Patent Grant
11581943
As computer memory storage and data bandwidth increase, so does the amount and complexity of data that businesses manage daily. Large-scale distributed storage systems, such as data centers, typically run many business operations. A datacenter, which also may be referred to as a server room, is a centralized repository, either physical or virtual, for the storage, management, and dissemination of data pertaining to one or more businesses. A distributed storage system may be coupled to client computers interconnected by one or more networks. If any portion of the distributed storage system has poor performance, company operations may be impaired. A distributed storage system therefore maintains high standards for data availability and high-performance functionality.
The present disclosure is illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings.
A host computer system, such as storage controller, may be designed to interact with a storage device, which may be part of a larger storage array, to execute storage commands and manage operation of the storage device. The host computer system may include one or more queues used for processing commands, implemented in system memory. Each queue may refer to a pair of corresponding submission and completion queues. The submission queues store storage commands to be fetched by the storage controller and/or storage device, while the completion queues store results provided by the storage controller and/or storage device indicating execution of corresponding storage commands. The host computer system may also include a kernel space device driver, executed by a processor. In certain systems, the kernel space device driver places commands onto the submission queues and reads results from the completion queues. In one embodiment, the storage commands may be generated by an application running in a user space on the host computer system, while the device driver runs in a kernel space on the host computer system. In other embodiments, storage commands are generated by initiator devices operatively coupled to the storage controllers.
Throughout the description that follows, the terms hardware queue(s), I/O queue(s) admin queue(s), submission queue(s), completion queue(s), and queue pair(s) may be used when describing the above referenced data structure(s). Depending on the particular implementation, any of the above referenced queues may be used to route and store different types of commands or acknowledgments, such as FCP commands and/or NVMe/FC related commands. In addition, although reference may be made to a single queue (e.g., a submission queue), depending on the embodiment, that single queue may have a corresponding queue (e.g., a completion queue) which together make up queue pair. In other embodiments, multiple submission queues may be associated with the same completion queue.
Modern computing systems generally segregate virtual memory into a kernel space and one or more user spaces. This separation is generally done in order to provide memory protection and hardware protection from malicious or errant software behavior. In general, the kernel space is reserved for running a privileged operating system kernel, kernel extensions, and device drivers, such as kernel space device drivers, while the user spaces are where application software executes. Since the kernel space device driver that manages the submission queues and completion queues runs in the kernel space, storage commands are generally passed from user space to kernel space, where they traverse a kernel stack before being placed onto the submission queue and retrieved by the storage device. The kernel stack may include the kernel space device driver, and possibly other modules, such as a block layer. Traversing this kernel stack can be a time consuming processes that increases a latency associated with execution of the storage commands.
In one embodiment, the system described herein introduces concurrent user space and kernel space access for commands having a variety of communication protocols (e.g., FCP, NVMe/FC, etc.) from the host computer system to storage controllers through private, reserved I/O queues. In one embodiment, the kernel space device driver on the host machine reserves certain I/O queues for direct access by an application running in user space, while still maintaining other I/O queues for use by the kernel space device driver itself. In this manner, the application running in user space can place certain types of storage commands directly onto the reserved I/O queues, without routing those commands through the kernel space. The application may bypass the kernel space for certain types of commands including latency sensitive input/output NVMe/FC commands such as read operations, write operations, etc. For other types of commands, however, such as FCP commands or other latency tolerant commands, the application may utilize the kernel space device driver running in kernel space to place the commands in corresponding I/O queues. Accordingly, the application can reduce the latency associated with processing certain types of commands by writing these commands directly to a reserved I/O queue. Furthermore, the application can provide an initiator device using a variety of communication protocols concurrent access to a single storage controller. In one embodiment, the storage device can fetch different commands from different I/O queues concurrently, including I/O queues reserved for use by both the user space and the kernel space.
Example methods, apparatus, and products for user space and kernel space access through private queues, in accordance with embodiments of the present disclosure are described with reference to the accompanying drawings, beginning with
System 100 includes a number of computing devices 164A-B. Computing devices (also referred to as “client devices” herein) may be embodied, for example, a server in a data center, a workstation, a personal computer, a notebook, or the like. Computing devices 164A-B may be coupled for data communications to one or more storage arrays 102A-B through a storage area network (‘SAN’) 158 or a local area network (‘LAN’) 160.
The SAN 158 may be implemented with a variety of data communications fabrics, devices, and protocols. For example, the fabrics for SAN 158 may include Fibre Channel, Ethernet, Infiniband, Serial Attached Small Computer System Interface (‘SAS’), or the like. Data communications protocols for use with SAN 158 may include Advanced Technology Attachment (‘ATA’), Fibre Channel Protocol, Small Computer System Interface (‘SCSI’), Internet Small Computer System Interface (‘iSCSI’), HyperSCSI, Non-Volatile Memory Express (‘NVMe’) over Fabrics, or the like. It may be noted that SAN 158 is provided for illustration, rather than limitation. Other data communication couplings may be implemented between computing devices 164A-B and storage arrays 102A-B.
The LAN 160 may also be implemented with a variety of fabrics, devices, and protocols. For example, the fabrics for LAN 160 may include Ethernet (802.3), wireless (802.11), or the like. Data communication protocols for use in LAN 160 may include Transmission Control Protocol (‘TCP’), User Datagram Protocol (‘UDP’), Internet Protocol (‘IP’), HyperText Transfer Protocol (‘HTTP’), Wireless Access Protocol (‘WAP’), Handheld Device Transport Protocol (‘HDTP’), Session Initiation Protocol (‘SIP’), Real Time Protocol (‘RTP’), or the like.
Storage arrays 102A-B may provide persistent data storage for the computing devices 164A-B. Storage array 102A may be contained in a chassis (not shown), and storage array 102B may be contained in another chassis (not shown), in implementations. Storage array 102A and 102B may include one or more storage array controllers 110A-D (also referred to as “controller” herein). A storage array controller 110A-D may be embodied as a module of automated computing machinery comprising computer hardware, computer software, or a combination of computer hardware and software. In some implementations, the storage array controllers 110A-D may be configured to carry out various storage tasks. Storage tasks may include writing data received from the computing devices 164A-B to storage array 102A-B, erasing data from storage array 102A-B, retrieving data from storage array 102A-B and providing data to computing devices 164A-B, monitoring and reporting of disk utilization and performance, performing redundancy operations, such as Redundant Array of Independent Drives (‘RAID’) or RAID-like data redundancy operations, compressing data, encrypting data, and so forth.
Storage array controller 110A-D may be implemented in a variety of ways, including as a Field Programmable Gate Array (‘FPGA’), a Programmable Logic Chip (‘PLC’), an Application Specific Integrated Circuit (‘ASIC’), System-on-Chip (‘SOC’), or any computing device that includes discrete components such as a processing device, central processing unit, computer memory, or various adapters. Storage array controller 110A-D may include, for example, a data communications adapter configured to support communications via the SAN 158 or LAN 160. In some implementations, storage array controller 110A-D may be independently coupled to the LAN 160. In implementations, storage array controller 110A-D may include an I/O controller or the like that couples the storage array controller 110A-D for data communications, through a midplane (not shown), to a persistent storage resource 170A-B (also referred to as a “storage resource” herein). The persistent storage resource 170A-B main include any number of storage drives 171A-F (also referred to as “storage devices” herein) and any number of non-volatile Random Access Memory (‘NVRAM’) devices (not shown).
In some implementations, the NVRAM devices of a persistent storage resource 170A-B may be configured to receive, from the storage array controller 110A-D, data to be stored in the storage drives 171A-F. In some examples, the data may originate from computing devices 164A-B. In some examples, writing data to the NVRAM device may be carried out more quickly than directly writing data to the storage drive 171A-F. In implementations, the storage array controller 110A-D may be configured to utilize the NVRAM devices as a quickly accessible buffer for data destined to be written to the storage drives 171A-F. Latency for write requests using NVRAM devices as a buffer may be improved relative to a system in which a storage array controller 110A-D writes data directly to the storage drives 171A-F. In some implementations, the NVRAM devices may be implemented with computer memory in the form of high bandwidth, low latency RAM. The NVRAM device is referred to as “non-volatile” because the NVRAM device may receive or include a unique power source that maintains the state of the RAM after main power loss to the NVRAM device. Such a power source may be a battery, one or more capacitors, or the like. In response to a power loss, the NVRAM device may be configured to write the contents of the RAM to a persistent storage, such as the storage drives 171A-F.
In implementations, storage drive 171A-F may refer to any device configured to record data persistently, where “persistently” or “persistent” refers as to a device's ability to maintain recorded data after loss of power. In some implementations, storage drive 171A-F may correspond to non-disk storage media. For example, the storage drive 171A-F may be one or more solid-state drives (‘SSDs’), flash memory based storage, any type of solid-state non-volatile memory, or any other type of non-mechanical storage device. In other implementations, storage drive 171A-F may include may include mechanical or spinning hard disk, such as hard-disk drives (‘HDD’).
In some implementations, the storage array controllers 110A-D may be configured for offloading device management responsibilities from storage drive 171A-F in storage array 102A-B. For example, storage array controllers 110A-D may manage control information that may describe the state of one or more memory blocks in the storage drives 171A-F. The control information may indicate, for example, that a particular memory block has failed and should no longer be written to, that a particular memory block contains boot code for a storage array controller 110A-D, the number of program-erase (‘PIE’) cycles that have been performed on a particular memory block, the age of data stored in a particular memory block, the type of data that is stored in a particular memory block, and so forth. In some implementations, the control information may be stored with an associated memory block as metadata. In other implementations, the control information for the storage drives 171A-F may be stored in one or more particular memory blocks of the storage drives 171A-F that are selected by the storage array controller 110A-D. The selected memory blocks may be tagged with an identifier indicating that the selected memory block contains control information. The identifier may be utilized by the storage array controllers 110A-D in conjunction with storage drives 171A-F to quickly identify the memory blocks that contain control information. For example, the storage controllers 110A-D may issue a command to locate memory blocks that contain control information. It may be noted that control information may be so large that parts of the control information may be stored in multiple locations, that the control information may be stored in multiple locations for purposes of redundancy, for example, or that the control information may otherwise be distributed across multiple memory blocks in the storage drive 171A-F.
In implementations, storage array controllers 110A-D may offload device management responsibilities from storage drives 171A-F of storage array 102A-B by retrieving, from the storage drives 171A-F, control information describing the state of one or more memory blocks in the storage drives 171A-F. Retrieving the control information from the storage drives 171A-F may be carried out, for example, by the storage array controller 110A-D querying the storage drives 171A-F for the location of control information for a particular storage drive 171A-F. The storage drives 171A-F may be configured to execute instructions that enable the storage drive 171A-F to identify the location of the control information. The instructions may be executed by a controller (not shown) associated with or otherwise located on the storage drive 171A-F and may cause the storage drive 171A-F to scan a portion of each memory block to identify the memory blocks that store control information for the storage drives 171A-F. The storage drives 171A-F may respond by sending a response message to the storage array controller 110A-D that includes the location of control information for the storage drive 171A-F. Responsive to receiving the response message, storage array controllers 110A-D may issue a request to read data stored at the address associated with the location of control information for the storage drives 171A-F.
In other implementations, the storage array controllers 110A-D may further offload device management responsibilities from storage drives 171A-F by performing, in response to receiving the control information, a storage drive management operation. A storage drive management operation may include, for example, an operation that is typically performed by the storage drive 171A-F (e.g., the controller (not shown) associated with a particular storage drive 171A-F). A storage drive management operation may include, for example, ensuring that data is not written to failed memory blocks within the storage drive 171A-F, ensuring that data is written to memory blocks within the storage drive 171A-F in such a way that adequate wear leveling is achieved, and so forth.
In implementations, storage array 102A-B may implement two or more storage array controllers 110A-D. For example, storage array 102A may include storage array controllers 110A and storage array controllers 110B. At a given instance, a single storage array controller 110A-D (e.g., storage array controller 110A) of a storage system 100 may be designated with primary status (also referred to as “primary controller” herein), and other storage array controllers 110A-D (e.g., storage array controller 110A) may be designated with secondary status (also referred to as “secondary controller” herein). The primary controller may have particular rights, such as permission to alter data in persistent storage resource 170A-B (e.g., writing data to persistent storage resource 170A-B). At least some of the rights of the primary controller may supersede the rights of the secondary controller. For instance, the secondary controller may not have permission to alter data in persistent storage resource 170A-B when the primary controller has the right. The status of storage array controllers 110A-D may change. For example, storage array controller 110A may be designated with secondary status, and storage array controller 110B may be designated with primary status.
In some implementations, a primary controller, such as storage array controller 110A, may serve as the primary controller for one or more storage arrays 102A-B, and a second controller, such as storage array controller 110B, may serve as the secondary controller for the one or more storage arrays 102A-B. For example, storage array controller 110A may be the primary controller for storage array 102A and storage array 102B, and storage array controller 110B may be the secondary controller for storage array 102A and 102B. In some implementations, storage array controllers 110C and 110D (also referred to as “storage processing modules”) may neither have primary or secondary status. Storage array controllers 110C and 110D, implemented as storage processing modules, may act as a communication interface between the primary and secondary controllers (e.g., storage array controllers 110A and 110B, respectively) and storage array 102B. For example, storage array controller 110A of storage array 102A may send a write request, via SAN 158, to storage array 102B. The write request may be received by both storage array controllers 110C and 110D of storage array 102B. Storage array controllers 110C and 110D facilitate the communication, e.g., send the write request to the appropriate storage drive 171A-F. It may be noted that in some implementations storage processing modules may be used to increase the number of storage drives controlled by the primary and secondary controllers.
In implementations, storage array controllers 110A-D are communicatively coupled, via a midplane (not shown), to one or more storage drives 171A-F and to one or more NVRAM devices (not shown) that are included as part of a storage array 102A-B. The storage array controllers 110A-D may be coupled to the midplane via one or more data communication links and the midplane may be coupled to the storage drives 171A-F and the NVRAM devices via one or more data communications links. The data communications links described herein are collectively illustrated by data communications links 108A-D and may include a Peripheral Component Interconnect Express (‘PCIe’) bus, for example.
Storage array controller 101 may include one or more processing devices 104 and random access memory (‘RAM’) 111. Processing device 104 (or controller 101) represents one or more general-purpose processing devices such as a microprocessor, central processing unit, or the like. More particularly, the processing device 104 (or controller 101) may be a complex instruction set computing (‘CISC’) microprocessor, reduced instruction set computing (‘RISC’) microprocessor, very long instruction word (‘VLIW’) microprocessor, or a processor implementing other instruction sets or processors implementing a combination of instruction sets. The processing device 104 (or controller 101) may also be one or more special-purpose processing devices such as an application specific integrated circuit (‘ASIC’), a field programmable gate array (‘FPGA’), a digital signal processor (‘DSP’), network processor, or the like.
The processing device 104 may be connected to the RAM 111 via a data communications link 106, which may be embodied as a high speed memory bus such as a Double-Data Rate 4 (‘DDR4’) bus. Stored in RAM 111 is an operating system 112. In some implementations, instructions 113 are stored in RAM 111. Instructions 113 may include computer program instructions for performing operations in in a direct-mapped flash storage system. In one embodiment, a direct-mapped flash storage system is one that that addresses data blocks within flash drives directly and without an address translation performed by the storage controllers of the flash drives.
In implementations, storage array controller 101 includes one or more host bus adapters 103A-C that are coupled to the processing device 104 via a data communications link 105A-C. In implementations, host bus adapters 103A-C may be computer hardware that connects a host system (e.g., the storage array controller) to other network and storage arrays. In some examples, host bus adapters 103A-C may be a Fibre Channel adapter that enables the storage array controller 101 to connect to a SAN, an Ethernet adapter that enables the storage array controller 101 to connect to a LAN, or the like. Host bus adapters 103A-C may be coupled to the processing device 104 via a data communications link 105A-C such as, for example, a PCIe bus.
