[v3,0/2] improve quiesce time for large amount of namespaces

Message

Sagi Grimberg July 26, 2020, 12:22 a.m. UTC

This set attempts to improve the quiesce time when using a large set of
namespaces, which also improves I/O failover time in a multipath environment.

We improve for both non-blocking hctxs (e.g. pci, fc, rdma) and blocking
hctxs (e.g. tcp) by splitting queue auiesce to async call_(s)rcu and
async_wait to wait for it to complete.

Changes from v2:
- made blk_mq_quiesce_queue_async operate on both blocking and
  non-blocking hctxs.
- removed separation between blocking vs. non-blocking queues
- dropeed patch from Chao
- dropped nvme-rdma test patch

Changes from v1:
- trivial typo fixes

Sagi Grimberg (2):
  blk-mq: add async quiesce interface
  nvme: improve quiesce time for large amount of namespaces

 block/blk-mq.c           | 32 ++++++++++++++++++++++++++++++++
 drivers/nvme/host/core.c |  4 +++-
 include/linux/blk-mq.h   |  4 ++++
 3 files changed, 39 insertions(+), 1 deletion(-)