In the presence of hardware offload (for data digest) we may not be
able to immediately release all PDUs to free a connection. Add a
state to wait for them to finish.
Fixes#2862
Change-Id: I5ecbdad394c0296af6f5c2310d7867dd9de154cb
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16637
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
A host will consider a QID as reusable once it disconnects
from the target. But our target does not immediately
free the QID's bit from the ctrlr->qpair_mask - it waits
until after a message is sent to the ctrlr's thread.
So this opens up a small window where the host makes
a valid connection with a recently free QID, but the
target rejects it.
When this happens, we will now start a 100us poller, and
recheck again. This will give those messages time to
execute in this case, and avoid unnecessarily rejecting
the CONNECT command.
Tested with local patch that injects 10us delay before
clearing bit in qpair_mask, along with fused_ordering
test that allocates and frees qpair in quick succession.
Also tested with unit tests added in this patch.
Fixes issue #2955.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I850b895c29d86be9c5070a0e6126657e7a0578fe
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17362
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
If we were not able to submit all configured
crypto ops, then we can just release crypto_ops
and mbuf object of these crypto ops and save
the actual number of submitted operation in
the accel task. Once all submitted operations
complete, poller will call
accel_dpdk_cryptodev_process_task func to submit
cyrpto operations for reamining data blocks.
If no crypto ops were submitted then the task
will be palced in the channel's queued_tasks
and poller will try to resubmit the task.
That in theory should increase performance
since we attempted to resubmit queued ops
with burst size==1 which is not efficient
Fixes issue #2907
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: I4d17e8ed1ad5383848e4d09c46009c6cb2834360
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16784
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
When accel task is processed is processed in
several iterations (submit part of cryops, wait
for completion and submit next part of cryops),
sgl is initialized with offset to exclude previously
processed blocks. However there is a bug since
spdk_iov_sgl_init doesn't advance iovs, as result
when we do sgl->iov->iov_len - sgl->iov_offset,
we may get unsigned int underflow.
Fix is init sgl with 0 offset and then advance it
with offset.
Modified unit test and added an assert in code to
verify this fix.
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: Ib53ff30f0c90d521f2cf6b3ec847b0d06869c2b5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17456
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
When RPC server is used for configuration, rpc_cmd
function waits 15 seconds to read all replies. If
mlx5 dpdk driver is used on slow machines or in
container, RPC framework_start_init may take more
than 15 seconds to execute. As result, rpc_cmd
exits earlier and output of some comamnds
remains in the pipe. Next call of rpc_cmd may
read wrong data, that leads to malformed json
config. To avoid this problem, redirect RPCs to
a regualr rpc socket.
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: Ibfcf56bb0a7f84f69394846d83746c91a4024b9e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16389
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
There's no point in keeping these separate as dnf-aware distros
also support yum and there are no plans to drop it anytime soon.
In fact, since the actual list of packages between dnf and yum
was different, the centos7 was not provisioned to the full extent.
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: Ieec6796bf457d37b2618a1c2756d281f4af0c5b4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16931
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Pawel Piatek <pawelx.piatek@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The new name puts more emphasis on what is the main designation of
the script as it does not really touch anything VM-related.
The vm_setup.sh is preserved as a symlink available for a transition
period.
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: I968a52cc069706f4c5e1b8a871988809e701a3fe
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16928
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
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>
Most of the information gathered there is outdated and generic and
falls out of scope of what vm_setup.sh/pkgdep is actually doing.
Simply mention the main purpose of the script, leaving actual
configuration to the user.
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: I126515dea019e7f1cd76c8be1339aea080d2a2b0
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16927
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
We no longer support ubuntu's Xenial and Bionic flavors so they can
be removed.
swupd, Clearlinux's package manager, is also no longer supported.
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: I526a89f4d3b3078949f235e46f8bb3a39b2a24b6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16926
Reviewed-by: Pawel Piatek <pawelx.piatek@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
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>
Some minor code shuffle + removal of the autorun-spdk.conf creation.
Creating this config has little sense as some of these flags cannot
be used together anyway - it basically serves as a dump of all
supported flags which we usually are having a hard time to keep up
to date. That said, autotest_common.sh (and get_config_params())
gives a better view as to what flags are actually supported and
how they are used in practice.
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: Ib223ec90be58e68ecab69176d213c353df530498
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16925
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Signed-off-by: Kuo Kan <kuox.kan@intel.com>
Change-Id: Ib3d33cefc78f543e157ea552ee88f0514e305054
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15795
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: I313d65b01c9214a6bde5775488fb32c70cefa4d6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15357
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This is the location freebsd_update_contigmem_mod() looks up to copy
the modules into right /boot directories.
