Patent Grant
11061835
Storage systems are designed to handle certain levels of IO workloads. When the workload is well within the designed load capacity, the IO processing latency may be flat. When the workload approaches or exceeds designed capacity, the processing latency may increase sharply. After the workload exceeds a set tipping point, the system may be pushed out of its stable state, and the IO handling latency may grow exponentially. Thus, it is helpful for a system to control the workload within this tipping point and prevent the overload from occurring. On the other hand, if the system controls the load too aggressively, this may cause the system to be underutilized.
Some systems throttle the total number of IO tasks in the system and reject incoming IOs upon detecting an overload situation. These systems may use some form of latency calculation over time as an indicator of the system load, which may work well assuming the IO requests follow a certain standard distribution or can be normalized using some adjustment (e.g., by IO size).
On the other hand, for certain IOs (e.g., those with different priorities) and certain services (sync or active/active replication), additional latencies may not be caused by system load. In this situation, it is not helpful to begin throttling IOs. For example, in sync replication, the time spent on remote data transfer does not contribute significantly to the local system load, and in active/active replication, the time spent to resolve distributed address lock collision does not indicate system overload. If the system gives high priority to certain application IOs over other application IOs, a longer average latency of lower priority IOs may due to scheduling queuing, not necessarily system overload.
This Summary is provided to introduce a selection of concepts in a simplified form that are further described herein in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
One aspect provides a method for input/output (IO) flow control in a storage system. The method includes receiving an IO latency factor for each IO of a plurality of IOs in a workload. The IO latency factor specifies a priority level. The method also includes receiving a component latency factor, with respect to each of the IOs in the workload, for each component of a plurality of components in the storage system. The component latency factor indicates a degree to which the component is considered in assessing the workload. The method also includes processing the plurality of IOs in the workload. The processing includes applying, during processing of the workload, the IO latency factor and the component latency factor to each of the IOs; and determining an effective average latency of the plurality of IOs in the workload as a function of the applied IO latency factors and the applied component latency factors. The method further includes modifying the IO flow control of incoming IOs in the storage system as a function of the effective average latency.
Another aspect provides a system for input/output (IO) flow control in a storage system. The system includes a memory having computer-executable instructions and a processor operable by a storage system. The processor executes the computer-executable instructions. The computer-executable instructions when executed by the processor cause the processor to perform operations. The operations include receiving an IO latency factor for each IO of a plurality of IOs in a workload. The IO latency factor specifies a priority level. The operations also include receiving a component latency factor, with respect to each of the IOs in the workload, for each component of a plurality of components in the storage system. The component latency factor indicates a degree to which the component is considered in assessing the workload. The operations further include applying, during processing of the workload, the IO latency factor and the component latency factor to each of the IOs; and determining an effective average latency of the plurality of IOs in the workload as a function of the applied IO latency factors and the applied component latency factors. The operations also include modifying the IO flow control of incoming IOs in the storage system as a function of the effective average latency.
A further aspect provides a computer program product for input/output (IO) flow control in a storage system. The computer program product includes the computer program product embodied on a non-transitory computer readable medium, the computer program product including instructions that, when executed by a computer, cause the computer to perform operations. The operations include receiving an IO latency factor for each IO of a plurality of IOs in a workload. The IO latency factor specifies a priority level. The operations also include receiving a component latency factor, with respect to each of the IOs in the workload, for each component of a plurality of components in the storage system. The component latency factor indicates a degree to which the component is considered in assessing the workload. The operations further include applying, during processing of the workload, the IO latency factor and the component latency factor to each of the corresponding IOs; and determining an effective average latency of the plurality of IOs in the workload as a function of the applied IO latency factors and the applied component latency factors. The operations also include modifying the IO flow control of incoming IOs in the storage system as a function of the effective average latency.
Objects, aspects, features, and advantages of embodiments disclosed herein will become more fully apparent from the following detailed description, the appended claims, and the accompanying drawings in which like reference numerals identify similar or identical elements. Reference numerals that are introduced in the specification in association with a drawing figure may be repeated in one or more subsequent figures without additional description in the specification in order to provide context for other features. For clarity, not every element may be labeled in every figure. The drawings are not necessarily to scale, emphasis instead being placed upon illustrating embodiments, principles, and concepts. The drawings are not meant to limit the scope of the claims included herewith.
Storage systems are designed to handle certain levels of IO workloads. When the workload is well within the designed load capacity, the IO processing latency may be flat. When the workload approaches or exceeds designed capacity, the processing latency may increase sharply. After the workload exceeds a set tipping point, the system may be pushed out of its stable state, and the IO handling latency may grow exponentially. Thus, it is helpful for a system to control the workload within this tipping point and prevent the overload from occurring. On the other hand, if the system controls the load too aggressively, this may cause the system to be underutilized.
Some systems throttle the total number of IO tasks in the system and reject incoming IOs upon detecting an overload situation. These systems may use an average IO latency value as an indicator of the system load, which may work well assuming the IO requests follow a certain standard distribution or can be normalized using some adjustment (e.g., by IO size).
On the other hand, for certain IOs (e.g., those with different priorities) and certain services (sync or active/active replication), additional latencies may not be caused by system load. In this situation, it is not helpful to begin throttling IOs. For example, in sync replication, the time spent on remote data transfer does not contribute significantly to the local system load, and in active/active replication, the time spent to resolve distributed address lock collision does not indicate system overload. If the system gives high priority to certain application IOs over other application IOs, a longer average latency of lower priority IOs may due to scheduling queuing, not necessarily system overload.
Illustrative embodiments provide a storage system with functionality for IO flow control in the storage system. The embodiments provide a solution to handle replication latency while maintaining optimal flow control. In embodiments, a sensitivity matrix is provided with a flow control mechanism which includes an IO latency factor and a component latency factor that are applied to IOs of a workload in order to determine latencies in the workload processes that account for the type of IO being processed (i.e., a priority level of the IO), as well as components and services associated with processing the IO. Timewise, the processes may also detect latency change trends by monitoring the rate of change of the average latency. If the latency increases, the but the rate of change is low, then the latency increase may be due to workload pattern changes that are capable of system handling. However, if the rate of change increases sharply, this may reflect a more significant situation such as signal overload.
