3566 Commits

Author SHA1 Message Date
Shuhei Matsumoto
e5c6b9c761 iscsi: turn <add/delete name&mask of IG> into functions
Group the code fragments of add/delete name and mask of initiators
and create spdk_iscsi_init_grp_add/delete_initiators/netmasks()
functions. Memory alloc/free is done in these functions.

Change-Id: I40f2873c5336a05813c0e34797c109386eda4229
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/381246
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
2017-11-03 14:08:47 -04:00
Shuhei Matsumoto
e5f7f8ba4a iscsi: delete spdk_iscsi_init_grp_destroy_by_tag()
This function is not used and there is already similar one.
Hence delete this function.

Change-Id: Iff290c4762cf5da7211382e367e5b137ab8fbf7d
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/381245
Reviewed-by: John Kariuki <John.K.Kariuki@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-11-03 14:08:47 -04:00
Jim Harris
11bd19c80c iscsi: remove global data members for non-configurable parameters
FirstBurstLength, MaxBurstLength and MaxRecvDataSegmentLength
cannot be configured, so there is no need to keep global data
members for these parameters - just use the default #defines
instead.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I4b47e00a5594da8ec0b87192be4a23c4a2145bde

Reviewed-on: https://review.gerrithub.io/385490
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>
2017-11-03 12:18:02 -04:00
Jim Harris
ed2f2d9d0e iscsi: remove configuration for unsupported parameters
Our iSCSI target does not support disabling InitialR2T,
DataPDUInOrder and DataSequenceInOrder, and will fail
if someone tries to disable them in the config file.

So instead, just do not support these parameters at all.
This simplifies the code and reduces confusion.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Icf1e01a6d12b758404769f77aa3f6221e6e3ee0d

Reviewed-on: https://review.gerrithub.io/385489
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
2017-11-03 12:18:02 -04:00
Jim Harris
cce7b3078d iscsi: remove global MaxOutstandingR2T parameter
This was not used anywhere - sessions default to
DEFAULT_MAXOUTSTANDINGR2T and never look at the global
MaxOutstandingR2T value.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ia4874d8d747063f729061124194b60d15ad3ddac

Reviewed-on: https://review.gerrithub.io/385488
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
2017-11-03 12:18:02 -04:00
Maciej Szwed
c40524fb81 unit/lvol: fix uuid setting in unit tests
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I868c3620edc13309d603cd29effa8e0a62788495

Reviewed-on: https://review.gerrithub.io/385411
Reviewed-by: Jim Harris <james.r.harris@intel.com>
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>
2017-11-02 14:13:03 -04:00
Maciej Szwed
ea22acd559 lvol: read lvols names on lvol store tasting
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I2077dab7b343e662bdcfd5681b4850c258f0431f

Reviewed-on: https://review.gerrithub.io/385406
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2017-11-02 13:59:48 -04:00
wenzhong wu
5069496ddc test/nvme: Add perf with AIO devices
Change-Id: I6507db2d3ea7276b9f204e68cbe0185110a5345c
Signed-off-by: wenzhong wu <wenzhongx.wu@intel.com>
Reviewed-on: https://review.gerrithub.io/384403
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>
2017-11-01 19:46:24 -04:00
Daniel Verkamp
c45021a194 autotest.sh: load block RAM disk module
This provides /dev/ram0 when available so that we can have a convenient
blcok disk to test the Linux AIO backend against.

Change-Id: I557dae4dcba918838f55f85cd5981922d765d40e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/385297
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2017-11-01 19:46:24 -04:00
Ziye Yang
43727fb7e5 nvmf/rdma: Add the buffer size check for data_buf_pool
Change-Id: I65e84971f2d55f27b0c0c1a1b226fc4da4b3cf89
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/382763
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-11-01 15:45:35 -04:00
Daniel Verkamp
eec7e868b3 version: v18.01-pre
Change-Id: Id3ccec9f5d77d4125b9ef70e286caac83a0ac2fe
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/385159
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-10-31 18:28:21 -04:00
Daniel Verkamp
8bbd56fb64 doc: enable Doxygen tree view navigation
This requires an override of Bootstrap's default box-sizing: border-box
on the nav bar elements so Doyxgen's tree view layout isn't broken.

