Lines Matching refs:deduplication
7 The dm-vdo (virtual data optimizer) target provides inline deduplication,
16 Because deduplication rates fall drastically as the block size increases, a
18 deduplication rates of 254:1, i.e. up to 254 copies of a given 4K block can
25 The design of dm-vdo is based on the idea that deduplication is a two-part
28 parts: a deduplication index (called UDS) that is used to discover
39 block sizes in order to achieve good deduplication rates, acceptable
78 ultimate goal of deduplication is to reduce storage costs. Since there is a
166 called the deduplication window. If new writes duplicate data that is older
171 result in no deduplication, because the beginning of the file will no
176 deduplication beyond the 256GB threshold, vdo can be configured to use a
177 larger index with a correspondingly larger deduplication window. (This
184 double the length of the deduplication window at the expense of doubling
188 the deduplication window by a factor of 10, at the expense of also
192 of deduplication detected. For most workloads with significant amounts of
193 duplicate data, sparse indexing will detect 97-99% of the deduplication
204 related to deduplication or compression.
210 related to deduplication and other vdo features. The data_vio is the
348 same logical address, because deduplication involves sharing blocks.
400 data_vio can write its data somewhere even if deduplication and
457 a. The agent initializes and sends its embedded deduplication request
458 (struct uds_request) to the deduplication index. This does not
463 b. If the deduplication index returns advice, the data_vio attempts to
469 address for deduplication.
530 the deduplication index is updated to reflect the location of the