In implementations, storage array controller 101 may include a host bus adapter 114 that is coupled to an expander 115. The expander 115 may be used to attach a host system to a larger number of storage drives. The expander 115 may, for example, be a SAS expander utilized to enable the host bus adapter 114 to attach to storage drives in an implementation where the host bus adapter 114 is embodied as a SAS controller.
In implementations, storage array controller 101 may include a switch 116 coupled to the processing device 104 via a data communications link 109. The switch 116 may be a computer hardware device that can create multiple endpoints out of a single endpoint, thereby enabling multiple devices to share a single endpoint. The switch 116 may, for example, be a PCIe switch that is coupled to a PCIe bus (e.g., data communications link 109) and presents multiple PCIe connection points to the midplane.
In implementations, storage array controller 101 includes a data communications link 107 for coupling the storage array controller 101 to other storage array controllers. In some examples, data communications link 107 may be a QuickPath Interconnect (QPI) interconnect.
A traditional storage system that uses traditional flash drives may implement a process across the flash drives that are part of the traditional storage system. For example, a higher level process of the storage system may initiate and control a process across the flash drives. However, a flash drive of the traditional storage system may include its own storage controller that also performs the process. Thus, for the traditional storage system, a higher level process (e.g., initiated by the storage system) and a lower level process (e.g., initiated by a storage controller of the storage system) may both be performed.
To resolve various deficiencies of a traditional storage system, operations may be performed by higher level processes and not by the lower level processes. For example, the flash storage system may include flash drives that do not include storage controllers that provide the process. Thus, the operating system of the flash storage system itself may initiate and control the process. This may be accomplished by a direct-mapped flash storage system that addresses data blocks within the flash drives directly and without an address translation performed by the storage controllers of the flash drives.
The operating system of the flash storage system may identify and maintain a list of allocation units across multiple flash drives of the flash storage system. The allocation units may be entire erase blocks or multiple erase blocks. The operating system may maintain a map or address range that directly maps addresses to erase blocks of the flash drives of the flash storage system.
Direct mapping to the erase blocks of the flash drives may be used to rewrite data and erase data. For example, the operations may be performed on one or more allocation units that include a first data and a second data where the first data is to be retained and the second data is no longer being used by the flash storage system. The operating system may initiate the process to write the first data to new locations within other allocation units and erasing the second data and marking the allocation units as being available for use for subsequent data. Thus, the process may only be performed by the higher level operating system of the flash storage system without an additional lower level process being performed by controllers of the flash drives.
Advantages of the process being performed only by the operating system of the flash storage system include increased reliability of the flash drives of the flash storage system as unnecessary or redundant write operations are not being performed during the process. One possible point of novelty here is the concept of initiating and controlling the process at the operating system of the flash storage system. In addition, the process can be controlled by the operating system across multiple flash drives. This is contrast to the process being performed by a storage controller of a flash drive.
A storage system can consist of two storage array controllers that share a set of drives for failover purposes, or it could consist of a single storage array controller that provides a storage service that utilizes multiple drives, or it could consist of a distributed network of storage array controllers each with some number of drives or some amount of Flash storage where the storage array controllers in the network collaborate to provide a complete storage service and collaborate on various aspects of a storage service including storage allocation and garbage collection.
In one embodiment, system 117 includes a dual Peripheral Component Interconnect (‘PCI’) flash storage device 118 with separately addressable fast write storage. System 117 may include a storage controller 119. In one embodiment, storage controller 119A-D may be a CPU, ASIC, FPGA, or any other circuitry that may implement control structures necessary according to the present disclosure. In one embodiment, system 117 includes flash memory devices (e.g., including flash memory devices 120a-n), operatively coupled to various channels of the storage device controller 119. Flash memory devices 120a-n, may be presented to the controller 119A-D as an addressable collection of Flash pages, erase blocks, and/or control elements sufficient to allow the storage device controller 119A-D to program and retrieve various aspects of the Flash. In one embodiment, storage device controller 119A-D may perform operations on flash memory devices 120a-n including storing and retrieving data content of pages, arranging and erasing any blocks, tracking statistics related to the use and reuse of Flash memory pages, erase blocks, and cells, tracking and predicting error codes and faults within the Flash memory, controlling voltage levels associated with programming and retrieving contents of Flash cells, etc.
In one embodiment, system 117 may include RAM 121 to store separately addressable fast-write data. In one embodiment, RAM 121 may be one or more separate discrete devices. In another embodiment, RAM 121 may be integrated into storage device controller 119A-D or multiple storage device controllers. The RAM 121 may be utilized for other purposes as well, such as temporary program memory for a processing device (e.g., a CPU) in the storage device controller 119.
In one embodiment, system 117 may include a stored energy device 122, such as a rechargeable battery or a capacitor. Stored energy device 122 may store energy sufficient to power the storage device controller 119, some amount of the RAM (e.g., RAM 121), and some amount of Flash memory (e.g., Flash memory 120a-120n) for sufficient time to write the contents of RAM to Flash memory. In one embodiment, storage device controller 119A-D may write the contents of RAM to Flash Memory if the storage device controller detects loss of external power.
In one embodiment, system 117 includes two data communications links 123a, 123b. In one embodiment, data communications links 123a, 123b may be PCI interfaces. In another embodiment, data communications links 123a, 123b may be based on other communications standards (e.g., HyperTransport, InfiniBand, etc.). Data communications links 123a, 123b may be based on non-volatile memory express (‘NVMe’) or NVMe over fabrics (‘NVMf’) specifications that allow external connection to the storage device controller 119A-D from other components in the storage system 117. It should be noted that data communications links may be interchangeably referred to herein as PCI buses for convenience.
System 117 may also include an external power source (not shown), which may be provided over one or both data communications links 123a, 123b, or which may be provided separately. An alternative embodiment includes a separate Flash memory (not shown) dedicated for use in storing the content of RAM 121. The storage device controller 119A-D may present a logical device over a PCI bus which may include an addressable fast-write logical device, or a distinct part of the logical address space of the storage device 118, which may be presented as PCI memory or as persistent storage. In one embodiment, operations to store into the device are directed into the RAM 121. On power failure, the storage device controller 119A-D may write stored content associated with the addressable fast-write logical storage to Flash memory (e.g., Flash memory 120a-n) for long-term persistent storage.
In one embodiment, the logical device may include some presentation of some or all of the content of the Flash memory devices 120a-n, where that presentation allows a storage system including a storage device 118 (e.g., storage system 117) to directly address Flash memory pages and directly reprogram erase blocks from storage system components that are external to the storage device through the PCI bus. The presentation may also allow one or more of the external components to control and retrieve other aspects of the Flash memory including some or all of: tracking statistics related to use and reuse of Flash memory pages, erase blocks, and cells across all the Flash memory devices; tracking and predicting error codes and faults within and across the Flash memory devices; controlling voltage levels associated with programming and retrieving contents of Flash cells; etc.
In one embodiment, the stored energy device 122 may be sufficient to ensure completion of in-progress operations to the Flash memory devices 120a-120n stored energy device 122 may power storage device controller 119A-D and associated Flash memory devices (e.g., 120a-n) for those operations, as well as for the storing of fast-write RAM to Flash memory. Stored energy device 122 may be used to store accumulated statistics and other parameters kept and tracked by the Flash memory devices 120a-n and/or the storage device controller 119. Separate capacitors or stored energy devices (such as smaller capacitors near or embedded within the Flash memory devices themselves) may be used for some or all of the operations described herein.
Various schemes may be used to track and optimize the life span of the stored energy component, such as adjusting voltage levels over time, partially discharging the storage energy device 122 to measure corresponding discharge characteristics, etc. If the available energy decreases over time, the effective available capacity of the addressable fast-write storage may be decreased to ensure that it can be written safely based on the currently available stored energy.
In one embodiment, two storage controllers (e.g., 125a and 125b) provide storage services, such as a SCS) block storage array, a file server, an object server, a database or data analytics service, etc. The storage controllers 125a, 125b may provide services through some number of network interfaces (e.g., 126a-d) to host computers 127a-n outside of the storage system 124. Storage controllers 125a, 125b may provide integrated services or an application entirely within the storage system 124, forming a converged storage and compute system. The storage controllers 125a, 125b may utilize the fast write memory within or across storage devices 119a-d to journal in progress operations to ensure the operations are not lost on a power failure, storage controller removal, storage controller or storage system shutdown, or some fault of one or more software or hardware components within the storage system 124.
In one embodiment, controllers 125a, 125b operate as PCI masters to one or the other PCI buses 128a, 128b. In another embodiment, 128a and 128b may be based on other communications standards (e.g., HyperTransport, InfiniBand, etc.). Other storage system embodiments may operate storage controllers 125a, 125b as multi-masters for both PCI buses 128a, 128b. Alternately, a PCI/NVMe/NVMf switching infrastructure or fabric may connect multiple storage controllers. Some storage system embodiments may allow storage devices to communicate with each other directly rather than communicating only with storage controllers. In one embodiment, a storage device controller 119a may be operable under direction from a storage controller 125a to synthesize and transfer data to be stored into Flash memory devices from data that has been stored in RAM (e.g., RAM 121 of
In one embodiment, under direction from a storage controller 125a, 125b, a storage device controller 119a, 119b may be operable to calculate and transfer data to other storage devices from data stored in RAM (e.g., RAM 121 of
A storage device controller 119A-D may include mechanisms for implementing high availability primitives for use by other parts of a storage system external to the Dual PCI storage device 118. For example, reservation or exclusion primitives may be provided so that, in a storage system with two storage controllers providing a highly available storage service, one storage controller may prevent the other storage controller from accessing or continuing to access the storage device. This could be used, for example, in cases where one controller detects that the other controller is not functioning properly or where the interconnect between the two storage controllers may itself not be functioning properly.
In one embodiment, a storage system for use with Dual PCI direct mapped storage devices with separately addressable fast write storage includes systems that manage erase blocks or groups of erase blocks as allocation units for storing data on behalf of the storage service, or for storing metadata (e.g., indexes, logs, etc.) associated with the storage service, or for proper management of the storage system itself. Flash pages, which may be a few kilobytes in size, may be written as data arrives or as the storage system is to persist data for long intervals of time (e.g., above a defined threshold of time). To commit data more quickly, or to reduce the number of writes to the Flash memory devices, the storage controllers may first write data into the separately addressable fast write storage on one more storage devices.
In one embodiment, the storage controllers 125a, 125b may initiate the use of erase blocks within and across storage devices (e.g., 118) in accordance with an age and expected remaining lifespan of the storage devices, or based on other statistics. The storage controllers 125a, 125b may initiate garbage collection and data migration data between storage devices in accordance with pages that are no longer needed as well as to manage Flash page and erase block lifespans and to manage overall system performance.
In one embodiment, the storage system 124 may utilize mirroring and/or erasure coding schemes as part of storing data into addressable fast write storage and/or as part of writing data into allocation units associated with erase blocks. Erasure codes may be used across storage devices, as well as within erase blocks or allocation units, or within and across Flash memory devices on a single storage device, to provide redundancy against single or multiple storage device failures or to protect against internal corruptions of Flash memory pages resulting from Flash memory operations or from degradation of Flash memory cells. Mirroring and erasure coding at various levels may be used to recover from multiple types of failures that occur separately or in combination.
The embodiments depicted with reference to
The storage cluster may be contained within a chassis, i.e., an enclosure housing one or more storage nodes. A mechanism to provide power to each storage node, such as a power distribution bus, and a communication mechanism, such as a communication bus that enables communication between the storage nodes are included within the chassis. The storage cluster can run as an independent system in one location according to some embodiments. In one embodiment, a chassis contains at least two instances of both the power distribution and the communication bus which may be enabled or disabled independently. The internal communication bus may be an Ethernet bus, however, other technologies such as PCIe, InfiniBand, and others, are equally suitable. The chassis provides a port for an external communication bus for enabling communication between multiple chassis, directly or through a switch, and with client systems. The external communication may use a technology such as Ethernet, InfiniBand, Fibre Channel, etc. In some embodiments, the external communication bus uses different communication bus technologies for inter-chassis and client communication. If a switch is deployed within or between chassis, the switch may act as a translation between multiple protocols or technologies. When multiple chassis are connected to define a storage cluster, the storage cluster may be accessed by a client using either proprietary interfaces or standard interfaces such as network file system (‘NFS’), common internet file system (‘CIFS’), small computer system interface (‘SCSI’) or hypertext transfer protocol (‘HTTP’). Translation from the client protocol may occur at the switch, chassis external communication bus or within each storage node. In some embodiments, multiple chassis may be coupled or connected to each other through an aggregator switch. A portion and/or all of the coupled or connected chassis may be designated as a storage cluster. As discussed above, each chassis can have multiple blades, each blade has a media access control (‘MAC’) address, but the storage cluster is presented to an external network as having a single cluster IP address and a single MAC address in some embodiments.
Each storage node may be one or more storage servers and each storage server is connected to one or more non-volatile solid state memory units, which may be referred to as storage units or storage devices. One embodiment includes a single storage server in each storage node and between one to eight non-volatile solid state memory units, however this one example is not meant to be limiting. The storage server may include a processor, DRAM and interfaces for the internal communication bus and power distribution for each of the power buses. Inside the storage node, the interfaces and storage unit share a communication bus, e.g., PCI Express, in some embodiments. The non-volatile solid state memory units may directly access the internal communication bus interface through a storage node communication bus, or request the storage node to access the bus interface. The non-volatile solid state memory unit contains an embedded CPU, solid state storage controller, and a quantity of solid state mass storage, e.g., between 2-32 terabytes (‘TB’) in some embodiments. An embedded volatile storage medium, such as DRAM, and an energy reserve apparatus are included in the non-volatile solid state memory unit. In some embodiments, the energy reserve apparatus is a capacitor, super-capacitor, or battery that enables transferring a subset of DRAM contents to a stable storage medium in the case of power loss. In some embodiments, the non-volatile solid state memory unit is constructed with a storage class memory, such as phase change or magnetoresistive random access memory (‘MRAM’) that substitutes for DRAM and enables a reduced power hold-up apparatus.
One of many features of the storage nodes and non-volatile solid state storage is the ability to proactively rebuild data in a storage cluster. The storage nodes and non-volatile solid state storage can determine when a storage node or non-volatile solid state storage in the storage cluster is unreachable, independent of whether there is an attempt to read data involving that storage node or non-volatile solid state storage. The storage nodes and non-volatile solid state storage then cooperate to recover and rebuild the data in at least partially new locations. This constitutes a proactive rebuild, in that the system rebuilds data without waiting until the data is needed for a read access initiated from a client system employing the storage cluster. These and further details of the storage memory and operation thereof are discussed below.
Each storage node 150 can have multiple components. In the embodiment shown here, the storage node 150 includes a printed circuit board 159 populated by a CPU 156, i.e., processor, a memory 154 coupled to the CPU 156, and a non-volatile solid state storage 152 coupled to the CPU 156, although other mountings and/or components could be used in further embodiments. The memory 154 has instructions which are executed by the CPU 156 and/or data operated on by the CPU 156. As further explained below, the non-volatile solid state storage 152 includes flash or, in further embodiments, other types of solid-state memory.
Referring to
Every piece of data, and every piece of metadata, has redundancy in the system in some embodiments. In addition, every piece of data and every piece of metadata has an owner, which may be referred to as an authority. If that authority is unreachable, for example through failure of a storage node, there is a plan of succession for how to find that data or that metadata. In various embodiments, there are redundant copies of authorities 168. Authorities 168 have a relationship to storage nodes 150 and non-volatile solid state storage 152 in some embodiments. Each authority 168, covering a range of data segment numbers or other identifiers of the data, may be assigned to a specific non-volatile solid state storage 152. In some embodiments the authorities 168 for all of such ranges are distributed over the non-volatile solid state storages 152 of a storage cluster. Each storage node 150 has a network port that provides access to the non-volatile solid state storage(s) 152 of that storage node 150. Data can be stored in a segment, which is associated with a segment number and that segment number is an indirection for a configuration of a RAID (redundant array of independent disks) stripe in some embodiments. The assignment and use of the authorities 168 thus establishes an indirection to data. Indirection may be referred to as the ability to reference data indirectly, in this case via an authority 168, in accordance with some embodiments. A segment identifies a set of non-volatile solid state storage 152 and a local identifier into the set of non-volatile solid state storage 152 that may contain data. In some embodiments, the local identifier is an offset into the device and may be reused sequentially by multiple segments. In other embodiments the local identifier is unique for a specific segment and never reused. The offsets in the non-volatile solid state storage 152 are applied to locating data for writing to or reading from the non-volatile solid state storage 152 (in the form of a RAID stripe). Data is striped across multiple units of non-volatile solid state storage 152, which may include or be different from the non-volatile solid state storage 152 having the authority 168 for a particular data segment.
