• Jeff Moyer's avatar
    aio: implement request batching · cfb1e33e
    Jeff Moyer authored
    Some workloads issue batches of small I/O, and the performance is poor
    due to the call to blk_run_address_space for every single iocb.  Nathan
    Roberts pointed this out, and suggested that by deferring this call
    until all I/Os in the iocb array are submitted to the block layer, we
    can realize some impressive performance gains (up to 30% for sequential
    4k reads in batches of 16).
    Signed-off-by: default avatarJeff Moyer <jmoyer@redhat.com>
    Signed-off-by: default avatarJens Axboe <jens.axboe@oracle.com>
direct-io.c 34.4 KB