Vast Data Ltd.

Alon Berger

Yogev Vaknin

Lior Klipper

Eli Malul

Niko Farhi

Itay Khazon

Or Yahalom

A method for compressing an evaluated chunk (EC), the method includes (i) selecting a compressing scheme (SC) of a set of candidate SCs to provide a selected SC; and (ii) compressing the EC using the selected SC to provide a compressed EC. A similar chunk that is similar to the EC is tied to a reference chunk (RC) by having the similar chunk compressed based on the RC. The selecting includes evaluating candidate SCs of the set. The selecting is responsive to a first relationship between (i) a similarity score indicative of a similarity between the EV chunk and the similar chunk, and (ii) a similarity score indicative of a similarity between the similar chunk and the RC. A first candidate SC of the set includes untying the similar chunk from the RC, and tying the EV to the similar chunk. A second candidate SC of the set includes self-compressing the EV without tying the EV to the similar chunk.

Similarity based compression

A method for storage system data aware compression, the method may include pre-compressing data units received by the storage system, by different pre-compression units to provide different pre-compressed versions of the data units; wherein the different pre-compression schemes are associated with different compression schemes, wherein at least some of the different compression schemes are data type specific compression schemes; calculating entropies of the different pre-compressed versions; and selecting a compression scheme out of the different compression schemes based on the entropies of the different pre-compressed versions.

Data aware compression in a storage system

A method for selectively untying at least one of compression related links to a stale reference chunk, the method may include determining whether a compression effectiveness condition is fulfilled in relation to a set of referring chunks that are compressed using the stale reference chunk and are linked to the to the stale reference chunk by the compression related links; wherein the compression effectiveness condition is responsive to, at least, a number of the referring chunks of the set; and untying the at least one compression related links to the stale reference chunks when the compression effectiveness condition is not fulfilled.

Untying compression related links to stale reference chunks

A method for recovering failed chunks, the method may include (i) obtaining a failure indication about a failure of a first number (X1) of failed chunks; wherein the chunks were stored in a group of disks, the group of disks is configured to store a second number (&#x3b1;) stripes of multiple (N) chunks, wherein each stripe comprises a first plurality (K) of data chunks and a second plurality (R) of parity chunks; wherein R exceeds and (ii) performing at least one recovery iteration until fulfilling a stop condition. Each recovery iteration of the at least one recovery iteration may include (a.i) selecting valid chunks to provide selected valid chunks, wherein a number of selected chunks is smaller than a product of a multiplication of R by &#x3b1;; (a.ii) retrieving valid data chunks that are relevant to the selected valid chunks; and (a.iii) attempting to reconstruct the failed chunks based on the retrieved chunks.

Growing community of inventors

Tel Aviv, Israel

Alon Berger