Each of the storage systems 102 is illustratively associated with a corresponding set of one or more of the host devices 101. The host devices 101 illustratively comprise servers or other types of computers of an enterprise computer system, cloud-based computer system or other arrangement of multiple compute nodes associated with respective users.
The host devices 101 in some embodiments illustratively provide compute services such as execution of one or more applications on behalf of each of one or more users associated with respective ones of the host devices. Such applications illustratively generate input/output (IO) operations that are processed by a corresponding one of the storage systems 102. The term “IO” as used herein refers to at least one of input and output. For example, IO operations may comprise write requests and/or read requests directed to stored data of a given one of the storage systems 102. The storage systems 102 illustratively comprise respective processing devices of one or more processing platforms. For example, the storage systems 102 can each comprise one or more processing devices each having a processor and a memory, possibly implementing virtual machines and/or containers, although numerous other configurations are possible.
The storage systems 102 may be implemented on a common processing platform, or on separate processing platforms.
The host devices 101 are illustratively configured to write data to and read data from the storage systems 102 in accordance with applications executing on those host devices for system users.
The term “user” herein is intended to be broadly construed so as to encompass numerous arrangements of human, hardware, software or firmware entities, as well as combinations of such entities. Compute and/or storage services may be provided for users under a Platform-as-a-Service (PaaS) model, an Infrastructure-as-a-Service (IaaS) model and/or a Function-as-a-Service (FaaS) model, although it is to be appreciated that numerous other cloud infrastructure arrangements could be used. Also, illustrative embodiments can be implemented outside of the cloud infrastructure context, as in the case of a stand-alone computing and storage system implemented within a given enterprise.
The network 104 is assumed to comprise a portion of a global computer network such as the Internet, although other types of networks can be part of the network 104, including a wide area network (WAN), a local area network (LAN), a satellite network, a telephone or cable network, a cellular network, a wireless network such as a WiFi or WiMAX network, or various portions or combinations of these and other types of networks. The network 104 in some embodiments therefore comprises combinations of multiple different types of networks each comprising processing devices configured to communicate using Internet Protocol (IP) or other communication protocols.
As a more particular example, some embodiments may utilize one or more high-speed local networks in which associated processing devices communicate with one another utilizing Peripheral Component Interconnect express (PCIe) cards of those devices, and networking protocols such as InfiniBand, Gigabit Ethernet or Fibre Channel. Numerous alternative networking arrangements are possible in a given embodiment, as will be appreciated by those skilled in the art.
The local storage system 102L comprises a plurality of storage devices 106L and an associated storage controller 108L. The storage devices 106L store storage volumes 110L and queues 115L. The storage volumes 110L illustratively comprise respective logical units (LUNs) or other types of logical storage volumes. The queues 115L may store incoming IOs waiting to be processed by the local storage system 102L.
Similarly, the remote storage system 102R comprises a plurality of storage devices 106R and an associated storage controller 108R. The storage devices 106R store storage volumes 110R, at least a portion of which represent respective LUNs or other types of logical storage volumes that are replicated from the local storage system 102L to the remote storage system 102R in accordance with a replication process. The storage devices 106R also store one or more queues 115R.
The storage devices 106 of the storage systems 102 illustratively comprise solid state drives (SSDs). Such SSDs are implemented using non-volatile memory (NVM) devices such as flash memory. Other types of NVM devices that can be used to implement at least a portion of the storage devices 106 include non-volatile random access memory (NVRAM), phase-change RAM PC-RAM) and magnetic RAM (MRAM). These and various combinations of multiple different types of NVM devices may also be used. For example, hard disk drives (HDDs) can be used in combination with or in place of SSDs or other types of NVM devices.
However, it is to be appreciated that other types of storage devices can be used in other embodiments. For example, a given storage system as the term is broadly used herein can include a combination of different types of storage devices, as in the case of a multi-tier storage system comprising a flash-based fast tier and a disk-based capacity tier. In such an embodiment, each of the fast tier and the capacity tier of the multi-tier storage system comprises a plurality of storage devices with different types of storage devices being used in different ones of the storage tiers.
For example, the fast tier may comprise flash drives or other types of SSDs while the capacity tier comprises HDDs. The particular storage devices used in a given storage tier may be varied in other embodiments, and multiple distinct storage device types may be used within a single storage tier. The term “storage device” as used herein is intended to be broadly construed, to encompass, for example, SSDs, HDDs, flash drives, hybrid drives or other types of storage devices.
In some embodiments, at least one of the storage systems 102 illustratively comprises a scale-out all-flash content addressable storage array such as an XtremIO storage array, of DELL EMC of Hopkinton, Mass.
The term “storage system” as used herein is therefore intended to be broadly construed and should not be viewed as being limited to content addressable storage systems or flash-based storage systems. A given storage system as the term is broadly used herein can comprise, for example, network-attached storage (NAS), storage area networks (SANs), direct-attached storage (DAS) and distributed DAS, as well as combinations of these and other storage types, including software-defined storage.
The storage controller 108L of local storage system 102L in the
Similarly, the storage controller 108R of remote storage system 102R includes replication control logic 112R and a flow controller 114T. In embodiments, the flow controllers 114L and 114T, in conjunction with the replication control logic 112L and 112R, respectively, facilitate IO flow control through the sensitivity matrix described herein. The sensitivity matrix operates on IO-related latencies and component- and service-related latencies to identify and assess actual latency values for a workload. In some embodiments, the terms component and service and are used interchangeably.
Although not explicitly shown in the Figure, additional components can be included in the storage controllers 108, such as signature generators utilized in generating content-based signatures of data pages.
The instances of replication control logic 112L and 112R are collectively referred to herein as replication control logic 112. Such replication control logic instances are also referred to herein as individually or collectively comprising at least a portion of a “replication engine” of the system 100.
The replication control logic 112 of the storage systems 102 controls performance of the replication process carried out between those storage systems, which as noted above in some embodiments further involves at least one of the host devices 101. The data replicated from the local storage system 102L to the remote storage system 102R can include all of the data stored in the local storage system 102L, or only certain designated subsets of the data stored in the local storage system 102L, such as particular designated sets of LUNs or other logical storage volumes. Different replication processes of different types can be implemented for different parts of the stored data. Also, the storage systems 102 can be configured to operate in different replication modes of different types at different times.
