Patent Application
20160154605
The present invention relates generally to computers, and more particularly, to mechanisms for migrating data segments in a computing storage environment.
In today's society, computer systems are commonplace. Computer systems may be In the field of computing, a “cache” typically refers to a small, fast memory or storage device used to store data or instructions that were accessed recently, are accessed frequently, or are likely to be accessed in the future. Reading from or writing to a cache is typically cheaper (in terms of access time and/or resource utilization) than accessing other memory or storage devices. Once data is stored in cache, it can be accessed in cache instead of re-fetching and/or re-computing the data, saving both time and resources.
Caches may be provided as multi-level caches. For example, a caching system may include both a “primary” and “secondary” cache. When reading data, a computing system or device may first look for data in the primary cache and, if the data is absent, look for the data in the secondary cache. If the data is not in either cache, the computing system or device may retrieve the data from disk drives or other storage devices. When writing data, a computing system or device may write data to the primary cache. This data may eventually be destaged to the secondary cache or a storage device to make room in the primary cache.
Storage environments in computer systems may include so-called tiered storage architectures, which may include a variety of storage mediums such as as enterprise hard disk drives (HDD), serial advanced technology attachment (SATA) disk drives, solid state drives (SSD), tape drives, and other devices. Data may be migrated between such devices. Placement of certain kinds of data in the appropriate medium may greatly enhance overall performance of the storage environment.
In an existing tiered migration mechanism, data is read from a source location and destaged to a target. During this step, data can still be destaged to the source, which if occurs is recorded in a bitmap. In a subsequent step, any new destages are withheld to the source while tracks are read that were previously destaged to the source and destaged to the target. This mechanism results in additional time being expended while new destages are withheld, and while the previously destaged tracks are re-read and destaged from the source to the target. A need exists for a mechanism that effectively reduces this additional time, among other factors, to increase storage performance.
Accordingly, and in view of the foregoing, various exemplary method, system, and computer program product embodiments for data processing in a computing storage environment by a processor device, the computing storage environment incorporating at least high-speed and lower-speed caches, and tiered levels of storage, are provided. At a time in which at least one data segment is to be migrated from one level to another level of the tiered levels of storage, a data migration mechanism is initiated by copying data resident in the lower-speed cache corresponding to the at least one data segment to be migrated to a target on the another level, reading remaining data, not previously copied from the lower-speed cache, from a source on the one level, and writing the remaining data to the target, and subsequent to the reading and the writing of the remaining data, destaging updates corresponding to the at least one data segment from either the higher and lower speed caches to the target. In addition to the foregoing exemplary embodiment, various other system and computer program product embodiments are provided and supply related advantages.
The foregoing summary has been provided to introduce a selection of concepts in a simplified form that are further described below 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 as an aid in determining the scope of the claimed subject matter. The claimed subject matter is not limited to implementations that solve any or all disadvantages noted in the background.
In order that the advantages of the invention will be readily understood, a more particular description of the invention briefly described above will be rendered by reference to specific embodiments that are illustrated in the appended drawings. Understanding that these drawings depict embodiments of the invention and are not therefore to be considered to be limiting of its scope, the invention will be described and explained with additional specificity and detail through the use of the accompanying drawings, in which:
As previously mentioned, in an existing tiered migration mechanism, data is read from a source location and destaged to a target. During this step, data can still be destaged to the source, which if occurs is recorded in a bitmap. In a subsequent step, any new destages are withheld to the source while tracks are read that were previously destaged to the source and destaged to the target. This mechanism results in additional time being expended while new destages are withheld. Any new writes from the host to these data segments will need to wait for the destages to finish, which may take a significant amount of time, since it may take such time to copy data from a source to target location (e.g., while the previously destaged tracks are re-read and destaged from the source to the target). In addition, this current mechanism does not examine data in cache when migration operations are performed. Such mechanism starts at a beginning of a data segment (e.g., an extent) and proceeds to the end in order. If tracks are being maintained in cache, alternatively, these tracks may be copied first, before the tracks get aged out of cache.
In view of this scenario, the mechanisms of the present invention utilize primary and secondary cache architectures to allow for more direct involvement of such caches in the data migration process. As a result, for example, destages (i.e., resources in the computing storage environment) are not held while other storage operations (such as the aforementioned reads and writes of the data being migrated) occur. For example, destage conflicts which may occur during data segment migration operations are in progress may be significantly reduced. Accordingly, overall storage performance and efficiencies are enhanced as will be further described.
