Commit Graph

453 Commits

Author SHA1 Message Date
Karol Latecki
226a705d83 test/nvmf: reduce number of loops in rpc.sh test
Running create/delete loop 50 times causes the test to
take over 10 minutes and time out in nightly version.

We have various code analyzer tests in place so running
the same script block over 50 times in hope of detecting
memory leak or some similar defect seems a bit redundant.

Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: Icb2acb0ffbbe63d3004532d0b4a261152891216a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9166
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Pawel Piatek <pawelx.piatek@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-08-20 07:29:25 +00:00
Michal Berger
4f99de088e test/nvmf: Wait for net devices after they are moved from extra netns
Fixes #2072

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: Iab6f1109cb4f3b31b3df62bb9ba678336c8b2502
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9168
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2021-08-13 07:20:50 +00:00
Jim Harris
0c64044400 test: add connect_stress test
This new connect_stress application connects to a
specified subsystem, creates some IO qpairs and
reads the CSTS register.  It goes through this loop
over and over again until the specified time expires.

The connect_stress.sh test script runs this application,
and then while it is running does continuous add_ns and
remove_ns RPCs.

This stresses nvmf handling of connect (admin + I/O) as
well as get_property commands.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8ab5156045cf5614f74988e38a9d37db96d7d5b9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8572
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Michal Berger <michalx.berger@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2021-07-19 13:50:29 +00:00
Michal Berger
742f04b3f7 check_format: Fixes for shellcheck's SC2251 directive
SC2251: This ! is not on a condition and skips errexit.
        Use && exit 1 instead, or make sure $? is checked.

This is critical since our test suites heavily depend on errexit
to catch all abnormal conditions. Replace ! foo ... with a call to
NOT() wherever possible. For the test/ocf pieces, use [[ ]] instead
to define the condition for the existance of the ocf bdev.

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: Ied3f99b9f1dc0594e4aef64fc21e51498f19ac23
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8504
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-06-30 22:43:05 +00:00
Shuhei Matsumoto
3aeeb4b68f test/nvmf_multipath: Retry checking if ANA state is changed with timeout
The latest Linux NVMe host (e.g. Linux kernel 5.12) have improved
the quality of multipath but still has an issue such that ANA state
is observed to be invalid even after connection is successfully
created.

By code inspection and system test, initializing ANA state may be
delayed even after connection is successfully created.

We can insert a short sleep but it will be better to retry checking
with timeout. The created function check_ana_state() is applied to
the remaining cases.

This fixes the part of the issue #1819.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ifc4eaef7c702d961caeee5bcdc9e6eab4704fc5d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8475
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-06-28 16:25:24 +00:00
Changpeng Liu
67cf3e1c0a test/vfio-user: use variables to make each line more shorter
Also rename `muser` to `vfio-user` finally.

Change-Id: Iaf76a4bfc8f7a35621fcb60fd78cd145ea219269
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8167
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-06-09 07:21:31 +00:00
Michal Berger
70f7ea3e30 test/nvmf: Simplify get_nvme_devs()
This function was unintentionally including trace lines in its output
by playing with stderr (where -x is redirecting its output by default).
Avoid that by simply listing the devices and doing proper checks from
within the actual test.

Spotted in https://github.com/spdk/spdk/issues/1973

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: If15375aca152aaa49267c9cc51e70fd859685ea1
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8156
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: Ben Walker <benjamin.walker@intel.com>
2021-06-04 19:58:56 +00:00
Changpeng Liu
5b532e80c8 test/vfio-user: add subnqn for all vfio-user tests
After commit a31e319f "nvme: init discovery ctrlr using nvme_ctrlr_process_init"
SPDK will not initialize vfio-user subsystem if we didn't specify it
in the command line, so add this parameter as other transports already use it.

Change-Id: I5331459e9a88d8d94fa8b6ce693e086516b9f0bc
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8120
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-06-03 04:03:04 +00:00
Michal Berger
fead05c025 test/nvmf: Rework the traps
Declare single trap from nvmftestinit() instead overriding main trap
depending on the use-case (veth vs phy).

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: I23c66fc5728510d06eee9837843f0734b2d03dcf
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7850
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-05-20 15:16:21 +00:00
Changpeng Liu
f4d2ba4371 test/nvmf: use recommended nvmf_create_subsystem rpc
There are logs like below in existing CI tests:
"nvmf_subsystem_create is deprecated, use nvmf_create_subsystem instead."

