CORPORATION 24 November 2015 30 June 2016
Virtual machine cluster backup MICROSOFT TECHNOLOGY LICENSING, LLC 10 November 2015 19 May 2016
See all similar patents <>

More Patents & Intellectual Property

PatSnap Solutions

PatSnap solutions are used by R&D teams, legal and IP professionals, those in business intelligence and strategic planning roles and by research staff at academic institutions globally.

PatSnap Solutions
Search & Analyze
The widest range of IP search tools makes getting the right answers and asking the right questions easier than ever. One click analysis extracts meaningful information on competitors and technology trends from IP data.
Business Intelligence
Gain powerful insights into future technology changes, market shifts and competitor strategies.
Workflow
Manage IP-related processes across multiple teams and departments with integrated collaboration and workflow tools.
Contact Sales
Clsoe
US10152399 Recovering stranded data 1 US10152399 Recovering stranded data 2 US10152399 Recovering stranded data 3