If there is a change in where a particular segment of data is located, e.g., during a data move or a data reconstruction, the authority 168 for that data segment should be consulted, at that non-volatile solid state storage 152 or storage node 150 having that authority 168. In order to locate a particular piece of data, embodiments calculate a hash value for a data segment or apply an inode number or a data segment number. The output of this operation points to a non-volatile solid state storage 152 having the authority 168 for that particular piece of data. In some embodiments there are two stages to this operation. The first stage maps an entity identifier (ID), e.g., a segment number, inode number, or directory number to an authority identifier. This mapping may include a calculation such as a hash or a bit mask. The second stage is mapping the authority identifier to a particular non-volatile solid state storage 152, which may be done through an explicit mapping. The operation is repeatable, so that when the calculation is performed, the result of the calculation repeatably and reliably points to a particular non-volatile solid state storage 152 having that authority 168. The operation may include the set of reachable storage nodes as input. If the set of reachable non-volatile solid state storage units changes the optimal set changes. In some embodiments, the persisted value is the current assignment (which is always true) and the calculated value is the target assignment the cluster will attempt to reconfigure towards. This calculation may be used to determine the optimal non-volatile solid state storage 152 for an authority in the presence of a set of non-volatile solid state storage 152 that are reachable and constitute the same cluster. The calculation also determines an ordered set of peer non-volatile solid state storage 152 that will also record the authority to non-volatile solid state storage mapping so that the authority may be determined even if the assigned non-volatile solid state storage is unreachable. A duplicate or substitute authority 168 may be consulted if a specific authority 168 is unavailable in some embodiments.
With reference to
In some systems, for example in UNIX-style file systems, data is handled with an index node or inode, which specifies a data structure that represents an object in a file system. The object could be a file or a directory, for example. Metadata may accompany the object, as attributes such as permission data and a creation timestamp, among other attributes. A segment number could be assigned to all or a portion of such an object in a file system. In other systems, data segments are handled with a segment number assigned elsewhere. For purposes of discussion, the unit of distribution is an entity, and an entity can be a file, a directory or a segment. That is, entities are units of data or metadata stored by a storage system. Entities are grouped into sets called authorities. Each authority has an authority owner, which is a storage node that has the exclusive right to update the entities in the authority. In other words, a storage node contains the authority, and that the authority, in turn, contains entities.
A segment is a logical container of data in accordance with some embodiments. A segment is an address space between medium address space and physical flash locations, i.e., the data segment number, are in this address space. Segments may also contain meta-data, which enable data redundancy to be restored (rewritten to different flash locations or devices) without the involvement of higher level software. In one embodiment, an internal format of a segment contains client data and medium mappings to determine the position of that data. Each data segment is protected, e.g., from memory and other failures, by breaking the segment into a number of data and parity shards, where applicable. The data and parity shards are distributed, i.e., striped, across non-volatile solid state storage 152 coupled to the host CPUs 156 (See
A series of address-space transformations takes place across an entire storage system. At the top are the directory entries (file names) which link to an inode. Modes point into medium address space, where data is logically stored. Medium addresses may be mapped through a series of indirect mediums to spread the load of large files, or implement data services like deduplication or snapshots. Medium addresses may be mapped through a series of indirect mediums to spread the load of large files, or implement data services like deduplication or snapshots. Segment addresses are then translated into physical flash locations. Physical flash locations have an address range bounded by the amount of flash in the system in accordance with some embodiments. Medium addresses and segment addresses are logical containers, and in some embodiments use a 128 bit or larger identifier so as to be practically infinite, with a likelihood of reuse calculated as longer than the expected life of the system. Addresses from logical containers are allocated in a hierarchical fashion in some embodiments. Initially, each non-volatile solid state storage unit 152 may be assigned a range of address space. Within this assigned range, the non-volatile solid state storage 152 is able to allocate addresses without synchronization with other non-volatile solid state storage 152.
Data and metadata is stored by a set of underlying storage layouts that are optimized for varying workload patterns and storage devices. These layouts incorporate multiple redundancy schemes, compression formats and index algorithms. Some of these layouts store information about authorities and authority masters, while others store file metadata and file data. The redundancy schemes include error correction codes that tolerate corrupted bits within a single storage device (such as a NAND flash chip), erasure codes that tolerate the failure of multiple storage nodes, and replication schemes that tolerate data center or regional failures. In some embodiments, low density parity check (‘LDPC’) code is used within a single storage unit. Reed-Solomon encoding is used within a storage cluster, and mirroring is used within a storage grid in some embodiments. Metadata may be stored using an ordered log structured index (such as a Log Structured Merge Tree), and large data may not be stored in a log structured layout.
In order to maintain consistency across multiple copies of an entity, the storage nodes agree implicitly on two things through calculations: (1) the authority that contains the entity, and (2) the storage node that contains the authority. The assignment of entities to authorities can be done by pseudo randomly assigning entities to authorities, by splitting entities into ranges based upon an externally produced key, or by placing a single entity into each authority. Examples of pseudorandom schemes are linear hashing and the Replication Under Scalable Hashing (‘RUSH’) family of hashes, including Controlled Replication Under Scalable Hashing (‘CRUSH’). In some embodiments, pseudo-random assignment is utilized only for assigning authorities to nodes because the set of nodes can change. The set of authorities cannot change so any subjective function may be applied in these embodiments. Some placement schemes automatically place authorities on storage nodes, while other placement schemes rely on an explicit mapping of authorities to storage nodes. In some embodiments, a pseudorandom scheme is utilized to map from each authority to a set of candidate authority owners. A pseudorandom data distribution function related to CRUSH may assign authorities to storage nodes and create a list of where the authorities are assigned. Each storage node has a copy of the pseudorandom data distribution function, and can arrive at the same calculation for distributing, and later finding or locating an authority. Each of the pseudorandom schemes requires the reachable set of storage nodes as input in some embodiments in order to conclude the same target nodes. Once an entity has been placed in an authority, the entity may be stored on physical devices so that no expected failure will lead to unexpected data loss. In some embodiments, rebalancing algorithms attempt to store the copies of all entities within an authority in the same layout and on the same set of machines.
Examples of expected failures include device failures, stolen machines, datacenter fires, and regional disasters, such as nuclear or geological events. Different failures lead to different levels of acceptable data loss. In some embodiments, a stolen storage node impacts neither the security nor the reliability of the system, while depending on system configuration, a regional event could lead to no loss of data, a few seconds or minutes of lost updates, or even complete data loss.
In the embodiments, the placement of data for storage redundancy is independent of the placement of authorities for data consistency. In some embodiments, storage nodes that contain authorities do not contain any persistent storage. Instead, the storage nodes are connected to non-volatile solid state storage units that do not contain authorities. The communications interconnect between storage nodes and non-volatile solid state storage units consists of multiple communication technologies and has non-uniform performance and fault tolerance characteristics. In some embodiments, as mentioned above, non-volatile solid state storage units are connected to storage nodes via PCI express, storage nodes are connected together within a single chassis using Ethernet backplane, and chassis are connected together to form a storage cluster. Storage clusters are connected to clients using Ethernet or fibre channel in some embodiments. If multiple storage clusters are configured into a storage grid, the multiple storage clusters are connected using the Internet or other long-distance networking links, such as a “metro scale” link or private link that does not traverse the internet.
Authority owners have the exclusive right to modify entities, to migrate entities from one non-volatile solid state storage unit to another non-volatile solid state storage unit, and to add and remove copies of entities. This allows for maintaining the redundancy of the underlying data. When an authority owner fails, is going to be decommissioned, or is overloaded, the authority is transferred to a new storage node. Transient failures make it non-trivial to ensure that all non-faulty machines agree upon the new authority location. The ambiguity that arises due to transient failures can be achieved automatically by a consensus protocol such as Paxos, hot-warm failover schemes, via manual intervention by a remote system administrator, or by a local hardware administrator (such as by physically removing the failed machine from the cluster, or pressing a button on the failed machine). In some embodiments, a consensus protocol is used, and failover is automatic. If too many failures or replication events occur in too short a time period, the system goes into a self-preservation mode and halts replication and data movement activities until an administrator intervenes in accordance with some embodiments.
As authorities are transferred between storage nodes and authority owners update entities in their authorities, the system transfers messages between the storage nodes and non-volatile solid state storage units. With regard to persistent messages, messages that have different purposes are of different types. Depending on the type of the message, the system maintains different ordering and durability guarantees. As the persistent messages are being processed, the messages are temporarily stored in multiple durable and non-durable storage hardware technologies. In some embodiments, messages are stored in RAM, NVRAM and on NAND flash devices, and a variety of protocols are used in order to make efficient use of each storage medium. Latency-sensitive client requests may be persisted in replicated NVRAM, and then later NAND, while background rebalancing operations are persisted directly to NAND.
Persistent messages are persistently stored prior to being transmitted. This allows the system to continue to serve client requests despite failures and component replacement. Although many hardware components contain unique identifiers that are visible to system administrators, manufacturer, hardware supply chain and ongoing monitoring quality control infrastructure, applications running on top of the infrastructure address virtualize addresses. These virtualized addresses do not change over the lifetime of the storage system, regardless of component failures and replacements. This allows each component of the storage system to be replaced over time without reconfiguration or disruptions of client request processing, i.e., the system supports non-disruptive upgrades.
In some embodiments, the virtualized addresses are stored with sufficient redundancy. A continuous monitoring system correlates hardware and software status and the hardware identifiers. This allows detection and prediction of failures due to faulty components and manufacturing details. The monitoring system also enables the proactive transfer of authorities and entities away from impacted devices before failure occurs by removing the component from the critical path in some embodiments.
Storage clusters 161, in various embodiments as disclosed herein, can be contrasted with storage arrays in general. The storage nodes 150 are part of a collection that creates the storage cluster 161. Each storage node 150 owns a slice of data and computing required to provide the data. Multiple storage nodes 150 cooperate to store and retrieve the data. Storage memory or storage devices, as used in storage arrays in general, are less involved with processing and manipulating the data. Storage memory or storage devices in a storage array receive commands to read, write, or erase data. The storage memory or storage devices in a storage array are not aware of a larger system in which they are embedded, or what the data means. Storage memory or storage devices in storage arrays can include various types of storage memory, such as RAM, solid state drives, hard disk drives, etc. The storage units 152 described herein have multiple interfaces active simultaneously and serving multiple purposes. In some embodiments, some of the functionality of a storage node 150 is shifted into a storage unit 152, transforming the storage unit 152 into a combination of storage unit 152 and storage node 150. Placing computing (relative to storage data) into the storage unit 152 places this computing closer to the data itself. The various system embodiments have a hierarchy of storage node layers with different capabilities. By contrast, in a storage array, a controller owns and knows everything about all of the data that the controller manages in a shelf or storage devices. In a storage cluster 161, as described herein, multiple controllers in multiple storage units 152 and/or storage nodes 150 cooperate in various ways (e.g., for erasure coding, data sharding, metadata communication and redundancy, storage capacity expansion or contraction, data recovery, and so on).
The physical storage is divided into named regions based on application usage in some embodiments. The NVRAM 204 is a contiguous block of reserved memory in the storage unit 152 DRAM 216, and is backed by NAND flash. NVRAM 204 is logically divided into multiple memory regions written for two as spool (e.g., spool_region). Space within the NVRAM 204 spools is managed by each authority 168 independently. Each device provides an amount of storage space to each authority 168. That authority 168 further manages lifetimes and allocations within that space. Examples of a spool include distributed transactions or notions. When the primary power to a storage unit 152 fails, onboard super-capacitors provide a short duration of power hold up. During this holdup interval, the contents of the NVRAM 204 are flushed to flash memory 206. On the next power-on, the contents of the NVRAM 204 are recovered from the flash memory 206.
As for the storage unit controller, the responsibility of the logical “controller” is distributed across each of the blades containing authorities 168. This distribution of logical control is shown in
In the compute and storage planes 256, 258 of
Still referring to
Because authorities 168 are stateless, they can migrate between blades 252. Each authority 168 has a unique identifier. NVRAM 204 and flash 206 partitions are associated with authorities' 168 identifiers, not with the blades 252 on which they are running in some. Thus, when an authority 168 migrates, the authority 168 continues to manage the same storage partitions from its new location. When a new blade 252 is installed in an embodiment of the storage cluster, the system automatically rebalances load by: partitioning the new blade's 252 storage for use by the system's authorities 168, migrating selected authorities 168 to the new blade 252, starting endpoints 272 on the new blade 252 and including them in the switch fabric's 146 client connection distribution algorithm.
From their new locations, migrated authorities 168 persist the contents of their NVRAM 204 partitions on flash 206, process read and write requests from other authorities 168, and fulfill the client requests that endpoints 272 direct to them. Similarly, if a blade 252 fails or is removed, the system redistributes its authorities 168 among the system's remaining blades 252. The redistributed authorities 168 continue to perform their original functions from their new locations.
The embodiments described herein may utilize various software, communication and/or networking protocols. In addition, the configuration of the hardware and/or software may be adjusted to accommodate various protocols. For example, the embodiments may utilize Active Directory, which is a database based system that provides authentication, directory, policy, and other services in a WINDOWS™ environment. In these embodiments, LDAP (Lightweight Directory Access Protocol) is one example application protocol for querying and modifying items in directory service providers such as Active Directory. In some embodiments, a network lock manager (‘NLM’) is utilized as a facility that works in cooperation with the Network File System (‘NFS’) to provide a System V style of advisory file and record locking over a network. The Server Message Block (‘SMB’) protocol, one version of which is also known as Common Internet File System (‘CIFS’), may be integrated with the storage systems discussed herein. SMP operates as an application-layer network protocol typically used for providing shared access to files, printers, and serial ports and miscellaneous communications between nodes on a network. SMB also provides an authenticated inter-process communication mechanism. AMAZON™ S3 (Simple Storage Service) is a web service offered by Amazon Web Services, and the systems described herein may interface with Amazon S3 through web services interfaces (REST (representational state transfer), SOAP (simple object access protocol), and BitTorrent). A RESTful API (application programming interface) breaks down a transaction to create a series of small modules. Each module addresses a particular underlying part of the transaction. The control or permissions provided with these embodiments, especially for object data, may include utilization of an access control list (‘ACL’). The ACL is a list of permissions attached to an object and the ACL specifies which users or system processes are granted access to objects, as well as what operations are allowed on given objects. The systems may utilize Internet Protocol version 6 (‘IPv6’), as well as IPv4, for the communications protocol that provides an identification and location system for computers on networks and routes traffic across the Internet. The routing of packets between networked systems may include Equal-cost multi-path routing (‘ECMP’), which is a routing strategy where next-hop packet forwarding to a single destination can occur over multiple “best paths” which tie for top place in routing metric calculations. Multi-path routing can be used in conjunction with most routing protocols, because it is a per-hop decision limited to a single router. The software may support Multi-tenancy, which is an architecture in which a single instance of a software application serves multiple customers. Each customer may be referred to as a tenant. Tenants may be given the ability to customize some parts of the application, but may not customize the application's code, in some embodiments. The embodiments may maintain audit logs. An audit log is a document that records an event in a computing system. In addition to documenting what resources were accessed, audit log entries typically include destination and source addresses, a timestamp, and user login information for compliance with various regulations. The embodiments may support various key management policies, such as encryption key rotation. In addition, the system may support dynamic root passwords or some variation dynamically changing passwords.