Change-Id: I38d1df10fef8d90e245bbd880cf85686c1aee470
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/384382
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2017-10-31 18:00:12 -04:00
Daniel Verkamp
8ccfe74abc SPDK 17.10
Change-Id: I3842b654167345326979177ffdf3d10a33fae70c
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/385145
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
v17.10
2017-10-31 17:14:58 -04:00
Isaac Otsiabah
ce18c1f121 RPC: Add rpc support to update firmware.
Modified the above files to add rpc support to update NVMe firmware. Currently,
the path parameter must be local to the RPC Server.

Change-Id: I2b14e37792a2f0a5759e8b13e21137e7f346e58e
Signed-off-by: Isaac Otsiabah <iotsiabah@us.fujitsu.com>
Reviewed-on: https://review.gerrithub.io/369083
Reviewed-by: Paul von Stamwitz <pvonstamwitz@us.fujitsu.com>
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>
2017-10-31 12:49:31 -04:00
Daniel Verkamp
872fdc8e41 bdev/virtio: check if unmap is supported via VPD page
As part of the SCSI target scan, request the Block Thin Provisioning VPD
page to determine if the target device supports Unmap, and report it via
the io_type_supported bdev callback.

Change-Id: Id2fdaf3a2cae72e6356a862d40ff772f9d12d144
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/384131
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
2017-10-30 12:17:50 -04:00
Daniel Verkamp
5304beccd3 bdev/virtio: move scan results into a structure
This prepares for adding more steps to the scanning phase.  Each step
will put its results into the scan info struct, and the final
alloc_virtio_disk() call will copy the info to the allocated disk at the
end of each target scan.

Change-Id: I836ada42e25c817bb1998328cb592acac25be08d
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/384130
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
2017-10-30 12:17:50 -04:00
Daniel Verkamp
b3781b227b blobcli: add bstype to blobstore info
Change-Id: Ib4fe119d42db943fd5b7f52836358a01cb4bc03f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/383639
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-29 16:06:29 -04:00
Daniel Verkamp
5b9f0ddc53 scsi: use scsi_spec.h enums for VPD page numbers
Change-Id: I9783803a2f1ce5bb16d9336f7fecbd4f06dcdd52
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/384136
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-29 12:12:47 -04:00
Lukasz Galka
d88fa70e58 test/lvol: update test plan with tasting test
Postivive test case for testing lvol tasting feature.

Change-Id: Ifa8b87978e40a719ca59603cfd41a8fd1b22c6f9
Signed-off-by: Lukasz Galka <lukaszx.galka@intel.com>
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/382687
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-27 15:42:47 -04:00
Piotr Pelplinski
511adde02f lvol: add lvs name in rpc calls
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: Ic6770371d9d62cbdd40ae0612eb4f7dceccd507f
Reviewed-on: https://review.gerrithub.io/383771
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
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>
2017-10-27 13:10:21 -04:00
Piotr Pelplinski
e5b0dd6ead pmem: bdev names for pmem bdevs
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: Ifbb02f99cd2e5752b2bc9091733b87ddadec11a4

Reviewed-on: https://review.gerrithub.io/383895
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-27 13:10:07 -04:00
Dariusz Stojaczyk
5447fb12a9 bdev_virtio: fix scan inquiry alloc_len
Some devices expect alloc_len
to be the same as payload len.

Kernel vhost-scsi reports:
Expected Transfer Length: 256 does
not match SCSI CDB Length: 255 for
SAM Opcode: 0x12.

Change-Id: I499290c207b77be6757441da002f9fcc9eebcecd
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/383779
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-27 13:07:25 -04:00
Dariusz Stojaczyk
cfa668375b bdev_virtio: retry sending scan requests
Scan requests will be re-sent
if non-critical failure has
happened.