Change-Id: Id257ab13120a71ad3d0ae7ed22ed6e0a4f005cf0
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7670
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Monica Kenguva <monica.kenguva@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-05-20 15:00:22 +00:00
Tomasz Zawadzki
1c9125e78e test: add bdev_wait_for_examine to static JSON configs
Runtime RPCs such as bdev creation has no chance to wait for
bdev examination to finish. To handle this case commit below
introduced bdev_wait_for_examine RPC, and built it into all newly
saved JSON configurations:
(e57bb1af)lib/bdev: build bdev_wait_for_examine into subsystem

Some tests generate the configuration by hand, rather than
saving it from an existing application.
This patch embeds this RPC into the test configs.

Fixes #1760

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I79f998d722a2d19aa98b78333c64dbd2c1151444
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7861
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2021-05-13 10:07:07 +00:00
Jonathan Teh
be6a01efb3 nvmf: Allow configurable controller ID range
Add {min,max}_cntlid to spdk_nvmf_subsystem, defaulting to 1 and
0xFFEF, respectively, and add nvmf_subsystem_set_cntlid_range() to
allow the controller range to be configured in the range [min_cntlid,
max_cntlid].

Also add {min,max}_cntlid to the nvmf_create_subsystem RPC to allow
the controller ID range to be specified when creating an nvmf
subsystem.

Signed-off-by: Jonathan Teh <jonathan.teh@mayadata.io>
Change-Id: I936db3bb0c9a38569063a6fd3c11df262dfad776
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7322
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2021-05-12 09:18:48 +00:00
Michal Berger
19f0c9a0d0 autotest: Replace fio.py with a bash wrapper in tests
fio.py simply wraps itself around fio and doesn't do anything that
would require python to be in use. Having it in a simple bash form
makes it easier to integrate it with autotest's common sh tooling
and to debug any potential issues with the underlying tests.

This also fixes #1919 by making sure only proper nvme devices are
selected for the nvmf targets.

Fixes: #1919.

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: I111d00df3c7b2517f431cae865e258a665c2ecb3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7684
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-05-12 08:48:10 +00:00
Maciej Wawryk
33227bbcc0 test/nvmf: add remove non-existent subsystem listener test
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: I3504e874d8ec1c8bacbd394e3d4d208dc155f45c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7038
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2021-05-05 13:33:11 +00:00
wanghailiangx
460bacc914 test/nvmf_tcp: allow tcp cases running in E810 NIC instead of virtual eth
Added nvmf_tcp_init() to run tcp through physical E810 network card.
If there is not E810 in system, tcp will still run on virtual eth.

Change-Id: I9a983c92175b27c45457682d42d72ef307fef260
Signed-off-by: wanghailiangx <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6932
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: <qun.wan@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Michal Berger <michalx.berger@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
2021-04-21 23:55:56 +00:00
Michal Berger
c09b139e61 test/nvmf: Use rxe_cfg to get rxe-enabled net devices
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: Iafc067f880525f25363db1adf9a94a9fc9215455
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6994
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-04-12 09:41:20 +00:00
Ben Walker
2ab0506ef7 test/nvmf: Don't load kernel modules for custom transports
For custom transports, skip the kernel module loading and
unloading steps.

Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: I193c62ffa0a9a5060b4bc504b39db3b6f660e1a3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3584
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2021-04-10 03:49:40 +00:00
Changpeng Liu
5922706ccb test/nvmf_vfio_user: simplify the creation of Unix domain socket
We only need to create an empty directory for vfio-user device,
the softlink isn't required anymore, so remove it.

Change-Id: Ie3f9ce73d287be3651f4ac06483888ac0f693700
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6954
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2021-03-30 11:46:32 +00:00
Pawel Piatek
191e6ab8d2 test/nvmf: fix non-root mode
- pass LD_LIBRARY_PATH
- use $SUDO_USER instead $USER
- support --huge-dir param via $SPDK_HUGE_DIR environment variable

Signed-off-by: Pawel Piatek <pawelx.piatek@intel.com>
Change-Id: Ib42fe8a10b2c5b7d8a888605da04fee98a600515
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6171
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2021-03-23 10:03:11 +00:00
Michal Berger
940cd3ae37 test/nvmf: Make sure RoCEv2 protocol is used by irdma platform
This is done in order to avoid hitting issues similar to #1747
for which https://review.spdk.io/gerrit/c/spdk/spdk/+/6106 was
submitted.

