Commit Graph

3253 Commits

Author SHA1 Message Date
Dariusz Stojaczyk
9760edb041 bdev_virtio: add defines for virtqueue IDs
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>
2017-10-16 15:48:09 -04:00
Dariusz Stojaczyk
8b0a4a3c53 bdev_virtio: implement multiqueue
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>
2017-10-16 15:48:09 -04:00
Dariusz Stojaczyk
14db5b6646 rte_virtio: removed virtio_logs.h
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>
2017-10-16 15:48:09 -04:00
Dariusz Stojaczyk
7e4f3dbfdc rte_virtio: remove virtio_queue.h/.c
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>
2017-10-16 15:48:09 -04:00
Dariusz Stojaczyk
66d101ffee rte_virtio: remove virtqueue_notify()
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>
2017-10-16 15:48:09 -04:00
Dariusz Stojaczyk
5b6e67886e vhost: added multi-process support
Added -i parameter to vhost that specifies DPDK shared memory id.

Fixes #171

Change-Id: I103eb57886eed2c1663137b5b8195a11039319fa
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/373692
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@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>
2017-10-16 15:29:58 -04:00
Pawel Wodkowski
cc3c79065c env: don't free DPDK eal arguments
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>
2017-10-16 15:29:58 -04:00
Tomasz Zawadzki
7aba48fe1e subsystem: move allocation of subsystem_init event to subsystem
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>
2017-10-16 15:14:36 -04:00
Tomasz Zawadzki
0473a303e0 ut/lvol: test vbdev_lvs_destruct() with lvol created
Previously vbdev_lvs_destruct() was only tested without lvols
created, so only simpler path was tested.

spdk_lvol_close/destroy() in unit tests now properly finishes
removing lvs and unregistering the device.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I5f0f1feee4642aa01554aa0b7781f5cd0e22a4e6
Reviewed-on: https://review.gerrithub.io/382283
Reviewed-by: Maciej Szwed <maciej.szwed@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>
2017-10-16 13:13:22 -04:00
Tomasz Zawadzki
9f12ec9d32 lvol: remove lvol from lvol_store->lvols list once in lvol destroy
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>
2017-10-16 13:13:22 -04:00
Tomasz Zawadzki
df45eaecf7 lvol: prevent unloading lvol store when lvols are open
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>
2017-10-16 13:13:22 -04:00
Daniel Verkamp
5aecabfbd5 bdev/virtio: remove unused virtio_user_dev parts
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>
2017-10-16 11:17:16 -04:00
Daniel Verkamp
64096b6031 bdev/virtio: check allocation in virtio_user_dev_init()
Change-Id: Ib8cc74b4b975013c97c3b5cc68489d8ac9b3970d
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382495
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: Changpeng Liu <changpeng.liu@intel.com>
2017-10-16 11:17:16 -04:00
Daniel Verkamp
7aa53faabd bdev/virtio: remove __rte_unused annotations
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>
2017-10-16 11:17:16 -04:00
Daniel Verkamp
c32510daa8 bdev/virtio: remove unused dirent.h and fcntl.h
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>
2017-10-16 11:17:16 -04:00
Daniel Verkamp
f5c4413ca4 bdev/virtio: use SPDK likely/unlikely macros
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>
2017-10-16 11:17:16 -04:00
Dariusz Stojaczyk
aab8511796 vhost_scsi: minor cleanup
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>
2017-10-13 19:13:00 -04:00
Shuhei Matsumoto
6bb01df6d7 iscsi: delete spdk_iscsi_init_grp_deletable() function
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>
2017-10-13 18:38:55 -04:00
Seth Howell
072d90ccc8 test/nvme: add app to check value of deallocated blocks
Useful in the case of drives that don't indicate this in their
information.