Signed-off-by: Michal Berger <michallinuxstuff@gmail.com>
Change-Id: Ic5919cc6382433c641c4c7a8b1100a50abfc246a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12925
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Use it in all of the places that were previously hooking
spdk_mempool_get.
Change-Id: I311f75fb9601b4f987b106160eb0a0014d3327cd
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16329
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This makes it much easier to mock this code in unit tests without having
to mock up the entire thread library.
Change-Id: Ic3d9cb826ae71af780a06f88669c37cef2c9a4ae
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16173
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
This OCF update is mainly focused on:
- New volume API
- New cache attach config instead of old cache device config
- UUID moved to different struct
- Persistent metadata is not supported due to metadata flapping (see 689c44c76ba87f80a9538c17220bb9ca6bffdda0 in OCF)
Signed-off-by: Amir Haroush <amir.haroush@huawei.com>
Signed-off-by: Shai Fultheim <shai.fultheim@huawei.com>
Change-Id: Ic3bc0f1b58550dc3b03b0afc9bcb43b2b9b988c6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17066
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Robert Baldyga
This allows the pipe to fill up entirely, instead of reserving 1 byte.
This tends to keep copies from the pipe aligned over time.
Change-Id: I4801d62fa839165efef61ea1c83f602931ee7018
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16990
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
As an lvstore is opening it calls spdk_bs_load(), which briefly opens
each blob and has no use for external snapshots. Since there is no point
in opening them at this time, don't open them. Once the blobstore has
been loaded, update lvs->load_esnaps so that external snapshots are
opened as the lvols open their blobs.
Change-Id: Ib16c8474300ff4b106aad0baa5b8b38332c23b01
Signed-off-by: Mike Gerdts <mgerdts@nvidia.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16424
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This provides the lib/lvol wrapper around blobstore's external
snapshots. Later commits make this work with vbdev_lvol.
The blobstore external snapshot implementation stores an opaque
identifier in an internal xattr. Lvstore uses this to store the
stringified UUID of the bdev that will act as the external snapshot.
This is used by the newly introduced spdk_lvol_create_esnap_clone() to
store the bdev UUID in the blob's metadata.
Change-Id: I58c7b32b656ad1d21a446e3b91e59e655efac7e4
Signed-off-by: Mike Gerdts <mgerdts@nvidia.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14977
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Mellanox Build Bot
This may have been needed in some previous iteration
of this duplicate QID test, but it's no longer required.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I5c788a50d9c87cec7268ebb6f64d91fdc7b00873
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17369
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
We need to be checking whether the specified qid
is too large or not - the current test says it is
doing that in the comments but is really just
checking the duplicate QID path (which following
test already covers).
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I21dac3c7ec83a5c8e31fac77481708d54cb40e9e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17368
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The 2 MiB minimum may be not reasonable for some users, so it is changed
to 4 KiB to allow wider range of possible values.
The new default is introduced to keep backward compatibility (2 MiB).
Signed-off-by: Szulik, Maciej <maciej.szulik@intel.com>
Change-Id: I450ff555f73ddd9be727ecc49209eb5af90fa88e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17406
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Community-CI: Mellanox Build Bot
Needed for the recent changes in the 6.2 kernel.
Also, add an extra patch to address changes in the net/core not
available in the out-of-tree driver.
Change-Id: I2e279a7728bbb462da99b79fad6a91ebd97ecae7
Signed-off-by: Michal Berger <michal.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17337
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Pawel Piatek <pawelx.piatek@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Kamil Godzwon <kamilx.godzwon@intel.com>
Needed for the recent changes in the 6.2 kernel.
Change-Id: I1788b11712dc581520ddcc5382894652be3a5576
Signed-off-by: Michal Berger <michal.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17336
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Pawel Piatek <pawelx.piatek@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Kamil Godzwon <kamilx.godzwon@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This application can be used to test AER flows related to doorbell
errors.
Signed-off-by: Szulik, Maciej <maciej.szulik@intel.com>
Change-Id: Idc04d326f08f8e04455c77ab8265cc601485afbe
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17401
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
This patch makes functions related to Asynchronous Event and error
handling public, so that they can be used in custom nvmf transport
compiled out of SPDK tree.
Signed-off-by: Szulik, Maciej <maciej.szulik@intel.com>
Change-Id: I253bb7cfc98ea3012c179a709a3337c36b36cb0e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17237
Community-CI: Mellanox Build Bot
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
unittest_sock unit tests fail on FreeBSD due to
ENOBUFS. Increase to buffer size to 4k for tests
to pass.