In the example depicted in
The cloud services provider 302 depicted in
In the example depicted in
In the example depicted in
Although not explicitly depicted in
In order to enable the storage system 306 and users of the storage system 306 to make use of the services provided by the cloud services provider 302, a cloud migration process may take place during which data, applications, or other elements from an organization's local systems (or even from another cloud environment) are moved to the cloud services provider 302. In order to successfully migrate data, applications, or other elements to the cloud services provider's 302 environment, middleware such as a cloud migration tool may be utilized to bridge gaps between the cloud services provider's 302 environment and an organization's environment. Such cloud migration tools may also be configured to address potentially high network costs and long transfer times associated with migrating large volumes of data to the cloud services provider 302, as well as addressing security concerns associated with sensitive data to the cloud services provider 302 over data communications networks. In order to further enable the storage system 306 and users of the storage system 306 to make use of the services provided by the cloud services provider 302, a cloud orchestrator may also be used to arrange and coordinate automated tasks in pursuit of creating a consolidated process or workflow. Such a cloud orchestrator may perform tasks such as configuring various components, whether those components are cloud components or on-premises components, as well as managing the interconnections between such components. The cloud orchestrator can simplify the inter-component communication and connections to ensure that links are correctly configured and maintained.
In the example depicted in
The cloud services provider 302 may also be configured to provide access to virtualized computing environments to the storage system 306 and users of the storage system 306. Such virtualized computing environments may be embodied, for example, as a virtual machine or other virtualized computer hardware platforms, virtual storage devices, virtualized computer network resources, and so on. Examples of such virtualized environments can include virtual machines that are created to emulate an actual computer, virtualized desktop environments that separate a logical desktop from a physical machine, virtualized file systems that allow uniform access to different types of concrete file systems, and many others.
For further explanation,
The storage system 306 depicted in
The example storage system 306 depicted in
The example storage system 306 depicted in
The storage system 306 depicted in
The storage system 306 depicted in
The storage system 306 depicted in
The software resources 314 may also include software that is useful in implementing software-defined storage (‘SDS’). In such an example, the software resources 314 may include one or more modules of computer program instructions that, when executed, are useful in policy-based provisioning and management of data storage that is independent of the underlying hardware. Such software resources 314 may be useful in implementing storage virtualization to separate the storage hardware from the software that manages the storage hardware.
The software resources 314 may also include software that is useful in facilitating and optimizing I/O operations that are directed to the storage resources 308 in the storage system 306. For example, the software resources 314 may include software modules that perform carry out various data reduction techniques such as, for example, data compression, data deduplication, and others. The software resources 314 may include software modules that intelligently group together I/O operations to facilitate better usage of the underlying storage resource 308, software modules that perform data migration operations to migrate from within a storage system, as well as software modules that perform other functions. Such software resources 314 may be embodied as one or more software containers or in many other ways.
Readers will appreciate that the presence of such software resources 314 may provide for an improved user experience of the storage system 306, an expansion of functionality supported by the storage system 306, and many other benefits. Consider the specific example of the software resources 314 carrying out data backup techniques through which data stored in the storage system may be copied and stored in a distinct location to avoid data loss in the event of equipment failure or some other form of catastrophe. In such an example, the systems described herein may more reliably (and with less burden placed on the user) perform backup operations relative to interactive backup management systems that require high degrees of user interactivity, offer less robust automation and feature sets, and so on.
The storage systems described above may carry out intelligent data backup techniques through which data stored in the storage system may be copied and stored in a distinct location to avoid data loss in the event of equipment failure or some other form of catastrophe. For example, the storage systems described above may be configured to examine each backup to avoid restoring the storage system to an undesirable state. Consider an example in which malware infects the storage system. In such an example, the storage system may include software resources 314 that can scan each backup to identify backups that were captured before the malware infected the storage system and those backups that were captured after the malware infected the storage system. In such an example, the storage system may restore itself from a backup that does not include the malware—or at least not restore the portions of a backup that contained the malware. In such an example, the storage system may include software resources 314 that can scan each backup to identify the presences of malware (or a virus, or some other undesirable), for example, by identifying write operations that were serviced by the storage system and originated from a network subnet that is suspected to have delivered the malware, by identifying write operations that were serviced by the storage system and originated from a user that is suspected to have delivered the malware, by identifying write operations that were serviced by the storage system and examining the content of the write operation against fingerprints of the malware, and in many other ways.
Readers will further appreciate that the backups (often in the form of one or more snapshots) may also be utilized to perform rapid recovery of the storage system. Consider an example in which the storage system is infected with ransomware that locks users out of the storage system. In such an example, software resources 314 within the storage system may be configured to detect the presence of ransomware and may be further configured to restore the storage system to a point-in-time, using the retained backups, prior to the point-in-time at which the ransomware infected the storage system. In such an example, the presence of ransomware may be explicitly detected through the use of software tools utilized by the system, through the use of a key (e.g., a USB drive) that is inserted into the storage system, or in a similar way. Likewise, the presence of ransomware may be inferred in response to system activity meeting a predetermined fingerprint such as, for example, no reads or writes coming into the system for a predetermined period of time.
Readers will appreciate that the various components depicted in
Readers will appreciate that the storage system 306 depicted in
The storage systems described above may operate to support a wide variety of applications. In view of the fact that the storage systems include compute resources, storage resources, and a wide variety of other resources, the storage systems may be well suited to support applications that are resource intensive such as, for example, AI applications. Such AI applications may enable devices to perceive their environment and take actions that maximize their chance of success at some goal. Examples of such AI applications can include IBM Watson, Microsoft Oxford, Google DeepMind, Baidu Minwa, and others. The storage systems described above may also be well suited to support other types of applications that are resource intensive such as, for example, machine learning applications. Machine learning applications may perform various types of data analysis to automate analytical model building. Using algorithms that iteratively learn from data, machine learning applications can enable computers to learn without being explicitly programmed.
In addition to the resources already described, the storage systems described above may also include graphics processing units (‘GPUs’), occasionally referred to as visual processing unit (‘VDUs’). Such GPUs may be embodied as specialized electronic circuits that rapidly manipulate and alter memory to accelerate the creation of images in a frame buffer intended for output to a display device. Such GPUs may be included within any of the computing devices that are part of the storage systems described above, including as one of many individually scalable components of a storage system, where other examples of individually scalable components of such storage system can include storage components, memory components, compute components (e.g., CPUs, FPGAs, ASICs), networking components, software components, and others. In addition to GPUs, the storage systems described above may also include neural network processors (‘NNPs’) for use in various aspects of neural network processing. Such NNPs may be used in place of (or in addition to) GPUs and may be also be independently scalable.
As described above, the storage systems described herein may be configured to support artificial intelligence applications, machine learning applications, big data analytics applications, and many other types of applications. The rapid growth in these sort of applications is being driven by three technologies: deep learning (DL), GPU processors, and Big Data. Deep learning is a computing model that makes use of massively parallel neural networks inspired by the human brain. Instead of experts handcrafting software, a deep learning model writes its own software by learning from lots of examples. A GPU is a modern processor with thousands of cores, well-suited to run algorithms that loosely represent the parallel nature of the human brain.
Advances in deep neural networks have ignited a new wave of algorithms and tools for data scientists to tap into their data with artificial intelligence (AI). With improved algorithms, larger data sets, and various frameworks (including open-source software libraries for machine learning across a range of tasks), data scientists are tackling new use cases like autonomous driving vehicles, natural language processing and understanding, computer vision, machine reasoning, strong AI, and many others. Applications of such techniques may include: machine and vehicular object detection, identification and avoidance; visual recognition, classification and tagging; algorithmic financial trading strategy performance management; simultaneous localization and mapping; predictive maintenance of high-value machinery; prevention against cyber security threats, expertise automation; image recognition and classification; question answering; robotics; text analytics (extraction, classification) and text generation and translation; and many others. Applications of AI techniques has materialized in a wide array of products include, for example, Amazon Echo's speech recognition technology that allows users to talk to their machines, Google Translate™ which allows for machine-based language translation, Spotify's Discover Weekly that provides recommendations on new songs and artists that a user may like based on the user's usage and traffic analysis, Quill's text generation offering that takes structured data and turns it into narrative stories, Chatbots that provide real-time, contextually specific answers to questions in a dialog format, and many others. Furthermore, AI may impact a wide variety of industries and sectors. For example, AI solutions may be used in healthcare to take clinical notes, patient files, research data, and other inputs to generate potential treatment options for doctors to explore. Likewise, AI solutions may be used by retailers to personalize consumer recommendations based on a person's digital footprint of behaviors, profile data, or other data.
Training deep neural networks, however, requires both high quality input data and large amounts of computation. GPUs are massively parallel processors capable of operating on large amounts of data simultaneously. When combined into a multi-GPU cluster, a high throughput pipeline may be required to feed input data from storage to the compute engines. Deep learning is more than just constructing and training models. There also exists an entire data pipeline that must be designed for the scale, iteration, and experimentation necessary for a data science team to succeed.
Data is the heart of modern AI and deep learning algorithms. Before training can begin, one problem that must be addressed revolves around collecting the labeled data that is crucial for training an accurate AI model. A full scale AI deployment may be required to continuously collect, clean, transform, label, and store large amounts of data. Adding additional high quality data points directly translates to more accurate models and better insights. Data samples may undergo a series of processing steps including, but not limited to: 1) ingesting the data from an external source into the training system and storing the data in raw form, 2) cleaning and transforming the data in a format convenient for training, including linking data samples to the appropriate label, 3) exploring parameters and models, quickly testing with a smaller dataset, and iterating to converge on the most promising models to push into the production cluster, 4) executing training phases to select random batches of input data, including both new and older samples, and feeding those into production GPU servers for computation to update model parameters, and 5) evaluating including using a holdback portion of the data not used in training in order to evaluate model accuracy on the holdout data. This lifecycle may apply for any type of parallelized machine learning, not just neural networks or deep learning. For example, standard machine learning frameworks may rely on CPUs instead of GPUs but the data ingest and training workflows may be the same. Readers will appreciate that a single shared storage data hub creates a coordination point throughout the lifecycle without the need for extra data copies among the ingest, preprocessing, and training stages. Rarely is the ingested data used for only one purpose, and shared storage gives the flexibility to train multiple different models or apply traditional analytics to the data.
Readers will appreciate that each stage in the AI data pipeline may have varying requirements from the data hub (e.g., the storage system or collection of storage systems). Scale-out storage systems must deliver uncompromising performance for all manner of access types and patterns—from small, metadata-heavy to large files, from random to sequential access patterns, and from low to high concurrency. The storage systems described above may serve as an ideal AI data hub as the systems may service unstructured workloads. In the first stage, data is ideally ingested and stored on to the same data hub that following stages will use, in order to avoid excess data copying. The next two steps can be done on a standard compute server that optionally includes a GPU, and then in the fourth and last stage, full training production jobs are run on powerful GPU-accelerated servers. Often, there is a production pipeline alongside an experimental pipeline operating on the same dataset. Further, the GPU-accelerated servers can be used independently for different models or joined together to train on one larger model, even spanning multiple systems for distributed training. If the shared storage tier is slow, then data must be copied to local storage for each phase, resulting in wasted time staging data onto different servers. The ideal data hub for the AI training pipeline delivers performance similar to data stored locally on the server node while also having the simplicity and performance to enable all pipeline stages to operate concurrently.
A data scientist works to improve the usefulness of the trained model through a wide variety of approaches: more data, better data, smarter training, and deeper models. In many cases, there will be teams of data scientists sharing the same datasets and working in parallel to produce new and improved training models. Often, there is a team of data scientists working within these phases concurrently on the same shared datasets. Multiple, concurrent workloads of data processing, experimentation, and full-scale training layer the demands of multiple access patterns on the storage tier. In other words, storage cannot just satisfy large file reads, but must contend with a mix of large and small file reads and writes. Finally, with multiple data scientists exploring datasets and models, it may be critical to store data in its native format to provide flexibility for each user to transform, clean, and use the data in a unique way. The storage systems described above may provide a natural shared storage home for the dataset, with data protection redundancy (e.g., by using RAID6) and the performance necessary to be a common access point for multiple developers and multiple experiments. Using the storage systems described above may avoid the need to carefully copy subsets of the data for local work, saving both engineering and GPU-accelerated servers use time. These copies become a constant and growing tax as the raw data set and desired transformations constantly update and change.
Readers will appreciate that a fundamental reason why deep learning has seen a surge in success is the continued improvement of models with larger data set sizes. In contrast, classical machine learning algorithms, like logistic regression, stop improving in accuracy at smaller data set sizes. As such, the separation of compute resources and storage resources may also allow independent scaling of each tier, avoiding many of the complexities inherent in managing both together. As the data set size grows or new data sets are considered, a scale out storage system must be able to expand easily. Similarly, if more concurrent training is required, additional GPUs or other compute resources can be added without concern for their internal storage. Furthermore, the storage systems described above may make building, operating, and growing an AI system easier due to the random read bandwidth provided by the storage systems, the ability to of the storage systems to randomly read small files (50 KB) high rates (meaning that no extra effort is required to aggregate individual data points to make larger, storage-friendly files), the ability of the storage systems to scale capacity and performance as either the dataset grows or the throughput requirements grow, the ability of the storage systems to support files or objects, the ability of the storage systems to tune performance for large or small files (i.e., no need for the user to provision filesystems), the ability of the storage systems to support non-disruptive upgrades of hardware and software even during production model training, and for many other reasons.
Small file performance of the storage tier may be critical as many types of inputs, including text, audio, or images will be natively stored as small files. If the storage tier does not handle small files well, an extra step will be required to pre-process and group samples into larger files. Storage, built on top of spinning disks, that relies on SSD as a caching tier, may fall short of the performance needed. Because training with random input batches results in more accurate models, the entire data set must be accessible with full performance. SSD caches only provide high performance for a small subset of the data and will be ineffective at hiding the latency of spinning drives.
Although the preceding paragraphs discuss deep learning applications, readers will appreciate that the storage systems described herein may also be part of a distributed deep learning (‘DDL’) platform to support the execution of DDL algorithms. Distributed deep learning may can be used to significantly accelerate deep learning with distributed computing on GPUs (or other form of accelerator or computer program instruction executor), such that parallelism can be achieved. In addition, the output of training machine learning and deep learning models, such as a fully trained machine learning model, may be used for a variety of purposes and in conjunction with other tools. For example, trained machine learning models may be used in conjunction with tools like Core ML to integrate a broad variety of machine learning model types into an application. In fact, trained models may be run through Core ML converter tools and inserted into a custom application that can be deployed on compatible devices. The storage systems described above may also be paired with other technologies such as TensorFlow, an open-source software library for dataflow programming across a range of tasks that may be used for machine learning applications such as neural networks, to facilitate the development of such machine learning models, applications, and so on.
Readers will further appreciate that the systems described above may be deployed in a variety of ways to support the democratization of AI, as AI becomes more available for mass consumption. The democratization of AI may include, for example, the ability to offer AI as a Platform-as-a-Service, the growth of Artificial general intelligence offerings, the proliferation of Autonomous level 4 and Autonomous level 5 vehicles, the availability of autonomous mobile robots, the development of conversational AI platforms, and many others. For example, the systems described above may be deployed in cloud environments, edge environments, or other environments that are useful in supporting the democratization of AI. As part of the democratization of AI, a movement may occur from narrow AI that consists of highly scoped machine learning solutions that target a particular task to artificial general intelligence where the use of machine learning is expanded to handle a broad range of use cases that could essentially perform any intelligent task that a human could perform and could learn dynamically, much like a human.
The storage systems described above may also be used in a neuromorphic computing environment. Neuromorphic computing is a form of computing that mimics brain cells. To support neuromorphic computing, an architecture of interconnected “neurons” replace traditional computing models with low-powered signals that go directly between neurons for more efficient computation. Neuromorphic computing may make use of very-large-scale integration (VLSI) systems containing electronic analog circuits to mimic neuro-biological architectures present in the nervous system, as well as analog, digital, mixed-mode analog/digital VLSI, and software systems that implement models of neural systems for perception, motor control, or multisensory integration.