A given storage volume designated for replication from the local storage system 102L to the remote storage system 102R illustratively comprises a set of one or more LUNs or other instances of the storage volumes 110L of the local storage system 102L. Each such LUN or other storage volume illustratively comprises at least a portion of a physical storage space of one or more of the storage devices 106L. The corresponding replicated LUN or other storage volume of the storage volumes 110R of the remote storage system 102R illustratively comprises at least a portion of a physical storage space of one or more of the storage devices 106R.
The replication control logic 112 of the storage systems 102 in some embodiments is configured to control the performance of corresponding portions of a replication process of the type illustrated in the flow diagram of
The storage controllers 108 of the storage systems 102 should also be understood to include additional modules and other components typically found in conventional implementations of storage controllers and storage systems, although such additional modules and other components are omitted from the figure for clarity and simplicity of illustration.
It will be assumed for the following description of the
The replication process more particularly comprises a replication process in which a consistency group comprising one or more storage volumes is replicated from the local storage system 102L to the remote storage system 102R as part of host IO handling. Such an arrangement is illustratively configured to guarantee data consistency between the storage volumes of the consistency group on the local and their corresponding replicated versions on the remote. The replication is illustratively implemented at least in part by or otherwise under the control of the local and remote instances of replication control logic 112L and 112R. Other types of replication arrangements can be used in other embodiments.
In embodiments in which the storage systems 102 comprise content addressable storage systems, address metadata is illustratively utilized to provide content addressable storage functionality within those systems. The address metadata in some embodiments comprises at least a portion of one or more logical layer mapping tables that map logical addresses of respective ones of the data pages of the storage volume to corresponding content-based signatures of the respective data pages. Examples of logical layer mapping tables and other metadata structures maintained by at least the storage controller 108R of remote storage system 102R will be described elsewhere herein.
The storage systems 102 in the
The storage systems 102 may be implemented on respective distinct processing platforms, although numerous other arrangements are possible. At least portions of their associated host devices may be implemented on the same processing platforms as the storage systems 102 or on separate processing platforms.
The term “processing platform” as used herein is intended to be broadly construed so as to encompass, by way of illustration and without limitation, multiple sets of processing devices and associated storage systems that are configured to communicate over one or more networks. For example, distributed implementations of the system 100 are possible, in which certain components of the system reside in one data center in a first geographic location while other components of the system reside in one or more other data centers in one or more other geographic locations that are potentially remote from the first geographic location. Thus, it is possible in some implementations of the system 100 for the storage systems 102 to reside in different data centers. Numerous other distributed implementations of the storage systems 102 and their respective associated sets of host devices are possible.
Additional examples of processing platforms utilized to implement storage systems and possibly their associated host devices in illustrative embodiments will be described in more detail below in conjunction with
It is to be appreciated that these and other features of illustrative embodiments are presented by way of example only and should not be construed as limiting in any way.
Accordingly, different numbers, types and arrangements of system components such as host devices 101, storage systems 102, network 104, storage devices 106, storage controllers 108 and storage volumes 110 can be used in other embodiments.
It should be understood that the particular sets of modules and other components implemented in the system 100 as illustrated in
For example, in other embodiments, at least portions of the above-described functionality for flow control in a replication process can be implemented in one or more host devices, or partially in a host device and partially in a storage system. Illustrative embodiments are not limited to arrangements in which all such functionality is implemented in local and remote storage systems or a host device, and therefore encompass various hybrid arrangements in which the functionality is distributed over one or more storage systems and one or more associated host devices, each comprising one or more processing devices. References herein to “one or more processing devices” configured to implement particular operations or other functionality should be understood to encompass a wide variety of different arrangements involving one or more processing devices of at least one storage system and/or at least one host device.
As another example, it is possible in some embodiments that the local storage system and the remote storage system can comprise different portions of the same storage system. In such an arrangement, a replication process is illustratively implemented to replicate data from one portion of the storage system to another portion of the storage system. The terms “local storage system” and “remote storage system” as used herein are therefore intended to be broadly construed so as to encompass such possibilities.
The operation of the information processing system 100 will now be described in further detail with reference to the flow diagrams of the illustrative embodiment of
The flow control process as illustrated in
In embodiments, a sensitivity matrix is provided with a flow control mechanism which includes an IO latency factor and a component latency factor that are applied to IOs of a workload in order to determine latencies in the workload processes that account for the type of IO being processed (i.e., a priority level of the IO), as well as components and services associated with processing the IO. The embodiments described herein defines a latency sensitivity factor (0<=f_io_latency<=1) to latency insensitive IOs (low priority IOs). In addition, the embodiments define a latency sensitivity factor (0<=f_comp_latency<=1) to latency insensitive components/services. Timewise, the processes may also detect latency change trends by monitoring the rate of change of the average latency. If the latency increases, the but the rate of change is low, then the latency increase may be due to workload pattern changes that are capable of system handling. However, if the rate of change increases sharply, this may reflect a more significant situation such as signal overload.
Turning now to
In block 204, the process 200A receives a component latency factor, with respect to each of the IOs in the workload, for each component (and/or service) in the storage system. The component latency factor is considered a second element of the sensitivity matrix. Components include, e.g., modules, caches, persistent storage, etc. The component latency factor indicates a degree to which the component is considered in assessing the workload. The component latency factor may be a value expressed as 0<=f_comp_latency<=1. For example, a component that should not be considered in a latency determination may be assigned a value of 0, while a component that should be considered in the latency determination may be assigned a value of 1. It will be understood that values between 0 and 1 may be assigned to a component when the component should be partially considered in determining latency of an IO. The component latency factor measures an amount of time the IO is processed through a corresponding one of the components. Services may include, e.g., synchronous replication remote data transfer functions (where the replication is synchronous replication), and address lock resolution functions (where the replication is active/active replication).
In block 206, the process 200A executes the plurality of IOs in the workload. In embodiments, the execution step includes applying, in block 208, the IO latency factor and the component latency factor to each of the corresponding IOs. In block 210, the process 200A determines an effective IO latency for each IO in the workload from the applied IO latency factor and the applied component latency factor. The effective IO latency determination is described further in
In block 212, the process 200A calculates the effective average latency over a number of IOs processed. The effective average latency step is described further in
In block 214, the process 200A may modify the flow control of incoming IOs as a function of the effective average latency determination. For example, upon determining the effective average latency is less than a threshold value, the process 200A increases an amount of the incoming IOs. Likewise, if the effective average latency is greater than a threshold value, the process 200A decreases the amount of the incoming IOs.