For the purposes of this disclosure, the phrase “secondary cache” is used to refer to any cache (including, for example, L2 or L3 cache) that resides between a primary cache and a storage device, such as a disk drive, tape drive, or the like.
Turning now to
In some embodiments, a storage manager 106, such as, the Tivoli® Storage Manager® (TSM) product marketed by International Business Machines (IBM®) Corporation, may be used for securely storing and managing data segments according to aspects of the present invention. The storage manager 106 may execute in a storage management server, such as a TSM server 102 or elsewhere. In one embodiment, the storage manager is operable by and/or in conjunction with processor device 105 as shown. One of ordinary skill in the art will appreciate that various other configurations of the processor 105, storage manager 106, and related additional processing and/or memory components are contemplated. IBM, Tivoli, and Tivoli Storage Manager are trademarks or registered trademarks of IBM Corporation.
The TSM may provide data storage services to clients, such as TSM clients 104a, for management of data. The TSM server 102 may store files sent to the TSM server 102 by one or more TSM clients 104a, 104b. The storage manager 106 and/or processor device 105 may allow a system administrator to configure storage pools, where a storage pool comprises a group of devices used for storing data received from the TSM clients 104a, 104b. Storage pools are used as targets for store operations from the TSM clients 104a, 104b, and are referenced in TSM server policies and other constructs for processing.
As shown, a variety of storage devices may be organized into a storage hierarchy. Storage media within the storage hierarchy may thus be grouped into data structures referred to herein as storage pools. The storage hierarchy may be organized to correspond with one or more metrics, such as a performance metric including write or read speeds. The storage hierarchy 108 as shown may be organized such that the top of the hierarchy may include a cache pool 110 having a highest amount or quality of a particular performance metric. Below the cache pool 110, a number of solid state drive (SSD) class devices may be organized into SSD pools by the same, similar, or other metrics (e.g., SSD pools 112 and 114).
Below the SSD pools 112 and 114, a first tier of disk pools (e.g., disk pools 116, 118, and 120) may be then organized. As one of ordinary skill in the art will appreciate, disk pools 116, 118, and 120 may include a variety of disk devices such as pools of enterprise disk drives, SATA disk drives, disk devices configured in a particular redundant array of independent disks (RAID) configuration, and the like.
The first tier of disk pools may be located above a second tier of disk pools (e.g., pools 122, 124, and 126) by virtue of exhibiting a greater amount, stronger attribute or attributes, or quality of the performance metric. Below the second tier of disk pools, an additional tier of tape pools (e.g., tape pools 128, 130, and 132) may then be organized. Various considerations for the organization of such storage hierarchies 108 may be apparent to one of ordinary skill in the art. In one embodiment, the system administrator may assist in performing such configurations in the storage hierarchy 108 by inputs to the TSM administrative client 104b or another mechanism. While tape pools 128, 130, and 132 are shown within the storage hierarchy 108 as shown, it should be noted that generally such tape pools are found in a storage subsystem external to those pools ranking higher in the hierarchy.
Referring to
In selected embodiments, the storage controller 200 includes one or more servers 206. The storage controller 200 may also include host adapters 208 and device adapters 210 to connect the storage controller 200 to host devices 106 and storage devices 203, 204, respectively. Multiple servers 206a, 206b may provide redundancy to ensure that data is always available to connected hosts 106. Thus, when one server 206a fails, the other server 206b may remain functional to ensure that I/O is able to continue between the clients 104 and the storage devices 204. This process may be referred to as a “failover.”
One example of a storage system 102 having an architecture similar to that illustrated in
In selected embodiments, each server 206 may include one or more processors 212 (e.g., n-way symmetric multiprocessors) and memory 214. The memory 214 may include volatile memory (e.g., RAM) as well as non-volatile memory (e.g., ROM, EPROM, EEPROM, hard disks, flash memory, etc.). The volatile memory and non-volatile memory may, in certain embodiments, store software modules that run on the processor(s) 212 and are used to access data in the storage devices 204. The servers 206 may host at least one instance of these software modules. These software modules may manage all read and write requests to logical volumes in the storage devices 204.