Readers will appreciate that the storage systems described above may be configured to support the storage or use of (among other types of data) blockchains. Such blockchains may be embodied as a continuously growing list of records, called blocks, which are linked and secured using cryptography. Each block in a blockchain may contain a hash pointer as a link to a previous block, a timestamp, transaction data, and so on. Blockchains may be designed to be resistant to modification of the data and can serve as an open, distributed ledger that can record transactions between two parties efficiently and in a verifiable and permanent way. This makes blockchains potentially suitable for the recording of events, medical records, and other records management activities, such as identity management, transaction processing, and others. In addition to supporting the storage and use of blockchain technologies, the storage systems described above may also support the storage and use of derivative items such as, for example, open source blockchains and related tools that are part of the IBM™ Hyperledger project, permissioned blockchains in which a certain number of trusted parties are allowed to access the block chain, blockchain products that enable developers to build their own distributed ledger projects, and others. Readers will appreciate that blockchain technologies may impact a wide variety of industries and sectors. For example, blockchain technologies may be used in real estate transactions as blockchain based contracts whose use can eliminate the need for 3rd parties and enable self-executing actions when conditions are met. Likewise, universal health records can be created by aggregating and placing a person's health history onto a blockchain ledger for any healthcare provider, or permissioned health care providers, to access and update.
Readers will appreciate that the usage of blockchains is not limited to financial transactions, contracts, and the like. In fact, blockchains may be leveraged to enable the decentralized aggregation, ordering, timestamping and archiving of any type of information, including structured data, correspondence, documentation, or other data. Through the usage of blockchains, participants can provably and permanently agree on exactly what data was entered, when and by whom, without relying on a trusted intermediary. For example, SAP's recently launched blockchain platform, which supports MultiChain and Hyperledger Fabric, targets a broad range of supply chain and other non-financial applications.
One way to use a blockchain for recording data is to embed each piece of data directly inside a transaction. Every blockchain transaction may be digitally signed by one or more parties, replicated to a plurality of nodes, ordered and timestamped by the chain's consensus algorithm, and stored permanently in a tamper-proof way. Any data within the transaction will therefore be stored identically but independently by every node, along with a proof of who wrote it and when. The chain's users are able to retrieve this information at any future time. This type of storage may be referred to as on-chain storage. On-chain storage may not be particularly practical, however, when attempting to store a very large dataset. As such, in accordance with embodiments of the present disclosure, blockchains and the storage systems described herein may be leveraged to support on-chain storage of data as well as off-chain storage of data.
Off-chain storage of data can be implemented in a variety of ways and can occur when the data itself is not stored within the blockchain. For example, in one embodiment, a hash function may be utilized and the data itself may be fed into the hash function to generate a hash value. In such an example, the hashes of large pieces of data may be embedded within transactions, instead of the data itself. Each hash may serve as a commitment to its input data, with the data itself being stored outside of the blockchain. Readers will appreciate that any blockchain participant that needs an off-chain piece of data cannot reproduce the data from its hash, but if the data can be retrieved in some other way, then the on-chain hash serves to confirm who created it and when. Just like regular on-chain data, the hash may be embedded inside a digitally signed transaction, which was included in the chain by consensus.
Readers will appreciate that, in other embodiments, alternatives to blockchains may be used to facilitate the decentralized storage of information. For example, one alternative to a blockchain that may be used is a blockweave. While conventional blockchains store every transaction to achieve validation, a blockweave permits secure decentralization without the usage of the entire chain, thereby enabling low cost on-chain storage of data. Such blockweaves may utilize a consensus mechanism that is based on proof of access (PoA) and proof of work (PoW). While typical PoW systems only depend on the previous block in order to generate each successive block, the PoA algorithm may incorporate data from a randomly chosen previous block. Combined with the blockweave data structure, miners do not need to store all blocks (forming a blockchain), but rather can store any previous blocks forming a weave of blocks (a blockweave). This enables increased levels of scalability, speed and low-cost and reduces the cost of data storage in part because miners need not store all blocks, thereby resulting in a substantial reduction in the amount of electricity that is consumed during the mining process because, as the network expands, electricity consumption decreases because a blockweave demands less and less hashing power for consensus as data is added to the system. Furthermore, blockweaves may be deployed on a decentralized storage network in which incentives are created to encourage rapid data sharing. Such decentralized storage networks may also make use of blockshadowing techniques, where nodes only send a minimal block “shadow” to other nodes that allows peers to reconstruct a full block, instead of transmitting the full block itself.
The storage systems described above may, either alone or in combination with other computing devices, be used to support in-memory computing applications. In memory computing involves the storage of information in RAM that is distributed across a cluster of computers. In-memory computing helps business customers, including retailers, banks and utilities, to quickly detect patterns, analyze massive data volumes on the fly, and perform their operations quickly. Readers will appreciate that the storage systems described above, especially those that are configurable with customizable amounts of processing resources, storage resources, and memory resources (e.g., those systems in which blades that contain configurable amounts of each type of resource), may be configured in a way so as to provide an infrastructure that can support in-memory computing. Likewise, the storage systems described above may include component parts (e.g., NVDIMMs, 3D crosspoint storage that provide fast random access memory that is persistent) that can actually provide for an improved in-memory computing environment as compared to in-memory computing environments that rely on RAM distributed across dedicated servers.
In some embodiments, the storage systems described above may be configured to operate as a hybrid in-memory computing environment that includes a universal interface to all storage media (e.g., RAM, flash storage, 3D crosspoint storage). In such embodiments, users may have no knowledge regarding the details of where their data is stored but they can still use the same full, unified API to address data. In such embodiments, the storage system may (in the background) move data to the fastest layer available—including intelligently placing the data in dependence upon various characteristics of the data or in dependence upon some other heuristic. In such an example, the storage systems may even make use of existing products such as Apache Ignite and GridGain to move data between the various storage layers, or the storage systems may make use of custom software to move data between the various storage layers. The storage systems described herein may implement various optimizations to improve the performance of in-memory computing such as, for example, having computations occur as close to the data as possible.
Readers will further appreciate that in some embodiments, the storage systems described above may be paired with other resources to support the applications described above. For example, one infrastructure could include primary compute in the form of servers and workstations which specialize in using General-purpose computing on graphics processing units (‘GPGPU’) to accelerate deep learning applications that are interconnected into a computation engine to train parameters for deep neural networks. Each system may have Ethernet external connectivity, InfiniBand external connectivity, some other form of external connectivity, or some combination thereof. In such an example, the GPUs can be grouped for a single large training or used independently to train multiple models. The infrastructure could also include a storage system such as those described above to provide, for example, a scale-out all-flash file or object store through which data can be accessed via high-performance protocols such as NFS, S3, and so on. The infrastructure can also include, for example, redundant top-of-rack Ethernet switches connected to storage and compute via ports in MLAG port channels for redundancy. The infrastructure could also include additional compute in the form of whitebox servers, optionally with GPUs, for data ingestion, pre-processing, and model debugging. Readers will appreciate that additional infrastructures are also be possible.
Readers will appreciate that the systems described above may be better suited for the applications described above relative to other systems that may include, for example, a distributed direct-attached storage (DDAS) solution deployed in server nodes. Such DDAS solutions may be built for handling large, less sequential accesses but may be less able to handle small, random accesses. Readers will further appreciate that the storage systems described above may be utilized to provide a platform for the applications described above that is preferable to the utilization of cloud-based resources as the storage systems may be included in an on-site or in-house infrastructure that is more secure, more locally and internally managed, more robust in feature sets and performance, or otherwise preferable to the utilization of cloud-based resources as part of a platform to support the applications described above. For example, services built on platforms such as IBM's Watson may require a business enterprise to distribute individual user information, such as financial transaction information or identifiable patient records, to other institutions. As such, cloud-based offerings of AI as a service may be less desirable than internally managed and offered AI as a service that is supported by storage systems such as the storage systems described above, for a wide array of technical reasons as well as for various business reasons.
Readers will appreciate that the storage systems described above, either alone or in coordination with other computing machinery may be configured to support other AI related tools. For example, the storage systems may make use of tools like ONXX or other open neural network exchange formats that make it easier to transfer models written in different AI frameworks. Likewise, the storage systems may be configured to support tools like Amazon's Gluon that allow developers to prototype, build, and train deep learning models. In fact, the storage systems described above may be part of a larger platform, such as IBM™ Cloud Private for Data, that includes integrated data science, data engineering and application building services. Such platforms may seamlessly collect, organize, secure, and analyze data across an enterprise, as well as simplify hybrid data management, unified data governance and integration, data science and business analytics with a single solution.
Readers will further appreciate that the storage systems described above may also be deployed as an edge solution. Such an edge solution may be in place to optimize cloud computing systems by performing data processing at the edge of the network, near the source of the data. Edge computing can push applications, data and computing power (i.e., services) away from centralized points to the logical extremes of a network. Through the use of edge solutions such as the storage systems described above, computational tasks may be performed using the compute resources provided by such storage systems, data may be storage using the storage resources of the storage system, and cloud-based services may be accessed through the use of various resources of the storage system (including networking resources). By performing computational tasks on the edge solution, storing data on the edge solution, and generally making use of the edge solution, the consumption of expensive cloud-based resources may be avoided and, in fact, performance improvements may be experienced relative to a heavier reliance on cloud-based resources.
While many tasks may benefit from the utilization of an edge solution, some particular uses may be especially suited for deployment in such an environment. For example, devices like drones, autonomous cars, robots, and others may require extremely rapid processing—so fast, in fact, that sending data up to a cloud environment and back to receive data processing support may simply be too slow. Likewise, machines like locomotives and gas turbines that generate large amounts of information through the use of a wide array of data-generating sensors may benefit from the rapid data processing capabilities of an edge solution. As an additional example, some IoT devices such as connected video cameras may not be well-suited for the utilization of cloud-based resources as it may be impractical (not only from a privacy perspective, security perspective, or a financial perspective) to send the data to the cloud simply because of the pure volume of data that is involved. As such, many tasks that really on data processing, storage, or communications may be better suited by platforms that include edge solutions such as the storage systems described above.
Consider a specific example of inventory management in a warehouse, distribution center, or similar location. A large inventory, warehousing, shipping, order-fulfillment, manufacturing or other operation has a large amount of inventory on inventory shelves, and high resolution digital cameras that produce a firehose of large data. All of this data may be taken into an image processing system, which may reduce the amount of data to a firehose of small data. All of the small data may be stored on-premises in storage. The on-premises storage, at the edge of the facility, may be coupled to the cloud, for external reports, real-time control and cloud storage. Inventory management may be performed with the results of the image processing, so that inventory can be tracked on the shelves and restocked, moved, shipped, modified with new products, or discontinued/obsolescent products deleted, etc. The above scenario is a prime candidate for an embodiment of the configurable processing and storage systems described above. A combination of compute-only blades and offload blades suited for the image processing, perhaps with deep learning on offload-FPGA or offload-custom blade(s) could take in the firehose of large data from all of the digital cameras, and produce the firehose of small data. All of the small data could then be stored by storage nodes, operating with storage units in whichever combination of types of storage blades best handles the data flow. This is an example of storage and function acceleration and integration. Depending on external communication needs with the cloud, and external processing in the cloud, and depending on reliability of network connections and cloud resources, the system could be sized for storage and compute management with bursty workloads and variable conductivity reliability. Also, depending on other inventory management aspects, the system could be configured for scheduling and resource management in a hybrid edge/cloud environment.
The storage systems described above may alone, or in combination with other computing resources, serves as a network edge platform that combines compute resources, storage resources, networking resources, cloud technologies and network virtualization technologies, and so on. As part of the network, the edge may take on characteristics similar to other network facilities, from the customer premise and backhaul aggregation facilities to Points of Presence (PoPs) and regional data centers. Readers will appreciate that network workloads, such as Virtual Network Functions (VNFs) and others, will reside on the network edge platform. Enabled by a combination of containers and virtual machines, the network edge platform may rely on controllers and schedulers that are no longer geographically co-located with the data processing resources. The functions, as microservices, may split into control planes, user and data planes, or even state machines, allowing for independent optimization and scaling techniques to be applied. Such user and data planes may be enabled through increased accelerators, both those residing in server platforms, such as FPGAs and Smart NICs, and through SDN-enabled merchant silicon and programmable ASICs.
The storage systems described above may also be optimized for use in big data analytics. Big data analytics may be generally described as the process of examining large and varied data sets to uncover hidden patterns, unknown correlations, market trends, customer preferences and other useful information that can help organizations make more-informed business decisions. Big data analytics applications enable data scientists, predictive modelers, statisticians and other analytics professionals to analyze growing volumes of structured transaction data, plus other forms of data that are often left untapped by conventional business intelligence (BI) and analytics programs. As part of that process, semi-structured and unstructured data such as, for example, internet clickstream data, web server logs, social media content, text from customer emails and survey responses, mobile-phone call-detail records, IoT sensor data, and other data may be converted to a structured form. Big data analytics is a form of advanced analytics, which involves complex applications with elements such as predictive models, statistical algorithms and what-if analyses powered by high-performance analytics systems.
The storage systems described above may also support (including implementing as a system interface) applications that perform tasks in response to human speech. For example, the storage systems may support the execution intelligent personal assistant applications such as, for example, Amazon's Alexa, Apple Siri, Google Voice, Samsung Bixby, Microsoft Cortana, and others. While the examples described in the previous sentence make use of voice as input, the storage systems described above may also support chatbots, talkbots, chatterbots, or artificial conversational entities or other applications that are configured to conduct a conversation via auditory or textual methods. Likewise, the storage system may actually execute such an application to enable a user such as a system administrator to interact with the storage system via speech. Such applications are generally capable of voice interaction, music playback, making to-do lists, setting alarms, streaming podcasts, playing audiobooks, and providing weather, traffic, and other real time information, such as news, although in embodiments in accordance with the present disclosure, such applications may be utilized as interfaces to various system management operations.
The storage systems described above may also implement AI platforms for delivering on the vision of self-driving storage. Such AI platforms may be configured to deliver global predictive intelligence by collecting and analyzing large amounts of storage system telemetry data points to enable effortless management, analytics and support. In fact, such storage systems may be capable of predicting both capacity and performance, as well as generating intelligent advice on workload deployment, interaction and optimization. Such AI platforms may be configured to scan all incoming storage system telemetry data against a library of issue fingerprints to predict and resolve incidents in real-time, before they impact customer environments, and captures hundreds of variables related to performance that are used to forecast performance load.
The storage systems described above may support the serialized or simultaneous execution artificial intelligence applications, machine learning applications, data analytics applications, data transformations, and other tasks that collectively may form an AI ladder. Such an AI ladder may effectively be formed by combining such elements to form a complete data science pipeline, where exist dependencies between elements of the AI ladder. For example, AI may require that some form of machine learning has taken place, machine learning may require that some form of analytics has taken place, analytics may require that some form of data and information architecting has taken place, and so on. As such, each element may be viewed as a rung in an AI ladder that collectively can form a complete and sophisticated AI solution.
The storage systems described above may also, either alone or in combination with other computing environments, be used to deliver an AI everywhere experience where AI permeates wide and expansive aspects of business and life. For example, AI may play an important role in the delivery of deep learning solutions, deep reinforcement learning solutions, artificial general intelligence solutions, autonomous vehicles, cognitive computing solutions, commercial UAVs or drones, conversational user interfaces, enterprise taxonomies, ontology management solutions, machine learning solutions, smart dust, smart robots, smart workplaces, and many others. The storage systems described above may also, either alone or in combination with other computing environments, be used to deliver a wide range of transparently immersive experiences where technology can introduce transparency between people, businesses, and things. Such transparently immersive experiences may be delivered as augmented reality technologies, connected homes, virtual reality technologies, brain-computer interfaces, human augmentation technologies, nanotube electronics, volumetric displays, 4D printing technologies, or others. The storage systems described above may also, either alone or in combination with other computing environments, be used to support a wide variety of digital platforms. Such digital platforms can include, for example, 5G wireless systems and platforms, digital twin platforms, edge computing platforms, IoT platforms, quantum computing platforms, serverless PaaS, software-defined security, neuromorphic computing platforms, and so on.
