This is more reliable than checking for the DPDK generated
/var/run/*config file, and is not DPDK dependent.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iadaba1c715e6fe2aafd7375831961b79ae31714a
Reviewed-on: https://review.gerrithub.io/362628
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iba5bb17a30b7d7ec39fe64df93860dd8500f2ad1
Reviewed-on: https://review.gerrithub.io/362607
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
The stub application will ensure that each
iSCSI test does not need to reinitialized DPDK
memory and NVMe devices. This drastically
cuts down on the amount of time needed to run
all of the iscsi_tgt tests.
While here, add a new common ISCSI_TEST_CORE_MASK
shell variable, eliminating a bunch of copies of
the 0xFFFF core mask, and ensuring the stub application
chooses a core mask that overlaps all of the iscsi_tgt
test cases.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ifae73276923258ff64370ae42e19cf1a4a2c2212
Reviewed-on: https://review.gerrithub.io/362454
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I1a4d9fd8940e17b2e4854edbe09ee5fe6fd62edb
Reviewed-on: https://review.gerrithub.io/362596
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Starting SPDK applications can take a long time due to
two factors: DPDK memory initialization and NVMe
device initialization.
This stub application facilitates eliminating those
delays by leveraging DPDK's multi-process mode. This
stub application acts as the primary process,
initializing DPDK as well as all NVMe devices bound
to userspace modules (uio/vfio). Then another
SPDK process can be started using the same instance
ID, which will make that SPDK process a secondary
process of the stub and leverage the DPDK memory and
NVMe device initialization already performed by the
primary process.
To start this will be used to accelerate the iSCSI
system level tests (in test/iscsi_tgt) to significantly
reduce test time in the CI pool.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3019c7d883f40b3ee8fb3345db013df2afc25645
Reviewed-on: https://review.gerrithub.io/362453
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I76b442115caa5e9320ded671be6bc54a6a98a2b4
Reviewed-on: https://review.gerrithub.io/362451
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This test sets DPDK_DIR to the main repository so does not build
DPDK on the mounted iSCSI LUN. So don't bother copying the
dpdk subdirectory to the iSCSI LUN which saves a few seconds
for every test run.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ieb04f94b7955acbafb283638531ad076afbf2302
Reviewed-on: https://review.gerrithub.io/362268
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
A single -L can be used to get the latency summary.
Two -L's (or -LL) can be used to get both the latency
summary and the detailed histogram.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3fc0f4e2dfff7b041a665fe35aa33f11e4c3ebad
Reviewed-on: https://review.gerrithub.io/362270
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This enables iSCSI tests to be more easily run in isolation.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I4868ca68fe16e06025fd36c62c41ad0694806051
Reviewed-on: https://review.gerrithub.io/361811
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This ensures that all spdk_bdev_io structures now have
an attached channel, simplifying some future work around
things like counting the number of outstanding IOs for
a given channel (which otherwise would have had to
account specially for resets).
Reset semantics are still that they affect the entire bdev
and not just the channel it was submitted on.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8aad21a88faacecfd94bdba350059528eb62c390
Reviewed-on: https://review.gerrithub.io/362251
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Change-Id: Id6a384b91d7ab40de4382601a771b2f02bf31e81
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/362280
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
The user should not see the bdev_io status directly; the NVMe and SCSI
error code wrappers provide the ability to translate to the desired
format regardless of what kind of error is stored inside the bdev_io.
Replace the spdk_bdev_io_completion_cb status parameter with a bool
simply indiciating whether the I/O completed successfully.
Change-Id: Iad18c2dac4374112c41b7a656154ed3ae1a68569
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/362047
Tested-by: <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This will make sure the hotplug instance not exit before all the hot insert and
remove events done, the setup.sh for hot insert events will use several seconds
sometimes.
Change-Id: I4ad61937760529547cdcf7701f3c3d9033121e45
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/362131
Tested-by: <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This is no longer used anywhere. For the places where we previously
used it, we've since found alternate solutions that do not
require it.
Change-Id: I738a80b95ef50348ce1c14969a3812b0a625b3fd
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/362064
Tested-by: <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
An ECN to the NVMe 1.3 specification has clarified that the NQN may
contain 223 bytes before the null terminator. Make all of our NQN
length checks consistently enforce this behavior.
Change-Id: Iebfd57d11abea64964c7a6ad9d886e40efa243c3
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
This will need to be configured globally for all channels.
Change-Id: I773252f220373617f8d09d1f24243db8095cf8a4
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Specify the function as a parameter to spdk_scsi_dev_queue_mgmt_task.
This makes the API clearer by making it explicit that the management
function is required for management tasks.
