Hybrid drive caching in a backup system with SSD deletion management

• US 10,019,172 B2
• Filed: 09/30/2016
• Issued: 07/10/2018
• Est. Priority Date: 01/15/2015
• Status: Active Grant

• Current Assignee: CommVault Systems Incorporated
• Original Assignee: CommVault Systems Incorporated
• Inventors: Mitkar, Amit, Erofeev, Andrei
• Primary Examiner(s): Chery, Mardochee
• Application Number:
  US15/282,944
• Publication Number:
  US 20170097770A1
• Time in Patent Office: 648 Days
• Field of Search: 711113
• CPC Class Codes: G06F 12/0871 Allocation or management of cache space
• CPC Class Codes: G06F 12/0873 Mapping of cache memory to specific storage devices or parts thereof
• CPC Class Codes: G06F 2212/1016 Performance improvement
• CPC Class Codes: G06F 2212/1036 Life time enhancement
• CPC Class Codes: G06F 2212/281 Single cache
• CPC Class Codes: G06F 2212/305 being part of a memory device, e.g. cache DRAM
• CPC Class Codes: G06F 3/061 Improving I/O performance
• CPC Class Codes: G06F 3/0616 in relation to life time, e.g. increasing Mean Time Between Failures [MTBF]
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/0653 Monitoring storage devices or systems
• CPC Class Codes: G06F 3/0655 Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
• CPC Class Codes: G06F 3/0656 Data buffering arrangements
• CPC Class Codes: G06F 3/0659 Command handling arrangements, e.g. command buffers, queues, command scheduling
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays

Abstract

Systems and methods can implement one or more intelligent caching algorithms that reduce wear on the SSD and/or to improve caching performance. Such algorithms can improve storage utilization and I/O efficiency by taking into account the write-wearing limitations of the SSD. Accordingly, the systems and methods can cache to the SSD while avoiding writing too frequently to the SSD to increase or attempt to increase the lifespan of the SSD. The systems and methods may, for instance, write data to the SSD once that data has been read from the hard disk or memory multiple times to avoid or attempt to avoid writing data that has been read only once. The systems and methods may also write large chunks of data to the SSD at once instead of a single unit of data at a time. Further, the systems and methods can write to the SSD in a circular fashion.

Claims

1. A data storage system for performing secondary copy operations, the system comprising:

a client computing device residing in a primary storage subsystem and having at least one software application installed thereon, the client computing device associated with and in networked communication with a storage system located in the primary storage subsystem, the storage system comprising a hard disk and a solid-state drive (SSD), the storage system configured to store primary data generated by the software application;

a storage manager implemented in a computing device and configured to instruct the client computing device to perform tasks associated with one or more data backup operations in which the primary data is copied to one or more secondary storage devices residing in a secondary storage subsystem to create one or more secondary copies having a different format than a native format of the primary data;

a storage driver that controls SSD cache operations as part of performing storage operations which are part of the data backup operations, the storage driver implemented in a hardware processor residing within the primary storage subsystem and configured to;

read a first data element from the hard disk;

store a first indication in memory that the first data element is to be cached in the SSD without actually caching the first data element in the SSD;

write the first data element to a buffer maintained in the memory;

read a second data element from the hard disk;

store a second indication in the memory that the second data element is to be cached in the SSD;

write the second data element to the buffer;

subsequent to storage of the second indication in the memory, determine that the buffer has reached capacity; and

in response to determining that the buffer has reached capacity;

determine whether the SSD is at capacity;

in response to determining that the SSD is at capacity, access a data structure in the memory, the data structure including entries corresponding to storage locations on the SSD that store cached data elements, wherein each respective entry in the data structure is usable to locate in the memory first information indicative of how recently accessed was the cached data element stored in the storage location to which the respective entry corresponds;

consult a plurality of entries in the data structure to locate the first information associated with a plurality of the cached data elements, to identify one or more of the plurality of data elements as candidates to discard;

discard one or more of the candidates from the SSD;

subsequent to discarding the one or more candidates, write the first and second data elements from the buffer to the SSD; and

update the data structure in the memory to include entries corresponding to the first and second data elements.

2. The system of claim 1, wherein the first and second indication comprise pointers to the first and second data elements.

3. The system of claim 1, wherein the storage driver is further configured to first cache the first and second data elements in a memory cache prior to caching the first and second data elements in the SSD.

4. The system of claim 3, wherein the storage driver is further configured to cache the first and second data elements in the SSD in response to the memory cache reaching capacity even if the buffer has not reached capacity.

5. The system of claim 1, wherein the storage driver is further configured to evict the first data element from the SSD in response to receiving a write to the first data element.

6. A method of performing data backup operations, comprising:

with a storage manager implemented in a computing device, instructing a client computing device residing in a primary storage subsystem to perform tasks associated with one or more data backup operations in which primary data generated by at least one software application executing on the client computing device is copied to one or more secondary storage devices residing in a secondary storage subsystem to create one or more secondary copies having a different format than a native format of the primary data,

the client computing device associated with and in networked communication with a storage system located in the primary storage subsystem, the storage system comprising a hard disk and a solid-state drive (SSD) operating as a cache for the hard disk, the storage system configured to store primary data generated by the software application;

with a storage driver implemented in a hardware processor and that controls SSD cache operations as part of performing storage operations which are part of the data backup operations;

reading a first data element from the hard disk;

storing a first indication in memory that the first data element is to be cached in the SSD without actually caching the first data element in the SSD;

writing the first data element to a buffer maintained in the memory;

reading a second data element from the hard disk;

storing a second indication in the memory that the second data element is to be cached in the SSD;

writing the second data element to the buffer;

subsequent to storage of the second indication in the memory, determining that the buffer has reached capacity; and

in response to determining that the buffer has reached capacity;

determining whether the SSD is at capacity;

in response to determining that the SSD is at capacity, accessing a data structure in the memory, the data structure including entries corresponding to storage locations on the SSD that store cached data elements, wherein each respective entry in the data structure is usable to locate in the memory information indicative of how recently accessed was the cached data element stored in the storage location to which the respective entry corresponds;

consulting a plurality of entries in the data structure to locate the first information associated with a plurality of the cached data elements, to identify one or more of the plurality of data elements as candidates to discard;

discarding one or more of the candidates from the SSD;

subsequent to said discarding the one or more candidates, writing the first and second data elements from the buffer to the SSD; and

updating the data structure in the memory to include entries corresponding to the first and second data elements.

7. The method of claim 6, wherein the first and second indication comprise pointers to the first and second data elements.

8. The method of claim 6, further comprising first caching the first and second data elements in a memory cache prior to caching the first and second data elements in the SSD.

9. The method of claim 8, further comprising caching the first and second data elements in the SSD in response to the memory cache reaching capacity even if the buffer has not reached capacity.

10. The method of claim 6, further comprising evicting the first data element from the SSD in response to receiving a write to the first data element.