Readers will appreciate that some transparently immersive experiences may involve the use of digital twins of various “things” such as people, places, processes, systems, and so on. Such digital twins and other immersive technologies can alter the way that humans interact with technology, as conversational platforms, augmented reality, virtual reality and mixed reality provide a more natural and immersive interaction with the digital world. In fact, digital twins may be linked with the real-world, perhaps even in real-time, to understand the state of a thing or system, respond to changes, and so on. Because digital twins consolidate massive amounts of information on individual assets and groups of assets (even possibly providing control of those assets), digital twins may communicate with each other to digital factory models of multiple linked digital twins.
The storage systems described above may also be part of a multi-cloud environment in which multiple cloud computing and storage services are deployed in a single heterogeneous architecture. In order to facilitate the operation of such a multi-cloud environment, DevOps tools may be deployed to enable orchestration across clouds. Likewise, continuous development and continuous integration tools may be deployed to standardize processes around continuous integration and delivery, new feature rollout and provisioning cloud workloads. By standardizing these processes, a multi-cloud strategy may be implemented that enables the utilization of the best provider for each workload. Furthermore, application monitoring and visibility tools may be deployed to move application workloads around different clouds, identify performance issues, and perform other tasks. In addition, security and compliance tools may be deployed for to ensure compliance with security requirements, government regulations, and so on. Such a multi-cloud environment may also include tools for application delivery and smart workload management to ensure efficient application delivery and help direct workloads across the distributed and heterogeneous infrastructure, as well as tools that ease the deployment and maintenance of packaged and custom applications in the cloud and enable portability amongst clouds. The multi-cloud environment may similarly include tools for data portability.
The storage systems described above may be used as a part of a platform to enable the use of crypto-anchors that may be used to authenticate a product's origins and contents to ensure that it matches a blockchain record associated with the product. Such crypto-anchors may take many forms including, for example, as edible ink, as a mobile sensor, as a microchip, and others. Similarly, as part of a suite of tools to secure data stored on the storage system, the storage systems described above may implement various encryption technologies and schemes, including lattice cryptography. Lattice cryptography can involve constructions of cryptographic primitives that involve lattices, either in the construction itself or in the security proof. Unlike public-key schemes such as the RSA, Diffie-Hellman or Elliptic-Curve cryptosystems, which are easily attacked by a quantum computer, some lattice-based constructions appear to be resistant to attack by both classical and quantum computers.
A quantum computer is a device that performs quantum computing. Quantum computing is computing using quantum-mechanical phenomena, such as superposition and entanglement. Quantum computers differ from traditional computers that are based on transistors, as such traditional computers require that data be encoded into binary digits (bits), each of which is always in one of two definite states (0 or 1). In contrast to traditional computers, quantum computers use quantum bits, which can be in superpositions of states. A quantum computer maintains a sequence of qubits, where a single qubit can represent a one, a zero, or any quantum superposition of those two qubit states. A pair of qubits can be in any quantum superposition of 4 states, and three qubits in any superposition of 8 states. A quantum computer with n qubits can generally be in an arbitrary superposition of up to 2{circumflex over ( )}n different states simultaneously, whereas a traditional computer can only be in one of these states at any one time. A quantum Turing machine is a theoretical model of such a computer.
The storage systems described above may also be paired with FPGA-accelerated servers as part of a larger AI or ML infrastructure. Such FPGA-accelerated servers may reside near (e.g., in the same data center) the storage systems described above or even incorporated into an appliance that includes one or more storage systems, one or more FPGA-accelerated servers, networking infrastructure that supports communications between the one or more storage systems and the one or more FPGA-accelerated servers, as well as other hardware and software components. Alternatively, FPGA-accelerated servers may reside within a cloud computing environment that may be used to perform compute-related tasks for AI and ML jobs. Any of the embodiments described above may be used to collectively serve as a FPGA-based AI or ML platform. Readers will appreciate that, in some embodiments of the FPGA-based AI or ML platform, the FPGAs that are contained within the FPGA-accelerated servers may be reconfigured for different types of ML models (e.g., LSTMs, CNNs, GRUs). The ability to reconfigure the FPGAs that are contained within the FPGA-accelerated servers may enable the acceleration of a ML or AI application based on the most optimal numerical precision and memory model being used. Readers will appreciate that by treating the collection of FPGA-accelerated servers as a pool of FPGAs, any CPU in the data center may utilize the pool of FPGAs as a shared hardware microservice, rather than limiting a server to dedicated accelerators plugged into it.
The FPGA-accelerated servers and the GPU-accelerated servers described above may implement a model of computing where, rather than keeping a small amount of data in a CPU and running a long stream of instructions over it as occurred in more traditional computing models, the machine learning model and parameters are pinned into the high-bandwidth on-chip memory with lots of data streaming though the high-bandwidth on-chip memory. FPGAs may even be more efficient than GPUs for this computing model, as the FPGAs can be programmed with only the instructions needed to run this kind of computing model.
The storage systems described above may be configured to provide parallel storage, for example, through the use of a parallel file system such as BeeGFS. Such parallel files systems may include a distributed metadata architecture. For example, the parallel file system may include a plurality of metadata servers across which metadata is distributed, as well as components that include services for clients and storage servers. Through the use of a parallel file system, file contents may be distributed over a plurality of storage servers using striping and metadata may be distributed over a plurality of metadata servers on a directory level, with each server storing a part of the complete file system tree. Readers will appreciate that in some embodiments, the storage servers and metadata servers may run in userspace on top of an existing local file system. Furthermore, dedicated hardware is not required for client services, the metadata servers, or the hardware servers as metadata servers, storage servers, and even the client services may be run on the same machines.
Readers will appreciate that, in part due to the emergence of many of the technologies discussed above including mobile devices, cloud services, social networks, big data analytics, and so on, an information technology platform may be needed to integrate all of these technologies and drive new business opportunities by quickly delivering revenue-generating products, services, and experiences—rather than merely providing the technology to automate internal business processes. Information technology organizations may need to balance resources and investments needed to keep core legacy systems up and running while also integrating technologies to build an information technology platform that can provide the speed and flexibility in areas such as, for example, exploiting big data, managing unstructured data, and working with cloud applications and services. One possible embodiment of such an information technology platform is a composable infrastructure that includes fluid resource pools, such as many of the systems described above that, can meet the changing needs of applications by allowing for the composition and recomposition of blocks of disaggregated compute, storage, and fabric infrastructure. Such a composable infrastructure can also include a single management interface to eliminate complexity and a unified API to discover, search, inventory, configure, provision, update, and diagnose the composable infrastructure.
In one embodiment, controller 410 is designated as the “primary” controller, which performs most or all of the I/O operations on the array 430. If, however, a software crash, hardware fault or other error occurs, the “secondary” controller 450 may be promoted to serve as the primary controller and take over all responsibilities for servicing the array 430. In one embodiment, storage controllers 410 and 450 are identical and any description of controller 410 herein may be equally attributed to storage controller 450.
Storage controller 410 may include software and/or hardware configured to provide access to storage devices 435A-n. In one embodiment, storage controller 410 is connected to storage device 435A-n over a data bus, such as a Peripheral Component Interconnect express (PCIe) bus that operates within the framework of the Non-Volatile Memory express (NVMe) communication interface. In one embodiment, initiator devices (e.g., 415 and/or 425) are connected to storage controllers (e.g., 410 and/or 450) via a fibre channel protocol. For example, initiator device 425 may communicate with a fibre-channel host bus adapter (e.g., FC HBA 453, 443) of storage controller 410 through a fibre-channel Small Computer System Interface (SCSI), fibre-channel NVMe interface, NVMe over fibre channel interface, etc.
In general, the NVMe/fibre-channel communication interfaces make use of submission and completion queues located on the host side for submitting storage commands and receiving confirmation of the execution of those commands on the storage devices. One of storage controllers 410 or 450, or storage devices 435A-n, may fetch commands from the submission queue, execute the fetched command, and return results to the completion queue. In another embodiment, the submission and completion queues are located on the storage devices. Fibre-channel NVMe, as a logical device interface, capitalizes on the low latency and internal parallelism of flash-based storage devices, mirroring the parallelism of contemporary CPUs, platforms and applications. NVMe allows levels of parallelism possible in modern solid state drives (SSDs) to be fully exploited by the host hardware and software. As a result, NVMe reduces I/O overhead and provides various performance improvements in comparison to previous logical device interfaces, including multiple, long command queues, and reduced latency.
Although storage controller 410 is shown as being separate from storage array 430, in some embodiments, storage controller 410 may be located within storage array 430. Storage controller 410 may include or be coupled to a base operating system (OS), a volume manager, and additional control logic for implementing the various techniques disclosed herein. In one embodiment, the OS is designed with flash storage in mind, so while it can use conventional SSDs to store data, it does not depend on a 512 byte random overwrite capability. Even on conventional SSDs, storage controller 410 can achieve better performance by writing and discarding data in large chunks. This style of I/O is sometimes called “flash friendly I/O.” This also makes it a much easier task to convert the OS to use the physical addressing of storage devices, as compared to conventional filesystems.
In one embodiment, the logic of storage controller 410 includes one or more user space applications 442 having an MVMe/FC stack and one or more kernel space device drivers 444 having an FCP stack. In one embodiment, there may be a kernel space device driver 444 on storage controller 410 corresponding to each of storage devices 435A-n in storage array 430. As new storage devices are connected to controller 410, new device drivers may be installed. These drivers may be similarly discarded when a corresponding device is disconnected from storage controller 410. Applications wishing to communicate with one of storage devices 435A-n, such as user space application 442, may do so via device driver 444. In one embodiment, multiple applications can access the same kernel space device driver 444 concurrently. In one embodiment, storage controller 450 includes a separate instance(s) of kernel space device driver 454 and one or more other user space applications 452. In one embodiment, storage controller 410 includes a number of I/O queues (e.g., submission queues) for storing commands to be fetched by one of storage devices 435A-n. Kernel space device driver 444 may reserve certain queues for direct access by user space application 442 in order to reduce the latency associated with processing certain types of commands (e.g., differentiated by communication protocol). Additional details regarding these I/O queues are provided below with respect to
Storage controller 410 may include and/or execute on any number of processing devices and may include and/or execute on a single host computing device or be spread across multiple host computing devices, depending on the embodiment. In some embodiments, storage controller 410 may generally include or execute on one or more file servers and/or block servers. Storage controller 410 may use any of various techniques for replicating data across devices 435A-n to prevent loss of data due to the failure of a device or the failure of storage locations within a device. Storage controller 410 may also utilize any of various deduplication techniques for reducing the amount of data stored in devices 435A-n by deduplicating common data.
In one embodiment, storage controller 410 may utilize logical volumes and mediums to track client data that is stored in storage array 430. A medium is defined as a logical grouping of data, and each medium has an identifier with which to identify the logical grouping of data. A volume is a single accessible storage area with a single file system, typically, though not necessarily, resident on a single partition of a storage device. The volumes may be logical organizations of data physically located on one or more of storage device 435A-n in storage array 430. Storage controller 410 may maintain a volume to medium mapping table to map each volume to a single medium, and this medium is referred to as the volume's anchor medium. A given request received by storage controller 410 may indicate at least a volume and block address or file name, and storage controller 410 may determine an anchor medium targeted by the given request from the volume to medium mapping table.
In various embodiments, multiple mapping tables may be maintained by storage controller 410. These mapping tables may include a medium mapping table and a volume to medium mapping table. These tables may be utilized to record and maintain the mappings between mediums and underlying mediums and the mappings between volumes and mediums. Storage controller 410 may also include an address translation table with a plurality of entries, wherein each entry holds a virtual-to-physical mapping for a corresponding data component. This mapping table may be used to map logical read/write requests from each of the initiator devices 415 and 425 to physical locations in storage devices 435A-n. A “physical” pointer value may be read from the mappings associated with a given medium during a lookup operation corresponding to a received read/write request. The term “mappings” is defined as the one or more entries of the address translation mapping table which convert a given medium ID and block number into a physical pointer value. This physical pointer value may then be used to locate a physical location within the storage devices 435A-n. The physical pointer value may be used to access another mapping table within a given storage device of the storage devices 435A-n. Consequently, one or more levels of indirection may exist between the physical pointer value and a target storage location.
In alternative embodiments, the number and type of client computers, initiator devices, storage controllers, networks, storage arrays, and data storage devices is not limited to those shown in
Network 420 may utilize a variety of techniques including wireless connections, direct local area network (LAN) connections, wide area network (WAN) connections such as the Internet, a router, storage area network, Ethernet, and others. Network 420 may comprise one or more LANs that may also be wireless. Network 420 may further include remote direct memory access (RDMA) hardware and/or software, transmission control protocol/internet protocol (TCP/IP) hardware and/or software, router, repeaters, switches, grids, and/or others. Protocols such as Fibre Channel, Fibre Channel over Ethernet (FCoE), iSCSI, and so forth may be used in network 420. The network 420 may interface with a set of communications protocols used for the Internet such as the Transmission Control Protocol (TCP) and the Internet Protocol (IP), or TCP/IP. In one embodiment, network 420 represents a storage area network (SAN) which provides access to consolidated, block level data storage. The SAN may be used to enhance the storage devices accessible to initiator devices so that the devices 435A-n appear to the initiator devices 415 and 425 as locally attached storage.
Initiator devices 415 and 425 are representative of any number of stationary or mobile computers such as desktop personal computers (PCs), servers, server farms, workstations, laptops, handheld computers, servers, personal digital assistants (PDAs), smart phones, and so forth. Generally speaking, initiator devices 415 and 425 include one or more processing devices, each comprising one or more processor cores. Each processor core includes circuitry for executing instructions according to a predefined general-purpose instruction set. For example, the x86 instruction set architecture may be selected. Alternatively, the ARM®, Alpha®, PowerPC®, SPARC®, or any other general-purpose instruction set architecture may be selected. The processor cores may access cache memory subsystems for data and computer program instructions. The cache subsystems may be coupled to a memory hierarchy comprising random access memory (RAM) and a storage device.
In one embodiment, initiator device 415 includes initiator application 412 and initiator device 425 includes initiator application 422. Initiator applications 412 and 422 may be any computer application programs designed to utilize the data on devices 435A-n in storage array 430 to implement or provide various functionalities. Initiator applications 412 and 422 may issue requests to read or write data from certain logical volumes data within storage system 400. Initiator applications 412 and 422 may communicate with the kernel and/or user space on its corresponding device to send data over a network interface. This data travels over network 420, hitting a network interface (e.g., via a FC HBA) on storage controller 410, which utilizes the submission queues to route data to its appropriate destination. Application 442 can utilize kernel space device driver 444 of storage controller 410 to service the read or write requests, as described in detail herein.
In one embodiment, initiator application 422 and/or user space application 442 may generate or issue storage commands to be executed on storage device 435A. These commands may include NVMe/FC commands, such as read operations, write operations, etc., or FCP commands, such as firmware updates, debug operations, asynchronous event notifications, etc. In one embodiment, storage controller 410 includes a number of queues 520, into which the storage commands may be placed and eventually fetched by storage device 435A for execution. In general, kernel space device driver 444 is responsible for management and allocation of queues 520 and for placing the storage commands into the queues 520.
For certain commands, user space application 442 can pass the commands to kernel space 514 for processing. Depending on the type of command, user space application 442 may make a system call 532 to a block layer 546 in kernel space 514. The block layer can translate a file referenced by the system call to storage blocks on storage device 435A and provide an indication of the corresponding storage blocks to kernel space device driver 444. In another embodiment, user space application 442 may pass the command directly to kernel space device driver 444. Upon receipt, kernel space device driver may send (535, 536) the command to a queue 524 or 526 that has been reserved for use by the kernel space device driver 444. In one embodiment, queue 524 is an admin queue, while queue 526 is an I/O queue. In other embodiments, queue 524 is a FCP queue and queue 226 is an NVMe/FC queue. In one embodiment, it is at the discretion of user space application 442 (e.g., via a FC HBA) which types of commands are routed through the kernel space 514, although kernel space device driver 444 may be configured to handle both fibre-channel SCSI commands and fibre-channel NVMe commands.