Change-Id: I92d893aadb6faebea81dd79729894d2c2fddf088
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
The type of a task is known due to the function used to submit it:
- spdk_scsi_dev_queue_task() for normal SCSI command tasks
- spdk_scsi_dev_queue_mgmt_task() for management tasks
Change-Id: I183a1f89ab85f3fce1de2491e77d95d4b147fd72
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Added new rpc commands together with underlying vhost API and tests.
Change-Id: Ib9c6a530d0909193ea5115aaac4920c44f39613c
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
This allows the iscsi_tgt tests to be run more easily
in isolation.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I1fa87e8b02f6e6ed62c75f07471d93ce84da30c2
The latency tracking is done with ranges of bucket arrays.
The bucket for any given I/O is determined solely by TSC
deltas - any translation to microseconds is only done after
the test is finished and statistics are printed.
Each range has a number of buckets determined by a
NUM_BUCKETS_PER_RANGE value which is currently set to 128.
The buckets in ranges 0 and 1 each map to one specific TSC
delta. The buckets in subsequent ranges each map to twice
as many TSC deltas as buckets in the previous range:
Range 0: 1 TSC each - 128 buckets cover deltas 0 to 127
Range 1: 1 TSC each - 128 buckets cover deltas 128 to 255
Range 2: 2 TSC each - 128 buckets cover deltas 256 to 511
Range 3: 4 TSC each - 128 buckets cover deltas 512 to 1023
Range 4: 8 TSC each - 128 buckets cover deltas 1024 to 2047
Range 5: 16 TSC each - 128 buckets cover deltas 2048 to 4095
etc.
While here, change some variable names and usage
messages to differentiate between the existing latency
tracking via vendor-specific NVMe log pages on Intel
NVMe SSDs, and the newly added latency tracking done
in software.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I299f1c1f6dbfa7ea0e73085f7a685e71fc687a2b
The bdev generation count is an internal implementation detail;
applications should not be reading or writing it.
Change-Id: Ic4455b7b72dc80babbc410420c89f52ef5d77e6d
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Also change the discovery/nvmf.sh test to use it.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I56bce9a84bd46f13b6d4f34da81abf23413f2598
The SCSI library already provides a callback when the task is released
(free_fn), so the user can update their own task counter.
Change-Id: I7fb13f6fff66dbba2315fd03fb06e49f793be123
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
The task free callback function is required, so make its assignment part
of task construction.
Change-Id: I2f5fdf73b064653ee85b4e7961cb1653a0a4107d
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Fix up a second copy of linux_iter_pci in the same manner as commit
6562e95092 (scripts/setup.sh: support
systems where more than one domain is used).
Change-Id: I3d9b842891d70c2960de8287e3b11c1a11b02d1f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Added 1 minute timeout for vhost to exit after receiving
INT signal. After timeout send KILL signal to vhost app
and exit with error.
Change-Id: Ib1659660667991b21103b3401bbd780290521433
Signed-off-by: Karol Latecki <karolx.latecki@intel.com>
The first time this test runs on a machine, it will not have the SSH key
in its known_hosts, so allow it to connect without user intervention.
Change-Id: I27f750f41e1819b526197af2d0b9ae15382d9aa4
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Blockdevs already indicate support for unmap via
spdk_bdev_io_type_supported(bdev, SPDK_BDEV_IO_TYPE_UNMAP).
Change-Id: I634f27a281fd900bb3a6da2e4ff8a74e43579578
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
We plan to use these buffers for more than just reads.
Change-Id: I8fa6cb432a6cfe4406fbf240cd3aa2ae4ab5f3d5
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
The bdev layer manages the bdev_io caller_ctx internally.
Change-Id: Icb5a4f26b090d6f761af988fb26a319005e66a6d
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
The SCSI layer was not using the task ID for anything; the iSCSI layer
was using it to store the task tag, so move it there and rename it to
"tag" to make its purpose clear.
Change-Id: Ibda4f4e215056116b9be4a3a0264f98bc4c29535
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Move the scsi_nvme translation code from the SCSI library into bdev, and
provide a generic way to translate any bdev_io status into a SCSI
status.
Change-Id: Ib61a6209387c24543e31574e2b5ca249e2ac8b74
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
RocksDB's build system does not correctly generate dependencies - if
headers have been removed in the SPDK repository since the previous
build, the .d files will prevent the build from continuing.
Avoid this by cleaning up any left-over build outputs from the previous
run.
Change-Id: Ib8669273eb38c241f83e14714683693430469462
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Convert autotest.config to a sourceable file. This enables direct or
indirect usage of variables and a chance to remove error prone
statements like '$(cat | grep | awk')'
Change-Id: I3ae4152fd7548e4b2bfd01c00b614155871b2db3
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
The contents of struct spdk_scsi_lun don't need to be part of the public
API.
