Enhancing data processing performance by cache management of fingerprint index

• US 9,098,424 B2
• Filed: 03/13/2013
• Issued: 08/04/2015
• Est. Priority Date: 05/07/2012
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Hyde, Joseph S. II, Roy, Subhojit
• Primary Examiner(s): Nguyen, Loan T
• Application Number:
  US13/801,472
• Publication Number:
  US 20130297884A1
• Time in Patent Office: 874 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 12/0833 in combination with broadcast means (e.g. for invalidation or updating)
• CPC Class Codes: G06F 12/0891 using clearing, invalidating or resetting means
• CPC Class Codes: G06F 12/122 of the least frequently used [LFU] type, e.g. with individual count value
• CPC Class Codes: G06F 12/128 adapted to multidimensional cache systems, e.g. set-associative, multicache, multiset or multilevel
• CPC Class Codes: G06F 16/10 File systems; File servers
• CPC Class Codes: G06F 16/13 File access structures, e.g. distributed indices arrangements of input from, or output to, record carriers G06F3/06
• CPC Class Codes: G06F 16/137 Hash-based content-based indexing of textual data G06F16/31
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/24556 Aggregation; Duplicate elimination
• CPC Class Codes: G06F 2212/62 Details of cache specific to multiprocessor cache arrangements

Abstract

Various embodiments for improving hash index key lookup caching performance in a computing environment are provided. In one embodiment, for a cached fingerprint map having a plurality of entries corresponding to a plurality of data fingerprints, reference count information is used to determine a length of time to retain the plurality of entries in cache. Those of the plurality of entries having a higher reference counts are retained longer than those having lower reference counts.

Claims

1. A method for improving hash index key lookup caching performance in a computing environment by a processor, comprising:

for a cached fingerprint map having a plurality of entries corresponding to a plurality of data fingerprints used by a data deduplication system, using reference count information obtained from a data deduplication engine to determine a length of time to retain the plurality of entries of the fingerprint map in cache, by;

examining the reference count information of the plurality of entries of the fingerprint map in the cache and a storage policy related to the plurality of entries to establish a retention duration for the plurality of entries, and

querying whether the reference count information for a data segment has been incremented, the incremented reference count information indicating a frequency of times the data segment has been accessed, or whether a predetermined time interval has expired;

if the reference count information for a data segment has not been incremented or if the predetermined time interval has not expired, reiterating the step of querying;

if the reference count information for a data segment has been incremented or if the predetermined time interval has expired in which no physical activity has been observed on a physical block, re-determining a new appropriate duration of retention in the cache; and

when the cache is full, retaining in the cache the plurality of entries of the fingerprint map having higher reference counts and removing from the cache the plurality of entries of the fingerprint map having lower reference counts.

2. The method of claim 1, further including performing the re-determining for every reference count increment.

3. The method of claim 1, wherein determining the length of time to retain the plurality of entries in cache includes implementing at least one policy corresponding to one of the length of time or at least one of the plurality of entries.

4. The method of claim 1, wherein the determining the length of time to retain the plurality of entries in cache is performed in approximate synchronization with a deduplication operation for those of the plurality of entries retained in the cache.

5. The method of claim 1, further comprising assigning a predetermined weight to the data segment that diminishes over time as physical activity observed on a physical block decreases.