765f4a7363
This test is meant to simulate uncommon network situations where lots of I/O are getting dropped before they get to the initiator. Essentially, we are trying to trigger the initiator timeout in the kernel which disconnects from the target and reconnects after 10 seconds. This test is different from the other tests that we have currently because it doesn't rely on killing either the target or initiator. Instead it expects the target to stay up and properly respond to the initiator error conditions. The hope is that the fio job running on the initiator can still complete successfully and the target doesn't crash due to improperly handling the disconnect and reconnect. This test should be added to the nightly CI jobs because it is rather time consuming. Change-Id: Id457d9eb21a980140f065663547b89b2c69ace93 Signed-off-by: Seth Howell <seth.howell@intel.com> Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464459 Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Jim Harris <james.r.harris@intel.com> Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com> Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com> |
||
|---|---|---|
| .. | ||
| host | ||
| target | ||
| common.sh | ||
| nvmf.sh | ||
| README.md | ||
| test_plan.md | ||
NVMe-oF test scripts
The test scripts in this directory hierarchy can be run in isolation by passing the --iso flag when running the test script. This will set up the RDMA NIC for testing and then tear it back down again when the test is completed.