US 8,914,597 B2Granted

Data archiving using data compression of a flash copy

AssigneeInternational Business Machines Corporation

InventorsMichael T. Benhase, Lokesh M. Gupta, Yu-Cheng Hsu, Alfred E. Sanchez

Life of this patent

Estimating the term…

Loading patent…

Abstract

Embodiments of the disclosure relate to archiving data in a storage system. An exemplary embodiment comprises making a flash copy of data in a source volume, compressing data in the flash copy wherein each track of data is compressed into a set of data pages, and storing the compressed data pages in a target volume. Data extents for the target volume may be allocated from a pool of compressed data extents. After each stride worth of data is compressed and stored in the target volume, data may be destaged to avoid destage penalties. Data from the target volume may be decompressed from a flash copy of the target volume in a reverse process to restore each data track, when the archived data is needed. Data may be compressed and uncompressed using a Lempel-Ziv-Welch process.

Claims11

Dependent claims

A computer implemented method for archiving data in a storage system utilizing a RAID-5 configuration, comprising:

making a first flash copy of data in a first storage volume while the first storage volume is off-line, wherein the first flash copy comprises a stride of data including one or more tracks of data and the data includes a previous parity;
compressing the stride of data, wherein the full stride of data is compressed such that each track of data is compressed into a set of compressed data pages;
destaging the compressed full stride of data;
computing a new parity from the compressed full stride of data without using the data and the previous parity;
storing the set of compressed data pages into a second storage volume;
uncompressing archived data in the second storage volume by:
making a second flash copy of data in the second storage volume, wherein the second flash copy includes the sets of compressed data pages and each set of compressed data pages corresponds to a track of uncompressed data pages in the first volume,
uncompressing data in each set of compressed data pages in the second flash copy into the corresponding track of uncompressed data, such that the data being uncompressed is uncompressed as a full stride worth, and
destaging the uncompressed data as the full stride worth and storing the uncompressed data in the first storage volume.

6 more elements

Dependencies are inferred from the claim text.

Facts

Application: 13/830,507Filed 14 Mar 2013 · continuation
Priority: 19 Nov 2010
Published: US 2013/0205109 A18 Aug 2013
Granted: 16 Dec 2014
Term ends: Not estimatedThe source records don’t support an estimate.

Classification4 codes

G06F 3/065
Horizontal data movement in storage systems, i.e. moving data in between storage devices or systems: replication mechanisms
G06F 11/1076
Adding special bits or symbols to the coded information, e.g. parity check, casting out 9's or 11's: parity data used in redundant arrays of…
G06F 2211/1014
Indexing scheme relating to G06F11/1076: compression, i.e. RAID systems with parity using compression techniques
G06F
Computing and data processing

Family

Application12/950,992Parent of this continuation · filed 19 Nov 2010
US 2013/0205109 A1Pre-grant publication · published 8 Aug 2013
US 2012/0131293 A1Published application
US 8,918,607 B2Related patent
US 8,914,597 B2This patent

From the US filing history. Foreign family members aren’t listed.