Fixes#2943
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: I55d1164d49edb2d90ebfe5f720a615f052ee52d9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17370
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
For some systems, depending on the mem distribution, 2GB per node may be too much. Just lower it to 1GB as the only thing we are verifying here
is HUGENODE usage in this test.
Also, make sure we always log output from setup.sh.
Change-Id: If7c382b442e9523fe5ad5df03110a8cc5467f1d9
Signed-off-by: Michal Berger <michal.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17367
Reviewed-by: Jaroslaw Chachulski <jaroslawx.chachulski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
This test scenario does the following:
- Attaches the controller to NVMe device.
- Injects an error timeout for admin command SPDK_NVME_OPC_GET_FEATURES
- Runs controller reset.
In this scenario the call for 'controller reset' should abort any outstanding requests that are waiting for completion defined in 'error injection' RPC call. Test fails if request(s) are not aborted (manually completed).
Signed-off-by: Yuri Kirichok <yuriy.kirichok@hpe.com>
Change-Id: I512de92e948d04cad538db378b44fd4d58d85bb3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17113
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
This will be useful in upcoming patch, where we
use the number of poll groups to dynamically pick
the buf_cache_size for each transport poll group.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Id166098244287c56f12cdd88ba27a17fa34a4348
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17331
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
If the controllers are left attached when the application is terminated,
the virtio library might receive notifications about memory being
unregistered from the mem_map. The apps in json_config test are
preallocating 1GB of memory, which should stop DPDK from releasing the
hugepages back to the system, but if they allocate more, that extra
pages can be released, which would generate the mem_map notifications .
This actually happened in #2951 - spdk_tgt was built with ocf support,
which preallocates an extra ~300MB mempools, exceeding 1GB, which caused
mem_map notifications to be sent when iscsi mempools were destroyed
triggering an assertion in virtio.
Another option to fix this would be to increase the size of the
preallocated memory, but detaching the controllers achieves the same
thing without requiring more resources.
Fixes#2951.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I743af39acfee68caba55ec4fccd593a696ab688b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17265
Reviewed-by: Karol Latecki <karol.latecki@intel.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>
It fixes the following error under clang:
/usr/bin/ld.bfd: bdev_nvme_ut.o: in function `bdev_nvme_get_mdns_discovery_info':
/home/ksztyber/src/spdk/module/bdev/nvme/bdev_mdns_client.c:578: undefined reference to `spdk_jsonrpc_begin_result'
/usr/bin/ld.bfd: /home/ksztyber/src/spdk/module/bdev/nvme/bdev_mdns_client.c:599: undefined reference to `spdk_jsonrpc_end_result'
It probably works on gcc, because the bdev_nvme_get_mdns_discovery_info
isn't called anywhere in the unit test and gets optimized away.
Fixes#2950
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I2bb856afbc1a1a7e882dec72e4182ad9d3b9b24a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17260
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
It fixes the following error under clang:
/usr/bin/ld.bfd: vfio_user_ut.o: in function `nvmf_transport_create_async_done':
/home/ksztyber/src/spdk/lib/nvmf/transport.c:203: undefined reference to `spdk_mempool_lookup'
It probably works on gcc, because the nvmf_transport_create_async_done
isn't called anywhere in the unit test and gets optimized away.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I497aae4d211d556a531455481ee9a69067988cce
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17259
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
There's no reason to check the OS to decide whether to build some unit
tests if we can rely on the configure parameters. For instance, on
FreeBSD, RDMA unit tests can be built and run successfully, while vhost
is always disabled in configure.
Fixes#2941.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I0073783dcafa932f3a7f48fa553e04be7ae44f84
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17182
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
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>
Community-CI: Mellanox Build Bot
When an esnap clone blob's external snapshot arrives after the blob is
opened, it can now be hot-added to the blob. Presumably the new device
replaces a place-holder device that did not really atteempt IO.
Change-Id: I622feb84efa66628debf44f7e7cb88b6a012db6d
Signed-off-by: Mike Gerdts <mgerdts@nvidia.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16232
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
To avoid races that lead to use-after-free errors during esnap device
hot add/remove, we need a way to ensure that the destroy callback does
not free a bs_dev until all consumers are done.
This adds reference counting to the create_channel() and
destroy_channel() callbacks. The reference couunt is initialized to 1
and is decremented by destroy(). The destroy() and destroy_channel()
callbacks are updated to free the bs_dev only when the reference count
drops to 0.
