Added new keyword 'Target' that will replace 'Dev'.
'Dev' is still usable, but deprecated and will be removed.
Change-Id: Iafd6114ef2cc5b2f8d58497e9fb454a3a237ed16
Signed-off-by: Sebastian Basierski <sebastianx.basierski@intel.com>
Reviewed-on: https://review.gerrithub.io/388568
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Multiple nbd disks can be enabled by it. These
created nbd disks can only be running on app start
core at present.
Stop running spdk_nbd_disk by nbd subsystem_fini
Example nbd start rpc request:
{
"jsonrpc": "2.0",
"id": 1,
"method": "start_nbd_disk",
"params": {
"bdev_name": "AIO1",
"nbd_device": "/dev/nbd1"
}
}
Change-Id: I426a10e2fe709f1862e44a7b75318ccb83517b3e
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/390344
Reviewed-by: Changpeng Liu <changpeng.liu@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>
Record multiple nbd-disks by linking them into
g_spdk_nbd. Multiple nbd-disks cat be created or
stopped by upcoming nbd RPC.
Change-Id: I868d07d33981c94c1f06a1b31cf55e91d9df4fa8
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/390170
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>
Upcoming nbd RPC functions need to track nbd_path.
Export spdk_nbd_disk's nbd_path and bdev_name by
short functions, and list these functions into
nbd_internal.h
Change-Id: I0ca021a5c83e860ad7513b89c9c7783722ab875a
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/390343
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Add g_spdk_nbd to record multi-nbd-disk in the
future. nbd subsystem will be used to init and
finish g_spdk_nbd and its linked spdk_nbd_disk.
Change-Id: Ia67caa57b9920d0080f8b2fa1c8e87615803e5fe
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/390097
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
nbd poller is put into spdk_nbd_disk.
nbd test app no longer needs to process spdk_bdev.
This enables upcomming patches to move nbd test app
functionality to SPDK library.
Change-Id: I1b563a49dc9488e8dcc20706be82b17fdbd07ff1
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/390093
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>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ie7a6513d45652d4a6420ac52b5ded39581d688c6
Reviewed-on: https://review.gerrithub.io/388944
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
In principle, we should not have active tasks, which means
that lun->tasks should be empty. But for the exceptional case,
we may still need to handle those active tasks, to make
the scsi related application continue running instead of quit.
We should not directly call spdk_scsi_lun_complete_task since
those tasks are already sent to bdev layer. And finally, those
tasks will be return (even aborted) by call backs. So we only need to
set task status to condition, but
not call spdk_scsi_lun_complete_task directly.
Change-Id: I6af2bda0f0b1de7b0c655d2ac2980ddca48c1162
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/386817
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Struct spdk_scsi_lun has the claimed flag as a member.
However the claimed flag is no longer required.
Moreover the claimed flag itself is not used but
spdk_scsi_lun_claim() and _unclaim() functions are used in the
UT code by hard to understand manner. Moving the logic into
spdk_scsi_lun_construct() and _destruct() in the UT code will
be more natural.
Hence remove the claimed flag from LUN and do a little refactoring
in the UT code.
Change-Id: Ica9680b49bbdb5be7c5c4161210fb3a6dcb35229
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/390566
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>
Based on the PG-IG map tree implmentation, the following new
JSON-RPC commands are supported:
- add_pg_ig_maps
- delete_pg_ig_maps
Change-Id: Iebc48e379aa8e06b5e7d57935845d6fd53f7f826
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/379936
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>
This patch add the internal mechanism to add/remove PG-IG maps
to/from an existing iSCSI target.
Next patch will add new JSON-RPC commands and python scripts.
Change-Id: Ib75d180197c5cb679ebfd21324dc36790b50a7aa
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/389667
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>
In iSCSI specification RFC7143, there is the following description
in the section 7.13:
All violations of iSCSI PDU exchange sequences specified in this
document are also protocol errors.
Any protocol error should be handled as iSCSI Reject response whose
the reject reason is Protocol Error.
However current implementation handles a minor PDU error as Drop
connection. This is too severe and change the code from Drop
connection to Reject response.
This issue was detected by libiscsi test suite.
Change-Id: Ie85c56f5dd523445530ec1ff71eda4f594ab73a0
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/389941
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Currently even if PG mapping is removed from iSCSI target,
corresponding SCSI port is not removed. Hence dynamic
reconfiguration of PG to existing iSCSI target is not supported.
This patch supports dynamic SCSI port removal when the
corresponding PG mapping is removed from the existing target.
Some refactoring for SCSI port addition is also done
Change-Id: Ib06bc10743eb088d023f425742e39bb24f1b0df1
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/389056
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Disambiguate the log components from the trace functionality
(include/spdk/trace.h).
The internal spdk_trace_flag structure and related functions will be
renamed in a later commit - this is just a find and replace on
SPDK_TRACE_* and SPDK_LOG_REGISTER_TRACE_FLAG().
Change-Id: I617bd5a9fbe35ffb44ae6020b292658c094a0ad6
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/376421
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
MaxQueueDepth is configurable for NVMf target by configuration
file. This patch makes this flexibility possible for iSCSI target
too. Increasing macro-defined constant for MaxQueueDepth consume
extra memory regardless of the necessity and hence it may be
better to avoid that.
Change-Id: I7fa9cf86b02c5a8b16411d4b4d356c6e6c0dc3eb
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/388552
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>
Change-Id: I8b77f8aa8e20a277d0a5e53688d7cef8674d6244
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/390497
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>
Move some of the code out of the function and rename it
to spdk_nvmf_rdma_qpair_initialize. In the future, the
operations left in initialize will end up being
deferred until the qpair is assigned to a poll group.
However, for this patch there is no functional change.
Change-Id: I0f64489ffbf1f8957358d3b1781acc430b77717c
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/389650
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>
All TCP socket operations in iSCSI should go through
functions defined in sock.c.
Two close() calls did not, so they are fixed in this patch.
Change-Id: Ia5a87fd4085eb5b7e6732dc7a505e19994669a7e
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/390568
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>
NVMe specification 1.3 added a new Admin command: Doorbell buffer config,
which is used to enhance the performance of host software running in
Virtual Machine, and the Doorbell buffer config feature is only used
for emulated NVMe controllers. There are two buffers: "shadow doorbell"
and "eventidx", host software running in VM will update appropriate
entry in the Shadow doorbell buffer instead of controller's doorbell
registers.
Change-Id: I639ddb5b9a0ca0305bf84035ca2a5e215be06b46
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/383042
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>
The function just needs to zero out metadata so that the
blobstore is effectively destroyed. If the user wants
to unmap the rest of the disk after the blobstore is
destroyed, they are free to do so. On future initializations
of blobstores the code will do the unmapping, so performance
is not impacted.
While here, implement the zeroing using the new
write_zeroes functionality instead of allocating a buffer
full of zeroes.
Change-Id: I7f18be0fd5e13a48b171ab3f4d5f5e12876023bc
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/390307
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>
Unmaps are only used within blobstore to improve device performance,
never to zero blocks. Therefore, if the device does not support
unmap, just skip it instead of writing zeroes.
This is different than devices that elect to implement the write
zeroes command as an unmap because they will return 0 for
subsequent reads. That optimization is still in effect.
Change-Id: Ie1bf98fe86d73b4ac40b41c0d2804db325716500
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/390306
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>
This patch just make sure SPDK support the hotplug of vfio-attached devices,
but there still issues when we get hotplug events from kernel, this patch tested
based on my modified local vfio-pci driver which just for test purpose and not upstream.
Change-Id: I974177e70e4133d2a583d00e714a7607765d3548
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/390580
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>
Change-Id: I054b0f20fa502f30ae3802f95ef108fc92132ff5
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/390558
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I927d659c93787f7ff15cb5aeb2a1c00d3e90e68a
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/390514
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>
This distinction was required to
be able to check if device has been
scanned already. However, with the
upcoming eventq support it will
be possible to re-scan the device
at any time. We could move the
vdev back and forth between the
lists, bu now that SCSI devices have
their own virtio_scsi_dev struct,
we can remove this distinction and
check the scan status from within
the struct itself.
Change-Id: If57e7ce4b9ce900aa36a5aeba9e4b4a432d3c757
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/390109
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>
Virtio-SCSI devices now have their
own structs. This patch introduces
only the struct, no functionality
has changed.
Change-Id: I04907497ed173747875e1b67acad38043bf4de09
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/390108
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>
Cleaned up and expanded documentation
of virtio bdev module.
Change-Id: I4b989ed8b4d5e0bc66c0f0706e61219daf4e2869
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/390107
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>
Change the command-line -r option to take precedence over the [Rpc]
section of the configuration file.
Change-Id: I6f043bafaa8b0ede10dd8a483ca77ad34ff7639a
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/390329
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
The config_text callback should only add a [Rpc] section if an
address is configured.
This avoids printing out a bogus configuration file
section with "Listen (null)".
Change-Id: Ibb734f6faab4c2587203623eee8a193f9a7207ba
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/390328
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Added virtio_pci_dev_init, an equivalent to
virtio_user_dev_init. It takes an opaque pci
context pointer that is provided via virtio
PCI enumerate API.
virtio_pci will do only PCI-related
initialization. The virtio_dev creation
and SCSI-specific logic now belong to upper
layers
Change-Id: I7ad450591f893c4ab953c09cfb6441b186736751
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388302
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>
Change-Id: I3cbb52cd9a4201704423b49eae74935b8a33b0fd
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/389903
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Some places used the convention 'rqpair' and others
'rdma_qpair'. For consistency, name them all 'rqpair'.
Change-Id: I131833d14efdfdbcbb99bea5d64cbcf99d9ec90b
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/389649
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>
Change-Id: I9afa07b5dae99955ba87d7c8130b2ce6f04e7941
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/389641
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>
There is a 1:1 correspondence between the two, but it is much
more useful to have a pointer to the poll group.
Change-Id: I8494b0573a9b2cce5819545548d0c65a18bdbe86
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/389640
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>
These aren't used quite yet, but they'll need to be called
by the user's application.
Change-Id: Id1fc44859350451a3e224f725add60d3a878d077
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/389639
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>
There isn't a way to remove a namespace just yet, but at least
adding one works.
Change-Id: I99416d1bc9cbc0e2303c16040d2311a07829cbea
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/388293
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>
This allows the to use a virtio_dev allocated as
a part of bigger struct - possibly a SCSI/BLK
specific wrapper.
As a part of this refactor, multiple vdev-related
functions have been renamed to keep the API clean.
Change-Id: If84bf03e4a1642869c2f1ba93939fb32c8fb5d57
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388298
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>
Tested with bdevio, hardcoded TUR response to test the start/stop
unit code
Change-Id: I5038e6bcce9fcd423f1b93c8bb8b466ee3817654
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/387183
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I4966d19b06d37bbcf4527cbd9c206e9a553e8fd2
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/390083
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: Jim Harris <james.r.harris@intel.com>
This patch is a preparation for dynamic reconfiguration of PG-IG maps.
Current PG-IG map is implemented by a fixed-size array. Linked list
will make much easier to support dynamic reconfiguration of PG-IG maps.
Current:
target - (1..n) ---> PG_map (1..1) -> PG
|
--> IG_map (1..1) -> IG
This proposal:
target - (1..n) -> PG_map --- (1..1) -> PG
|
-- (1..m) -> IG_map - (1..1) -> IG
Change-Id: I92f668b81cdd8003aff222926f8f1ed96b61e56d
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/385532
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Similar flags will be added at the blobstore level in a future
patch.
This allows backwards compatibility - i.e. allow older blobstore
applications to open blobstores created by newer blobstore
applications with new features. Any blob's using a new feature
should have an associated flag set in one of three new flag masks:
- invalid: if a bit is set in this mask that the application is not
aware of, do not allow the blob to be opened
- data_ro: if a bit is set in this mask that the application is not
aware of, allow the blob to be opened, but do not allow
write I/O nor any operation that changes metadata
- md_ro: if a bit is set in this mask that the application is not
aware of, allow the blob to be opened for performing any
kind of I/O, but do not allow any operation that changes
metadata
While here, bump SPDK_BS_VERSION to 3. We intend this to be the
last change made to SPDK_BS_VERSION - future versioning will be
done via blobstore or per-blob feature flags instead.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: If059e38bfffbeec25c849a7629a81193b12302c4
Reviewed-on: https://review.gerrithub.io/388703
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>
Some nbd io type has no payload, like NBD_CMD_DISC.
Change-Id: I17babf625f51d32bf07fa7a9b6a7396660b39cd5
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/389779
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
By supporting the management based on linked list for PG and IG
the group state of PG and IG are no longer necessary.