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: I95817f63287795f438f1d392cf1fb2894226ce0e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6240
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-03-03 08:12:26 +00:00
wanghailiangx
9c6548838a test/fio: add bs=4096 for fio_nvme
Since 'bs=4k' was removed from example_config.fio, although the
default bs value is 4096, but it would still be better to just
specify bs=4096 here.

Change-Id: I7c3bf10c10e42573ecb6683a371c3e81d3241cec
Signed-off-by: wanghailiangx <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6251
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2021-03-02 08:02:46 +00:00
Jim Harris
ab0a3f8f33 nvmf: do not pause a namespace when resizing
SPDK block devices can only be resized up when
it is open. So there is no need to pause the
associated namespace itself when resized - just
pausing the subsystem is enough.

Also modify the ns_hotplug_test to do null bdev
resizing - this will help test this resize code path.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3cb7b9de0892c296f2abf2280bed434d18ebe6b5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6467
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2021-02-22 10:05:11 +00:00
Changpeng Liu
a3b56e7f4d test/nvmf_vfio_user: add one more device to the target
Previously we only tested one device with vfio-user target,
now add one more device to the test script.

Change-Id: I6923a313b23f93e6fdc3f25baa060b9af43ba7f7
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6228
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-02-09 11:31:16 +00:00
Michal Berger
37d8b241a8 test/nvmf: Add DIF test utilizing the digest functionality
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: I511d04ff75d5b6b4213e6186b0314a5db1ce722d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6028
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2021-02-09 11:26:51 +00:00
Ziye Yang
d4c412720f test/nvmf: Add the digest test in multipath.sh
Since this script is only running tcp transport,
so we can enable the header and data digest configuration
when running nvme connect option.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I9954af0fc9798cc565c2a439ecba1707d3629e83
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6119
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2021-02-04 08:42:33 +00:00
Changpeng Liu
3b673b8431 nvmf/vfio_user: disable vfio_user by default
Users can use "--with-vfio-user" to enable it when testing it.
For CI configuration, we add a new test flag SPDK_TEST_VFIOUSER
to enable CI tests.

Change-Id: Id284df721171d01cc52491ebf4088bcc17eee147
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6139
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2021-01-29 15:15:23 +00:00
Ben Walker
312a9d603d nvmf: Subsystem pauses only pause admin queues
Additionally, the user can specify a namespace to also pause during the
operation.

This allows for the management of hosts, listeners, and the addition of
namespaces all while I/O to other namespaces is occurring. Pausing a
specific namespace also allows for the removal of that namespace without
impacting I/O to other namespaces in the subsystem.

Change-Id: I364336df16df92fe2069114674cb7a68076de6fb
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4997
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2021-01-26 17:38:54 +00:00
Karol Latecki
1963b478f7 test/nvmf: add Intel E810 RDMA nic's detection
Check if E810 series cards are installed in system.
No need to check for specific model as all are RDMA
capable. See: https://ark.intel.com/content/www/us/
en/ark/products/series/184846/intel-ethernet-network
-adapter-e810-series.html

Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: If4c11ee5b65ca0f545100581782fa4263a92921d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5943
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
2021-01-22 08:33:05 +00:00
Karol Latecki
45866e50c3 test/nvmf: try to initialize only available RDMA NICs
Instead of rushing and probing all drivers for all NICs,
first try to check which RDMA drivers are already loaded.
Try only to use these NICs which drivers are already
available. This makes it easier to select which NIC
vendor will be used in test, as not all NICs will be
listed under /sys/class/infiniband (even if physically
present in system).

If for some reason a preloaded driver is detected, but
no physical NIC is seen in lspci - fall back to "old way"
and try to all NICs known to us.

Also includes code change to following if block, just
for style consistency in function.

Change-Id: Idc5756b5d4927b0ff11b5a37ed3729995f5c8f8a
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5948
Community-CI: Broadcom CI
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2021-01-22 08:33:05 +00:00
Karol Latecki
40597c9b95 test/nvmf: fix driver list for Mellanox ConnectX-4
CeonnectX-4 and X-5 share the same set of drivers.
mlx4_* drivers were mistakenly added for ConnectX-4
while actually they're used by ConnectX-3.
https://community.mellanox.com/s/article/mellanox-linux
-driver-modules-relationship--mlnx-ofed-x

Change-Id: I03de970fad6497c98a6873a25a5df66a0de8312c
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5947
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2021-01-22 08:33:05 +00:00
Michal Berger
5636dabc3d test/nvmf: Add tests covering usage of DIF
Change-Id: I95eedb1bc21e296113d7f5853ab286d966adf1b8
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5568
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2021-01-21 16:43:54 +00:00
Changpeng
3ff9c13614 NVMe/vfio-user: add initial version vfio-user transport to NVMe driver
When NVMf target linked with vfio-user library, we can use
vfio-user client library to connect to the target.