In selected embodiments, the memory 214 may include a cache 218. Whenever a client 104 (e.g., an open system or mainframe server 104) performs a read operation, the server 206 that performs the read may fetch data from the storages devices 204 and save it in its cache 218 in the event it is required again. If the data is requested again by a client 104, the server 206 may fetch the data from the cache 218 instead of fetching it from the storage devices 204, saving both time and resources. Similarly, when a client 104 performs a write, the server 106 that receives the write request may store the write in its cache 218, and destage the write to the storage devices 204 at a later time. When a write is stored in cache 218, the write may also be stored in non-volatile storage (NVS) 220 of the opposite server 206 so that the write can be recovered by the opposite server 206 in the event the first server 206 fails.
Referring to
Using the secondary cache 300, if a read request is received by a server 206 (e.g.,
In certain embodiments, the secondary cache 300 may be sized to provide about one to twenty percent, or in other embodiments about five percent of the total storage capacity of the storage system 102. Thus, for a storage system 102 that contains about ten terabytes (TB) of storage (from both hard disk drives 204 and solid state drives 204), about 0.5 TB of this storage space may be used as a secondary, “Flash” cache 300. Such a large amount of secondary cache 300 may allow data to be destaged from the secondary cache 300 far less frequently than conventional primary or secondary caches. As an example, a very large secondary cache 300 could store writes for an entire day without having to destage the writes to the disk drives 204. The writes could then be destaged at night or during a period of relative inactivity. Cache management algorithms may be redesigned to efficiently utilize the additional space in the secondary cache 300 and take advantage of the performance improvements that are possible using a large secondary cache 300.
As shown in
In addition, each track in the secondary cache 300 may have a secondary stride control block (SSCB) associated therewith. The SSCB, like the STCB may include diagnostic and/or statistical information, but instead relating to strides (groups of tracks) stored in the secondary cache 300. The SSCB may also be referred to herein as Cache Flash Element (CFE). In certain embodiments, the SSCBs for all the strides may be stored in an SSCB table 308 stored in the secondary cache 300 as shown, or elsewhere.
Similarly, the primary cache 218 may also store metadata 304a associated with the secondary cache 300. For example, the primary cache 218 may store a secondary cache index table (SCIT) 308 that provides a directory for tracks in the secondary cache 300. In certain embodiments, the SCIT 308 is essentially a hash table with a constant hash function. To locate a specific track in the SCIT 308, the hash function may convert a track identifier (e.g., a track number) to a hash value. This hash value may then be looked up in the SCIT 308 to find the STCB for the track. Alternatively, the SCIT 308 could be incorporated into a cache directory of the primary cache 218, thereby providing a single hash table that stores tracks for both the primary and secondary caches 218, 300. In selected embodiments, the SCIT 308 is kept exclusively in the primary cache 218. The SCIT 308 may be built or rebuilt (in the event of a failover, failback, or initial microcode load (IML)) by reading the STCB table 306 in the secondary cache 300.
In certain embodiments, the primary cache 218 may also store a list of free tracks (LOFT) 310 that indicates which tracks in the secondary cache 300 are free (i.e., unoccupied). This list 310 may be used to locate free space in the secondary cache 300 in order to destage data from the primary cache 218 to the secondary cache 300. In selected embodiments, inserting or removing tracks from the LOFT 310 may be performed in a log structured manner. For example, tracks may be inserted at the end of the LOFT 310 and deleted from the front of the LOFT 310. The LOFT 310 may be kept exclusively in the primary cache 218 and may be built or rebuilt by reading the STCB table 306 in the secondary cache 300.
The primary cache 218 may also store a sorted tree of tracks (STOT) 312 that sorts the tracks by “trackid” or some other indicator. The STOT 312 may be used to minimize seek time (on the disk drives 204) when destaging tracks from the secondary cache 300 to the disk drives 204. The STOT 312 may be kept exclusively in the primary cache 218 and may be built or rebuilt by reading the STCB table 306 in the secondary cache 300.
The primary cache 218 may also store statistics per stride (STATS) 314 for each stride having one or more tracks in the secondary cache 300. A “stride’ refers to a set of logically sequential data that might be segmented across multiple disks combined with additional parity information as is for example used in a RAID-5 (redundant array of inexpensive disks) configuration. In general, the STATS 314 may be used to determine which tracks require the least number of disk operations (“disk ops”) to destage from the secondary cache 300 to the disk drives 204. In general, the destage penalty for a track will be less where more tracks are present in a stride. When selecting tracks to destage, tracks requiring the least number of disk ops may be destaged first to minimize resource utilization. In selected embodiments, the STATS 314 may store information such as the number of tracks that are present in the secondary cache 300 for each stride, and the number of disk ops required to destage a track in a stride. In certain embodiments, the STATS 314 may store a “recency” bit for each stride. The recency bit may be incremented each time an eviction process passes through a stride. The recency bit may be reset each time a track is added to a stride. The recency bit may be used to keep strides in the secondary cache 300 that are actively being written to. The STATS 314 may be kept exclusively in the primary cache 218 and may be built or rebuilt by reading the STCB table 306 in the secondary cache 300.