Change-Id: I249424cacd2d27dda4e4cb2182442d0d1e9bfb8e
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/388863
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Current fixed sized array for iSCSI target is not thread safe.
When newly created targets are inserted into the array, multiple
targets may be inserted into the same position. Linked list is
better than fixed size array to support dynamic reconfiguration.
Change-Id: I4db5a3ec16844db06e0cfcd2aef1f97952f15afa
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/385371
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
The results of access control procedure for login in the
spdk_iscsi_tgt_node_access() is defined in the following table:
+------------------------------+
|iscsi name |netmask |result |
+------------------------------+
+------------------------------+
|denied |- |denied |
+------------------------------+
|allowed |allowed |allowed |
+------------------------------+
|allowed |denied |next IG |
+------------------------------+
|not found |- |next IG |
+------------------------------+
However current implementation have redundant repetition in the
spdk_iscsi_tgt_node_access() and the above definition is not
visible. Hence refactor spdk_iscsi_tgt_node_access().
Besides refactor spdk_iscsi_tgt_node_allow_iscsi_name() because
it has redundant repetition too.
Add UT code for these changes.
Change-Id: If06d87c1246c85439ee0482149bd887a7b53b169
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/379935
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>
Naming rule of access control of iSCSI target does not reveal its
intention. Hence change it before refactoring to avoid unnecessary
repeated procedure.
Change-Id: I4064ec0a5a2b52244b6de3958ee2ab41342d1a57
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/381248
Reviewed-by: Jim Harris <james.r.harris@intel.com>
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>
In the accessibility control of iSCSI target, "ALL" is used to allow
ANY IP address-port pair or iSCSI name of initiators. However iSCSI
targets cannot know ALL initiators beforehand.
Hence "ANY" will be better than "ALL" and will avoid misunderstanding.
Comments and iscsi_tgt test code are also changed and UT code is added.
Change-Id: Id004d819df6e9ee89f6c1db2e4b4c149be062733
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/385168
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Althrough the two functions are empty now, but they are not
vhost_scsi specific.
Change-Id: I331a455374f7dd92fd76cab255a43072baceb0dd
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/389477
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>
Use the existing bdev_null_destruct() function instead of open-coding
the bdev cleanup; the bdev_null_finish() path neglected to free the bdev
name.
Change-Id: Ie74be39b0475674f70c3999bbe2f21caab2e2e20
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/389867
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
As of this patch, it is unused.
Change-Id: I15f42b8cc43e3792ae69c91f3911b7853d5b5664
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/388292
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>
It has all the same properties of uniqueness, so
implement it as an io_channel to take advantage
of the other infrastructure for message passing
already available.
Change-Id: I1777b91f0597a5a43ac0d0bbfdf878e874eb04f3
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/388291
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>
This correctly puts all of the I/O channels on the right
thread during shutdown.
Change-Id: I432c8cb981a68b40639f8876dae42597a9e6a85f
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/389637
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>
When device was reinitialized, the old
virtqueue memory used to leak. While
here, also added a doc for virtio_dev_init.
Change-Id: I9bb8dbfa5d68deeb73e71567a7e51b82f869537a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388297
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>
The vbdev_* functions that were declared in lvol.h are all internal to
the lvol vbdev implementation; they don't need to be in the public
header.
vbdev_get_lvs_bdev_by_lvs() is moved to the top of the file so it
doesn't need a forward declaration (no code change).
Change-Id: I98282d3cb0008da5c5b5059eee335219dc929f1c
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/389894
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Modify the vbdev_get_lvol_store_by_uuid() API function to take the UUID
as a string instead of a uuid_t, since this simplifies the calling code.
This also allows us to remove #include <uuid/uuid.h> from the public
API, giving us the freedom to change the underlying UUID implementation
later if necessary without breaking API.
Change-Id: Ib360281f384f95722c5ab64e75dcf3603f826e4c
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/389893
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
All of the call sites already have a lvs pointer; there's no need to
look up the lvs by UUID again.
Change-Id: Icef54d84e7c89f682ea47f10b282839ab4237ce0
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/389892
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
The array of message strings is now only used in vhost_user.c, so it
doesn't need to be exported.
Change-Id: I40163b95a52a1762eb3639db5553814bf1299959
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/389652
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: Ben Walker <benjamin.walker@intel.com>
The bdev module get_ctx_size callback is only necessary if it returns a
non-zero size.
Change-Id: I00ca366b8a1949bdb091c5e8aefb19cb606481d0
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/389900
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Rather than iterating over the g_nvme_bdevs list to determine if a bdev
is an NVMe bdev, we can just compare the module pointer.
Also, the function can take a spdk_bdev pointer directly rather than
casting from a void pointer.
Change-Id: Iccf3c9b3263e9b2d67d07d037dc00d1cbc0f22a1
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/389899
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This patch will make sure the nvme bdev work in correct way when we delete
bdev by using rpc method and then exit the app.
Change-Id: I19172440d46d96c7396282e1bef07d98ab601390
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/389930
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
replace the bdev_nvme_destruct() with spdk_bdev_unregister(),
clean all the resource in the bdev layer.
Change-Id: Ic4b85dee6225f42babe868796a8c24dec5c22af6
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/389855
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Currently SPDK NVMeoF will allocate data buffer from mempool, however,
some data buffers may not block size aligned, this is okay for NVMe
backend but will fail for AIO backend. 4KiB aligned data buffers
should be okay for most AIO backends.
Change-Id: If7b9c2962d716addbd755e80e59620377f2ba488
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/389245
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>
The 'm' variable was only used in sizeof expressions; m was a struct
vhost_user_msg, and we already have one of those called 'msg' in the
function where it was needed.
A previous commit removed a RTE_USED() marking on m, which introduced a
warning on clang, since it can now see that m is unused.
Fixes: 73bfcede86 ("rte_virtio: remove rte_memzone from vq")
Change-Id: I63eb0d82c7c750b4181b6312bbda82ef3213c205
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/389648
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Also removed vdev->started field.
Used vdev->status field to determine
if a device has been `started`.
This is simply a cleanup.
Change-Id: Ieb06b03b3bd60bd5906b41c987c418604906c913
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388296
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
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>
Now that vtpci_internal has been removed,
the vdev->id and g_ctrlr_counter are
obsolete and can be removed as well.
Change-Id: Ia1e83cdc81552173f4b57283f83c5791e2b90daa
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388301
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Removed another direct DPDK dependency.
Change-Id: I12d9a49fb16fbefad42c09f46c280f6f7be094d1
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388300
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Use standard spdk_dma_malloc instead.
This removes another direct DPDK
dependency. Yet, for multi-process
support we will more likely use a
memzone for the entire virtio device,
not it's virtqueues.
Change-Id: I57119ad830b573b718605b46cc3099b105651ee9
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385629
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Replaced them with spdk alternatives.
While here, also clarified the documentation
for virtio_*mb.
Change-Id: Ia604e9abd8eadc18fa3ea1a782e29e7da6b3c162
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385627
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>
Currently there are a bunch of asserts() on metadata
descriptors - change these to fail the blob parsing
instead.
While here also return -ENOMEM if any of the memory
allocations fail.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ie37b73c57b304d05a45d10a8d33bcc1d47e7a1be
Reviewed-on: https://review.gerrithub.io/388702
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
data_ro means that write, write_zeroes and unmap operations are not
allowed.
md_ro means that resize, set_xattr and remove_xattr are not
allowed.
There is no code yet that can activate this - it is coming in a future
patch. Two usages are planned though:
1) a user explicitly marks a blob as read-only - this is persisted so that
future loads of the blob will ensure the blob cannot be modified - neither
metadata nor data
2) a future feature flag framework (how's that for alliteration) may allow
a blob to be opened, but not allow metadata modifications, if there are
feature flags set in the blob's or blobstore's metadata that the
application does not understand
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I247fd900430c56f7176edfb80dddd5a1a6c8dc87
Reviewed-on: https://review.gerrithub.io/388663
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>
There are two ways to set stockets to nonblocking type:
- ioctl with FIONBIO
- fcntl with O_NONBLOCK
Those two should be equivalent for sockets used in SPDK.
During testing it was shown that VPP interprets only
the second type, so this patch changes all occurences of it.
When here, more descriptive error logs were set in case of
failure.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ifa5b30e3a4fa04fe23f41fa2ae9dab4b01dd7d3c
Reviewed-on: https://review.gerrithub.io/388816
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>
Moved some vq-related functions
to virtio.c. It's the only place
they're used in.
This patch also removes the
virtqueue_full() function. It's
not used anywhere.
Note: all the functions content
has been moved 1:1.
Change-Id: Ib854fc0836378e6955c0a7358ecabcf2c3107d06
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385628
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Only multi-process shared controllers should be inserted into the shared
list in g_spdk_nvme_driver. To accomplish this, create a second
per-process global list of attached controllers (g_nvme_attached_ctrlrs)
and rename the driver struct field to shared_attached_ctrlrs to clarify
its purpose. Additionally, a new helper function, nvme_ctrlr_shared(),
returns whether a given controller should be on the shared or
per-process list.
Change-Id: I46d4e558ece8b7fc3d28868e32bb56d794f21aab
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/389190
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Simplify the PCIe transport by using an existing function to look up a
controller by transport ID.
Change-Id: I261865df1ba23069b052ca64944b7637d70c85ba
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/388701
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Each process should manage its own list of controllers that are
initializing; the list doesn't need to be shared between processes.
This is the first step toward preventing non-PCI controllers from being
added into the shared attached_ctrlrs list.
Change-Id: Ia6f85fe89e28a04f0950da5362bb2f49d1b76da9
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/388695
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
If the user calls spdk_rpc_close() multiple times, there would be a
double free. This is not normally possible when using the SPDK event
framework RPC subsystem, since it will only call spdk_rpc_close() once,
but it doesn't hurt to make the RPC library public API handle this case.
Fixes GitHub issue #219.
Change-Id: I80cff0ed871dec6b90bd2658e85b0cd0914b6ada
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/389394
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Change the return type of spdk_bdev_register related
functions and try to handle the duplicated name
issue.
Change-Id: I23af11583cf2050579d1624508306a35394bffde
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/388178
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Use the new one from io_channel.h.
Change-Id: I7bf6729caf6eeebcb58450a36119601957ad5da4
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/388290
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
This function will send a message to each allocated
thread asynchronously, then call a callback on
the originating thread.
Change-Id: I3ebe7c6c5b460a944a32487d1091b601a482a256
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/388041
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
This simplifies the public API and requirements for
user applications.
Change-Id: Ibb0d25a7838a0fa683f39e79cb4fef78adf6aee8
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/388040
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>
Using pthead_detach to let system take back the resources owned
by SPDK created thread for nbd kernel module.
Change-Id: I39f3c0b60ecf57f3227a7b4733a0f144a6e169c5
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/388722
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Make this generic and not directly dependent on
the event framework. That way our libraries can
register pollers without adding a dependency.
Change-Id: I7ad7a7ddc131596ca1791a7b0f43dabfda050f5f
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387690
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>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Id0f7751d8889584fff1a947160ee89e2f158af1c
Reviewed-on: https://review.gerrithub.io/388943
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
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>
With configuration where there are nested lvol stores we
encounter situation when hotremove and fini functions try
to unload the same lvol store second time (previous unloading
have not finished yet).
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Icb5d430d17024fbda0e6113b380d8f346a3e9a84
Reviewed-on: https://review.gerrithub.io/388790
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
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>
It doesn't need to be accessed outside of bdev.c.
Change-Id: Ib1a1abe88b0993e391e0a39c5483781b2c0ad523
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/388508
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: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
The io_device_unregister callback might be
deferred and called on a different core, but
the virtio device has to be released from
the same thread that created it. Hence, once
the unregister callback is called, it has
to send yet another msg to the vdev-owning
thread. Since all virtio devices are currently
created on the same thread, no mutexes are
needed. They will need to be introduced once
we publish the API to connect to virtio
controllers.
This patch also defers bdev_virtio module-
-finish until all virtio_devs are destroyed.
Change-Id: Iaafceefa1e862b839b5db8c6c4975bf51441a083
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388835
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This will allow us to send a message
to a virtqueue via spdk_thread_send_msg.
Change-Id: I8502f27e74de107bc5e5ccf2939448896579acc2
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388834
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
We previously used a separate io_device
for each bdev created from a virtio_dev.
The new approach makes us reuse the same
io_channel for different bdevs on the same
core. It also provides a built-in safety
check for freeing virtio_dev only when
all io_channels on this device have been
closed.
Change-Id: Iaae66964f90aa3cef95ed2e261c6f3dfb2f26caa
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388505
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Currently on blobstore creation we use write zeros everytime.