This is actually required, as
some Virtio SCSI devices require
a dummy request to clear it's
POWER ON OCCURED unit attention
status after Virtio device init.
The very first request might fail
with asc = 0x29 (POWER ON, RESET,
OR BUS RESET OCCURED), but
subsequent requests will be
processed correctly.

Change-Id: I809bfe7952062995078f33dccb92192d722e6574
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/383689
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>
2017-10-27 13:07:25 -04:00
Tomasz Zawadzki
fde584034d lvol: give EEXIST error code on lvs name conflict
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I1df83cbd6414a1bb8f54328c735950b9476e323b
Reviewed-on: https://review.gerrithub.io/384105
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Piotr Pelpliński <piotr.pelplinski@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-27 13:07:09 -04:00
Pawel Wodkowski
ff1863f428 vhost: interrupts coalescing
Virtio spec say that any IRQ requests are only hints. So try to limit
number of interrupts generated by vhost by defining minimum interval
between sending IRQ. Coalescing is disabled by default. Can be enabled
using RPC command 'set_vhost_controller_coalescing'.

Change-Id: I9b96014d004ea0ea022b4498c6b47d30d867091a
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/378130
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>
2017-10-27 13:06:40 -04:00
Pawel Wodkowski
fb0b17a19f test/vhost: always print command output
In case of error the message is command output and is confusing:

	ERROR! While executing FIO jobs - RC: 1, Err message:
	hostname=VM-11-0xC0000000, be=0, 64-bit, os=Linux, arch=x86-64,
	fio=fio-2.2.10, flags=1
	19:04:59 hostname=VM-10-0x30000000, be=0, 64-bit, os=Linux,
	arch=x86-64, fio=fio-2.2.10, flags=1

So change this to always print command output then error message.

Change-Id: Iee4b25a00438c153a0d4d250ae43fc0d283faf33
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/383596
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-27 13:06:40 -04:00
Pawel Wodkowski
d02bfbd3af test/vhost: print backtrace in failure handler
Change-Id: Ic42b54ba502259b73b8110d75dd5ab032f1f0928
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/383490
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-27 13:06:40 -04:00
Pawel Wodkowski
a30865f142 autotest_common.sh: use full file path in backtrace print
If $rootdir is not set then '.' is prepended to the path of source file
on stack frame. Use unmodified "${BASH_SOURCE[$i]}" to fix this.

Change-Id: Ib927db9a4e56320fea73ca1b76b8f58730a9ae5f
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/383801
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>
2017-10-27 13:06:40 -04:00
Seth Howell
8bfcbf0c8a rdma: in qpair_destroy, free recvs struct array
Fixing a memory leak.

Change-Id: I410986bb9d73818b0dd141a24a28a81a37bd8937
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/384109
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-27 13:06:21 -04:00
Pawel Kaminski
bd34b7d9bb test/vhost: Fix write with verification.
Change is needed because fio job (trim_write_read)
submits unmap first and then write,
but sometimes write finishes before unmap.
It casues that write fails with verification.

Nvm Express 1.3:
"The controller fetches SQ entries in order from the Submission Queue,
however, it may then execute those commands in any order. "

Change-Id: Ia399e5677051c2e2077fe3082ede846a8ac9dd49
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/383436
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-27 13:06:03 -04:00
Tomasz Zawadzki
11104c1c85 fio_plugin: add back bdev and copy engine finish
During SPDK asynchronous finish cleaning up of bdev and
copy engine was removed. Now it is added back taking
into account asynchronous nature of those two calls.

Only when spdk environment was initialized, on fio_exit
SPDK environment is cleaned up. Similar to init path,
this is done in temporary SPDK thread.

When in here, fixed fio_thread->iocq memleak.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I4558af4539dd2617d17aeda9b568b697ea54ff44
Reviewed-on: https://review.gerrithub.io/383731
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-27 13:03:55 -04:00
Tomasz Zawadzki
6c54c13cd4 event/subsystem/bdev: asynchronous SPDK finish
First this change moves spdk_subsystem_fini() to trigger on
spdk_app_stop(). This ensures that spdk_subsystem_fini() is called
before reactors are stopped in spdk_reactors_stop().

