Enabling Intra-Plane Parallel Block Erase to Alleviate the Impact of Garbage Collection

[摘要] Garbage collection (GC) in NAND flash can significantly decrease I/O performance in SSDs bycopying valid data to other locations, thus blocking incoming I/O requests. To help improveperformance, NAND flash utilizes various advanced commands to increase internal parallelism.Currently, these commands only parallelize operations across channels, chips, dies, and planes,neglecting the block-level and below due structural bottlenecks along the data path and risk ofdisturbances that can compromise valid data by inducing errors. However, due to the triple-wellstructure of the NAND flash plane architecture and erasing procedure, it is possible to erasemultiple blocks within a plane, in parallel, without being restricted by structural limitations ordiminishing the integrity of the valid data. The number of page movements due to multiple blockerases can be restrained so as to bound the overhead per GC. Moreover, more capacity can bereclaimed per GC which delays future GCs and effectively reduces their frequency. Such anIntra-Plane Parallel Block Erase (IPPBE) in turn diminishes the impact of GC on incomingrequests, improving their response times. Experimental results show that IPPBE can reduce thetime spent performing GC by up to 50.7% and 33.6% on average, read/write response time by upto 47.0%/45.4% and 16.5%/14.8% on average respectively, page movements by up to 52.2% and26.6% on average, and blocks erased by up to 14.2% and 3.6% on average. An energy analysisconducted indicates that by reducing the number of page copies and the number of block erases,the energy cost of garbage collection can be reduced up to 44.1% and 19.3% on average.

[发布机构] the University of Pittsburgh