HPE 3PAR数据消重压缩方案.pdf

HPE 3PAR数据消重压缩方案 HPE 3PAR Adaptive Data Reduction The HPE 3PAR StoreServ data reduction story 1 2 3 4 Zero Detect Deduplication Compression Data Packing Remove zeros inline Prevent storing duplicate data Reduce data footprint Pack odd-sized data together When used together, the Adaptive Data Reduction technologies will operate in this order We will go through them in this order as this is the correct way to position them to customers 数据消重Deduplication 3 HPE 3PAR StoreServ deduplication Advanced inline, in-memory deduplication Dedup lookup table Potential duplicates are confirmed with a bit-for-bit check Host writes data to the array The 3PAR ASIC/CPU checks Duplicates are removed, only held in cache pages to to see if the pages are unique data is flushed to the increase write performance duplicates of existing pages SSDs reducing writes The 3PAR ASIC, paired with Express Index lookup tables provides high performance, low-latency inline deduplication 3PAR Thin deduplication Accelerated by the ASIC and Express Indexing 1. Host Write 1 3 2. Write Acknowledge to host 000..110 Write 5a 1 Cach 000..110