Finish paths for subsystems, bdevs and copy engine is now
asynchronous.
Each of those three mentioned have to make sure they are
asynchronous as well.

Only bdev that currently has requirement for asynchronous finish
are logical volume.
Thus the change in vbdev_lvol.c making it move to next bdev module
only after all lvol stores were unloaded.

Fio_plugin finish of bdev and copy_engine was removed for now.
Next patch in series adds it back with async support.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I80ee2d084f3d82c50bf1329e08996604ae61b1b3
Reviewed-on: https://review.gerrithub.io/381536
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>
2017-10-27 13:03:55 -04:00
Dariusz Stojaczyk
071cc42c7b bdev_virtio: remove internal README.md
The *TODO* section was outdated. Most of
this README's contents have been already
moved to doc/virtio.md and doc/bdev.md.

Change-Id: I2f2108afdc543276c9f08ae053ccebdbd6b1a229
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/384054
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-27 11:02:48 -04:00
Pawel Kaminski
29d4d1de08 test/vhost: Fio test for vhost initiator for nvme disk larger than 4G.
Change-Id: I3a017612dcadd519cfd427ba43450fa4d54edfce
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/381150
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-10-27 08:46:06 -04:00
Tomasz Zawadzki
9583e73901 lvol: remove lvs from global list after callback
Inserting into g_spdk_lvol_pairs list is done in vbdev_lvs_create_cb,
at that point it is known that it can be used. Meanwhile removing
was done at start of _vbdev_lvs_remove, to prevent possibility to
access it when waiting for destruct callback to complete.

This made checking if the g_spdk_lvol_pairs list is empty unreliable
to detect if all lvs were destroyed - they could still be being
processed and callback not yet called.

This patch removes lvs from global list only after the callback of
_vbdev_lvs_remove is called.

It will be used in future patch during asynchronous
finish of vbdev module to determine when all lvs were removed.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I638fe63a80b3cf00e9773f5a8c7be315d2c05555
Reviewed-on: https://review.gerrithub.io/382986
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-26 17:23:58 -04:00
Tomasz Zawadzki
2196023bc7 lvol: consolidate vbdev_lvs_unload and vbdev_lvs_destruct
To avoid code duplication those two functions were merged.
New _vbdev_lvs_remove function deals with differences by
additional argument "destroy".

No functional difference should be observed after this patch.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I09067646ec9b9656f361077c54906a618e4e0c48
Reviewed-on: https://review.gerrithub.io/383908
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-10-26 17:23:58 -04:00
Tomasz Zawadzki
ebf0312eef lvol: Add vbdev_lvs_destruct() and change unload behaviour [3/3]
This patch adds new API to remove logical volume store
from device it is on. It is only used from RPC, when
user explicitly requests. It allows to use the device to
use as any other bdev.

vbdev_lvs_unload() is now only called from hotremove and
during application shutdown. Which makes it possible to
load it again during application start up.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: If6452ecc3fff99237d1704ff7cd8de4d7133221d
Reviewed-on: https://review.gerrithub.io/382021
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-26 17:23:58 -04:00
Daniel Verkamp
d189b8eedd blob_bdev: add unmap -> write_zeroes fallback
If the bdev doesn't support unmap, we should not send unmap I/O.
Instead, use spdk_bdev_write_zeroes(), which has a fallback in the bdev
layer for devices that don't natively support it.

Change-Id: I1bd05d3518716f8e60501dbb4f9da0fee23cf7c2
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/383491
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-10-26 17:23:58 -04:00
Maciej Szwed
e68e2e749b lvol: do not unload/destroy lvs when operation on lvol is pending
There is a scenario where we can try do unload or remove
lvol store while lvol present on that lvol store is being
closed or destroyed.