Some drives does not support write zeros, but support unmap.
We should do write zeroes only on metadata and try to unmap
data clusters
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Iae36c1ccacc08340e79ad40c4c9a2c53dda920ba
Reviewed-on: https://review.gerrithub.io/387152
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>
Using pthread_create is much cleaner, and avoids race
conditions related to the forked process sharing memory
with the primary process. Specifically this fixes
a double spdk_event_call() of the shutdown event - one
from each process. The primary process may have already
recycled the shutdown event, and when the forked process
calls it again, hilarity ensues.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3e4b77b8b380a8fa0227b770758099bcee0ef35b
Reviewed-on: https://review.gerrithub.io/388520
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>
dev_fd => fd for /dev/nbdX device node
spdk_sp_fd => fd that SPDK will use to poll for new
I/O requests from the kernel nbd thread
kernel_sp_fd => fd passed to the kernel to send I/O
to SPDK
This enables an upcoming patch to switch from using
fork() to pthread_create().
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I0840a35eb1ba12810b7fc12775ee0df9ad3d99f9
Reviewed-on: https://review.gerrithub.io/388519
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>
"OK/NG" may be only used in Japan. It may cause misunderstanding.
Hence remove "OK/NG" or change to "Allowed/Denied".
Access control of iSCSI target follows further refactoring.
Hence to save the amount of change, "OK/NG"s are mainly removed.
Change-Id: I1f2ef9bc2be21caa86a6ae98377b6d6b3f85386a
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/385075
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>
The vdev->ctx conversion is now
straighforward and doesn't need
any macro.
Change-Id: I88b0cf3fa5e95b93e5f69a0a3ae9508f9fac3683
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385625
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>
This is a single header file that
provides access to all virtio initiator
capabilities. This is a preparation
to exporting rte_virtio as a separate
spdk lib. Also renamed virtio_dev.c.
Change-Id: If45a0cadc61943b6ffd87cf70a59321a83b238a6
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385624
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>
It's contents have been moved to
virtio_user/vhost.h and virtio_dev.h.
The virtio_user_dev struct can't be hidden
in virtio_user.c (similarly to the virtio_hw),
due to another abstraction layer in virtio_user
- vhost-user and vhost-kernel. Even though only
vhost-user is implemented now, let's not close
the possibility to implement vhost-kernel in
the future. The vhost-user/vhost-kernel code
should probably be placed in separate files,
with the virtio_user_dev struct in common
vhost.h header.
Change-Id: I36ee96eff30b398dd129953a874513e727619f98
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385622
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>
Moved it's contents to virtio_user.c.
Having this logic separated across
multiple files doesn't make much sense.
Change-Id: Ib2daaa56e1b3d755d9476abca247c7cbcfa7096b
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385621
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>
Renamed all vtpci functions.
While here, also added some documentation.
Change-Id: Id24aaab8c5b556b969c60ee1c95b9d46936ea13d
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385426
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>
virtio_hw struct definition is now hidden
in virtio_pci.c. The API to enumerate all
PCI devices is available through virtio_dev.h.
Change-Id: Ib9c968732d9f78204e9664c426ad99542cfe8c93
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385425
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>
The vtpci layer is about to be removed.
This is only 1:1 code move, all functions
will be renamed/refactored in future patches.
Change-Id: I63c1b30fdaf6eff2e5d8bf60e62c87c2cb9f2b15
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385424
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>
Now that legacy PCI support has
been dropped, we can safely assume
there's only one backend type
per device. So the vtpci_internal
- containing process-local data -
can be removed.
Change-Id: I15d87a280b74318c7a44ee60ce3408756d1f5a69
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385423
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>
This patch initiates the removal
of the vtpci layer from rte_virtio.
The general idea is to provide separate
virtio_dev_construct and virtio_dev_init
functions. construct would just allocate
and setup the struct data. init would
be the one to start the device via
MMIO/vhost-user. virtio_dev_construct
takes 2 params - backend ops and backend
context. The context is kept as void*
and can be cast to proper structs inside
backend ops callbacks.
Change-Id: I1d6d92e1cf09b9d0c9fa4fd2cb70203e3fc7e65b
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/387553
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>
We currently pass virtio_user_dev as
an argument to various function in belief
they will access the virtio_dev via
virtio_user_dev->vdev field. However,
this field is about to be removed soon.
This patch is a mid-step towards a bigger
change. See the next patch for details.
Change-Id: Ie684aa1614d9777d79d350bbfda79effe2a2d5f6
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385422
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>
It's been only used in 1 place.
Change-Id: I0b7c9cdb809a6946eda5ee361362dec86e57b4ef
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385623
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>
This is required for future changes.
The general idea is to provide separate
virtio_dev_construct and virtio_dev_init
functions. construct would just allocate
and setup the struct data, while init
would be the one to start the device via
MMIO/vhost-user. If we want to destruct
a non-initialized device, there's no
need to do a reset.
Change-Id: Ib8ce56169e86e43fba8fcd1bf6c2a5b12ed99966
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385421
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>
Even though config change intrrupt
handlers are still required, we need
them only for real PCI devices.
They should be handled internally
in vhost_pci.
However, current QEMU implementation
doesn't ever change SCSI PCI config,
so no interrupt handler is required
for now.
We might want to add it together with
Virtio-Blk, as PCI config will change
there with each resize.
Change-Id: Iece024cd31c788857ce900385e289758ca3f5948
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385304
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>
It's been only used in 1 place.
Change-Id: I3e933d3fb0816ea30f983fb3de69ce49238c3b72
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385303
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>
When there are no lvols present on lvol store
spdk_bdev_module_examine_done function is not called
when tasting is done.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ia6c559f392148e3b4444dbc547df462bbe02356d
Reviewed-on: https://review.gerrithub.io/388402
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>
To add initiators to an existing target, manage name and netmask
of initiator group by linked list. It is not easy for array to
detect duplication and change configuration.
Change-Id: Id9e77740e24ac309a33d8de1be37663681160d94
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/379932
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
spdk_iscsi_init_grp_create_from_configfile() returns 0 even if
creating an initiator group (IG) is failed due to empty netmask or
initiator name. This will be unexpected behavior for end users.
Hence change the return code from 0 to -ENVAL for this failure.
Besides do the following.
Change other error return codes in the function by using errno too.
Current IG don't have any UT code in repository. UT code to confirm
this fix is also submitted.
Change-Id: Ic918feb5c6a3e772b325664d881b2673b553a217
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/384408
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ic11a56c5616098ff42f31f78aa96289af5965118
Reviewed-on: https://review.gerrithub.io/387611
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: If89275acfb1560982e332148a99ed3c83f8cb34f
Reviewed-on: https://review.gerrithub.io/387609
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
We used to unlink the unix domain socket
regardless of who created it. Even we
got the "socket already exists" error
on init, we would still unlink the socket
on shutdown.
Change-Id: Ib14382d6d7e127d8f51f6544cbb063594e040879
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388284
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Deinitialize only those subsystem that
have been fully initialized.
Change-Id: I86cdd4cda0a80c107956843ed8198072e898a743
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/386892
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
spdk_bdev_nvme_io_passthru_md() is verified on QEMU NVMe
and will be verified on Cosmos mini OpenSSD.
Change-Id: Ib759b6b6095deaa4ae7cf746f3a241f678295605
Signed-off-by: Young Tack Jin <youngtack.jin@circuitblvd.com>
Reviewed-on: https://review.gerrithub.io/387114
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>
- for environments that don't support rlimits
Change-Id: I6dde1eb9e1cb2274462a450625d8bc70a3889163
Signed-off-by: John Meneghini <johnm@netapp.com>
Reviewed-on: https://review.gerrithub.io/386355
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
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>
We probably do not allocate the mgmt_channel when we destroy the
rdma queue pair, add the judgment before put the io channnel.
Change-Id: I528c9686907c04c5025ff9d3872f24f2996e9d33
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/388159
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>
Change the return type of spdk_channel_msg from
void to int. If this msg executed in a failure,
we do not need continue sending the message to other
threads, we can just tell the original thread, and
let the orgiginal thread call the spdk_channel_for_each_cpl
call back.
Thus we can track the qpair creation/destroy case for bdev
reset in nvme bdev module;
Change-Id: Ide9dffd1f84a29fcf61d8339a9ece2a0245d968d
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/387284
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8ea8c59a0c67176c0c0c39abf807afad61ff3828
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387689
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>
Change-Id: I864cd8a6c206dfbe62fcb3f72275c1ae51aa4ed7
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387688
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>
We always unregister pollers from the core they're running on,
so we don't need the async completion event when unregistering
them. To avoid changing the logic, create events instead.
Change-Id: Ib50d93e1578684bea69200d89a5e0d383acc8cfe
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387685
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>
Register all pollers to the current core. If necessary, send
an event to the correct core before registering.
Change-Id: Ie34cc8b11143a58c0f621c87c409a3d09d929648
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387682
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
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>
This is the inverse operation of spdk_io_channel_get_ctx.
Change-Id: Ica6593240dfb05cb53dc7ec910bc0a78270e81c0
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387679
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>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Change-Id: Ib1e184f831eef82432308279c6d8ea43088748ef
Signed-off-by: Liang Yan <liang.z.yan@intel.com>
Reviewed-on: https://review.gerrithub.io/387273
Reviewed-by: Ziye Yang <optimistyzy@gmail.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>
Use the env abstraction PCI functions to compare PCI addresses so that
details like whether or not domain is specified or whether 0-padding is
present don't affect the comparison.
For example, 0000:01:00.0 should compare equal to 01:00.0.
Change-Id: I9f3aaeb5f8fdbf3e246e31a41b4c09151288015e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/387202
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: Ibe31b961fec36644cf64716c512429d68e873e88
Signed-off-by: Ed rodriguez <edwinr@netapp.com>
Reviewed-on: https://review.gerrithub.io/386170
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Currently when one of lvols fail during loading we end up
with empty lvol store loaded, where we actually should
unload lvol store as well.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I90ce3b79baba0db0d875b106c94924be394aada9
Reviewed-on: https://review.gerrithub.io/385950
Reviewed-by: Piotr Pelpliński <piotr.pelplinski@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This patch make the cache buffer shift of blobfs configurable. We
can configure the cache buffer shift according workload, it will
help to improve the performance.
Change-Id: Ied1c2e5d6fd9eaa7aa0759c03c654fcf2e77aa23
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/383381
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This helps enforce uniqueness of the subsystem id and
allows for quick lookup by that id.
Change-Id: I4d2948892839d42b8c2b2a406682848415ad2bd6
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/376251
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>
DPDK 17.11-rc3 removes pci_probe*
and pci_detach functions. It introduces
different ones - rte_eal_dev_attach/detach.
Those have a slightly different signature.
Change-Id: Iadde9ff37c64190dad41929997f9ff78379f36e1
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/387656
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
DPDK 17.11-rc1 moved a part of it's
eal code into two separate libraries.
Change-Id: Ibcea448487a001c30abb68447e3fe2104ba9a7c3
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/387655
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
DPDK 17.11-rc3 switched to IOVA-centric
addressing. The old API is still available,
but is deprecated.
Change-Id: I7b54a1e626e39368acd2190dec725dbf30c7a5de
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/387654
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
DPDK 17.11 removed all rte_config.h includes
from rte_*.h headers, meaning we should either
use gcc param -include rte_config.h (just
like DPDK does), or include this file before
each other rte_*.h include. Since we're using
the latter approach in many places already,
I decided to follow it.
While here, also removed rte_vdev.h dependency
from rte_virtio/virtio_user.c. It's not used
anyway.
Change-Id: I865ee9f828211c03a60fd0446f7a418d5dddd140
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/387653
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Legacy PCI code is hard to maintain
and compiles with DPDK 17.05 only.
If we ever need this functionality
in SPDK, we should first add proper
env/pci layer for direct UIO/VFIO
communication, and then revisit this
topic.
Change-Id: I25622c16f467633e01003c9edbb7e6f297c68a86
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/385302
Reviewed-by: Jim Harris <james.r.harris@intel.com>
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>
Because ppc64 has less strict memory ordering behaviour
than x86 we need to introduce a memory barrier when
polling for completions due to possible reordering
of tracker and cpl access.
Change-Id: Id17116c38b2ba69154c175c539fc97c60897deb0
Signed-off-by: Jonas Pfefferle <jpf@zurich.ibm.com>
Reviewed-on: https://review.gerrithub.io/383728
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>
When an iSCSI connection is closed, spdk_iscsi_conn_stop_poller()
is called in spdk_iscsi_conn_destruct() or
spdk_iscsi_conn_check_shutdown().