Since kernel space device driver 444 runs in kernel space 514, storage commands from user space application 442 and/or initiator application 422 that are passed to kernel space device driver 444 before being placed onto one of the queues 520 may experience some additional latency associated with traversing the kernel stack (i.e., block layer 546, kernel space device driver 444 and any other components in kernel space 514). Accordingly, in one embodiment, user space application 442 is configured to place certain commands directly into one of queues 520 without routing the commands through kernel space 514. For example, user space application 442 may place (231) certain latency-sensitive NVMe/FC commands, or commands having a particular communication protocol, directly into I/O queue 522. This prevents any delay associated with routing the commands through kernel space 514. In one embodiment, storage controller 410 includes memory mapped registers called doorbell registers. When the user space application 442 writes a command to the memory of a particular queue, it also updates the doorbell register to point to this newly written memory location (e.g., an index into the queue for NVMe/SCSI). Since the queue memory is previously registered with the storage device on queue creation for the doorbell register, the device knows where to look for the new command.
In one embodiment, to configure I/O queue 522 for direct access from initiator device 425 via user space 512, user space application 442 may send a system call or command 533 to kernel space device driver 444 for reservation of the I/O queue. Kernel space device driver 444 may determine whether or not an I/O queue has already been reserved for user space application 442, and if not, may allocate I/O queue 522. In one embodiment, system call 533 requests that the kernel map some of the user space memory so writes to it get sent by direct memory access (DMA) or memory mapped I/O, to the device. In one embodiment, the request sent to the kernel is an I/O control system call (e.g., ioctl) to create the queue and the corresponding memory mapping. The queue creation turns into a command sent to the drive, and the memory mapping is handled by an I/O memory management unit (IOMMU). Once allocated, kernel space device driver 444 may return a confirmation that the queue has been reserved for user space application 442, and user space application 442 is free to directly place storage commands onto I/O queue 522.
In one embodiment, a storage device (e.g., 435A of
Referring to
At block 640, method 600 receives a second command, having a different communication protocol than the first command, such as a first NVMe/FC command from the application 422 of initiator device 425. In one embodiment, application 422 issues the first NVMe/FC command. At block 650, method 600 sends the first NVMe/FC command directly to a second I/O queue 522 of the plurality of queues 520 without routing the first NVMe/FC command through the kernel space 514 of the storage controller 410. In one embodiment, user space application can place the first NVMe/FC command onto I/O queue 522, which has been reserved for direct access by user space application 442.
At block 660, method 600 receives a second NVMe/FC command from application 422 of initiator device 425. The second NVMe/FC command may be the same as or similar to the first NVMe/FC command, in that it includes a read command or a write command. In another embodiment, the second NVMe/FC command may be received from some other applications besides application 422, such as user space application 442. In one embodiment, however, the second NVMe/FC command may be passed through kernel space 514 rather than written directly onto an I/O queue 520. At block 670, method 600 routes the second NVMe/FC command through kernel space device driver 444 in kernel space 514 of the storage controller 410. Kernel space device driver 444 is configured to process any type of command including either FCP commands or NVMe/FC commands, e.g., via an FC HBA. Thus, it is at the instruction of the FC HBA whether to place commands directly onto an I/O queue or to route the commands through kernel space 514. At block 680, method 600 sends the second NVMe/FC command to a third I/O queue 526 of a plurality of queues 520, where the third I/O queue 526 is reserved for use by the kernel space device driver 444. As a result, method 600 can place commands on queues 520 concurrently and can write commands from the first queue 524, the second I/O queue 522, and the third I/O queue 526 to storage device 435A concurrently. In one embodiment, storage device 435A and/or initiator device 425 can retrieve pending commands from any of queues 520 concurrently, as well. In this manner, both applications in user space 512 and drivers in kernel space 514 can have concurrent access to storage device 435A.
Referring to
Referring to
While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any inventions or of what may be claimed, but rather as descriptions of features specific to particular embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments separately or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In certain circumstances, multitasking and parallel processing may be advantageous. Moreover, the separation of various system components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
Thus, particular embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In certain implementations, multitasking and parallel processing may be advantageous.
This application is a continuation of U.S. patent application Ser. No. 16/370,527, filed Mar. 29, 2019, which is a continuation-in-part of, and claims priority to, U.S. patent application Ser. No. 15/416,990 filed Jan. 26, 2017, now U.S. Pat. No. 10,678,432, issued Jun. 9, 2020, which claims priority to U.S. Provisional Patent Application No. 62/403,868 filed Oct. 4, 2016, the entire contents of each of which are hereby incorporated by reference herein.
| Number | Name | Date | Kind |
|---|---|---|---|
| 4200841 | Nagata et al. | Apr 1980 | A |
| 5390327 | Lubbers et al. | Feb 1995 | A |
| 5479653 | Jones | Dec 1995 | A |
| 5649093 | Hanko et al. | Jul 1997 | A |
| 5715193 | Norman | Feb 1998 | A |
| 5764767 | Beimel et al. | Jun 1998 | A |
| 5912595 | Ma et al. | Jun 1999 | A |
| 5920501 | Norman | Jul 1999 | A |
| 5953255 | Lee | Sep 1999 | A |
| 6182214 | Hardjono | Jan 2001 | B1 |
| 6275898 | DeKoning | Aug 2001 | B1 |
| 6535417 | Tsuda et al. | Mar 2003 | B2 |
| 6643748 | Wieland | Nov 2003 | B1 |
| 6725392 | Frey et al. | Apr 2004 | B1 |
| 6766515 | Bitar et al. | Jul 2004 | B1 |
| 6836816 | Kendall | Dec 2004 | B2 |
| 6859112 | Mason | Feb 2005 | B2 |
| 6985995 | Holland et al. | Jan 2006 | B2 |
| 7032125 | Holt et al. | Apr 2006 | B2 |
| 7051155 | Talagala et al. | May 2006 | B2 |
| 7065617 | Wang | Jun 2006 | B2 |
| 7069383 | Yamamoto et al. | Jun 2006 | B2 |
| 7076606 | Orsley | Jul 2006 | B2 |
| 7107480 | Moshayedi et al. | Sep 2006 | B1 |
| 7159150 | Kenchammana-Hosekote et al. | Jan 2007 | B2 |
| 7162575 | Dalal et al. | Jan 2007 | B2 |
| 7164608 | Lee | Jan 2007 | B2 |
| 7334156 | Land et al. | Feb 2008 | B2 |
| 7370220 | Nguyen et al. | May 2008 | B1 |
| 7424498 | Patterson | Sep 2008 | B1 |
| 7424592 | Karr et al. | Sep 2008 | B1 |
| 7444532 | Masuyama et al. | Oct 2008 | B2 |
| 7480658 | Heinla et al. | Jan 2009 | B2 |
| 7536506 | Ashmore et al. | May 2009 | B2 |
| 7558859 | Kasiolas et al. | Jul 2009 | B2 |
| 7565446 | Talagala et al. | Jul 2009 | B2 |
| 7613947 | Coatney et al. | Nov 2009 | B1 |
| 7619932 | Jones et al. | Nov 2009 | B2 |
| 7681104 | Sim-Tang et al. | Mar 2010 | B1 |
| 7681105 | Sim-Tang et al. | Mar 2010 | B1 |
| 7730258 | Smith et al. | Jun 2010 | B1 |
| 7743276 | Jacobson et al. | Jun 2010 | B2 |
| 7757038 | Kitahara | Jul 2010 | B2 |
| 7778960 | Chatterjee et al. | Aug 2010 | B1 |
| 7814272 | Barrall et al. | Oct 2010 | B2 |
| 7814273 | Barrall | Oct 2010 | B2 |
| 7818531 | Barrall | Oct 2010 | B2 |
| 7827351 | Suetsugu et al. | Nov 2010 | B2 |
| 7827439 | Mathew et al. | Nov 2010 | B2 |
| 7870105 | Arakawa et al. | Jan 2011 | B2 |
| 7885938 | Greene et al. | Feb 2011 | B1 |
| 7886111 | Klemm et al. | Feb 2011 | B2 |
| 7908448 | Chatterjee et al. | Mar 2011 | B1 |
| 7916538 | Jeon et al. | Mar 2011 | B2 |
| 7941697 | Mathew et al. | May 2011 | B2 |
| 7958303 | Shuster | Jun 2011 | B2 |
| 7971129 | Watson et al. | Jun 2011 | B2 |
| 7991822 | Bish et al. | Aug 2011 | B2 |
| 8010485 | Chatterjee et al. | Aug 2011 | B1 |
| 8010829 | Chatterjee et al. | Aug 2011 | B1 |
| 8020047 | Courtney | Sep 2011 | B2 |
| 8046548 | Chatterjee et al. | Oct 2011 | B1 |
| 8051361 | Sim-Tang et al. | Nov 2011 | B2 |
| 8051362 | Li et al. | Nov 2011 | B2 |
| 8060798 | Roohparvar et al. | Nov 2011 | B2 |
| 8082393 | Galloway et al. | Dec 2011 | B2 |
| 8086634 | Mimatsu | Dec 2011 | B2 |
| 8086911 | Taylor | Dec 2011 | B1 |
| 8090837 | Shin et al. | Jan 2012 | B2 |
| 8108502 | Tabbara et al. | Jan 2012 | B2 |
| 8117388 | Jernigan, IV | Feb 2012 | B2 |
| 8120959 | Lee et al. | Feb 2012 | B2 |
| 8140821 | Raizen et al. | Mar 2012 | B1 |
| 8145736 | Tewari et al. | Mar 2012 | B1 |
| 8145838 | Miller et al. | Mar 2012 | B1 |
| 8145840 | Koul et al. | Mar 2012 | B2 |
| 8176360 | Frost et al. | May 2012 | B2 |
| 8180855 | Aiello et al. | May 2012 | B2 |
| 8200922 | McKean et al. | Jun 2012 | B2 |
| 8225006 | Karamcheti | Jul 2012 | B1 |
| 8225329 | Lynn | Jul 2012 | B1 |
| 8239618 | Kotzur et al. | Aug 2012 | B2 |
| 8244999 | Chatterjee et al. | Aug 2012 | B1 |
| 8271996 | Gould et al. | Sep 2012 | B1 |
| 8305811 | Jeon | Nov 2012 | B2 |
| 8315999 | Chatley et al. | Nov 2012 | B2 |
| 8327080 | Der | Dec 2012 | B1 |
| 8351290 | Huang et al. | Jan 2013 | B1 |
| 8375146 | Sinclair | Feb 2013 | B2 |
| 8397016 | Falagala et al. | Mar 2013 | B2 |
| 8402152 | Duran | Mar 2013 | B2 |
| 8412880 | Leibowitz et al. | Apr 2013 | B2 |
| 8423739 | Ash et al. | Apr 2013 | B2 |
| 8429436 | Fillingim et al. | Apr 2013 | B2 |
| 8473778 | Simitci et al. | Jun 2013 | B2 |
| 8479037 | Chatterjee et al. | Jul 2013 | B1 |
| 8498967 | Chatterjee et al. | Jul 2013 | B1 |
| 8522073 | Cohen | Aug 2013 | B2 |
| 8533527 | Daikokuya et al. | Sep 2013 | B2 |
| 8544029 | Bakke et al. | Sep 2013 | B2 |
| 8589625 | Colgrove et al. | Nov 2013 | B2 |
| 8595455 | Chatterjee et al. | Nov 2013 | B2 |
| 8615599 | Takefman et al. | Dec 2013 | B1 |
| 8627136 | Shankar et al. | Jan 2014 | B2 |
| 8627138 | Clark et al. | Jan 2014 | B1 |
| 8638602 | Horn | Jan 2014 | B1 |
| 8660131 | Vermunt et al. | Feb 2014 | B2 |
| 8661218 | Piszczek et al. | Feb 2014 | B1 |
| 8694719 | Lassa et al. | Apr 2014 | B2 |
| 8700875 | Barron et al. | Apr 2014 | B1 |
| 8706694 | Chatterjee et al. | Apr 2014 | B2 |
| 8706914 | Duchesneau | Apr 2014 | B2 |
| 8707112 | Roohparvar et al. | Apr 2014 | B2 |
| 8713405 | Healey, Jr. et al. | Apr 2014 | B2 |
| 8725730 | Keeton et al. | May 2014 | B2 |
| 8737136 | Cometti | May 2014 | B2 |
| 8756387 | Frost et al. | Jun 2014 | B2 |
| 8762793 | Grube et al. | Jun 2014 | B2 |
| 8773903 | Lee et al. | Jul 2014 | B2 |
| 8775868 | Colgrove et al. | Jul 2014 | B2 |
| 8788913 | Xin et al. | Jul 2014 | B1 |
| 8799746 | Baker et al. | Aug 2014 | B2 |
| 8819311 | Liao | Aug 2014 | B2 |
| 8819383 | Jobanputra et al. | Aug 2014 | B1 |
| 8819503 | Melik-Martirosian | Aug 2014 | B2 |
| 8824261 | Miller et al. | Sep 2014 | B1 |
| 8838883 | DAbreu et al. | Sep 2014 | B2 |
| 8843700 | Salessi et al. | Sep 2014 | B1 |
| 8850108 | Hayes et al. | Sep 2014 | B1 |
| 8850288 | Lazier et al. | Sep 2014 | B1 |
| 8856593 | Eckhardt et al. | Oct 2014 | B2 |
| 8856619 | Cypher | Oct 2014 | B1 |
| 8862847 | Feng et al. | Oct 2014 | B2 |
| 8862928 | Xavier et al. | Oct 2014 | B2 |
| 8868825 | Hayes et al. | Oct 2014 | B1 |
| 8874836 | Hayes et al. | Oct 2014 | B1 |
| 8886778 | Nedved et al. | Nov 2014 | B2 |
| 8898383 | Yamamoto et al. | Nov 2014 | B2 |
| 8898388 | Kimmel | Nov 2014 | B1 |
| 8904231 | Coatney et al. | Dec 2014 | B2 |
| 8918478 | Ozzie et al. | Dec 2014 | B2 |
| 8930307 | Colgrove et al. | Jan 2015 | B2 |
| 8930633 | Amit et al. | Jan 2015 | B2 |
| 8949502 | McKnight et al. | Feb 2015 | B2 |
| 8959110 | Smith et al. | Feb 2015 | B2 |
| 8966343 | Syu et al. | Feb 2015 | B2 |
| 8972818 | Strauss et al. | Mar 2015 | B2 |
| 8977597 | Ganesh et al. | Mar 2015 | B2 |
| 9003144 | Hayes et al. | Apr 2015 | B1 |
| 9009724 | Gold et al. | Apr 2015 | B2 |
| 9021053 | Bembo et al. | Apr 2015 | B2 |