Turning now to
In block 224, the process 200B sums the component latency values for each of the components and, in block 226, the process 200B multiplies the sum of the component latency values by the IO latency value, yielding an effective IO latency value attributed to the IO. This effective IO latency value may be used as a load indicator value (e.g., replacing IO latency statistics).
Turning now to
Determining the effective average latency includes, in block 236, trending the current average latency calculated for the IOs processed in the workload and a previous average latency calculated for IOs processed in a previous workload.
The particular processing operations and other system functionality described in conjunction with the flow diagrams of
Functionality such as that described in conjunction with the flow diagrams of
For example, storage controllers such as storage controllers 108 of storage systems 102 that are configured to control performance of one or more steps of the
In some implementations of the
An address-to-hash (“A2H”) utilized in some embodiments comprises a plurality of entries accessible utilizing logical addresses as respective keys, with each such entry of the A2H table comprising a corresponding one of the logical addresses, a corresponding hash handle, and possibly one or more additional fields.
A hash-to-data (“H2D”) table utilized in some embodiments comprises a plurality of entries accessible utilizing hash handles as respective keys, with each such entry of the H2D table comprising a corresponding one of the hash handles, a physical offset of a corresponding one of the data pages, and possibly one or more additional fields.
A hash metadata (“HMD”) table utilized in some embodiments comprises a plurality of entries accessible utilizing hash handles as respective keys. Each such entry of the HMD table comprises a corresponding one of the hash handles, a corresponding reference count and a corresponding physical offset of one of the data pages. A given one of the reference counts denotes the number of logical pages in the storage system that have the same content as the corresponding data page and therefore point to that same data page via their common hash digest. The HMD table may also include one or more additional fields.
A physical layer based (“PLB”) table utilized in some embodiments illustratively comprises a plurality of entries accessible utilizing physical offsets as respective keys, with each such entry of the PLB table comprising a corresponding one of the physical offsets, a corresponding one of the hash digests, and possibly one or more additional fields.
As indicated above, the hash handles are generally shorter in length than the corresponding hash digests of the respective data pages, and each illustratively provides a short representation of the corresponding full hash digest. For example, in some embodiments, the full hash digests are 20 bytes in length, and their respective corresponding hash handles are illustratively only 4 or 6 bytes in length.
Also, it is to be appreciated that terms such as “table” and “entry” as used herein are intended to be broadly construed, and the particular example table and entry arrangements described above can be varied in other embodiments. For example, additional or alternative arrangements of entries can be used.
In some embodiments, the storage system may comprise an XtremIO storage array or other type of content addressable storage system suitably modified to incorporate functionality for flow control processes in conjunction with a replication process as disclosed herein.
An illustrative embodiment of such a content addressable storage system will now be described with reference to
Although it is assumed that both the local storage system 102L and the remote storage system 102R are content addressable storage systems in some embodiments, other types of storage systems can be used for one or both of the local storage system 102L and the remote storage system 102R in other embodiments. For example, it is possible that at least one of the storage systems 102 in an illustrative embodiment need not be a content addressable storage system and need not include an ability to generate content-based signatures. In such an embodiment, at least portions of the process functionality of the one or more storage systems can be implemented in a host device.
The storage controller 408 in the present embodiment is configured to implement functionality for flow control processes of the type previously described in conjunction with
The storage controller 408 includes distributed modules 412 and 414, which are configured to operate in a manner similar to that described above for respective corresponding replication control logic 112 and flow controllers 114 of the storage controllers 108 of system 100. Module 412 is more particularly referred to as distributed replication control logic, and illustratively comprises multiple replication control logic instances on respective ones of a plurality of distinct nodes. Module 414 is more particularly referred to as a distributed flow controller, and illustratively comprises multiple flow control instances on respective ones of the distinct nodes.
The content addressable storage system 405 in the
The storage controller 408 of the content addressable storage system 405 is implemented in a distributed manner so as to comprise a plurality of distributed storage controller components implemented on respective ones of the storage nodes 415. The storage controller 408 is therefore an example of what is more generally referred to herein as a “distributed storage controller.” In subsequent description herein, the storage controller 408 is referred to as distributed storage controller 408.
Each of the storage nodes 415 in this embodiment further comprises a set of processing modules configured to communicate over one or more networks with corresponding sets of processing modules on other ones of the storage nodes 415. The sets of processing modules of the storage nodes 415 collectively comprise at least a portion of the distributed storage controller 408 of the content addressable storage system 405.
The modules of the distributed storage controller 408 in the present embodiment more particularly comprise different sets of processing modules implemented on each of the storage nodes 415. The set of processing modules of each of the storage nodes 415 comprises at least a control module 408C, a data module 408D and a routing module 408R. The distributed storage controller 408 further comprises one or more management (“MGMT”) modules 408M. For example, only a single one of the storage nodes 415 may include a management module 408M. It is also possible that management modules 408M may be implemented on each of at least a subset of the storage nodes 415. A given set of processing modules implemented on a particular one of the storage nodes 415 therefore illustratively includes at least one control module 408C, at least one data module 408D and at least one routing module 408R, and possibly a management module 408M.
Communication links may be established between the various processing modules of the distributed storage controller 408 using well-known communication protocols such as IP, Transmission Control Protocol (TCP), and remote direct memory access (RDMA). For example, respective sets of IP links used in data transfer and corresponding messaging could be associated with respective different ones of the routing modules 408R.
Although shown as separate modules of the distributed storage controller 408, the modules 412 and 414 in the present embodiment are assumed to be distributed at least in part over at least a subset of the other modules 408C, 408D, 408R and 408M of the storage controller 408. Accordingly, at least portions of the flow control functionality of the modules 412 and 414 may be implemented in one or more of the other modules of the storage controller 408. In other embodiments, the modules 412 and 414 may be implemented as stand-alone modules of the storage controller 408. In embodiments, the flow control processes described in
The storage devices 406 may be configured to store volumes 418, as well as metadata pages 420 and user data pages 422 and may also store additional information not explicitly shown such as checkpoints and write journals. The metadata pages 420 and the user data pages 422 are illustratively stored in respective designated metadata and user data areas of the storage devices 406. Accordingly, metadata pages 420 and user data pages 422 may be viewed as corresponding to respective designated metadata and user data areas of the storage devices 406. A given “page” as the term is broadly used herein should not be viewed as being limited to any particular range of fixed sizes. In some embodiments, a page size of 8 kilobytes (KB) is used, but this is by way of example only and can be varied in other embodiments. For example, page sizes of 4 KB, 16 KB or other values can be used. Accordingly, illustrative embodiments can utilize any of a wide variety of alternative paging arrangements for organizing the metadata pages 420 and the user data pages 422.
