Hi Jens, currently blk-mq reorders requests when adding them to the plug because the request list can't do efficient tail appends. When the plug is directly issued using ->queue_rqs that means reordered requests are passed to the driver, which can lead to very bad I/O patterns when not corrected, especially on rotational devices (e.g. NVMe HDD) or when using zone append. This series first adds two easily backportable workarounds to reverse the reording in the virtio_blk and nvme-pci ->queue_rq implementations similar to what the non-queue_rqs path does, and then adds a rq_list type that allows for efficient tail insertions and uses that to fix the reordering for real and then does the same for I/O completions as well. Diffstat: block/blk-core.c | 6 +- block/blk-merge.c | 2 block/blk-mq.c | 42 ++++++++--------- block/blk-mq.h | 2 drivers/block/null_blk/main.c | 9 +-- drivers/block/virtio_blk.c | 53 ++++++++++------------ drivers/nvme/host/apple.c | 2 drivers/nvme/host/pci.c | 46 ++++++++----------- include/linux/blk-mq.h | 99 ++++++++++++++++++++---------------------- include/linux/blkdev.h | 11 +++- io_uring/rw.c | 4 - 11 files changed, 133 insertions(+), 143 deletions(-)
