Update spdk_thread_poll() to count SPDK thread stats correctly on multiple
SPDK threads per reactor configuration.
spdk_thread_poll() gets start time and reads TSC at end as end time,
and then gets delta between them as run time. Run time is added to idle
time or busy time according to the result of polling.
Reactor overhead is included into the next thread which calls
spdk_thread_poll() now.
spdk_thread_poll() saves the end time to the current thread to use it
as the start time of the next thread.
Unit test framework for this patch and the next patch need to access
thread->tsc_last. In the next patch, reactor will use the end time of
the current thread to the start time of the next thread in reactor_run()
to realize the idea.
Hence add an new API spdk_thread_get_last_tsc(). The corresponding
variable is named as tsc_last and it is good and is aligned with
DPDK (DPDK has used tsc_start and tsc_end as variable name). But
last_tsc will be better as API name because the last TSC value is
easier to understand.
Then add necessary unit test and update the unit test framework.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I5e465e9283c032acb427576d0c90f9e1414f2271
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1048
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: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Group the global parameters into the global structure
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: I552b536869221efb58bc30820b7adfc01c74c293
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1388
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
This function kicks off the draining process, so name it appropriately.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: Ic447aaa01612f6355ff4404d476419b55a3d0cff
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1386
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
In practice this worked out fine because the next step did an
spdk_for_each_core() which would always complete after the
performance dump with our current event library. But just in case,
make this an explicit wait.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: I07b96772ba15113cd04453243c980c6e405be872
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1385
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
More descriptive name. This is the number of outstanding
construct_job operations.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: I5c79ae06a521a8b6ef930146b0ce08791370a25c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1384
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Begin shifting to a model of "jobs", each defined as a single-threaded
I/O pattern.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: If6c0cfc1a59d3acdec1e1e6ad65a16f810582aa8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1382
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
There's one of these per core and it's a collection of other
jobs to run, so name it reactor.
In the longer term, this reactor will go away and each "job"
will map to a separate spdk_thread.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: Ica5b19e6edb2509b48059d829e22a734acd6b298
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1381
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
The revert asynchronous API doesn't run as the *real* asynchronous
way, because the drive can only support synchronous module and only
1 session is supported. The reason why we added this API is that
RPC call has the default timeout value here, while the revert may
take over several minutes, the API itself doesn't short the revert
action, so just remove it and use the synchronous API instead.
The revert action will erase all the users data and bring the drive
back to the factory state, it should run in the synchronous mode,
so just remove the asynchronous API and we can increase the timeout
value when using RPC to call this API.
Change-Id: I08a082edea6385e378399423bbb229d05f8bc262
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1232
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Inform the user that something actually happened
during the test, rather than just displaying
"Test start/end".
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: I69a048a5a2fd47a3f18ea2988a06aee439c06fc3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1412
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
"ls" is not needed in for loops based on filename
expansions.
Additionally "ls" was treated as first
element of for loop which cased "No corresponding
object" message to be printed which could be
mistakenly considered a problem during the build.
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: If5bfdb15410da36c98d9992cd04a02906599a3e0
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1411
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>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
This will allow to test parts of compress bdev on systems
that do not have all types of PMDs.
Once case if for testing in VMs.
For reference on changes in execution time. Current times:
Per-patch = 8 seconds
Nightly = 84 seconds
Running the script twice in this patch, most likely doubles the time.
It is not an issue in per-patch, but if increasing nightly times is blocking
different solution could be done here.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I684569651f2290956f94fcec99cebf0fe13ba0d2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1364
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>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
In case there are no /dev/nvme* devices found, the test will continue
regardless trying to pass literal glob strings as an argument to nvme.
This, of course, fails, e.g:
ci.spdk.io/public_build/autotest-per-patch_7066.html
Avoid this by generating list of the nvme devices and abort the test
gracefully in case it's empty.
Change-Id: I71628aa78a5cfc6c5696f1fc17ed3480d4c642ee
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1392
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
super->clean value signifies if blobstore was unloaded
cleanly.
If it was not, then during bs_load the _spdk_bs_recover()
procedure if called.
Meanwhile bs->clean is always set to 1 after load, causing very first
blob_persist to also re-write super block with the super->clean
set to 0. To signify that md has changed and possibly trigger
the recovery if clean bs unload does not occur.
When the re-write of super block succeeds the bs->clean is set to 0,
because further re-writes of super block are not needed on next
blob persist.
This patch resolves issue when:
1) reading super block fails - execution should backoff, to prevent
writing an empty buffer as super block !
2) writing super->clean = 0 to the super block fails - execution
again should fail, and bs->clean should not be set to 0. It will
cause next persist to attempt re-write again.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ia07cc5c6c107310059b50886edb7283c176b9169
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1164
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>
This change verifies that not only it is possible to open
the snapshot, but also the spdk_bs_create_snapshot() reported
success.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ifb7fcc91802c838710f1f9be41090057268a5900
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1262
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>
blob_create_snapshot_power_failure() test always attempted
snapshot creation until the snapshot did open.
Which meant that on bs reload after dirty shutdown,
the original blob might be in unrecoverable state.
UT did not verify create call beyond that point.
Next patch will stop after snapshot is possible to be opened,
AND the spdk_bs_create_snapshot() returned success.