However, through both paths, g_num_connections[] is decremented
twice:
(1) in spdk_iscsi_conn_stop_poller()
(2) in spdk_iscsi_conn_free()
This behavior makes g_num_connections[] negative unexpectedly and
for some cases load balancing does not work and the same CPU is
always selected.
How to fix:
spdk_iscsi_conn_stop_poller() is called in the following functions:
- spdk_iscsi_conn_check_shutdown()
- spdk_iscsi_conn_destruct()
- spdk_iscsi_conn_handle_idle().
[Idea 1]
Remove the code to decrement g_num_connections[] from
spdk_iscsi_conn_free().
[Idea 2]
Remove the code to decrement g_num_connections[] from
spdk_iscsi_conn_stop_poller(). Add the code to decrement
g_num_connections[] to __add_idle_conn().
[Idea 1] is simple because just only one line is deleted.
[Idea 2] may be more symmetric than [Idea 1] but to find the right
place to add the code in __add_idle_conn() is not clear and
difficult.
Hence [Idea 1] is proposed.
[Idea 1] may not be the optimal one and more refactoring may be
done.
Change-Id: I81050f4a0e7b3ddd40896f46ab2eb8de14bbcb3a
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/384026
Reviewed-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
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>
Change-Id: I2524b7881885a0784492a8189bf22a0b8c92d470
Signed-off-by: Ed rodriguez <edwinr@netapp.com>
Reviewed-on: https://review.gerrithub.io/386169
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The following functions returns 1 and 0 for succcess and error,
respectively:
- spdk_iscsi_tgt_node_allow_ipv6()
- spdk_iscsi_tgt_node_allow_ipv4()
- spdk_iscsi_tgt_node_allow_netmask()
- spdk_iscsi_tgt_node_access()
Using bool for this purpose will avoid our misunderstanding.
Change-Id: I927876e0503c0eee5364e829a4713f9a345996f6
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/383664
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
In the Appendix C. SendTargets Operation in the iSCSI Specification
(RFC7143), there is the following description:
In a Discovery session, a target MUST return all path information
(IP address-port pairs and Target Portal Group Tags) for the
targets on the target Network Entity that the requesting
initiator is authorized to access.
However no description such that Target Portal Group Tag is used
to check authorization of the requesting initiator.
Moreover, according to the iSCSI Specification (RFC7143),
Target Portal Group Tag is unique within an iSCSI Target Node.
Tarrget Portal Group Tag identifies a portal group within an
iSCSI node.
However, current SPDK uses Target Portal Group Tag to check
authorization of the requesting initiator by mistake. This
implementation does not have any compatibility with other storage.
Hence delete the code related with Target Portal Group Tag from
SendTargets function.
Change-Id: If4b79f0d8fe8f5892a798e4f6716045fd18cf0a4
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/383660
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
SPDK have used "*" and "[*]" as wildcard address
for iSCSI network portal. These abbreviations may be convenient
but unusual. If "*" or "[*]" is used, output warning message
and forcefully overwrite "*" or "[*]" by "0.0.0.0" or "[::]"
respectively.
After confirming that the usage of "*" and "[*]" is not used any
more, the code for "*" and "[*]" will be deleted.
Change-Id: Ibb8fb0d4598ffa1f7b1690ad6afd10d5ae162612
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/383556
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>
There is case like no memory to create the channel.
Needs to handle this properly.
Change-Id: I5d13d18037e6aa8f057769b1ef345f45597b22af
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/386016
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: Jim Harris <james.r.harris@intel.com>
There are two separate abstraction layers:
* vsocket - which represents a unix domain socket
* virtio_net - which represents a vsocket connection
There can be many connections
on the same socket. vsocket
provides an API to enable/disable
particular virtio features on
the fly, but it's the virtio_net
that uses these features.
virtio_net used to rely on
vsocket->features during
feature negotiation, breaking
the layer encapsulation (and
yet causing a deadlock - two
locks were being locked in a
separate order). Now each
virtio_net device has it's own
copy of vsocket features, created
at the time of virtio_net creation.
vsocket->features have to be
still present, as features can be
enabled/disabled while no
virtio_net device has been
created yet.
Fixes#214
Change-Id: Ic4b2dd8cae6050813fc9a420b2ed30bc5ae60393
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/386294
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The process of spdk_bdev_finish will always result in an
early call to the user's completion notification - prior
to the actual shutdown events happening.
Change-Id: Ib53393deb794b616d2b7ec94cb41502305bd99b7
Reviewed-on: https://review.gerrithub.io/386707
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Change-Id: Idc39c101c23cebe9538d59c0026d169c93c44e23
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/386715
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>
Change-Id: I482ad9e722f6fb775c1c91c8661212250a6914bc
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/386722
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Some devices may report a RTD3E time that is shorter than their actual
shutdown time in practice; force the timeout to be at least 10 seconds
to allow for a reasonable amount of shutdown time.
This doesn't add any extra delay for devices that do complete the
shutdown process within their reported RTD3E time, since we will return
as soon as the device reports that it is finished shutting down.
Change-Id: I365e66ba6a938400be516df170bd3ff288810caf
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/386719
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
1) Replace some perror() calls with SPDK_ERRLOG
2) Use spdk_conf_section_get_boolval() to simplify the code
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I2a6d0773b09ad16ea35cb6d2f18a9e0977dba31c
Reviewed-on: https://review.gerrithub.io/386666
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>
With the new asynchronous subsystem finish framework, we can
drive shutdown of existing connections as part of the subsystem
finish path instead of a separate spdk_iscsi_shutdown function
called as the shutdown function in response to SIGINT.
This is a step towards enabling a single target app that
supports multiple protocols (i.e. iSCSI + vhost + NVMe-oF).
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Id9f596a8091912a72ab7eb93cb45a46fdb130a48
Reviewed-on: https://review.gerrithub.io/386695
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
RPC is a default feature required for almost all usages,
so enable RPC by default, but with a UNIX domain socket
for security reasons.
-r can now be used from the command line to specify
an alternative RPC listen address from the default
/var/tmp/spdk.sock.
Remove the Enable parameter from the Rpc config section
but still allow specifying an alternative listen address
using the Listen parameter as an alternative to the
command line option. This keeps backward compatibility
for this release for anyone using the configuration file
still.
Remove the Rpc sections from all configuration files
that were using them, except for those that specified
alternate TCP ports for multi-process test cases. We
can fix these later to use an alternate UNIX domain
socket and to use the command line instead.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ife0d03fcab638c67b659f1eb85348ddc2b55c4c4
Reviewed-on: https://review.gerrithub.io/386561
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 is a helper function that eliminates a lot of
duplicated code in our target applications, specifically
around common command line argument parsing and usage
messages. This patch only moves the iscsi, nvmf and
vhost targets to use this function, but there are other
test/example applications that could also take advantage
of it to reduce duplicated code and improve consistency.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I1903de3daed90ac6282b006a8283b9df07ce37e9
Reviewed-on: https://review.gerrithub.io/386542
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
spdk_sock_getaddr() (in lib/net/sock.c) only support IPv4.
Hence IPv6 cannot be used in SPDK iSCSI target.
By adding the code to support IPv6 transparently, IPv6 becomes
available in SPDK iSCSI target.
Change-Id: I236f2c6cb1e61283dde090729fecd8f743cec3fc
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/383672
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
cmd and cpl rings must be aligned on page size boundaries.
Change-Id: I103eed32adfaa4388bc7d672ee166973f796b343
Signed-off-by: Jonas Pfefferle <jpf@zurich.ibm.com>
Reviewed-on: https://review.gerrithub.io/383727
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
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>
Show total accessible clusters when listing lvol stores
instead of total blocks. This is more readable for user.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I22a14f626816769cf2f494ae30cfd8ee63897771
Reviewed-on: https://review.gerrithub.io/385634
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
At the moment there was no way to a user of blobstore api to know,
how many clusters are availible to him. Total_clusters describes
number of clusters for metadata and user data.
New field added total_data_clusters, keeping number of clusters
that can be used to create blobs - meaning just user data.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I60555217644557410844f74628375a6b46fd2ac7
Reviewed-on: https://review.gerrithub.io/385633
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This allows us to remove some duplicated code from our
main target applications.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I15b517fd2b58ce682660b4f6ba0b8412beda053b
Reviewed-on: https://review.gerrithub.io/385714
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.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>
RPC is core functionality for SPDK applications and should always
be initialized last (after all subsystems have been initialized).
So make RPC a first class citizen and integrate it with the
app framework directly instead of making it an "optional" subsystem.
Then we initializing it after all subsystems have completed
initialization, and tear it down before tearing down subsystems.
We can also do some other cleanup while here - for example, reactors
are already started when spdk_rpc_initialize() is called, so remove
the extra event that was added during initialization since this is no
longer needed.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I4cc63586a6d55be68786629a2176c61a88979267
Reviewed-on: https://review.gerrithub.io/385914
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
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>
There is a race condition here, where kernel could have
outstanding I/O to nbd device at the same time we terminate
the nbd application. In this case, we cannot free the
spdk_nbd_disk since it contains the io structure that
will be referenced when the SPDK poller completes one
of those I/O.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I1bde240af904957f4d2bfa358dc673105d266986
Reviewed-on: https://review.gerrithub.io/385927
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
There may have the situation that associated socket does
not have enough memory for the event pool and the related
ring buffer. As the event pool will be created at any
available socket, this will be same for the ring.
The basic idea is to first allocate the memory for the
core associated socket and then try other available sockects
before terminating.
Change-Id: I52c240289899c136b607629c12c0250ad859c8ac
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/385972
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Previously lack of support for specific bdev was not known to user.
This impacts all unmap operations, such as initialization of blobstore.
It should be useful to user to know it will take longer
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I89bf3bc0342558fda9a8964fb5cb1daa3a8ed79e
Reviewed-on: https://review.gerrithub.io/385999
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>
The end goal is to have the application create one poll group per core.
Then each poll group will have a single CQ per network device and an I/O
channel per back-end storage device to poll.
This is just the first step toward that, which is to wire up the
creation of the per-core poll groups in the application.
Note that the app poll groups don't do anything yet. We'll need
additional library API changes to make the library use the existing poll
groups, rather than creating a new poll group per subsystem as we do
right now.
Change-Id: I2d4e2a5e5aa354d37714750f1d5b1d1e4ab9edce
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/381887
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>
When a ctrlr is failed to initialize and to respond other
requests, the nvme_ctrlr_fail() will be always called. Add
a log there to have the traddr information so that applications
can know which ctrlr has the problem.
Change-Id: I951062a51349af81a505472f79e3c00a1ead2fbf
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/386189
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>
According to the current code, rdma qpair is always created
by the thread on acceptor_core, thus we need to
change the related I/O channel during polling if the core
configured for subsystem is not same with the acceptor core.\
With this patch, we can run NVMe-oF tgt with multiple cores,
and each subsystem can configure different core to handle.
Change-Id: I6163a871f65115e545a4f3fd9cc46b3bafb13249
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/383683
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: Jim Harris <james.r.harris@intel.com>
Change-Id: I3db00323c20786713750d13a61b1531d8b1ce7f6
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/386087
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>
During tasting, if bdev is already claimed, we send errors on screen.
This is expected behavior so we should send only debug logs.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ic5766cfa3aed88099415991998381de69ee8b8b6
Reviewed-on: https://review.gerrithub.io/384229
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Piotr Pelpliński <piotr.pelplinski@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Change-Id: Ibdfa8be770d7bfcb2baaf29fa5b32dea064ffbd0
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/383383
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: Jim Harris <james.r.harris@intel.com>
NVMe 1.2 introduced a new Identify Controller field, RTD3E ("RTD3 Entry
Latency"), which allows the device to report the expected time for a
normal shutdown. Use this as the timeout for the shutdown process when
available instead of hard-coding 5 seconds.
Change-Id: I14e7223c81ba397771cf00b49f034f25d21b6e82
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/385301
Tested-by: SPDK Automated Test System <sys_sgsw@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>
spdk_pci_device_claim() can be used to ensure only one process
at a time uses any given PCI device. Previously this was only
used in the bdev_nvme driver - other apps like nvme/perf do
not use spdk_pci_device_claim() and could effectively rip out
the device from a running bdev-based app like the NVMe-oF target.
So instead of modifying all of the nvme apps, put this logic into
the core nvme driver instead so that all applications get the
benefit transparently. Save the fd when the controller is constructed
and then close it when the controller is destructed to handle the
detach (including hotplug) cases.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I5dc48a2e41dc06707800f15a9e1f9141477628c6
Reviewed-on: https://review.gerrithub.io/385524
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
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>
This allows users of this interface to then close the fd
when they want to release the claim.