The user data pages 422 are part of a plurality of LUNs configured to store files, blocks, objects or other arrangements of data, each also generally referred to herein as a “data item,” on behalf of users of the content addressable storage system 405. Each such LUN may comprise particular ones of the above-noted pages of the user data area. The user data stored in the user data pages 422 can include any type of user data that may be utilized in the system 100. The term “user data” herein is therefore also intended to be broadly construed.
A given storage volume for which content-based signatures are generated using modules 412 and 414 illustratively comprises a set of one or more LUNs, each including multiple ones of the user data pages 422 stored in storage devices 406. The content addressable storage system 405 in the embodiment of
Each of the metadata pages 420 characterizes a plurality of the user data pages 422. For example, a given set of user data pages representing a portion of the user data pages 422 illustratively comprises a plurality of user data pages denoted User Data Page 1, User Data Page 2, . . . User Data Page n. Each of the user data pages in this example is characterized by a LUN identifier, an offset and a content-based signature. The content-based signature is generated as a hash function of content of the corresponding user data page. Illustrative hash functions that may be used to generate the content-based signature include the above-noted SHA1 secure hashing algorithm, or other secure hashing algorithms known to those skilled in the art, including SHA2, SHA256 and many others. The content-based signature is utilized to determine the location of the corresponding user data page within the user data area of the storage devices 406.
Each of the metadata pages 420 in the present embodiment is assumed to have a signature that is not content-based. For example, the metadata page signatures may be generated using hash functions or other signature generation algorithms that do not utilize content of the metadata pages as input to the signature generation algorithm. Also, each of the metadata pages is assumed to characterize a different set of the user data pages.
A given set of metadata pages representing a portion of the metadata pages 420 in an illustrative embodiment comprises metadata pages denoted Metadata Page 1, Metadata Page 2, . . . Metadata Page m, having respective signatures denoted Signature 1, Signature 2, . . . Signature m. Each such metadata page characterizes a different set of n user data pages. For example, the characterizing information in each metadata page can include the LUN identifiers, offsets and content-based signatures for each of the n user data pages that are characterized by that metadata page. It is to be appreciated, however, that the user data and metadata page configurations described above are examples only, and numerous alternative user data and metadata page configurations can be used in other embodiments.
Ownership of a user data logical address space within the content addressable storage system 405 is illustratively distributed among the control modules 408C.
The flow control functionality provided by modules 412 and 414 in this embodiment is assumed to be distributed across multiple distributed processing modules, including at least a subset of the processing modules 408C, 408D, 408R and 408M of the distributed storage controller 408.
For example, the management module 408M of the storage controller 408 may include a replication control logic instance that engages corresponding replication control logic instances in all of the control modules 408C and routing modules 408R in order to implement a replication process. In some embodiments, the content addressable storage system 405 comprises an XtremIO storage array suitably modified to incorporate flow control functionality as disclosed herein.
In arrangements of this type, the control modules 408C, data modules 408D and routing modules 408R of the distributed storage controller 408 illustratively comprise respective C-modules, D-modules and R-modules of the XtremIO storage array. The one or more management modules 408M of the distributed storage controller 408 in such arrangements illustratively comprise a system-wide management module (“SYM module”) of the XtremIO storage array, although other types and arrangements of system-wide management modules can be used in other embodiments. Accordingly, flow control functionality in some embodiments is implemented under the control of at least one system-wide management module of the distributed storage controller 408, utilizing the C-modules, D-modules and R-modules of the XtremIO storage array.
In the above-described XtremIO storage array example, each user data page has a fixed size such as 8 KB and its content-based signature is a 20-byte signature generated using the SHA1 secure hashing algorithm. Also, each page has a LUN identifier and an offset, and so is characterized by <lun_id, offset, signature>.
The content-based signature in the present example comprises a content-based digest of the corresponding data page. Such a content-based digest is more particularly referred to as a “hash digest” of the corresponding data page, as the content-based signature is illustratively generated by applying a hash function such as the SHA1 secure hashing algorithm to the content of that data page. The full hash digest of a given data page is given by the above-noted 20-byte signature. The hash digest may be represented by a corresponding “hash handle,” which in some cases may comprise a particular portion of the hash digest. The hash handle illustratively maps on a one-to-one basis to the corresponding full hash digest within a designated cluster boundary or other specified storage resource boundary of a given storage system. In arrangements of this type, the hash handle provides a lightweight mechanism for uniquely identifying the corresponding full hash digest and its associated data page within the specified storage resource boundary. The hash digest and hash handle are both considered examples of “content-based signatures” as that term is broadly used herein.
Examples of techniques for generating and processing hash handles for respective hash digests of respective data pages are disclosed in U.S. Pat. No. 9,208,162, entitled “Generating a Short Hash Handle,” and U.S. Pat. No. 9,286,003, entitled “Method and Apparatus for Creating a Short Hash Handle Highly Correlated with a Globally-Unique Hash Signature,” both of which are incorporated by reference herein.
As mentioned previously, storage controller components in an XtremIO storage array illustratively include C-module, D-module and R-module components. For example, separate instances of such components can be associated with each of a plurality of storage nodes in a clustered storage system implementation.
The distributed storage controller in this example is configured to group consecutive pages into page groups, to arrange the page groups into slices, and to assign the slices to different ones of the C-modules. For example, if there are 1024 slices distributed evenly across the C-modules, and there are a total of 16 C-modules in a given implementation, each of the C-modules “owns” 1024/16=64 slices. In such arrangements, different ones of the slices are assigned to different ones of the control modules 408C such that control of the slices within the storage controller 408 of the storage system 405 is substantially evenly distributed over the control modules 408C of the storage controller 408.
The D-module allows a user to locate a given user data page based on its signature. Each metadata page also has a size of 8 KB and includes multiple instances of the <lun_id, offset, signature> for respective ones of a plurality of the user data pages. Such metadata pages are illustratively generated by the C-module but are accessed using the D-module based on a metadata page signature.