Scenario:
1. send delete_bdev rpc command
2. command returns before lvol is actually closed/destroyed
   (does not wait for callback)
3. send destroy_lvol_store rpc command
4. lvs is destroyed before lvol is destroyed
5. lvol destroy callback is called on destroeyd lvol store

Aboive scenario can be reproduced using:
spdk/test/vhost/spdk_vhost.sh --integrity-lvol-scsi

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ie715279195bd4b1145cf05d4f5a8477b4fac87f7
Reviewed-on: https://review.gerrithub.io/383595
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-26 17:23:58 -04:00
Maciej Szwed
2baeea7dd4 bdev: add callback to spdk bdev unregister and bdev destruct
Currently deleting bdev does not support asynchronous delete
operations. Because of that results are returned before device
is actually deleted and some operation can be peformed on that
device after removal of this device started.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I305c302d8abd5d7c2c0f947fca70c58396872132
Reviewed-on: https://review.gerrithub.io/383732
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-26 17:23:58 -04:00
Liang Yan
32b35d9958 nvme/perf: check if aio files exist while no NVMe controller found
Change-Id: I9ced263535e8cd9c9503a208a77832140833c9d3
Signed-off-by: Liang Yan <liang.z.yan@intel.com>
Reviewed-on: https://review.gerrithub.io/383952
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-26 15:41:50 -04:00
Dariusz Stojaczyk
a17d431612 bdev_virtio: fix setting name for modern pci devices
It used to be NULL.

Fixes: a85a4452
("bdev_virtio/rpc: add construct_virtio_user_scsi_bdev")

Change-Id: I490b41571e5667cf95b59b2e316006d1ef7381e8
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/383892
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-26 15:09:57 -04:00
Piotr Pelplinski
d17345183e lvol: updated documentation.
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I566a4d277ac1595fa7b4d630df52301a9abeec49
Reviewed-on: https://review.gerrithub.io/381629
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-26 15:04:27 -04:00
Piotr Pelplinski
9d17cbdd23 blob: fix bug when specifing cluster size < 4096
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I59cbef4ce1bfe8af113c66c2c9cb9f208440c0aa

Reviewed-on: https://review.gerrithub.io/383887
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-26 14:21:22 -04:00
Karol Latecki
957ebeb506 test/vhost: remove read tests from vhost initiator
Removing read and randread from test runs as read operations are
performed as part of write with verify enabled tests.

Slight code cleanup included.

Change-Id: Ia3b92ed16cf4c1b873d0f54a0c0677c52f9b726a
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/383770
Reviewed-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
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>
2017-10-26 14:08:21 -04:00
Pawel Kaminski
b84cf820af test/vhost: Test Plan for vhost initiator.
Change-Id: I51a45ef1d94de6324744af7801b59a6b73578dd2
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/377563
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
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>
2017-10-26 14:07:59 -04:00
Pawel Wodkowski
a85a4452f3 bdev_virtio/rpc: add construct_virtio_user_scsi_bdev
Change-Id: I2a351442ead0874d98bdfb23079a723d7665dbb1
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/381186
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-25 18:31:56 -04:00
Daniel Verkamp
d822c2055e rte_virtio: check payload size in vhost_user_read
Make sure the recv() can't write beyond the end of the msg buffer.

Change-Id: Ibc4bb51ac3a1c2a027a458d59356b7a5496eca7e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/383646
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
2017-10-25 18:30:18 -04:00
Daniel Verkamp
22077b210b rte_virtio: use size_t/ssize_t in vhost_user_read
Use the correct size types (rather than int) for values passed to and
returned from recv().

Change-Id: I2d38eed63e2d9c9f056d1053e156088fd361c88b
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/383645
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
2017-10-25 18:30:18 -04:00
Jim Harris
e6d053e78a lvol: add lvol unique name
Add a name to each lvol which is persisted as a blob
xattr.  lvol names must be unique within its
lvolstore.

While here, fix a few lvol_ut issues that were caught
as part of testing the lvol unique names.  Also fix
a couple of tests that registered the wrong string
name with CUnit.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I6d24d241e8f52158d14886f928d41823bbc93fa9

Reviewed-on: https://review.gerrithub.io/383567
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-25 12:10:38 -04:00