Skip to content

nvme-multipath: round-robin I/O policy

Hannes Reinecke linux-nvme 1 version New

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 Latest2 patches 0 repliesNew

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/2nvme-multipath: add 'iopolicy' subsystem attributedrivers/nvme/host/core.c drivers/nvme/host/multipath.c drivers/nvme/host/nvme.h+54 -12 replies
2/2nvme-multipath: round-robin I/O policydrivers/nvme/host/multipath.c drivers/nvme/host/nvme.h+47 -01 reply
2/2nvme-multipath: round-robin I/O policy+0 -02 replies
2/2nvme-multipath: round-robin I/O policy+0 -00 replies
2/2nvme-multipath: round-robin I/O policy+0 -00 replies

Reviews trailers per patch

No Reviewed-by, Acked-by or Tested-by trailers for v1 yet.

Read the v1 thread

Cover letter [PATCH 0/2] nvme-multipath: round-robin I/O policy

Hi all,

after my NUMA path balancing patch hasn't met with universal approval, here's now my take on a 'real' round-robin I/O scheduler for NVMe multipathing. With this patch I'm able to boost I/O performance from 127k/127k randrw to 156k/156k randrw (as measured by fio).
Testbed was two dual 32G FC HBAs connected back-to-back with nvmet against a 1G zram-backed namespace.

As usual, comments and reviews are welcome.

Hannes Reinecke (2):
nvme-multipath: add 'iopolicy' subsystem attribute
nvme-multipath: round-robin I/O policy

 drivers/nvme/host/core.c      |  6 +++
 drivers/nvme/host/multipath.c | 88 ++++++++++++++++++++++++++++++++++++++++++-
 drivers/nvme/host/nvme.h      |  8 ++++
 3 files changed, 101 insertions(+), 1 deletion(-)
Signature · 1 line
2.16.4

Read the cover letter in its thread