Shuhei Matsumoto 80e81273e2 bdev/nvme: Do not use ctrlr for I/O submission if reconnect failed repeatedly ... If ctrlr_loss_timeout_sec is set to -1, reconnect is tried repeatedly indefinitely, and I/Os continue to be queued. This patch adds another option fast_io_fail_timeout_sec, a flag fast_io_fail_timedout to nvme_ctrlr. If the time fast_io_fail_timeout_sec passed after starting reset, set fast_io_fail_timedout to true not to use the path for I/O submission. fast_io_fail_timeout_sec is initialized to zero as same as ctrlr_loss_timeout_sec and reconnect_delay_sec. The name of the parameter follows the famous DM-multipath, its fast_io_fail_tmo. Change-Id: Ib870cf8e2fd29300c47f1df69617776f4e67bd8c Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10301 Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Community-CI: Mellanox Build Bot Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com> Reviewed-by: Jim Harris <james.r.harris@intel.com>		2022-01-17 14:25:15 +00:00
..
accel	idxd: Add support for vectored crc32 + copy	2022-01-12 08:20:39 +00:00
bdev	bdev/nvme: Do not use ctrlr for I/O submission if reconnect failed repeatedly	2022-01-17 14:25:15 +00:00
blob	blob: use uint64_t for unmap and write_zeroes lba count	2021-10-14 08:17:16 +00:00
blobfs	blobfs: check return value of strdup in blobfs_fuse_start()	2021-06-16 08:53:21 +00:00
env_dpdk	so_ver: increase all major versions	2021-02-05 14:43:47 +00:00
event	nvmf: remove accept poller from generic layer	2021-12-14 13:18:33 +00:00
scheduler	gscheduler: use current tsc for decision.	2021-12-31 09:21:27 +00:00
sock	sock: Fix SPDK_ZEROCOPY do not work for IPV6	2021-11-30 09:09:03 +00:00
Makefile	scheduler: create public API and subsystem for scheduler/governor	2021-09-07 07:33:03 +00:00