The metadata page signature in this embodiment is a 20-byte signature but is not based on the content of the metadata page. Instead, the metadata page signature is generated based on an 8-byte metadata page identifier that is a function of the LUN identifier and offset information of that metadata page.
If a user wants to read a user data page having a particular LUN identifier and offset, the corresponding metadata page identifier is first determined, then the metadata page signature is computed for the identified metadata page, and then the metadata page is read using the computed signature. In this embodiment, the metadata page signature is more particularly computed using a signature generation algorithm that generates the signature to include a hash of the 8-byte metadata page identifier, one or more ASCII codes for particular predetermined characters, as well as possible additional fields. The last bit of the metadata page signature may always be set to a particular logic value so as to distinguish it from the user data page signature in which the last bit may always be set to the opposite logic value.
The metadata page signature is used to retrieve the metadata page via the D-module. This metadata page will include the <lun_id, offset, signature> for the user data page if the user page exists. The signature of the user data page is then used to retrieve that user data page, also via the D-module.
Write requests processed in the content addressable storage system 405 each illustratively comprise one or more IO operations directing that at least one data item of the storage system 405 be written to in a particular manner. A given write request is illustratively received in the storage system 405 from a host device over a network. In some embodiments, a write request is received in the distributed storage controller 408 of the storage system 405 and directed from one processing module to another processing module of the distributed storage controller 408. For example, a received write request may be directed from a routing module 408R of the distributed storage controller 408 to a particular control module 408C of the distributed storage controller 408. Other arrangements for receiving and processing write requests from one or more host devices can be used.
The term “write request” as used herein is intended to be broadly construed, so as to encompass one or more IO operations directing that at least one data item of a storage system be written to in a particular manner. A given write request is illustratively received in a storage system from a host device.
In the XtremIO context, the C-modules, D-modules and R-modules of the storage nodes 415 communicate with one another over a high-speed internal network such as an InfiniBand network. The C-modules, D-modules and R-modules coordinate with one another to accomplish various IO processing tasks.
The write requests from the host devices identify particular data pages to be written in the storage system 405 by their corresponding logical addresses each comprising a LUN ID and an offset.
As noted above, a given one of the content-based signatures illustratively comprises a hash digest of the corresponding data page, with the hash digest being generated by applying a hash function to the content of that data page. The hash digest may be uniquely represented within a given storage resource boundary by a corresponding hash handle.
The content addressable storage system 405 utilizes a two-level mapping process to map logical block addresses to physical block addresses. The first level of mapping uses an address-to-hash (“A2H”) table and the second level of mapping uses a hash metadata (“HMD”) table, with the A2H and HMD tables corresponding to respective logical and physical layers of the content-based signature mapping within the content addressable storage system 405. The HMD table or a given portion thereof in some embodiments disclosed herein is more particularly referred to as a hash-to-data (“H2D”) table.
The first level of mapping using the A2H table associates logical addresses of respective data pages with respective content-based signatures of those data pages. This is also referred to as logical layer mapping. The second level of mapping using the HMD table associates respective ones of the content-based signatures with respective physical storage locations in one or more of the storage devices 106. This is also referred to as physical layer mapping.
Examples of these and other metadata structures utilized in illustrative embodiments were described above in conjunction with
For a given write request, hash metadata comprising at least a subset of the above-noted tables is updated in conjunction with the processing of that write request. The A2H, H2D, HMD and PLB tables described above are examples of what are more generally referred to herein as “mapping tables” of respective distinct types. Other types and arrangements of mapping tables or other content-based signature mapping information may be used in other embodiments. Such mapping tables are still more generally referred to herein as “metadata structures” of the content addressable storage system 405. It should be noted that additional or alternative metadata structures can be used in other embodiments. References herein to particular tables of particular types, such as A2H, H2D, HMD and PLB tables, and their respective configurations, should be considered non-limiting and are presented by way of illustrative example only. Such metadata structures can be implemented in numerous alternative configurations with different arrangements of fields and entries in other embodiments.
The logical block addresses or LBAs of a logical layer of the storage system 405 correspond to respective physical blocks of a physical layer of the storage system 405. The user data pages of the logical layer are organized by LBA and have reference via respective content-based signatures to particular physical blocks of the physical layer.
Each of the physical blocks has an associated reference count that is maintained within the storage system 405. The reference count for a given physical block indicates the number of logical blocks that point to that same physical block.
In releasing logical address space in the storage system, a dereferencing operation is generally executed for each of the LBAs being released. More particularly, the reference count of the corresponding physical block is decremented. A reference count of zero indicates that there are no longer any logical blocks that reference the corresponding physical block, and so that physical block can be released.
It should also be understood that the particular arrangement of storage controller processing modules 408C, 408D, 408R and 408M as shown in the
Additional examples of content addressable storage functionality implemented in some embodiments by control modules 408C, data modules 408D, routing modules 408R and management module(s) 408M of distributed storage controller 408 can be found in U.S. Pat. No. 9,104,326, entitled “Scalable Block Data Storage Using Content Addressing,” which is incorporated by reference herein. Alternative arrangements of these and other storage node processing modules of a distributed storage controller in a content addressable storage system can be used in other embodiments.
In some embodiments, the local and remote storage systems are illustratively implemented as respective content addressable storage systems, but in other embodiments one or more of the storage systems can instead be a traditional storage array, which does not support any type of content addressable storage functionality, with any missing functionality being provided by a host device. Accordingly, functionality for flow control in replication as disclosed herein can be implemented in a storage system, in a host device, or partially in a storage system and partially in a host device.
It is to be appreciated that the particular advantages described above and elsewhere herein are associated with particular illustrative embodiments and need not be present in other embodiments. Also, the particular types of information processing system features and functionality as illustrated in the drawings and described above are exemplary only, and numerous other arrangements may be used in other embodiments.
Illustrative embodiments of processing platforms utilized to implement host devices and storage systems with flow control functionality will now be described in greater detail with reference to
The cloud infrastructure 500 further comprises sets of applications 510-1, 510-2, . . . 510L running on respective ones of the VMs/container sets 502-1, 502-2, . . . 502-L under the control of the virtualization infrastructure 504. The VMs/container sets 502 may comprise respective VMs, respective sets of one or more containers, or respective sets of one or more containers running in VMs.
