Commit a78b7bb1 authored by Seth Howell's avatar Seth Howell Committed by Darek Stojaczyk
Browse files

test/nvmf: avoid running bdevperf on top of nvmf_tgt 



When you run verify on bdev perf, it rejects any user provided core
masks and pins itself to core 0. We were also running the NVMe-oF target
on cores 0-3. Occasionally I was seeing the shutdown tests failing
during the waitforio step. It seemed like the target and bdevperf were
both still online during this failure, so my hypothesis is that the
bdevperf poller was stealing all of the cycles from the NVMe-oF poller
completing I/O so the I/O wasn't completing.

Even if that's not what's happening, it is probably a good idea to split
the NVMe-oF application and bdevperf onto different cores.

Change-Id: Ib3b5b00e639ebd14bd1ed2cfb4b7782076ca364c
Signed-off-by: default avatarSeth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462551


Reviewed-by: default avatarZiye Yang <ziye.yang@intel.com>
Reviewed-by: default avatarChangpeng Liu <changpeng.liu@intel.com>
Reviewed-by: default avatarDarek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: default avatarDarek Stojaczyk <dariusz.stojaczyk@intel.com>
parent 53c9f435

test/nvmf/target/shutdown.sh

+2 −2
Original line number Diff line number Diff line
@@ -36,7 +36,7 @@ function waitforio() { 


timing_enter shutdown

nvmftestinit

nvmfappstart "-m 0xF"

nvmfappstart "-m 0x1E"



$rpc_py nvmf_create_transport $NVMF_TRANSPORT_OPTS -u 8192
@@ -70,7 +70,7 @@ timing_exit create_subsystems 


timing_enter test1

# Run bdev_svc, which connects but does not issue I/O

$rootdir/test/app/bdev_svc/bdev_svc -i 1 -r /var/tmp/bdevperf.sock -c $testdir/bdevperf.conf &

$rootdir/test/app/bdev_svc/bdev_svc -m 0x1 -i 1 -r /var/tmp/bdevperf.sock -c $testdir/bdevperf.conf &

perfpid=$!

waitforlisten $perfpid /var/tmp/bdevperf.sock

$rpc_py -s /var/tmp/bdevperf.sock wait_subsystem_init