The metadata 304a, 304b described above may be structured and stored in various different ways and is not limited to the illustrated structure or organization. The metadata 304a, 304b is provided by way of example to show one technique for storing and structuring the metadata 304a, 304b. For example, in certain embodiments, the data and metadata may be stored together in the secondary cache 300 in a circular log-structured array. Other methods for structuring and storing metadata 304a. 304b may be used and are encompassed within the scope of the invention.
As previously mentioned, one advantage of a large secondary cache 300 is that data can be destaged from the secondary cache 300 far less frequently than conventional secondary caches. This may enable more data to accumulate in the secondary cache 300 before it is destaged to the disk drives 204. Accordingly, in selected embodiments, an apparatus and method in accordance with the invention may be configured to wait for full strides of data to accumulate and coalesce in the secondary cache 300 before the data is destaged to the disk drives 204. As explained above, this may minimize the number of disk ops required to destage data from the secondary cache 300 to the disk drives 204, thereby improving overall system performance.
Referring to
To avoid destage conflicts that may result in a DRAM demote to Flash Cache if a data segment (e.g., stride) is being destaged in progress, an out of order migration operation (similar to a RAID rebuild) for Read Miss, and Write (Flash Cache) may be incorporated. Accordingly, in step 404, data resident in the lower-speed (Flash Cache) is copied to the target, and in step 406, the remaining data, not previously copied, is read from the source and copied to the target (step 408). The method 400 then ends (step 408).
The data migration mechanism implemented using Flash Cache may be further adapted for implementing a preference of data movement of the partial data segments to the lower speed cache (again, e.g., Flash Cache) based on several metrics. Two possible such metrics are the amount of holes and data “hotness,” or a data heat metric. One objective of the preference of data movement previously described is to free up more space in the higher speed cache with a subsequent destage operation (more data being destaged) and coalesce into a single write to the secondary, lower speed cache.
In a subsequent step, a second pass is completed. In this pass, the tiered storage system copies that data which has not been copied in the first pass (step 510). The source file is read and then the target file is written to. In this pass, if it is determined that data must be destaged from DRAM cache (higher-speed) to make space for new writes (step 512), then the data segments are destaged to Flash Cache (lower-speed) (step 514). This significantly reduces the destage conflicts since destages are not held off for the entire pass.
Once the second pass is complete, the logical extent is switched to point to the new physical extent (or whichever data segment is undergoing migration) (step 516), and the method 500 ends (step 518).
In some cases, for example if the Flash Cache is currently full of modified data, or otherwise inaccessible, it may not be possible at a particular point in time to destage to Flash Cache. In this case, the tiered storage system may switch to an alternative method of destaging in which Flash Cache is not implemented (and destages are held, for example, until data is migrated).
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or computer program product. Accordingly, aspects of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects that may all generally be referred to herein as a “circuit,” “module” or “system.” Furthermore, aspects of the present invention may take the form of a computer program product embodied in one or more computer readable medium(s) having computer readable program code embodied thereon.
Any combination of one or more computer readable medium(s) may be utilized. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that may contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing. Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages, such as the “C” programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider).
Aspects of the present invention are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, may be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer readable medium that may direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the computer readable medium produce an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks. The computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagram in the above figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block might occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, may be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
While one or more embodiments of the present invention have been illustrated in detail, one of ordinary skill in the art will appreciate that modifications and adaptations to those embodiments may be made without departing from the scope of the present invention as set forth in the following claims.
This application is a Continuation of U.S. patent application Ser. No. 14/066,147, filed on Oct. 29, 2013, which is a Continuation of U.S. patent application Ser. No. 13/746,973, now U.S. Pat. No. 9,032,153, filed on Jan. 22, 2013.
| Number | Date | Country | |
|---|---|---|---|
| Parent | 14066147 | Oct 2013 | US |
| Child | 15015294 | US | |
| Parent | 13746973 | Jan 2013 | US |
| Child | 14066147 | US |