This prepares for calling spdk_pci_device_claim() in the
nvme driver to cover not just the bdev_nvme driver but all
of our nvme example and test applications as well. We'll
want the fd returned so that we can properly close it during
detach (including hotplug) use cases.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8b149cc4e778ba31c0e7045b858c8a1561b6b7af
Reviewed-on: https://review.gerrithub.io/385523
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.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>
If the default config file does not exist, keep the
app's config_file options field as NULL, so that the
app code will not fail when trying to open a non-existent
file.
Also leverage the recent iSCSI and NVMe-oF refactoring,
to just skip trying to read config file parameters if no
config file exists (or the requisite section in the config
file is not present). vhost already handled this so it did
not need to be modified.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ic32f0a7a8ce85322a8effd537b62d14732d7b82e
Reviewed-on: https://review.gerrithub.io/385497
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
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>
Previously users would have to pass CHAP and Mutual as
separate words on the DiscoveryAuthMethod line - but
this was problematic since then we would have to check
that the user did not specify Mutual without CHAP.
So instead just make Mutual infer CHAP.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I183d59145abb97198984541157522d6483b18e7c
Reviewed-on: https://review.gerrithub.io/385495
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Some invalid parameters would result in an immediate app exit, while
others such as DefaultTime2Wait would adjust an invalid value
rather than causing an app exit.
Instead, be consistent and just ignore any invalid values, with an
error message.
One exception is the CHAP + Mutual check - this will be fixed
in a separate patch.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I867e4a2a5685aec73df5e556d529b0356a9c3070
Reviewed-on: https://review.gerrithub.io/385494
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>
Move all of the code related to reading global iSCSI
parameters to a new function.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iccbb75996b29b0b7a87c602042f13aaf7935d7e1
Reviewed-on: https://review.gerrithub.io/385493
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>
spdk_iscsi_app_read_parameters() does an SPDK_DEBUGLOG
for each of the global parameters - consolidate these
and move them to a separate function.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: If1543f9f5846420bf75f7a4aebaf540106f1df69
Reviewed-on: https://review.gerrithub.io/385492
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Modify spdk_iscsi_app_read_parameters() so that it sets
up all of the default values first, and then reads the
config file to update any parameters that may have been
specified.
This is in preparation for breaking out the config file
reading into a separate function that can be skipped
if no config file is available. In this case it will just
use the defaults.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I0b9026ea87d171be22085a6baca24e2022cb58dd
Reviewed-on: https://review.gerrithub.io/385491
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>
spdk_iscsi_tgt_node_access() (in lib/iscsi/tgt_node.c) regards
empty netmask of IG as ALL (allow all initiator's IP address).
However any user cannot create IG whose netmask is empty by both
JSON-RPC and config file. Instead user can create IG whose
netmask is ALL.
The code to regard empty netmask of IG as ALL never run in production.
Hence delete the code and add UT to confirm the fix.
Change-Id: Ib7206d0986db9093cfb6b36191be26293ff6c67a
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/382920
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>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
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>
There are some upcoming changes which will deprecate
the old lvsuuid_blobid name in favor of an
lvs_name/lvol_name name where these names are
user-specified.
In preparation for this change, rename the previous
lvol->name to lvol->old_name. This will allow us
to add a new lvol->name but keep the original
old_name during the transition.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I10deb219097fa8726c146ab2427ee7373933b97d
Reviewed-on: https://review.gerrithub.io/383534
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>
Each lvolstore now has a unique name which is persisted to
metadata. Eventually this will provide a friendlier
way to reference logical volumes, in the form
lvolstore_name/lvol_name.
This patch only covers the unique lvolstore name. An
lvolstore may not be created nor loaded if its name
conflicts with an already loaded blobstore.
Currently there is no way to rename an lvolstore to
resolve a conflict. This will be coming in the future.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I842f13b79776e5b8f81e56de10778c35328e8cd3
Reviewed-on: https://review.gerrithub.io/383533
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>
Fix up the two existing instances of trailing whitespace in text files,
and add a check to enforce that no new trailing whitespace is added.
Change-Id: I2197bed69bb356142aa6d2e4e8261c7434dd358b
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/383291
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>
Replace POSIX and standard C #includes with the central SPDK stdinc.h
and remove the rte_virtio exclusion from header checking in
scripts/check_format.sh
Change-Id: Ie53d11de7cd9a51c59957e3c500bd8b9b4c4bc5e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/383003
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Remove the exclusion of the rte_virtio code from scripts/check_format.sh
since we will be maintaining this code going forward (unlike rte_vhost,
which we intend to keep up to date with upstream DPDK).
Change-Id: I30c186e566ca777dff552a36af53443d197a8824
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/383002
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
If an I/O fails during the write zeroes fallback to write on a split
I/O, the previous code would call spdk_bdev_io_complete() again on the
same I/O, causing infinite recursion.
Fix this by restoring the original user callback before completing the
I/O, as well as using _spdk_bdev_io_complete() rather than
spdk_bdev_io_complete() to avoid double-counting the statistics.
This also preserves the original bdev_io->status code set by the module,
rather than always setting it to SPDK_BDEV_IO_STATUS_FAILED.
Change-Id: Ib71fa6e54eed3d5823652971f7c439e0ff236fc1
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/383506
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
This patch is a continuation of patch https://review.gerrithub.io/#/c/383252/
on which this series should be rebased. This series introduces
spdk_lvol_open function where reference counter should be also used.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I962db95eaba34c7c18e639076ad86696e8209196
Reviewed-on: https://review.gerrithub.io/383264
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
If we don't delete the super blob, this blob structure
will leak.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I56d0ca4884846aee0c7865f9c600d6c43811373c
Reviewed-on: https://review.gerrithub.io/383311
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
This will be used in a future patch to ensure we do not
allow creating or loading an lvolstore with a names that
matches an already opened lvolstore.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I37e8786f91cd578dd36fbec99ca23609419fc8f8
Reviewed-on: https://review.gerrithub.io/383012
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>
Currently this is just a free(), but a future patch will
also remove spdk_lvol_stores from a common list.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iff0f14fbe2003448d24f6fb1484f0e95acfe90ff
Reviewed-on: https://review.gerrithub.io/383011
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
This patch introduces lvol store and lvols parameters saving
on persistent memories and loading it from saved data on app start.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ia63f0cf3d6365d59f31c5f0a1724636bfe73b5b8
Reviewed-on: https://review.gerrithub.io/375764
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 vhost connection can be closed
concurrently from 2 places:
* the connection thread itself
* rte_vhost_driver_unregister
The connection thread will terminate
the connection if any recv error
occured. The unregister function
will terminate the connection
together with the thread.
However, there is no sychronization
between those two. The connection
thread runs in the background
without any mutex.
The rte_vhost_driver_unregister
now signals the connection thread
to terminate itself and waits
until it's killed.
Change-Id: I012e97ebb8a79edcb2c17c28b2fc7e8041bf92b3
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/383085
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
pci_dump_json_config() is used for both legacy and modern PCI virtio
devices, so move it out of the #ifdef PCI_LEGACY_SUPPORT so it is
available when building against older DPDK versions.
Change-Id: I986f9e6a81abda64d77f954b15807d06e35d1748
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/383487
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
It is possible that a user will call spdk_bs_unload() with blobs
list not-empty. Instead of just asserting that, now the call fails
with appropriate error.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I83818453d6c90ff9b5bf657c90e12b2f9d5ca013
Reviewed-on: https://review.gerrithub.io/383220
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
17.05-rc4 is the version e.g.
rte_pci_ioport_read function was
introduced in. The bdev_virtio
module previously did not compile
with older DPDK versions.
Change-Id: Ib96d5d7934166acc552515b02bfba25b71929438
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382829
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>
This was looking at req, but req had already been allocated and checked
for NULl previously; this line was intended to be checking lvol_req.
Change-Id: I8603d35fb4582c109e9d02f4964bbd6d21735324
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/383312
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Casting pointers without checking their length could
potentially lead to a crash
Change-Id: I7c61e5818ecfbf32bb363858965503341353c51e
Signed-off-by: Pawel Niedzwiecki <pawelx.niedzwiecki@intel.com>
Reviewed-on: https://review.gerrithub.io/382420
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Unmap does not guarantee that erased blocks will return all zeroes.
using write_zeroes when unmapping metadata gives the
desired behavior for a blob.
Only metadata pages will be cleared with write_zeroes in this patch;
blob data clusters will still call unmap. This behavior may be made
configurable in a later patch (to allow the user to request zeroing of
clusters rather than just unmapping).
Change-Id: I1b210abac110867ce703bcfdeb634eb45aa9d5c9
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/372004
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
if write_zeroes is not supported by the block device, we can get the
same behavior by simply writing a buffer full of zeroes to the blocks
we want to erase. I also incorporate splitting into the bdev layer to
accomodate large i/o.
Change-Id: I8fa1bfaaf22d7bfc6e3afb6e89d22fa9f7767e55
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/373829
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
This is necessary to avoid failing very large write_zeroes operations.
This is the minimal workaround to get the current bdevio tests to pass -
the real fix will be implemented in the bdev layer later.
Change-Id: I4e49f1b4da5d4c7f9507757d6c71ba3880d22437
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/383306
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
There is no need to wait until an atexit() to unlink these - we can do it immediately
since the open refs will still be valid.
Note: changed the remove() calls to unlink() to be more precise, since these are
files and not directories.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ib160131bcf3beb9783c6fc4de021f64c43c943a9
Reviewed-on: https://review.gerrithub.io/382697
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
This goes along with previous patch in series.
Adding functionality to remove logical volume store from
device.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I6338a35ed02838498a3cd9bb2dddd25803e65f79
Reviewed-on: https://review.gerrithub.io/382020
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>
Currently exposed API allows to load/unload and to
initialize blobstore on a device.
A spdk_bs_destroy() call is added in order to reach
functional parity with spdk_bs_init(). It was not
possible to remove blobstore from device from within
SPDK previously.
spdk_bs_destroy() takes blobstore pointer as argument
(instead of bs_dev), because blobstore has to be already
loaded to destroy it.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I2c493a4407868fcf08fd1766a19fc8463f634ef5
Reviewed-on: https://review.gerrithub.io/382019
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>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I3a86f28056e67b3c237441fb1048ca6ccd081ae7
Reviewed-on: https://review.gerrithub.io/383252
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>
Close and destroy lvol functions should support callback
functions so that they can be processed sequentially
and also give user result.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I9e87fb281916c65c17b2b7e54e91228844962048
Reviewed-on: https://review.gerrithub.io/383230
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>
SPDK can now be compiled without
the virtio driver.
Change-Id: I92999c871d28875d519749a73a7f2230c3881fbe
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382828
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>
We only sync the metadata and data in the runtime of blobstore, which
means we only update the used md bitmap and used clusters bitmap in memory.
if the system crushed, we have no chance to sync the used md bitmap and
used clusters bitmap into disk, then next time when we try to load the
blobstore, all the data will lost, this patch add the logic to recover the
valid data from last dirty shutdown. We will go through all the metadata pages
to find all valid data and rebuild them.
Change-Id: Ieb7c5f932206b1b68fdde0cee35f2d2cb3a4f309
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/376470
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>
A recent patch did some refactoring on how the superblock is
written out - it introduced a bug where on load we would
write out INVALID for super_blob id and a null bstype when
clearing the clean bit.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I1d6256e35030645b3e8fda83bfe0f74aeb635733
Reviewed-on: https://review.gerrithub.io/383129
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Some future patches will require specifying an lvol_store
name when calling spdk_lvs_init(). This means that passing
NULL for spdk_lvs_opts will no longer be an option. So
add an spdk_lvs_opts_init() (similar to spdk_bs_opts_init)
which will initialize a default value for the cluster size.
While here, prepend an underscore to spdk_setup_lvs_opts, since
this function is not part of the public SPDK API.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I155bcfd0c396017304bb3d58b7511ada71dade17
Reviewed-on: https://review.gerrithub.io/383030
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
init_grp.c has init_grp_destroy() function but does not have
init_grp_create() function. Hence add init_grp_create() function.
init_grp_create() function check duplication of init groups.
Change-Id: I49c64254846ae4edd7a0bb2cf3250fb6f53239f4
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/381243
Reviewed-by: John Kariuki <John.K.Kariuki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
We interpeted max request queue
count as number of all queues.
It did not take into account
eventq and controlq.
This patch also fixes overall
max_queues negotiation for
modern PCI devices.
Fixes 8b0a4a3 ("bdev_virtio: implement multiqueue")
Change-Id: I834cb973772ca5946ac26d18bd3eeb2783f48ea9
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382816
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>
It was wrongly assumed that
each READ will contain at least
one iovec. This could potentially
corrupt the desc array.