This patch makes it easier to recreate same starting
conditions after snapshot did not open.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I1901b29a8319b2203a855e7879821ed3850f4917
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1261
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>
In general it is not possible to delete snapshot when
there are clones on top of it.
There is special case when there is just a single clone
on top that snapshot.
In such case the clone is 'merged' with snapshot.
Unallocated clusters in clone, are filled with the ones
in snapshot (if allocated there).
Similar behavior should have occurred for extent pages.
This patch adds the implementation for moving EP from
snapshot to clone along with UT.
The UT exposes the issue by allowing delete_blob
to proceed beyond just unrecoverable snapshot blob.
Fixes#1291
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ib2824c5737021f8e8d9b533a4cd245c12e6fe9fa
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1163
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This patch is used to add the async network I/O support in
sock layer. If code is configured with I/O uring, --with-uring,
we can use io uring in Linux (version >=5.4-rc3).
PS: We also make VPP's default priority > uring, because
for the iSCSI or sock test linked with VPP. It tests VPP with
a given address (which is not a special VPP can only open address),
so using uring can also listen those address succefully. And if we make
uring with priority > VPP, actually, VPP will not tested in those cases.
Additionally, the current CI pool is not ready for test, we need
wait for the CI system ready. And I test on my local platform, it works.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ie8ee3c8ddf8d2a7264f2b382376733e002816dcc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/952
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Previously the macro SN32_LT and SN32_GT had been added to iSCSI
library. But such comparisons may be used in other libraries.
So add two inline helper functions spdk_sn32_lt() and spdk_sn32_gt()
to include/spdk/util.h.
Add unit test for these functions. These functions are located in
header file but math.c is the place if they are located in source file.
Hence add unit test as the one for math.c.
The next patch replaces the macro SN32_LT and SN32_GT by
spdk_sn32_lt() and spdk_sn32_gt() in iSCSI library, respectively.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Id3e4d80fea98ad4ae1516e27b9c9e8ec6f37e7a8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1346
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The function is almost 20 lines long and it essentialy
appends two lines two a specified file. We don't need it.
Change-Id: I565de8e54aa71b04f15745456bec7b2b3b8fc178
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1288
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>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
There's no reason not to publish those. Especially if
they're needed in other public headers.
Change-Id: I7dfc6922fcc0dfc46822ad8a16a375f997b98e84
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1041
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Overwrite ini config with json and use it in such a form throughout
the entire test run.
This patch is the beginning of the series targeting conversion of
ini config to json in blockbdev tests.
Change-Id: Ic64f24b2ea9df85ad1ba3d038a78384e6f2badf9
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/530
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Do not use iter_pci_class_code function in tests to
iterate over NVMe drives. This function can return
drives which at the moment of execution can not be
whitelisted for use.
This can result in test errors (such as simply
bdev_nvme_attach_controller RPC command failing) or
even using and deleting data from NVMe drive which
was not meant to be used in tests.
Fixes#1235
Change-Id: I82b9935fc88605b636c2096be6c71d4880a567c8
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1309
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This function removes leftover fio files, but fio is
not run in this test. Remove it.
Change-Id: I1522a018c9cc3093bd1bcb1c2361dd7b31deacbe
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1292
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>
NVMe specification in ch.7.6 "Controller Initialization" suggests to
use only Set Features "Number of queues" command and says nothing
about Get Features. All required information is available after Set
Num Queues step.
Fixes#1270
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: Ide38ba9c7f063f1d6b13bfce4232c588cc906784
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1271
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
The fedora machines running unit tests will require this package to run
the ABI compliance checking tests.
Change-Id: I9f9307c04e235cb9b6f78c4908609a529a86ccba
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1137
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>
We don't fail the test based on missing symbols so printing out the
information about them during tests is not super useful. Restricting the
output to what caused the test to fail will allow for simpler debugging.
Change-Id: I7b251dfe39c940074d7c8d887941adb635fd3965
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1094
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This test checks to confirm that the major version for the SO
has been incremented if symbols have been removed or changed since
the last release or the minor version if symbols have been added.
Change-Id: I2bbef858c4cb18afbb854c90782495c45605c63d
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1068
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>
The hardcoded path is replaced with $CONFIG_FIO_SOURCE_DIR as defined
during the compile time.
Additionally, all checks which determine if fio is available are now
based on $CONFIG_FIO_PLUGIN=y knob instead of the presence of the fio
repo.
Change-Id: Ie469747f3863c9561f53d32e8c3f29778afaaf74
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1108
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
The next patch will create poll group threads dynamically for
NVMe-oF target, and will need to wait for completion of poll group and
I/O channel destroy. This is a preparation for the next patch.
Add callback function and its argument to spdk_nvmf_poll_group_destroy(),
and to struct spdk_nvmf_poll_group, respectively.
The callback has not only cb_arg but also status as its parameters even
if the next patch always sets the status to zero. The reason is to follow
spdk_nvmf_tgt_destroy's callback and to process any case that the status
is nonzero in future.
spdk_nvmf_poll_group_destroy() sets the passed callback to the passed
poll group.
Then spdk_nvmf_tgt_destroy_poll_group() calls the held callback in the
end.
This change will ensure all pollers are being unregistered and
all I/O channels are being released.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ifb854066a5259a6029d55b88de358e3346c63f18
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/495
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>
