[RFC,0/5] scsi: target: XCOPY performance

Message

David Disseldorp March 23, 2020, 4:54 p.m. UTC

These changes remove unnecessary heap allocations in the XCOPY
READ/WRITE dispatch loop.

Synthetic benchmarks on my laptop using the libiscsi iscsi-dd utility
(--xcopy --max 1 --blocks 65535 src=dst) against a target backed by an 8G
zram (DEBUG_KMEMLEAK=y) iblock backstore (avg across four runs) show:
before: 5.35776G/s
after:  6.12636G/s (approx. +14%)

Feedback appreciated.

Cheers, David

----------------------------------------------------------------
David Disseldorp (5):
      scsi: target: use #def for xcopy descriptor len
      scsi: target: drop xcopy DISK BLOCK LENGTH debug
      scsi: target: avoid per-loop XCOPY buffer allocations
      scsi: target: increase XCOPY I/O size
      scsi: target: avoid XCOPY per-loop read/write cmd allocations

 drivers/target/target_core_xcopy.c | 135 ++++++++++-------------------
 drivers/target/target_core_xcopy.h |  14 +--
 2 files changed, 57 insertions(+), 92 deletions(-)