Change-Id: I48ca7efbe4bea897e0ad16184452bddcf3daf49b
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/383009
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Only the initial xmit_pkt is checked
against an error, the subsequent
xmits are just asserted. As scan
messages are sent 1-by-1 if the first
request (containing 3 iovectors) has
been enqueued successfully so should
the next ones.
Change-Id: Ie102256a42ef1c67132d606af90ab96771adba10
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382784
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
In case of not enough free descriptors
the bdev_virtio will fail the I/O with
NOMEM status.
Change-Id: I1cb0cd5453ff70468898bc8e414b53b9c64dbe50
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382783
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Previously all bdevs were using
hardcoded name Virtio0.
Change-Id: Ib990027a0edd4e200aa4b6f4689ccb9e0824a9c3
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382926
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This doesn't change any behavior
as queue_idx was always either
0 or -1, but makes it clear that
this function always returns
-1 on error. This is required
by current io_channel implementation.
Change-Id: I2b613ab9ff1e48d5b4aee0cd499bbc0a04cb765c
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382927
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Always start bdev pollers on the calling core.
This removes the lcore concept from the bdev poller abstraction and
simplifies the job of spdk_bdev_initialize() callers providing their own
poller and event implementations.
All callers except the NVMe bdev hotplug poller already used the current
core as the parameter. The NVMe HotplugPollCore option was undocumented
and unused in any of the tests or example configuration files, so it
should be safe to remove.
Change-Id: I93b466e1e58901b8785c40cbe296fa46c157850f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382857
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
A single thread that initialized
bdev_virtio subsystem will be used
to poll control queues for all
virtio devices.
Every io_channel will put it's e.g.
RESET requests to the controlq MP-SC
spdk_ring. The controlq poller will
dequeue these requests and put them
into the virtio queue. The same
poller will then poll for completions
and send them to proper threads
that submitted given requests.
Change-Id: I90ae7c5d76dc89cc52ff69cf2a60e27a9314557c
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382201
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>
Added a wrapper for rte_ring_count().
Change-Id: Ia12fde3f250604a0f801309ed1c4706a311e7896
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382919
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Some error messages were printed
outside of the error-checking
if() condition.
Fixes: bd273d4 ("rte_vhost: replace strerror() with spdk_strerror_r()")
Change-Id: Icf965ae56ffc2e0970572308b38607ac63cdb1f2
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382943
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Our previous implementation makes the buffer allocation
in an unfair way and this patch can solve this issue.
With this patch, we can use limited buffer to support
high I/O depth.
Change-Id: I0e7a073c0b4539090218aa461d50620287bb4b63
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/382528
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>
Values from previous bdev_ios
were reused and were taken into
account e.g. in bdev_io_get_buf()
to check if a buffer is already
assigned.
Change-Id: I239aaf83a4ce8a9342c1820e3ac9e9ccf6a28336
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382959
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>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I9218b618544def301a4509eda1b266390a80dba5
Reviewed-on: https://review.gerrithub.io/382830
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Add newlines to the debug logs.
Also dump the mismatched bstype via SPDK_TRACEDUMP() rather than as a
string, since it may not be null terminated.
Change-Id: Icad567373c56f24aea550903a1370c3734465472
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382855
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Previously, spdk_trace_dump() took a const uint8_t * as the buffer, but
it is more flexible to allow any type to be passed (we are just going to
interpret it as an array of bytes anyway).
Change-Id: I1750316928cd330ed461bb513ff8af37e0170ef3
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382854
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Rather than using char arrays to represent blobstore types, just use the
publicly-defined struct spdk_bs_type.
Change-Id: I8bbfd95085e16f9d53106c176038e067ff1266d7
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382853
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
These #defines are not currently used, and they have equivalents already
defined in spdk/pci_ids.h:
VIRTIO_PCI_VENDORID == SPDK_PCI_VID_VIRTIO
VIRTIO_PCI_DEVICEID_SCSI_MODERN == PCI_DEVICE_ID_VIRTIO_SCSI_MODERN
Change-Id: I0016ab0a26f4aa7ff4a5ee10f66da867b590e0e6
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382734
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
strerror() is potentially not thread safe; use the thread-safe SPDK
wrapper instead.
Change-Id: I5f6f4b0b19a0298b07f71f05aee4574e8b21f5fa
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382732
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>
This patch also introduces
vq->poller_ctx. It will be later
reused for per-virtqueue task pools
to allow multiple threads using
the same virtqueue.
Since at the time of scanning there
is no I/O traffic, this field is
now being used to keep scan base
pointer. It has to be freed if an
initialization error occurs.
Change-Id: Ia54ee6c8402d38218dc811b4994761105d17269a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382199
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>
This is required for virtio-initiator,
where multiple io_channels have to
share the same virtio queue. A single
poller will receive responses from
a virtio queue and send the completions
to the thread that submitted bdev_io.
Change-Id: I951c7655aaa17d41a680d437661afff27d2c3077
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382200
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
The get_lvol_stores RPC had typos in the free_blocks and total_blocks
fields (they were named "free_num_blocks" and "total_num_blocks", which
didn't match the names of the actual variables).
Change-Id: Ib66b04ec2f0c272048a826bfa59338db1d028e34
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382522
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I85ce977183be4de9efacb66637e7895f22f58508
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382521
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This allows the caller to know which bdev module is exporting the bdev
and therefore how to interpret the driver_specific fields.
Change-Id: I09641645875827eabc0a831fff5b0b5bed6b03d0
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382519
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>
Each virtqueue will now contain
it's own buffer for I/O tasks.
Some of the task struct fields
are now the same across subsequent
I/Os, so they can be now set
just once - at the vdev start/stop.
This simplifies the code, the
debugging process and also introduces
additional sanity check preventing
vhost from processing two requests
with the same id at the same time.
Change-Id: Idcf388e8bf7c92e5536199c35eb0eb6339c00d84
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/369114
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This enable storing SPDK specific stuff per queue. First use of
this will be event index feature.
Change-Id: Ieca6fa47a6f2e23bec73d2cda8b0ed8b9185bd28
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/376636
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Introducing bstype as a way to identify and verify
blobstore type.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I50267b5408625be10fe0c146ae329016d5509b4a
Reviewed-on: https://review.gerrithub.io/380476
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
The virtio bdev should only attempt to issue SBC commands if the SCSI
device is a block device.
Change-Id: Ib29edbd19f9f34bdafe5ea3f7085c57537134625
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382714
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
The SCSI spec defines two separate fields within the first byte of
the Inquiry data. Define them as bitfields and add enum values for the
peripheral qualifier field.
Change-Id: Ibbb158338da199fc1b67b04c52ec91633577c571
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382713
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
the function of spdk_iscsi_find_init_grp() is duplicated with
of spdk_iscsi_init_grp_find_by_tag(). The later one should be kept.
Hence delete former one.
Change-Id: I8d397648bd400550445de49c8a7731f0932f5324
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/381244
Reviewed-by: John Kariuki <John.K.Kariuki@intel.com>
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>
Change-Id: I6d3669bc19b51fd72af7ea27aa4d2a88dee59e58
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382509
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Remove some magic numbers from the code.
Change-Id: I494d57331888dd03f0bbff1f6beeac46139d7e96
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382348
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Virtqueues now have to be "acquired"
by a logical CPU core in order to
perform any traffic on them. The
acquire mechanism is thread-safe to
prevent two reactors accessing the
same virtqueue at the same time.
For now a single virtqueue
may be used by only one io_channel.
Support for shared virtqueues will
be implemented in future.
Added new param "Queues" to the
virtio config file for VirtioUser
bdevs. VirtioPci will use the
max available queues num -
negotiated during QEMU startup.
Change-Id: I3fd4b9d8c470f26ca9b84838b3c64de6f9e48300
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/377337
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>
Replaced old PMD_*LOG with
* SPDK_WARNLOG
* SPDK_ERRLOG
* SPDK_DEBUGLOG
Added 3 new trace flags:
* virtio_dev - SPDK_TRACE_VIRTIO_DEV
* virtio_pci - SPDK_TRACE_VIRTIO_PCI
* virtio_user - SPDK_TRACE_VIRTIO_USER
This patch also makes error
messages to be printed on
non-debug builds. Some messages
should be still reworded, but
that will be done in a separate
patch.
Change-Id: I2dd4c71dfce20cde0ef010a1d91ac6f166bb2c98
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382620
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>
Moved their contents to virtio_dev
files. virtio_queue was already deeply
connected with virtio_dev. There's
no need to keep them separate.
Change-Id: I540c04eb954fe0618817c020f9453aebf3d98ba9
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382619
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Simplified some code.
Change-Id: I9fc42da93a4c2df3714775d73508de118a5e6b1a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382618
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Documentation of rte_eal_init() lie. At least two parameters (huge-dir
and file-prefix) are held and used internally trought the lifetime of
application.
Change-Id: Ie418b5f2b0d7fbea5c217e47a555a520d3256360
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/382677
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Previously two spdk_events were allocated in spdk_app_start().
Now app allocated spdk_event for function to be called after
initialization is complete. Meanwhile subsystem allocates
its own spdk_event.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I4822f76d30cc2f7b95a86a4ffbfc61b80c0a903e
Reviewed-on: https://review.gerrithub.io/382673
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>
spdk_lvol_destroy() and spdk_lvol_close() behave very similar to
each other. With exception that spdk_lvol_destroy() deletes blob,
after closing the blob.
The order of calls in spdk_lvol_destroy() case:
- spdk_lvo_destroy() calls spdk_bs_md_close_blob()
- _spdk_lvol_delete_blob_cb is callback from closing the blob,
which calls spdk_bs_md_delete_blob()
- _spdk_lvol_close_blob_cb is callback from deleting the blob
The order of calls in spdk_lvol_close() case:
- spdk_lvo_close() calls spdk_bs_md_close_blob()
- _spdk_lvol_close_blob_cb is callback from closing the blob
Lvol was removed from lvol store lvol list in two cases,
spdk_lvol_destroy() and _spdk_lvol_close_blob_cb().
This caused lvol to be removed twice from the list in
lvol destroy case.
This change makes it so it is more clear, that lvol is removed
from lvol store lvol list in both cases and just once.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I204645850ca2c46f03a9035518b00f50c75e2b1a
Reviewed-on: https://review.gerrithub.io/382425
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>
Similar to blobstore unload, lib/lvol assumes that unloading
lvol store is only possible after no lvols on it are open.
Before spdk_lvs_unload() is possible, for each lvol
on that lvol store spdk_lvol_close() or spdk_lvol_destroy()
has to be called.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I86bae67ec322a61fdc0045d799854eecd1f36407
Reviewed-on: https://review.gerrithub.io/382252
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>
Several fields in struct virtio_user_dev are not referenced anywhere (a
few have cleanup code but no other assignments); remove them.
Also drop is_vhost_user_by_type() and virtio_user_handle_cq(), which
aren't used anywhere.
Change-Id: I7c80ccbadbd5263a2886dc9028108b898d6485ae
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382505
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
These are just noise, since we don't enable the unused parameter
warning.
Also remove an unused variable, txvq, in virtio_dev_start() that
had been left behind since it was marked as __rte_unused.
Change-Id: I7bda85ef5f2208dd36d8f1806d8241a04b893123
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382494
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: Changpeng Liu <changpeng.liu@intel.com>
These were included under #ifdef RTE_EXEC_ENV_LINUXAPP, which is not
defined in the SPDK build system, so they were already not getting
included.
Change-Id: I6b90c8230632647bb9237f86ec52c09133891a2d
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382488
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: Changpeng Liu <changpeng.liu@intel.com>
Replace the DPDK rte_branch_prediction.h likely/unlikely with
spdk/likely.h spdk_likely/spdk_unlikely.
Change-Id: I51ad42ee2b29b8f33436fa960deda67a0dd0b0f0
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382486
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Clarify some error messages
and simplify the code.
Change-Id: I586ea55a1d9fa10142d4a9d469b62f1b83076cd5
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/381925
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This function was only useful for old (and incorrect) iSCSI
topology with SPDK. Hence this function can be removed.
Change-Id: I6147382b0731a896df3c988fae0173923a9a85fc
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/381242
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: John Kariuki <John.K.Kariuki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
These are identical now that the spdk_bdev_io I/O-specific unions were
combined.
Change-Id: I2579f4fd100c5ebb3550b806c7fdac38c6160a69
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382373
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
For the normal case, we can avoid re-adding it into
pending data buf list if there is no buffer.
Change-Id: I400e3c6c60bb1d1df13782faf2dd32ca2bd897a3
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/382402
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>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: If809fe808150498c7ad6797855fda3097e3b0c84
Reviewed-on: https://review.gerrithub.io/382470
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>
This patch reduce duplicate data structure and make some functions common
for both bs load and unload porcess in the future.