| 9021215 | Meir et al. | Apr 2015 | B2 |
| 9025393 | Wu et al. | May 2015 | B2 |
| 9043372 | Makkar et al. | May 2015 | B2 |
| 9053808 | Sprouse et al. | Jun 2015 | B2 |
| 9058155 | Cepulis et al. | Jun 2015 | B2 |
| 9116819 | Cope et al. | Aug 2015 | B2 |
| 9117536 | Yoon et al. | Aug 2015 | B2 |
| 9122401 | Zaltsman et al. | Sep 2015 | B2 |
| 9134908 | Horn et al. | Sep 2015 | B2 |
| 9153337 | Sutardja | Oct 2015 | B2 |
| 9158612 | Roohparvar et al. | Oct 2015 | B2 |
| 9171627 | Lee et al. | Oct 2015 | B2 |
| 9189650 | Jaye et al. | Nov 2015 | B2 |
| 9201733 | Verma et al. | Dec 2015 | B2 |
| 9207876 | Shu et al. | Dec 2015 | B2 |
| 9251066 | Colgrove et al. | Feb 2016 | B2 |
| 9274893 | Chen | Mar 2016 | B2 |
| 9304856 | Tressler et al. | Apr 2016 | B2 |
| 9323667 | Bennett | Apr 2016 | B2 |
| 9323681 | Apostolides et al. | Apr 2016 | B2 |
| 9348538 | Mallaiah et al. | May 2016 | B2 |
| 9384082 | Lee et al. | Jul 2016 | B1 |
| 9390019 | Patterson et al. | Jul 2016 | B2 |
| 9405478 | Koseki et al. | Aug 2016 | B2 |
| 9412471 | Kim et al. | Aug 2016 | B2 |
| 9432541 | Ishida | Aug 2016 | B2 |
| 9477632 | Du | Oct 2016 | B2 |
| 9552299 | Stalzer | Jan 2017 | B2 |
| 9613704 | Lee | Apr 2017 | B2 |
| 9720754 | Karakulak et al. | Aug 2017 | B2 |
| 9785357 | Raghu et al. | Oct 2017 | B2 |
| 9792998 | Yang et al. | Oct 2017 | B1 |
| 9818478 | Chung | Nov 2017 | B2 |
| 9829066 | Thomas et al. | Nov 2017 | B2 |
| 9857992 | Pangal et al. | Jan 2018 | B2 |
| 9934872 | Magia et al. | Apr 2018 | B2 |
| 9972396 | Naik et al. | May 2018 | B1 |
| 10223028 | Gorobets et al. | Mar 2019 | B2 |
| 10283205 | Malshe et al. | May 2019 | B2 |
| 10296231 | Tsou et al. | May 2019 | B2 |
| 10347330 | Zeng et al. | Jul 2019 | B2 |
| 10347344 | Malshe et al. | Jul 2019 | B2 |
| 10482983 | Alhussien et al. | Nov 2019 | B2 |
| 10489075 | Choi et al. | Nov 2019 | B2 |
| 10521287 | Khoueir et al. | Dec 2019 | B2 |
| 10521353 | Lim | Dec 2019 | B2 |
| 10756816 | Dreier | Aug 2020 | B1 |
| 10852956 | Li | Dec 2020 | B1 |
| 20020144059 | Kendall | Oct 2002 | A1 |
| 20030105984 | Masuyama et al. | Jun 2003 | A1 |
| 20030110205 | Johnson | Jun 2003 | A1 |
| 20030231072 | Mason | Dec 2003 | A1 |
| 20040161086 | Buntin et al. | Aug 2004 | A1 |
| 20050001652 | Malik et al. | Jan 2005 | A1 |
| 20050076228 | Davis et al. | Apr 2005 | A1 |
| 20050235132 | Karr et al. | Oct 2005 | A1 |
| 20050273310 | Newburn | Dec 2005 | A1 |
| 20050278460 | Shin et al. | Dec 2005 | A1 |
| 20050283649 | Turner et al. | Dec 2005 | A1 |
| 20060015683 | Ashmore et al. | Jan 2006 | A1 |
| 20060095610 | Arndt et al. | May 2006 | A1 |
| 20060112250 | Walker | May 2006 | A1 |
| 20060114930 | Lucas et al. | Jun 2006 | A1 |
| 20060143648 | Shinokawa | Jun 2006 | A1 |
| 20060174157 | Barrall et al. | Aug 2006 | A1 |
| 20060248294 | Nedved et al. | Nov 2006 | A1 |
| 20070079068 | Draggon | Apr 2007 | A1 |
| 20070214194 | Reuter | Sep 2007 | A1 |
| 20070214314 | Reuter | Sep 2007 | A1 |
| 20070234016 | Davis et al. | Oct 2007 | A1 |
| 20070268905 | Baker et al. | Nov 2007 | A1 |
| 20070285986 | Eguchi et al. | Dec 2007 | A1 |
| 20080080709 | Michtchenko et al. | Apr 2008 | A1 |
| 20080095375 | Tateoka et al. | Apr 2008 | A1 |
| 20080107274 | Worthy | May 2008 | A1 |
| 20080155191 | Anderson et al. | Jun 2008 | A1 |
| 20080295118 | Liao | Nov 2008 | A1 |
| 20090077208 | Nguyen et al. | Mar 2009 | A1 |
| 20090138654 | Sutardja | May 2009 | A1 |
| 20090216910 | Duchesneau | Aug 2009 | A1 |
| 20090216920 | Lauterbach et al. | Aug 2009 | A1 |
| 20100017444 | Chatterjee et al. | Jan 2010 | A1 |
| 20100017650 | Chin et al. | Jan 2010 | A1 |
| 20100042636 | Lu | Feb 2010 | A1 |
| 20100094806 | Apostolides et al. | Apr 2010 | A1 |
| 20100115070 | Missimilly | May 2010 | A1 |
| 20100125695 | Wu et al. | May 2010 | A1 |
| 20100162076 | Sim-Tang et al. | Jun 2010 | A1 |
| 20100169707 | Mathew et al. | Jul 2010 | A1 |
| 20100174576 | Naylor | Jul 2010 | A1 |
| 20100268908 | Ouyang et al. | Oct 2010 | A1 |
| 20100312915 | Marowsky-Bree et al. | Dec 2010 | A1 |
| 20110035540 | Fitzgerald et al. | Feb 2011 | A1 |
| 20110040925 | Frost et al. | Feb 2011 | A1 |
| 20110060927 | Fillingim et al. | Mar 2011 | A1 |
| 20110119462 | Leach et al. | May 2011 | A1 |
| 20110126269 | Youngworth | May 2011 | A1 |
| 20110219170 | Frost et al. | Sep 2011 | A1 |
| 20110238625 | Hamaguchi et al. | Sep 2011 | A1 |
| 20110264843 | Haines et al. | Oct 2011 | A1 |
| 20110302369 | Goto et al. | Dec 2011 | A1 |
| 20110320688 | Lee et al. | Dec 2011 | A1 |
| 20120011398 | Eckhardt et al. | Jan 2012 | A1 |
| 20120030529 | Roohparvar et al. | Feb 2012 | A1 |
| 20120079318 | Colgrove et al. | Mar 2012 | A1 |
| 20120110249 | Jeong et al. | May 2012 | A1 |
| 20120131253 | McKnight et al. | May 2012 | A1 |
| 20120150826 | Vijayan Retnamma et al. | Jun 2012 | A1 |
| 20120158923 | Mohamed et al. | Jun 2012 | A1 |
| 20120191900 | Kunimatsu et al. | Jul 2012 | A1 |
| 20120198152 | Terry et al. | Aug 2012 | A1 |
| 20120198261 | Brown et al. | Aug 2012 | A1 |
| 20120209943 | Jung | Aug 2012 | A1 |
| 20120226934 | Rao | Sep 2012 | A1 |
| 20120239976 | Cometti et al. | Sep 2012 | A1 |
| 20120239991 | Melik-Martirosian | Sep 2012 | A1 |
| 20120246435 | Meir et al. | Sep 2012 | A1 |
| 20120260055 | Murase | Oct 2012 | A1 |
| 20120311557 | Resch | Dec 2012 | A1 |
| 20130022201 | Glew et al. | Jan 2013 | A1 |
| 20130024875 | Wang et al. | Jan 2013 | A1 |
| 20130036314 | Glew et al. | Feb 2013 | A1 |
| 20130042056 | Shats et al. | Feb 2013 | A1 |
| 20130060884 | Bembo et al. | Mar 2013 | A1 |
| 20130067188 | Mehra et al. | Mar 2013 | A1 |
| 20130073894 | Xavier et al. | Mar 2013 | A1 |
| 20130124776 | Hallak et al. | May 2013 | A1 |
| 20130132800 | Healey, Jr. et al. | May 2013 | A1 |
| 20130151653 | Sawicki et al. | Jun 2013 | A1 |
| 20130151771 | Tsukahara et al. | Jun 2013 | A1 |
| 20130173853 | Ungureanu et al. | Jul 2013 | A1 |
| 20130185612 | Lee et al. | Jul 2013 | A1 |
| 20130238554 | Yucel et al. | Sep 2013 | A1 |
| 20130259234 | Acar et al. | Oct 2013 | A1 |
| 20130262758 | Smith et al. | Oct 2013 | A1 |
| 20130339314 | Carpentier et al. | Dec 2013 | A1 |
| 20130339635 | Amit et al. | Dec 2013 | A1 |
| 20130339818 | Baker et al. | Dec 2013 | A1 |
| 20140006688 | Yu et al. | Jan 2014 | A1 |
| 20140040535 | Lee et al. | Feb 2014 | A1 |
| 20140040683 | Roohparvar et al. | Feb 2014 | A1 |
| 20140040702 | He et al. | Feb 2014 | A1 |
| 20140047263 | Coatney et al. | Feb 2014 | A1 |
| 20140047269 | Kim | Feb 2014 | A1 |
| 20140059405 | Syu et al. | Feb 2014 | A1 |
| 20140063721 | Herman et al. | Mar 2014 | A1 |
| 20140064048 | Cohen et al. | Mar 2014 | A1 |
| 20140068224 | Fan et al. | Mar 2014 | A1 |
| 20140075252 | Luo et al. | Mar 2014 | A1 |
| 20140101511 | Strauss et al. | Apr 2014 | A1 |
| 20140136880 | Shankar et al. | May 2014 | A1 |
| 20140164881 | Chen et al. | Jun 2014 | A1 |
| 20140181402 | White | Jun 2014 | A1 |
| 20140237164 | Le et al. | Aug 2014 | A1 |
| 20140279936 | Bembo et al. | Sep 2014 | A1 |
| 20140280025 | Eidson et al. | Sep 2014 | A1 |
| 20140281770 | Kim et al. | Sep 2014 | A1 |
| 20140289588 | Nagadomi et al. | Sep 2014 | A1 |
| 20140359202 | Sun et al. | Dec 2014 | A1 |
| 20140359346 | Chen | Dec 2014 | A1 |
| 20140380125 | Calder et al. | Dec 2014 | A1 |
| 20140380126 | Yekhanin et al. | Dec 2014 | A1 |
| 20140380319 | Haverkamp et al. | Dec 2014 | A1 |
| 20150019798 | Huang | Jan 2015 | A1 |
| 20150032720 | James | Jan 2015 | A1 |
| 20150039645 | Lewis | Feb 2015 | A1 |
| 20150039849 | Lewis | Feb 2015 | A1 |
| 20150089283 | Kermarrec et al. | Mar 2015 | A1 |
| 20150089623 | Sondhi et al. | Mar 2015 | A1 |
| 20150100746 | Rychlik et al. | Apr 2015 | A1 |
| 20150134824 | Mickens et al. | May 2015 | A1 |
| 20150153800 | Lucas et al. | Jun 2015 | A1 |
| 20150180714 | Chunn et al. | Jun 2015 | A1 |
| 20150199232 | Tressler et al. | Jul 2015 | A1 |
| 20150280959 | Vincent | Oct 2015 | A1 |
| 20160070474 | Yu et al. | Mar 2016 | A1 |
| 20160125956 | Magia et al. | May 2016 | A1 |
| 20160147582 | Karakulak et al. | May 2016 | A1 |
| 20160179597 | Gorobets et al. | Jun 2016 | A1 |
| 20160357458 | Pangal et al. | Dec 2016 | A1 |
| 20170109040 | Raghu et al. | Apr 2017 | A1 |
| 20170123971 | Kanaujia | May 2017 | A1 |
| 20170287568 | Yang et al. | Oct 2017 | A1 |
| 20180052611 | Guilford et al. | Feb 2018 | A1 |
| 20180373437 | Navon et al. | Dec 2018 | A1 |
| 20190042343 | Khoueir et al. | Feb 2019 | A1 |
| 20190056994 | Shulkin et al. | Feb 2019 | A1 |
| 20190066802 | Malshe et al. | Feb 2019 | A1 |
| 20190103164 | Malshe et al. | Apr 2019 | A1 |
| 20190237146 | Malshe et al. | Aug 2019 | A1 |
| 20190265909 | Frolikov | Aug 2019 | A1 |
| 20190295660 | Malshe et al. | Sep 2019 | A1 |
| Number | Date | Country |
|---|---|---|
| 2164006 | Mar 2010 | EP |
| 2256621 | Dec 2010 | EP |
| 2639997 | Sep 2013 | EP |
| 2006069235 | Jun 2006 | WO |
| 2008103569 | Aug 2008 | WO |
| 2008157081 | Dec 2008 | WO |
| 2012174427 | Dec 2012 | WO |
| 2013032544 | Mar 2013 | WO |
| 2013032825 | Mar 2013 | WO |
| 2002013033 | Sep 2013 | WO |
| Entry |
|---|
| Hwang et al., “RAID-x: A New Distributed Disk Array for I/O-Centric Cluster Computing,” HPDC '00 Proceedings of the 9th IEEE International Symposium on High Performance Distributed Computing, IEEE, 2000, pp. 279-286. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2015/018169, dated May 15, 2015. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2015/034302, dated Sep. 11, 2015. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2015/039135, dated Sep. 18, 2015. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2015/039136, dated Sep. 23, 2015. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2015/039137, dated Oct. 1, 2015. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2016/016504, dated Jul. 6, 2016. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2016/023485, dated Jul. 21, 2016. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2016/024391, dated Jul. 12, 2016. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2016/026529, dated Jul. 19, 2016. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2016/031039, dated May 5, 2016. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2016/033306, dated Aug. 19, 2016. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2016/042147, dated Nov. 30, 2016. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2016/047808, dated Nov. 25, 2016. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2016/054080, dated Dec. 21, 2016. |
| International Search Report and the Written Opinion of the International Searching Authority, PCT/US2016/056917, dated Jan. 27, 2017. |
| International Search Report, PCT/US2015/034291, dated Sep. 30, 2015. |
| International Search Report, PCT/US2015/039142, dated Sep. 24, 2015. |
| International Search Report, PCT/US2015/044370, dated Dec. 15, 2015. |
| International Search Report, PCT/US2016/014356, dated Jun. 28, 2016. |
| International Search Report, PCT/US2016/014357, dated Jun. 29, 2016. |
| International Search Report, PCT/US2016/014361, dated May 30, 2016. |
| International Search Report, PCT/US2016/014604, dated May 19, 2016. |
| Kim et al., “Data Access Frequency based Data Replication Method using Erasure Codes in Cloud Storage System,” Journal of the Institute of Electronics and Information Engineers, Feb. 2014, vol. 51, No. 2, pp. 85-91. |
| Schmid, “RAID Scaling Charts, Part 3:4-128 kB Stripes Compared,” Tom's Hardware, http://www.tomshardware.com/reviews/RAID-SCALING-CHARTS.1735-4.html, Nov. 27, 2007, pp. 1-2. |
| Stalzer, “FlashBlades: System Architecture and Applications,” Proceedings of the 2nd Workshop on Architectures and Systems for Big Data, Association for Computing Machinery, New York, NY, 2012, pp. 10-11. |
| Storer et al., “Pergamum: Replacing Tape with Energy Efficient, Reliable, Disk-Based Archival Storage,” Fast '08: 6th USENIX Conference on File and Storage Technologies, San Jose, CA, Feb. 26 to Feb. 29, 2008, pp. 1-16. |
| Wong et al., “Verifiable secret redistribution for archive systems,” In: Proceedings on First International IEEE Security in Storage Workshop 2002, (SISW '02), Dec. 11, 2002, pp. 1-12. |
| Number | Date | Country | |
|---|---|---|---|
| 20200343974 A1 | Oct 2020 | US |
| Number | Date | Country | |
|---|---|---|---|
| 62403868 | Oct 2016 | US |
| Number | Date | Country | |
|---|---|---|---|
| Parent | 16370527 | Mar 2019 | US |
| Child | 16927023 | US |
| Number | Date | Country | |
|---|---|---|---|
| Parent | 15416990 | Jan 2017 | US |
| Child | 16370527 | US |
