Method for populating a cache index on a deduplicated storage system
US10175894B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 24, 2016 |
| Grant date | Jan 8, 2019 |
| Priority date | — |
| Expiry date | Mar 24, 2036 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06F2212/621
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method, article of manufacture, and apparatus for populating an index cache on a deduplicated storage system is discussed. A determination to flush an in-memory index to a hard drive (“HDD”) on the deduplicated storage system is made, wherein the in-memory index comprises in-memory hash buckets containing fingerprint identifiers and container identifiers. A first HDD index is loaded from the HDD into a memory, wherein the first index includes a plurality of HDD buckets. The fingerprint identifiers and the container identifiers are merged from the in-memory hash buckets into the HDD buckets. The HDD buckets are mapped to a plurality of solid state drive (“SSD”) buckets, the SSD buckets together comprising a SSD index. The fingerprint identifiers and container identifiers are inserted into the plurality of SSD buckets.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.