Change-Id: I101b77871054557380610fd901ab38bada463202
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
The RocksDB SPDK environment no longer depends directly on DPDK.
Change-Id: Ifcabcd137292f86724a1e3fed93abb94fa5a2344
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Fix the incorrect iSCSI PID ($pid) and also terminate nvmf_tgt on
failure.
Change-Id: I92457591c98c12f101a1713763ed9dc1feb32cb9
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Similar to commit 378fc7787c, remove
unnecessary process_core calls.
Change-Id: I2fb55e39770ca57274c177fce3161f46a94d4efe
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Setting max_sectors_kb to 4k was workaround and is no longer needed.
Vhost must work with arbitrary guest settings.
Change-Id: I9ff9d752916e200e79cdd2b4b3d64afdecae11bc
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Fix up all existing spacing errors in comments and add an automated
check for patterns like /*comment*/.
Change-Id: I28f61c93612dc0f8aed66bd509da78e91ea9737e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Also adds the automation test case for using remote
NVMe devices exported by NVMe-oF target.
Change-Id: I2b839a4eeec33d5b0c30d654e6013ad8c7949e23
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
The new format is: domain.bus.device.function
For this format, since we use '.' as separator,
to avoid misusing, we only support the following:
1 domain.bus.device.function ( 4 values provided)
2 bus.device.function (3 values provoided with domain = 0)
3 bus.device (2 values provided with domain = 0, function = 0)
Change-Id: Ide03db38b4ac7802cf36f0e536e8b997101d6cd3
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
A 100us is so small that applying the quirk to the specific
SSDs that require the delay is more trouble than it is worth.
So remove the quirk and always wait 100us before re-enabling
the NVMe SSD during initialization.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Id6a8cc6e35d103fffdf135580301fc3e5b27e722
The bdevperf reset test only executes in the nightly test run, so this
problem wasn't caught during review.
It gets stuck in an infinite loop and produces lots of log output; turn
it off to avoid filling up the disk with logs until we determine what
broke it.
Change-Id: I7601ba324a0531de3733cf5784ccd46da5618082
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Queue aborts that would exceed the abort command limit
in software as a convenience for the user.
Change-Id: I8c1f0380984cc6c0cdb453db961939a7f571b336
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Core dumps stop working if the path is longer than 64 bytes.
Use readlink to shorten some of the very long relative paths.
Change-Id: I5e7eb6580ca581c5ac3a71afb7b62953836e2660
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
It has been discovered that some devices require
a very small delay before writing CC.EN to 1 after
CSTS.RDY goes to 0.
Change-Id: I73d31726d17ebf5bbec7ee528e2f98fcd05234dd
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
This patch removes comments within configuration files for tests
that are not relevant to the test itself.
It reduces the need to update comments in test config files with each update.
As well it makes those same as other test configuration files.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I48116613435fadf0738b5a948d32f458c7ce06be
In the cache_append_no_cache test case, we need to
sync the file first, before calling cache_free_buffers().
Otherwise the buffers do not really get freed since they
contain dirty data.
This fixes a couple of memory leak bugs detected with
CONFIG_ASAN=y.
Reported-by: John Meneghini <john.meneghini@netapp.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: If1ff6ed7d9e7a6dc67af0a2baf3b2555ace610ee
This parameter is not actually used by the unit
tests using the bdev, but setting it to a non-zero
value silences a couple of static analysis errors.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Id53a17bcd1f4ec51f35a954ec0f6e6ea9803086e
This fixes multiple SCSI reset issue.
This patch does not remove sleep in iSCSI tests.
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I5e9f3705e5dc34004b9d1b9e40fbdcb04a3bee4e
Some intermittent issues still observed with multiple
resets in quick succession. Reverting for now while the
issue is more fully root caused.
This reverts commit 7fa7f91ee3.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I493b564e8a110bbfb7a6cc47107d53d6eca40053
Automated test scripts now set up 4096 huge pages by default,
so we can now safely allocate the default 4GB for blobfs cache.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8aea322068a5df79ca75737c43a4e0e80e7d2be4
The bdev product_name field is used in the Inquiry command translation
and was previously uninitialized.
Change-Id: Ie9d056ddaddfbb60ce5c3444ed87f852c00a296d
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Rather than re-running setup.sh during the vhost tests, just
pre-configure NRHUGE to the necessary value for all setup.sh invocations
during autotest.
Change-Id: I1a4d9a7f7ab52082a8f626c3c64807417a493b5f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