Signed-off-by: Mike Gerdts <mgerdts@nvidia.com>
Change-Id: Ie0b873717e431b33ce6548f878643dbc66d4f956
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16422
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
As the blobstore is being unlaoded, async esnap channel destructions may
be in flight. In such a case, spdk_bs_unload() needs to defer the unload
of the blobstore until channel destructions are complete.
The following commands lead to the illustrated states.
bdev_malloc_create -b malloc0
bdev_lvol_clone_bdev lvs1 malloc0 eclone
.---------. .--------.
| malloc0 |<--| eclone |
`---------' `--------'
bdev_lvol_snapshot lvs1/eclone snap
.---------. .------. .--------.
| malloc0 |<--| snap |<--| eclone |
`---------' `------' `--------'
bdev_lvol_clone lvs1/snap eclone
.--------.
,-| eclone |
.---------. .------.<-' `--------'
| malloc0 |<--| snap |
`---------' `------'<-. .-------.
`-| clone |
`-------'
As the blobstore is preparing to be unloaded spdk_blob_unload(snap) is
called once for eclone, once for clone, and once for snap. The last of
these calls happens just before spdk_bs_unload() is called.
spdk_blob_unload() needs to destroy channels on each thread. During this
thread iteration, spdk_bs_unload() starts. The work performed in the
iteration maintains a reference to the blob, and as such it
spdk_bs_unload() cannot do its work until the iteration is complete.
Change-Id: Id9b92ad73341fb3437441146110055c84ee6dc52
Signed-off-by: Mike Gerdts <mgerdts@nvidia.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14975
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This adds support for inflate and decouple for esnap clones. Since there
are no immediate consumers that will provide back_bs_dev->is_zeroes()
that can return true, a shortcut is taken in that inflate and decouple
of esnap clones are the same.
Signed-off-by: Mike Gerdts <mgerdts@nvidia.com>
Change-Id: I4d2e6565126991acd650f073ce876466334e986d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11574
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
An esnap clone needs special handling as snapshots are created and
removed. In particular: the following must exist on the blob that
directly references the external snapshot and must be removed from
others:
- Ensure SPDK_BLOB_EXTERNAL_SNAPSHOT invalid flag exists only on the
esnap clone.
- Ensure BLOB_EXTERNAL_SNAPSHOT_ID internal xattr exists only on the
esnap clone.
- Clean up any esnap IO channels on a blob that is no longer an esnap
clone due to snapshot creation or removal.
See the diagrams and description in blob_esnap_clone_snapshot() in
blob_ut.c for details.
Signed-off-by: Mike Gerdts <mgerdts@nvidia.com>
Change-Id: Ie4125d64d5bac9cfa7d6c7cc9a543d72a169f6ee
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11573
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
The channel passed to blob IO operations is useful for tracking
operations within the blobstore and the bs_dev that the blobstore
resides on. Esnap clone blobs perform reads from other bs_devs and
require per-thread, per-bs_dev channels.
This commit augments struct spdk_bs_channel with a tree containing
channels for the external snapshot bs_devs. The tree is indexed by blob
ID. These "esnap channels" are lazily created on the first read from an
external snapshot via each bs_channel. They are removed as bs_channels
are destroyed and blobs are closed.
Change-Id: I97aebe5a2f3584bfbf3a10ede8f3128448d30d6e
Signed-off-by: Mike Gerdts <mgerdts@nvidia.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14974
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Also, drop some code that's essentially not needed to improve
readability.
Change-Id: I5fda1c179983ce905661918e6f821eca486bb58d
Signed-off-by: Michal Berger <michal.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17218
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Try to create virtio blk transport. Transport is
created at application start, so EEXIST error is
expected.
This is aimed purely at using
rpc_virtio_blk_create_transport() from vhost_rpc.c
to increase code coverage.
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: Iba87ef73f8d5a962bf5eac28c7e6c93bdb65b67f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16436
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
On FreeBSD spdk_uuid_parse() will fail if the UUID doesn't have the
variant/version fields filled in correctly. So, use a proper UUID in
the test to make them pass on FreeBSD.
Fixes#2942.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I7c5384086c6828c7380f9d128878578301077b17
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17184
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
As per https://github.com/DPDK/dpdk/commit/71998eb61ff
Change-Id: Ie4e5a38976145e1037ef45593b4dc4265091482d
Signed-off-by: Michal Berger <michal.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17322
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Pawel Piatek <pawelx.piatek@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The change in question is already available upstream.
Change-Id: I26a641f8314a3292d57124056ac197e1f861685d
Signed-off-by: Michal Berger <michal.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/17321
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Pawel Piatek <pawelx.piatek@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