In some implementations of the
An example of a hypervisor platform that may be used to implement a hypervisor within the virtualization infrastructure 504 is the VMware® vSphere® which may have an associated virtual infrastructure management system such as the VMware® vCenter™. The underlying physical machines may comprise one or more distributed processing platforms that include one or more storage systems. In other implementations of the
As is apparent from the above, one or more of the processing modules or other components of system 100 may each run on a computer, server, storage device or other processing platform element. A given such element may be viewed as an example of what is more generally referred to herein as a “processing device.” The cloud infrastructure 500 shown in
The processing platform 600 in this embodiment comprises a portion of system 100 and includes a plurality of processing devices, denoted 602-1, 602-2, 602-3, . . . 602-K, which communicate with one another over a network 604.
The network 604 may comprise any type of network, including by way of example a global computer network such as the Internet, a WAN, a LAN, a satellite network, a telephone or cable network, a cellular network, a wireless network such as a WiFi or WiMAX network, or various portions or combinations of these and other types of networks.
The processing device 602-1 in the processing platform 600 comprises a processor 610 coupled to a memory 612. The processor 610 may comprise a microprocessor, a microcontroller, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), graphics processing unit (GPU) or other type of processing circuitry, as well as portions or combinations of such circuitry elements.
The memory 612 may comprise random access memory (RAM), read-only memory (ROM), flash memory or other types of memory, in any combination. The memory 612 and other memories disclosed herein should be viewed as illustrative examples of what are more generally referred to as “processor-readable storage media” storing executable program code of one or more software programs.
Articles of manufacture comprising such processor-readable storage media are considered illustrative embodiments. A given such article of manufacture may comprise, for example, a storage array, a storage disk or an integrated circuit containing RAM, ROM, flash memory or other electronic memory, or any of a wide variety of other types of computer program products. The term “article of manufacture” as used herein should be understood to exclude transitory, propagating signals. Numerous other types of computer program products comprising processor-readable storage media can be used.
Also included in the processing device 602-1 is network interface circuitry 614, which is used to interface the processing device with the network 604 and other system components and may comprise conventional transceivers.
The other processing devices 602 of the processing platform 600 are assumed to be configured in a manner similar to that shown for processing device 602-1 in the figure.
Again, the particular processing platform 600 shown in the figure is presented by way of example only, and system 100 may include additional or alternative processing platforms, as well as numerous distinct processing platforms in any combination, with each such platform comprising one or more computers, servers, storage devices or other processing devices.
For example, other processing platforms used to implement illustrative embodiments can comprise converged infrastructure such as VxRail™, VxRack™, VxRack™ FLEX, VxBlock™, or Vblock® converged infrastructure from VCE, the Virtual Computing Environment Company, now the Converged Platform and Solutions Division of Dell EMC.
It should therefore be understood that in other embodiments different arrangements of additional or alternative elements may be used. At least a subset of these elements may be collectively implemented on a common processing platform, or each such element may be implemented on a separate processing platform.
As indicated previously, components of an information processing system as disclosed herein can be implemented at least in part in the form of one or more software programs stored in memory and executed by a processor of a processing device. For example, at least portions of the flow control functionality of one or more components of a storage system as disclosed herein are illustratively implemented in the form of software running on one or more processing devices.
It should again be emphasized that the above-described embodiments are presented for purposes of illustration only. Many variations and other alternative embodiments may be used. For example, the disclosed techniques are applicable to a wide variety of other types of information processing systems, host devices, storage systems, storage nodes, storage devices, storage controllers, replication processes, flow controllers and associated control logic and metadata structures. Also, the particular configurations of system and device elements and associated processing operations illustratively shown in the drawings can be varied in other embodiments. Moreover, the various assumptions made above in the course of describing the illustrative embodiments should also be viewed as exemplary rather than as requirements or limitations of the disclosure. Numerous other alternative embodiments within the scope of the appended claims will be readily apparent to those skilled in the art.
| Number | Name | Date | Kind |