Change-Id: I40b2135e89a705aa5073c1ded4c7b28be4b32f6e
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/381912
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>
Three new RPC are added, that allow to control pmem pool file.
- create_pmem_pool(path to file, total file size, block size)
- pmem_pool_info(path to file)
- delete_pmem_pool(path to file)
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Id9025b7d988608957700b41f74874159d18c6ad3
Reviewed-on: https://review.gerrithub.io/379006
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Remove one use of DPDK-specific functions in the virtio initiator code.
Change-Id: I538185270da83674e937dac64c9b1130fab36ac4
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382074
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
This is required for adding
optional params for vdevs.
Since virtio-initiator README.md
had to be changed, some outdated
entries from TODO section has
been removed as a part of this
patch as well.
Change-Id: I472a966d8e4166305fb19ad3ab20e53289a1e071
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382347
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>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I68a56666d30a550de4a2dc5a66fb669dfbad12dd
Reviewed-on: https://review.gerrithub.io/379659
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>
Current implementation supports only adding port to scsi_dev.
This change is required to support dynamic remapping of portals.
Change-Id: Idce49aeae43c8861ebe2807df853694f7bacf884
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/379931
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>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Some problems with indirect descriptors shown. Disable it for now to
have time to investigate it.
Change-Id: I8c6cfff94dc2159ab01f72986a8ae7d42c353e8b
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/382301
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
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>
The construct_malloc_bdev RPC method now takes an optional "name"
parameter to request a specific name for the created bdev, rather than
using the auto-generated Malloc%d-style name.
scripts/rpc.py is updated to add the new optional parameter, and it uses
-b/--name to match the corresponding parameter to construct_nvme_bdev.
Also update one of the test scripts to use the new parameter to get test
coverage.
Change-Id: I1f5bf76f406b8ea8a709d856f7624a38fbfa0d5f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/381728
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Change it from error_log to debug_log level to
avoid missleading while there does not have
GPT_PROTECTIVE_MBR type.
Change-Id: I51f7bf2994db227b4c9f1bf80d3bb0e05c047e59
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/382080
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>
For using SoftRoce, there will be packets loss,
so we need to use this value for re-transmission.
retry_count means the maximum number of times that
a data transfer operation should be retried on the
connection when an error occurs.
Change-Id: Ibd81a33d3838bbdf0c054f01666e7ec59bb0a38f
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/382079
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>
bdev_opened field in spdk_bdev structure is no longer required.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ie4a368425b11b1c2e1a3a48b5858857b3935498b
Reviewed-on: https://review.gerrithub.io/381375
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Idd19b8be38a843dfd50710c09d0c6c31773c2f0c
Reviewed-on: https://review.gerrithub.io/380014
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
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>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ia6b6e5352ce4da04784fb0a3ea1efd0552650067
Reviewed-on: https://review.gerrithub.io/381548
Reviewed-by: Piotr Pelpliński <piotr.pelplinski@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
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>
Fixed typos, updated comments and
simplified the code.
Change-Id: I7eaa7227518d376d86cd4a6eb0348f1efc7b47fd
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382024
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>
In multiprocess applications some shared memory files are left around
after a primary process exits because they can be used by secondary
processes to init memory. However, all primary dpdk processes create
these folders so we need to delete them after a single process spdk
application exits.
Change-Id: If51be95811fb66632316ae260762e5291641b537
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/381721
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>
This is needed for proper IO channel allocation failure handling.
Change-Id: I795e5bcce5296a52c119d2300974b8cb3fc0d576
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/381187
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Closing the framework has to go through all subsystems
without failure, so return codes are unnecessary.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I53c9b4df12d2357e641130869f398b18637e6ff7
Reviewed-on: https://review.gerrithub.io/381681
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
spdk_app_fini() changed to void, as no operation within it
can fail with meaningful return code.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: If77cbf745a8e3fcba4ea24411aa1816f3910cde7
Reviewed-on: https://review.gerrithub.io/381537
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>
The task was being aborted before
setting it's free_cb. This
results in i.e. not allowing
vhost device to stop it's pollers,
as it would endlessly wait for
this task to finish.
Change-Id: I0de2d1f21da109db1045e433c07f153316e09997
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/381866
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>
Every descriptor may now contain
a separate descriptor table.
This increases the maximum number
of concurrent IO in a virtqueue
from about (vq->size / 3) to
(vq->size * SPDK_VHOST_IOVS_MAX).
Knowing that SPDK_VHOST_IOVS_MAX
is 128, and assuming that vq->size
is 128 (current hardcoded limit
for QEMU), this gives us over 16k
concurrent possible iovectors
on the fly
Change-Id: I0853d80f6f90d53f8774231972b430a5bf05460e
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/373703
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>
Also squashed function has_next_desc
into get_next_desc to simplify the
code.
We can't just mask indexes with
(desc_table_size - 1), since in
indirect descriptors case
desc_table_size might not be a
power of 2.
Change-Id: I8053b0e37c553548d76c7a9cfe6b4dbc11c28cfc
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/373744
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>
It was en empty function before.
Also, don't stop the device in
virtio_user_dev_uninit, the device
is stopped separately before
removing (unititializing) it.
Change-Id: Ib540ee4a55bd3f983b50f35a138c1690daba1d98
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379156
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>
This patch also resets each device
before destructing it. This is urgently
required for virtio_pci, as it notifies
the QEMU about our shutdown.
This patch fixes running subsequent
bdev_virtio instances in PCI mode within
the same vhost.
Change-Id: I2569251362f2aaf058f6e44f068b280244bd38c1
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/381201
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>
With this new API, callers can attach one specific ctrlr identified by
the transport ID directly along with optional ctrlr opts. If connecting
to multiple controllers, it is still suggested to use spdk_nvme_probe()
and filter the requested controllers with the probe callback.
Two primary use cases:
1) connecting to the NVMe-oF discovery controller
2) more straightforward way to connect a specific controller (avoiding
the probe callback)
A typical usage of this API with specific ctrlr_opts:
1. struct spdk_nvme_ctrlr_opts user_opts = {}
2. Call spdk_nvme_ctrlr_get_default_ctrlr_opts(&user_opts, sizeof(user_opts))
3. Modify the content of the initialized user_opts with user required value like
user_opts.num_io_queues = 8
4. Call spdk_nvme_connect(&trid, &user_opts, sizeof(user_opts))
Change-Id: Idf67ee5966f6753918c12604342c892d2f3bbe3a
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/370634
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>
This change is relating to add a new public API spdk_nvme_connect() under
include/spdk/nvme.h. This new spdk_nvme_connect() API will connect the user
specified trid and have a user optional ctlr opts. Rename this API and make
it as public.
A typical usage of this API as following:
1. struct spdk_nvme_ctrlr_opts user_opts = {}
2. Call spdk_nvme_ctrlr_get_default_ctrlr_opts(&user_opts, sizeof(user_opts))
3. Modify the content of the initialized user_opts with user required value like
user_opts.num_io_queues = 8
4. Call spdk_nvme_connect(&trid, &user_opts, sizeof(user_opts))
Change-Id: Ideec8247365ebf7dd15069e29821be8ea27b08be
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/380849
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>
With current SPDK_BDEV_LARGE_BUF_MAX_SIZE
set to 65536, we can allocate at most
4095 16-byte SCSI UNMAP block descriptors.
A single descriptor can UNMAP up to 4GB.
That gives us a hard limit of ~16 terabytes
of data that can be unmmapped by a single
request.
The same limit is also enforced by the
SCSI standard, as the entire UNMAP request
length must be smaller than 65536.
Change-Id: I4d91fa60fd28133a058b87e88a1a14ce662a659a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/381447
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>
A single timeout error message is printed on the
screen already, so the user knows about the
timeout. Instead of aborting the app here, wait
endlessly for the event to complete. User
can kill the app any time if he wants to.
Change-Id: Ie1853e27b277d654a8e1099866d120f7a51638ba
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/381075
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
One instance of strerror() was introduced after the spdk_strerror_r()
function was introduced in commit 4d43844f4d. Replace it with the
thread-safe version.
Change-Id: I83c6702f7965044ef5fa3577175f89a13dad833f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/381601
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>
Move local copy of linux header code
to internal include/linux directory.
Change-Id: I81049ff956c72bb32c099a3087cf5f43de911ce4
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/381275
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
We don't support PPC.
Since the code around is changing
let's remove it.
To keep the codebase small.
It's so huge already.
Change-Id: I86b15ae9f6de7b9e612542c8e846aa11047e282a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/381624
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Moved virtio backend specific code out
of common feature negotiation path.
virtio-pci features are stored in PCI
register. Before feature negotiation
they can be considered device (host)
features. They have to be negotiated
with local features and written back
into the very same register.
For virtio-user, the situation is a
bit different - vhost-user protocol
contains two feature-related commands
GET_FEATURES and SET_FEATURES. While
SET_ sends already negotiated features,
GET_ always returns device (host)
features.
Previously, we used to store native
device (host) features in local
variables to (ineptly) make the
negotiation path the same for
virtio-pci and virtio-user.
Instead of fixing this functionality,
it has been removed. Now, the
vtpci->get_features might be either
negotiated or not. This is now stated
in this function's doc.
This solution doesn't have any
drawbacks and simplifies the code.
Change-Id: I270e9cad8baaeae61b58992ee06e9069eac10aaf
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/381472
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>
Added vtpci_init/deinit() that set up
vtpci_internal for given virtio device.
This patch allows having multiple
devices with different vtpci_ops.
Change-Id: I249999cc24073b3de032db194730f496badd0f38
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/381311
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>
A few foundational change to support safe removal of portal.
- global login poller -> login poller per portal
- Caching portal data for active connection
Change-Id: I62f4d90c9ac11a433ad47421b2b0c69bfc3c70b7
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/379930
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>
Check duplication of registration of portals by using a global
portal list
Change-Id: I608fc9bd4473c11e69686e6474892f3f4272cd53
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/379929
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>
Group the code fragments of open/close portal procedure
and create spdk_iscsi_portal_open/close() function.
Change-Id: Id6e291f3f6e5a926f3ea0d01741a200fa64db81b
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/379934
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>
This function was only useful for old (and incorrect) iSCSI topology.
Hence this function can be removed.
Change-Id: I1898f6a5fbffd27a55904a55cd137dafbbdf5946
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/381241
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>
When constructing a SCSI device, LUN 0 must be assigned to some LUN.
However, the current code was assuming that LUN 0 had to be in the first
array element of lun_id_list in spdk_scsi_dev_construct(). Combined
with the scripts/rpc.py implementation that uses a Python (unordered)
dictionary object to generate the lun_ids array, there could be cases
where LUN 0 exists in the list but isn't first.
Fix the check by allowing LUN 0 in any position of the lun_id_list
array.
Change-Id: I39f387ec238fcecca8d2d786d3d42c42a4790637
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/381611
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
This change allows for spdk_app_stop() to be executed on a DPDK lcore
instead outside of DPDK lcore range.
This is preparation for SPDK asynchronous finish, to assure
calling spdk_app_stop() from master core.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Iedc878346c74296b105f93507b2c858aedfbf16e
Reviewed-on: https://review.gerrithub.io/381535
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Piotr Pelpliński <piotr.pelplinski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Poller registered at the end of spdk_rpc_subsystem_setup() was
never unregistered.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Id24e88a76798ba3f739614e5e357877e0404f9e4
Reviewed-on: https://review.gerrithub.io/381534
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>
The newly added UT code will exercise the cases that opts_size is
smaller and equal to the current version of spdk_nvme_io_qpair_opts.
This is for the backward compatibilty when SPDK components are built
as the shared library later.
Change-Id: Ic906d765f5b638070e3d9c8e38827577c625b679
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/380893
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>
In preparation to replace them with
standard functions. As these macros
are used to assign values as well,
changing them to functions is done
in a separate patch as a part of
reworking vtpci init/deinit.
Change-Id: I4f6398342b06dc9036afece3f902506e9b72a301
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/381310
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>
We don't support it. It's not
negotiated by SPDK vhost so the
code worked so far.
Change-Id: Ibc515dcc1ebffc6936ee7f5465c4c73001e9b1ed
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/381274
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>
Functionality of resizing logical volumes is currently
a work in progress, thus it is disabled in this patch.
It is no longer possible to use RPC and lib functionality.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I518e7196096f52e3ad9e91d658e1bb6c3301b688
Reviewed-on: https://review.gerrithub.io/380916
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Currently there is no way to know total space availible on lvol store or
how much is left after creating lvol bdevs.