Here is the three examples that can work with target:

identify -r 'trtype:VFIOUSER traddr:/var/run/muser/domain/muser0/8' -g
perf -r 'trtype:VFIOUSER traddr:/var/run/muser/domain/muser0/8' -g -q 1 -o 4096 -w read -t 10
reconnect -r 'trtype:VFIOUSER traddr:/var/run/muser/domain/muser0/8' -g -q 32 -o 4096 -w randrw \
-M 50 -t 10 -c 0xE

You can run the following test script test/nvmf/target/nvmf_vfio_user.sh to have a quick test,
currently enabled with NVMe Identify,Perf,Reconnect tools.

Change-Id: Ieb9842b2f372184fffbf7f23e4aad26feb47c350
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3839
Community-CI: Broadcom CI
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>
2021-01-21 05:00:18 +00:00
Ziye Yang
a8ebf6ac53 nvmf perf test: Add the data integrity test.
Just change the test for QD=32 in order not adding the addtional
test time.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ic801fffd904aecfd7ccdc89d04f67273dbdf2753
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5908
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2021-01-15 08:30:34 +00:00
Maciej Wawryk
24ad09ba2f test: Replace spdk/nvmecli with stock nvmecli
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: I00998ce36b46902687065c5fa4684da9b7dd26d4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5541
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
2021-01-04 16:28:01 +00:00
yidong0635
d949f55737 test/nvmf_example: Remove duplicated test code.
Only need to add command about sudo -u "$USER" for
non root user.

Signed-off-by: yidong0635 <dongx.yi@intel.com>
Change-Id: I3b6dbea0175a60b19627cd64d21da3d59309f47f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5563
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-12-14 14:34:14 +00:00
yidong0635
decdfa0b22 test/common: Add bdev_nvme_set_options before "bdev_nvme_attach_controller".
This patch is base on the patch about adding item "keep_alive_timeout_ms".
exposing bdev_nvme_set_options this method that existed but not used.

If we meet the keep alive timeout issue or some intermittent failure, we can
change the keep alive timer from host side. This is also an example to
demonstrate some special items that we can finetune.

Our host app is using json config, which gets config from the target side and
overwrite it .
Exposing this bdev_nvme_set_options that users can quickly change the setting
to fit the real testing environment. Strictly it's not a bug of target, just
make it more compatible.

Signed-off-by: yidong0635 <dongx.yi@intel.com>
Change-Id: Ic1e8a2757dd5ed359500e1692f16e448fab0d4fb
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5333
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2020-12-09 08:27:06 +00:00
Ben Walker
af07b82fa2 nvmf: The maximum number of namespaces a subsystem may contain must now
always be specified

Previously the parameter was optional and the size could be increased as
necesary. Now, it is required and a hard maximum. Later another function
could be added to dynamically increase or reduce this number if
necessary.

Change-Id: I3524ac737a6b592b4f6ce14ea48d3742a352c70f
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4996
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2020-12-01 10:20:43 +00:00
Tomasz Zawadzki
8c3e71f0f9 script/gen_nvme: do not generate legacy configuration
gen_nvme.sh will no longer generate the legacy configuration.
"--json" option will still work for any current users of the script.

Tests were modified to no longer use the "--json" option.
Meanwhile others were simplified with switch to "--json-with-subsystems".

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I8450be98660e54c64c27d8401fc40d649f9403ea
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4802
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2020-10-22 17:08:41 +00:00
Ben Walker
6723bd0c0f nvmf: nvmf_subsystem_remove_host RPC now disconnects hosts
If a host matching the removed hosts' NQN exists, it is now
disconnected.