|---|---|---|---|
| 7475124 | Jiang et al. | Jan 2009 | B2 |
| 8327103 | Can et al. | Dec 2012 | B1 |
| 8380928 | Chen et al. | Feb 2013 | B1 |
| 8429346 | Chen et al. | Apr 2013 | B1 |
| 8515911 | Zhou et al. | Aug 2013 | B1 |
| 8539148 | Chen et al. | Sep 2013 | B1 |
| 8566483 | Chen et al. | Oct 2013 | B1 |
| 8583607 | Chen et al. | Nov 2013 | B1 |
| 8683153 | Long et al. | Mar 2014 | B1 |
| 8712976 | Chen et al. | Apr 2014 | B1 |
| 8775388 | Chen et al. | Jul 2014 | B1 |
| 8782324 | Chen et al. | Jul 2014 | B1 |
| 8799601 | Chen et al. | Aug 2014 | B1 |
| 8909887 | Armangau et al. | Dec 2014 | B1 |
| 8930746 | Chen et al. | Jan 2015 | B1 |
| 8954699 | Chen et al. | Feb 2015 | B1 |
| 8977812 | Chen et al. | Mar 2015 | B1 |
| 9104326 | Frank et al. | Aug 2015 | B2 |
| 9152336 | Chen et al. | Oct 2015 | B1 |
| 9208162 | Hallak et al. | Dec 2015 | B1 |
| 9286003 | Hallak et al. | Mar 2016 | B1 |
| 9304889 | Chen et al. | Apr 2016 | B1 |
| 9317435 | Bairavasundaram | Apr 2016 | B1 |
| 9355112 | Armangau et al. | May 2016 | B1 |
| 9384206 | Bono et al. | Jul 2016 | B1 |
| 9395937 | Si et al. | Jul 2016 | B1 |
| 9449011 | Chen et al. | Sep 2016 | B1 |
| 9459809 | Chen et al. | Oct 2016 | B1 |
| 9460102 | Bono et al. | Oct 2016 | B1 |
| 9477431 | Chen et al. | Oct 2016 | B1 |
| 9513814 | Can et al. | Dec 2016 | B1 |
| 9529545 | Bono et al. | Dec 2016 | B1 |
| 9542125 | Chen | Jan 2017 | B1 |
| 9594514 | Bono et al. | Mar 2017 | B1 |
| 9684593 | Chen et al. | Jun 2017 | B1 |
| 9710187 | Si et al. | Jul 2017 | B1 |
| 9811288 | Chen et al. | Nov 2017 | B1 |
| 9817766 | Si et al. | Nov 2017 | B1 |
| 10037369 | Bono et al. | Jul 2018 | B1 |
| 10048874 | Shveidel et al. | Aug 2018 | B1 |
| 10082959 | Chen et al. | Sep 2018 | B1 |
| 10095428 | Meiri et al. | Oct 2018 | B1 |
| 10152381 | Shvaiger et al. | Dec 2018 | B1 |
| 10176046 | Hu et al. | Jan 2019 | B1 |
| 10235066 | Chen et al. | Mar 2019 | B1 |
| 10248623 | Chen et al. | Apr 2019 | B1 |
| 10261853 | Chen et al. | Apr 2019 | B1 |
| 10310951 | Chen et al. | Jun 2019 | B1 |
| 10324640 | Chen et al. | Jun 2019 | B1 |
| 10338851 | Kronrod et al. | Jul 2019 | B1 |
| 10353616 | Tao et al. | Jul 2019 | B1 |
| 10359968 | Chen et al. | Jul 2019 | B1 |
| 10374792 | Meiri et al. | Aug 2019 | B1 |
| 10394485 | Chen et al. | Aug 2019 | B1 |
| 10402283 | Chen et al. | Sep 2019 | B1 |
| 10409493 | Kucherov et al. | Sep 2019 | B1 |
| 10459632 | Chen et al. | Oct 2019 | B1 |
| 10459883 | Meiri et al. | Oct 2019 | B1 |
| 10496489 | Chen et al. | Dec 2019 | B1 |
| 10496668 | Meiri et al. | Dec 2019 | B1 |
| 10496672 | Meiri et al. | Dec 2019 | B2 |
| 10565058 | Meiri et al. | Feb 2020 | B1 |
| 20130204960 | Ashok | Aug 2013 | A1 |
| 20130205005 | Ashok et al. | Aug 2013 | A1 |
| 20140304437 | Ashok et al. | Oct 2014 | A1 |
| 20150089008 | Sridharan | Mar 2015 | A1 |
| 20160291876 | Alatorre | Oct 2016 | A1 |
| 20160291892 | Rao | Oct 2016 | A1 |
| 20170156161 | Kang et al. | Jun 2017 | A1 |
| 20170242596 | Liu | Aug 2017 | A1 |
| 20170371558 | George et al. | Dec 2017 | A1 |
| 20180011801 | Sengupta | Jan 2018 | A1 |
| 20190121558 | Lee et al. | Apr 2019 | A1 |
| 20190332443 | Kelly | Oct 2019 | A1 |
| 20190372866 | Ganguli | Dec 2019 | A1 |
| 20200034058 | Shveidel | Jan 2020 | A1 |
| 20200125291 | Shveidel | Apr 2020 | A1 |
| 20200274823 | Yang | Aug 2020 | A1 |
| Entry |
|---|
| U.S. Appl. No. 15/499,943, filed Apr. 28, 2017, Kucherov et al. |
| U.S. Appl. No. 15/499,949, filed Apr. 28, 2017, Chen et al. |
| U.S. Appl. No. 15/499,951, filed Apr. 28, 2017, Chen et al. |
| U.S. Appl. No. 15/656,168, filed Jul. 21, 2017, Hu et al. |
| U.S. Appl. No. 15/656,170, filed Jul. 21, 2017, Chen et al. |
| U.S. Appl. No. 15/797,324, filed Oct. 30, 2017, Chen et al. |
| U.S. Appl. No. 16/042,363, filed Jul. 23, 2018, Chen et al. |
| U.S. Appl. No. 16/038,543, filed Jul. 18, 2018, Chen et al. |
| U.S. Appl. No. 16/048,767, filed Jul. 30, 2018, Chen et al. |
| U.S. Appl. No. 16/169,202, filed Oct. 24, 2018, Chen et al. |
| U.S. Appl. No. 16/177,782, filed Nov. 1, 2018, Hu et al. |
| U.S. Appl. No. 16/167,858, filed Oct. 23, 2018, Chen et al. |
| U.S. Appl. No. 16/175,979, filed Oct. 31, 2018, Hu et al. |
| U.S. Appl. No. 16/157,528, filed Oct. 11, 2018, Chen et al. |
| U.S. Appl. No. 16/162,786, filed Oct. 17, 2018, Hu et al. |
| U.S. Appl. No. 16/164,005, filed Oct. 18, 2018, Chen et al. |
| U.S. Appl. No. 16/264,825, filed Feb. 1, 2019, Chen et al. |
| U.S. Appl. No. 16/254,899, filed Jan. 23, 2019, Chen et al. |
| U.S. Appl. No. 16/254,897, filed Jan. 23, 2019, Chen et al. |
| U.S. Appl. No. 16/264,982, filed Feb. 1, 2019, Chen et al. |
| U.S. Appl. No. 16/263,414, filed Jan. 31, 2019, Meiri et al. |
| U.S. Appl. No. 16/375,001, filed Apr. 4, 2019, Chen et al. |
| U.S. Appl. No. 16/380,087, filed Apr. 10, 2019, Kronrod et al. |
| U.S. Appl. No. 16/592,271, filed Oct. 3, 2019, Chen et al. |
| U.S. Appl. No. 16/592,328, filed Oct. 3, 2019, Barabash et al. |
| U.S. Appl. No. 16/667,453, filed Oct. 29, 2019, Chen et al. |
| U.S. Appl. No. 16/668,661, filed Oct. 30, 2019, Kronrod et al. |
| U.S. Appl. No. 16/743,274, filed Jan. 15, 2020, Chen et al. |
| U.S. Appl. No. 16/747,169, filed Jan. 20, 2020, Chen et al. |
| U.S. Appl. No. 16/786,422, filed Feb. 10, 2020, Kronrod et al. |
| U.S. Appl. No. 16/788,461, filed Feb. 12, 2020, Chen et al. |
| U.S. Appl. No. 16/773,303, filed Jan. 27, 2020, Hu et al. |
| U.S. Appl. No. 16/511,676, filed Jul. 15, 2019, Chen et al. |
| Notice of Allowance dated May 18, 2021 for U.S. Appl. No. 16/786,422; 19 pages. |