Four new fields should were added to get_lvol_stores:
- total number of blocks
- number of free blocks left
- block size (currently always 4096, but should be known to user)
- cluster size
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I93dec2d4b2843f0ee51dc9883c8451cf55353f7b
Reviewed-on: https://review.gerrithub.io/381131
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Piotr Pelpliński <piotr.pelplinski@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Fixes github issue #29.
Because of how we handle the blobid and pagenum in blobstore,
it was possible to have blobstore inadvertently open the wrong
blob if open is provided a blobid where the lower 32 bits match
an existing blob but the upper 32 are clear.
Patch does the following:
- removes assert() that caught this on MD load and replace with
an error given that this condition can be induced via the API
- cleanup of pagenum and blobid conversion/handling to make it
clearer how they're related and converted
- new UTs that would have failed w/o the new check in place
Change-Id: I2b49b237922b3b8cfc4df296f5bc20195e41dc41
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/380872
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>
Add a new parameter for the default ctrlr opts initialization.
This is to make sure future compatibility when SPDK components
are built as a shared library. User's version and SPDK's version
may be in different size.
The change here is to make sure the backward compatibility when
new fields are added in the struct spdk_nvme_ctrlr_opts.
Change-Id: Icfc9640993cb06063b825d4df5835d920dd374e5
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/380846
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>
New optional parameter -c or --cluster_sz in construct_lvol_store() RPC,
as well as in vbdev_lvol and lvol lib API.
This parameter allows to configure cluster size of blobstore that lvol store
is build upon.
When this parameter is not specified, default of 1GiB is used.
spdk_lvs_opts struct was created to facilitate any future options when
creating lvol store.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ibfe8765ede3e78ff19c36f46043e4cec2e5c9f97
Reviewed-on: https://review.gerrithub.io/379356
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Piotr Pelpliński <piotr.pelplinski@intel.com>
It's not used anywhere. There's already a
vtpci->set_status(RESET) equivalent that
does the same.
Change-Id: I0f04ba094848806c647ede4be2ef77b423ead288
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379337
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This makes us open only as many descriptors as we need.
Change-Id: I2dbce218efdd37f015a0d4b250be9539373c6028
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379336
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Also add a unit test that reproduces the original issue and passes
with the one line fix.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I120d42ba7b6cfa4a2cb11e6cc08885d95316fe81
Reviewed-on: https://review.gerrithub.io/380703
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This puts responsibility on the caller to free the buffer
and do any other cleanup associated with the partition base
(for example, GPT buffer).
While here, also clean up a bunch of places where on
various failures during initialization, it would just
free the buffer instead of calling spdk_bdev_part_base_free().
The latter is required to make sure the bdev descriptor
gets closed as well.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ic000339459eca4a4a1d103da2e1f3feffe7e764f
Reviewed-on: https://review.gerrithub.io/378653
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
At very high queue depths, bdev modules may not have enough
internal resources to track all of the incoming I/O. For example,
we allocate a finite number of nvme_request objects per allocated
queue pair. Currently if these resources are exhausted, the
bdev module will return failure (with no indication why) which
gets propagated all the way back to the application.
So instead, add SPDK_BDEV_IO_STATUS_NOMEM to allow bdev modules
to indicate this type of failure. Also add handling for this
status type in the generic bdev layer, involving queuing these
I/O for later retry after other I/O on the failing channel have
completed.
This does place an expectation on the bdev module that these
internal resources are allocated per io_channel. Otherwise we
cannot guarantee forward progress solely on reception of
completions. For example, without this guarantee, a bdev
module could theoretically return ENOMEM even if there were
no I/O oustanding for that io_channel. nvme, aio, rbd,
virtio and null drivers comply with this expectation already.
malloc only complies though when not using copy offload.
This patch will fix malloc w/ copy engine to at least
return ENOMEM when no copy descriptors are available. If the
condition above occurs, I/O waiting for resources will get
failed as part of a subsequent reset which matches the
behavior it has today.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iea7cd51a611af8abe882794d0b2361fdbb74e84e
Reviewed-on: https://review.gerrithub.io/378853
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Use SPDK bdev subsystem to allow basic IO to pmem pool
using pmemblk_* calls.
New pmem bdev can be constructed using RPC call
construct_pmem_bdev PMEM_FILE
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: If5ca94161fe53644b8fccd3b77de5479da1b2e55
Reviewed-on: https://review.gerrithub.io/376973
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>
A few small tweaks to make this function easier to read:
- Return void (the return value is always 0 and never used)
- Split out Fabrics/admin queue processing 'if' block
- Remove unnecessary switch on status (it can only be 2 values)
Additionally, simplify the I/O command checking logic: we don't need to
check for CC.EN = 1, because it is only possible for I/O queues to be
created after CC.EN is set to 1.
Change-Id: Ib4c39a6e0d9e28912dbb0f0737fd223be0a80207
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/379218
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>
virtio_dev can now be freed via virtio_dev_deinit.
While here, also rename virtio_init_device to
virtio_dev_init for name consistency.
This patch also adds some error-checking.
Change-Id: Ic1222756b8686fbd8a14d8631f25525249529e1d
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379335
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>
Added virtio_hw->pci_bar[6] to store information
about mapped memory regions. They have to be
stored to make it possible to unmap them.
The unmapping itself is done in a separate
patch.
Change-Id: I5dcffd0674e855a02086b3d8e4adc5fac451229a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/380779
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>
Generic virtio_dev has the same field already.
The field was previously used to store vhost-user
GET_QUEUE_NUM response, that will be later assigned
to virtio_dev->max_queues via virtio_user_read_dev_config.
This patch removes virtio_user_dev->max_queues
with entire virtio_user_read_dev_config functionality
for virtio_user.
Change-Id: I508f728215a95cf977d6b0b20350fcf2ae11fe3a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379155
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>
Replaced direct DPDK calls with SPDK env/pci
equivalents. This patch also makes the PCI scan
happen only conditionally when user has
configured proper field in the bdev_virtio config
file.
Change-Id: Ib6ad81d0b421b20ad0cd9d02cb40b2213af823e6
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379489
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
The same condition is already checked
in spdk_bdev_free_io().
Change-Id: I31f937036d3835e2d16633c6338ebca1a2237de9
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379722
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
A device without LUNs can't be used at all,
so remove it automatically
Change-Id: Iefea73916c83dfddf0229bbfac5dacb23590d920
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/371299
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>
A random host ID is generated per SPDK application startup if the user
doesn't specify a host ID during controller startup.
This also changes the default host NQN for NVMe-oF connections to a
random UUID NQN based on the host ID.
Change-Id: Ib0f70dd63e53087716842b412a1f134a9991d4da
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/380528
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Also updated docs.
Change-Id: I2e53c31b2c9c575d8adea23ed92f113e69f324ed
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/380490
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>
Current UNMAP implementation supports only
up to 2^32-1 unmapped blocks per request.
Change-Id: Ib473831fa32aaba465f76694afad71137288a73a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/377688
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>
This is required for upcoming UNMAP implementation.
Change-Id: I81fb744e0813121cebd64aa60a03a80bfbecc94d
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/377421
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>
This is required for upcoming UNMAP
implementation in bdev_virtio.
While here, also added documentation for
spdk_bdev_io_get_buf().
Change-Id: Ia769ee9b8b132f31208ae66598b29a1c9ed37312
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379721
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>
A vdev can change between the time the event
is enqueued and executed on proper reactor.
To detect this case, the event callback
was looking up vdev with the same name and
comparing it with old vdev pointer (from
the enqueue). This is now being simplified,
by looking up the current vdev just by
it's ID.
Change-Id: I33de03809b9d56840dd99caa8ccdf190a631ef31
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/380647
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>
This makes the async event body non-blocking
and also fixes potential deadlock scenario:
* call_external_event() enqueues vhost_event
* destroy_device() locks g_spdk_vhost_mutex
* destroy_device() enqueues it's vhost_event
* reactor dequeues events
* cb from call_external_event is dequeued first
* g_spdk_vhost_mutex is locked (deadlock)
* destroy_device() times out, abort()
Change-Id: If8f51ada3ee5c47ba126f74187a40a285c001c77
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/380634
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>
spdk_bdev_unmap_blocks() accepts a 64-bit number of blocks, which can
exceed the NVMe Dataset Management range's 32-bit number of blocks,
which can represent up to 2 TB with 512-byte blocks.
We can support up to 0.5 PB unmap requests by using the maximum number
of descriptors in a single Dataset Management command, which should be
sufficient for now.
Change-Id: I0a4ee77a9be148355991e1a081007ffa020a3ee5
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/379202
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This patch adds hotremove support of lvol base bdev
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I04dc7a0cc73fd6959824873f354d5c7db8c09a9b
Reviewed-on: https://review.gerrithub.io/379348
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
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>
This is in preparation for enabling hot remove of logical volumes when
their underlying blobstore device is hot-removed.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I310a3f64f0de5d628609c20a1a3b4d38df0755aa
Reviewed-on: https://review.gerrithub.io/377041
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Previously incorrectly it was assumed that cluster size
was always to be 1MiB. For most evident example of this
please see spdk_lvol_create() sz > free_clusters comparison.
This is now fixed and lvol->sz was changed to lvol->cluster_num.
It was done to increase readability - only dealing with
number of clusters when creating or resizing lvol.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: If8cdbad18978319e57b6952dbf5a55d56785f108
Reviewed-on: https://review.gerrithub.io/380467
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>
This patch allows unmap bdev_io to
be used with spdk_bdev_io_get_buf.
bdev_io->iovs/iovcnt has been zeroed-out for other
I/O types to overwrite any previous values/pointers.
Change-Id: I570a4d82d9e4db6630a6831b1aab3259fb46cdd8
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/377687
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>
Three checks are added to options passed to spdk_bs_init,
with appropriate errors returned:
- whether any of the options is set to 0
- device size has to be bigger than cluster size
- pages reserved for metadata exceed total number of clusters
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Idee3c194b653e737ec7c7a768f1973ff72452c5b
Reviewed-on: https://review.gerrithub.io/379676
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Now bs_dev is destroyed only in two instances:
- within spdk_bs_init() on failure path
- vbdev_lvs_create() if spdk_lvs_init() errors out,
before even calling spdk_bs_init()
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I7b8af39fbe83907b0c47797f0f55ca3b941729d9
Reviewed-on: https://review.gerrithub.io/379848
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Change-Id: Ic094c34f1dc9063f12df80d77b2c70ebae9a4977
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/380066
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Fixes condition where blobstore was prematurely calling the
application callback on spdk_bs_unload(), if the application
tries to do something too quickly bad things happen.
To avoid application changes with how the g_devlist_mutex is
held, it is no longer held while calling
_spdk_io_device_attempt_free() because the app unload CB is
called from that function and may want to call
spdk_io_device_unregister() from its unload CB. So the lock
is now held and releases strictly around the list its
protecting which allows the CB from _spdk_io_device_attempt_free()
to be called without issue.
Change-Id: Ib451cfe6b33ea0c3f9e66c86785316f9d88837c7
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/377872
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>
This reverts commit d3828a23ec.
GitHub issue #202 reports that this causes a crash with two or more
iSCSI connections on the same LUN.
Change-Id: I9ffb85d393eb506aac9d176299a3b3bcf021a38c
Reviewed-on: https://review.gerrithub.io/379866
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>
Change-Id: I46d564523ea20bc7c79a3896dfb024d3d5172a93
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/379911
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ia07efcdec742d6ae5339e9f1c860ab58107d9f85
Signed-off-by: Jin Tsai <caijin11331007@gmail.com>
Reviewed-on: https://review.gerrithub.io/379928
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>
Until now we queued all IO to hardcoded
SCSI target 0.
Change-Id: Iefb229899725f53f26e927c4fb23e8d1d613c187
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379840
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>
replaced "remove_vhost_scsi_controller" and "remove_vhost_blk_controller"
with "remove_vhost_controller".
Change-Id: I6f4b180054c13f25aae992e9be50375d3750a376
Signed-off-by: Pawel Niedzwiecki <pawelx.niedzwiecki@intel.com>
Reviewed-on: https://review.gerrithub.io/377197
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>
bdev_module_init_done could be called
multiple times when more than device
is available.
Change-Id: I17ee63a818945359648953c4f8f67678d10e8907
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379864
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>
Added new struct virtio_driver together
with it's global instance. The struct should
keep all bdev_virtio related information.
Change-Id: If78967c68c4131c89cd86cb4b46f5f0194bca323
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379863
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>
This patch only adds the pci_virtio.c file,
without changing any functionality. This
is required for future rte_virtio migration
to SPDK.
Change-Id: I7774cdfdaf8934fde588e25b5db5dd86a9cbfb3f
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/379484
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>