Change-Id: I0bec29eda2dc220114b9197d4eb765899b9e1517
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4684
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>
Community-CI: Broadcom CI
2020-10-22 03:55:57 +00:00
Michal Berger
e351dca373 test/nvmf: Replace [ with [[ test in allocate_nic_ips()
The former will force Bash to complain if $ip consists of more than
one ip address. E.g.:

  1:08:55	# '[' -z 192.168.121.37 192.168.121.36 ']'
  line 104: [: 192.168.121.37: binary operator expected

The alternative is to properly quote the $ip inside [, however, [[
is always the safest approach.

Change-Id: Iced7319a106ce35a183840984aa6e6e1e52caa16
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4478
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-10-08 13:11:29 +00:00
Shuhei Matsumoto
1e6152c185 test/nvmf_target: Test ANA by Linux kernel host native multipath
Create a subsystem with two listeners.

Linux kernel NVMe host connects to the subsystem via the two listeners.

Then while the host runs FIO, change ANA state of the two listeners.

The expected result is that FIO completes without any error.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ibb8174e87ab0d1e15cf345684431cd109789452c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4121
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2020-09-28 08:32:30 +00:00
Shuhei Matsumoto
fae6cbbaed test/nvmf_target: Virtual network using veth and bridge for TCP transport
Disconnect test requires not the second TCP port but the second IP address,
and hence it is disabled for TCP transport now.

Besides, related with this, popular Linux iSCSI initiator requires
not multiple TCP ports but multiple IP addresses for login redirection
feature. Using multiple IP addresses will be reasonable also for
NVMe-oF TCP transport.

Hence following the recent change in iSCSI test, create multiple
IP addresses network using veth device and ether bridge.

After this patch, target_disconnect test will be enabled for TCP
transport automatically.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I593090dd5b763e90dceb8eeee7a7b79971367b8d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4089
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-09-28 08:32:30 +00:00
Shuhei Matsumoto
8701f636c6 test/nvmf_example: Not echo but substitute directly to NVMF_EXAMPLE variable
Following the last patch, simply set NVMF_EXAMPLE directly without
using echo.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ibc3b9268263f44c0b865a15a1ed1a15a404ed23e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4091
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2020-09-16 07:55:28 +00:00
Shuhei Matsumoto
0ecb36c727 test/nvmf: Use $USER instead of logname to follow other cases
$USER gives the login name who logged in the terminal and
logname prints the login name who logged in the session.

test/nvmf/common.sh has used $USER to start the SPDK application,
as non-root but test/nvmf/host/perf.sh and
test/nvmf/target/nvmf_example.sh have used logname to start the
example application as non-root.

It looks OK to use $USER to start application as non-root like other
cases.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ia0a17e3bd37a76e4d808e5816ba6716920f8f340
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4090
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-09-16 07:55:28 +00:00
yidong0635
744448260b test/nvmf: Remove duplicated code target second port.
This is already defined in nvmf common file. so remove it.

Signed-off-by: yidong0635 <dongx.yi@intel.com>
Change-Id: I40b003c8361fe889e9ed6a2add9878e362b5e966
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4056
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Broadcom CI
2020-09-07 09:29:49 +00:00
Michal Berger
63ebdf5943 test/nvmf: Use NOT() for the negative multicontroller test
Change-Id: I5f631c854e0cb8440508dc24bcee033b481cf741
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3930
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2020-08-31 07:46:43 +00:00
Michal Berger
a79e33eb54 test/nvmf: [multicontroller] Run bdevperf tests without data verification
Change-Id: I8e5f6c286a640e0e8077cf08388a4b6c5af30169
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3929
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-08-28 22:00:50 +00:00
Michal Berger
e1dc45b0fa test/bdevperf: Keep bdevperf output around
Potential bdevperf failure is hidden out from the user as it's
std{out,err} is redirected to a file which is purged upon exiting
from the test.

For the sake of debugging, print contents of the output file before
removing it.

Change-Id: Ifd0ff94aa1812ec518c60ada5a63342d7d5b80dd
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3917
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-08-26 09:46:50 +00:00
Michal Berger
3797a38dc6 test/nvmf: [multicontroller] Don't wait indefinitely for the controllers
Also, replace unexisting pass call with a simple sleep.

Change-Id: I5c0197109410df51df3ebe81596b5c0b1b103343
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3915
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-08-26 09:46:50 +00:00
Seth Howell
24b6d3cbdb test/nvmf: add a test for attaching to controllers.
Just demonstrate the several ways we have to use the
attach_controller rpc.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I86d2f9f2dd55f7637d0f2ecc46a3817221001a8f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3615
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-08-21 08:25:14 +00:00