Change-Id: I128fb613cbc4638b9dcbe234b6bae6d056e48f71
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/379689
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-13 18:09:08 -04:00
prital shah
75e31e26e3 doc:add Performance report section
Change-Id: I3dc7aa70d8a326fb842a2dcbd6a8f9032d98b154
Signed-off-by: prital shah <prital.b.shah@intel.com>
Reviewed-on: https://review.gerrithub.io/382375
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-10-13 16:15:40 -04:00
prital shah
7806883764 doc:add tools section
Change-Id: I6e8a6d636b8d7236a40b7da34722c77677b6cc91
Signed-off-by: prital shah <prital.b.shah@intel.com>
Reviewed-on: https://review.gerrithub.io/382374
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-13 16:15:40 -04:00
Daniel Verkamp
35875d5314 bdev/rbd: combine readv and writev functions
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>
2017-10-13 15:25:51 -04:00
Ziye Yang
847c1c3ad4 nvmf/rdma: Remove rdmq_req if there is error or obtaining buf.
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>
2017-10-13 15:13:31 -04:00
Maciej Szwed
f1c7998742 lvol: return meaningful RPC errors
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>
2017-10-13 14:50:30 -04:00
Cunyin Chang
5bf109d507 blob: Optimization of data structure and functions for bs load and unload.
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>
2017-10-13 14:49:30 -04:00
Tomasz Zawadzki
1887183f13 bdev_pmem: pmem pool file managment via RPC
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>
2017-10-13 10:48:39 -04:00
Pawel Niedzwiecki
c31fb325a7 vhost_scsi: fail requests to device marked for removal
Change-Id: Ie9eea844a64653cf9c016eb3ad96c80546600762
Signed-off-by: Pawel Niedzwiecki <pawelx.niedzwiecki@intel.com>
Reviewed-on: https://review.gerrithub.io/382170
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>
2017-10-13 10:47:32 -04:00
Daniel Verkamp
709f7b0104 bdev/virtio: replace rte_read/write with spdk_mmio
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>
2017-10-13 10:46:00 -04:00
Daniel Verkamp
15e978340d mmio: add functions for 1 and 2 byte I/O accesses
Change-Id: I7a325ddd8db3424207cf2e561c6d6e894f549989
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382073
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>
2017-10-13 10:46:00 -04:00
Dariusz Stojaczyk
201c0188ac bdev_virtio: define virtio devs in separate config sections
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>
2017-10-12 19:40:19 -04:00
Hailiang Wang
f062f79768 scripts: replace NRHUGE with HUGEMEM in setup.sh
This allows to use same command
for allocating hugepages on
systems with different hugepage
sizes.

The old NRHUGE variable can be
still set on Linux machines,
but is currently undocumented.

Change-Id: I1fba315d95e9aae8b6a8c9c445deb447fecc65dc
Signed-off-by: Hailiang Wang <hailiangx.e.wang@intel.com>
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/369546
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-12 18:27:21 -04:00
Daniel Verkamp
0722434074 nvme/identify: print discovery log contents
Now that we can connect directly to a discovery service via
spdk_nvme_connect(), it is useful to have the ability to dump its
discovery log page in the identify example.

Change-Id: Ie32f7ae2f0725874fed56258aa3c07d619fce0dd
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382208
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-12 16:39:55 -04:00
Daniel Verkamp
415dcbf8cd doc: add JSON-RPC docs for nvmf_tgt methods
This is a first pass at adding documentation for JSON-RPC methods.

Currently, this covers the following nvmf_tgt RPC methods:
- get_nvmf_subsystems
- construct_nvmf_subsystem
- delete_nvmf_subsystem

Change-Id: I51f74eed52e68fef8307a278b2e36c326689bf92
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/381559
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-12 16:37:52 -04:00
Maciej Szwed
ee732292d6 lvol: create super blob on lvolstore initialization
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>
2017-10-12 16:34:54 -04:00
Shuhei Matsumoto
75af8a1081 scsi: add UT code for spdk_scsi_dev_add/delete_port
scsi_dev's port management became a little complex by supporting
delete port operation. Bugs were detected by code review. Hence
UT code were added. Submit UT code to master.

Change-Id: I7449dab9032683311268fcccc20513ee78fc981b
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/381913
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-12 15:46:14 -04:00
Shuhei Matsumoto
0e5b81b3d7 scsi: remove port from scsi_dev dynamically
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>
2017-10-12 15:46:14 -04:00
Pawel Wodkowski
205a00d9fa vhost: disable indirect descriptors
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>
2017-10-12 14:21:43 -04:00
Daniel Verkamp
6f6645e2d8 bdev/malloc: allow user to specify bdev name
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>
2017-10-11 23:55:45 -04:00
Ziye Yang
e35816b4be bdev/gpt: change the log level.
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>
2017-10-11 14:00:16 -04:00
Ziye Yang
b114103736 nvme_rdma: set retry_count field in rdma_conn_param
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>
2017-10-11 13:59:10 -04:00
GangCao
13d4f08480 nvme/example: add the call to spdk_nvme_connect()
In this identify example, added a call to the newly introduced
public spdk_nvme_connect() API so that other related change can
refer to this one as an example.

Change-Id: Iba97b6e52810a66d4c781bb563985e84ffb86708
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/382070
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-11 13:58:14 -04:00
Maciej Szwed
e46404f9cb bdev: remove bdev_opened field from spdk_bdev structure
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>
2017-10-11 12:13:38 -04:00
Maciej Szwed
6ae7b826ca lvol: claim base bdev on lvol load
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>
2017-10-11 12:13:38 -04:00
Maciej Szwed
c4fe479812 blob: add support for base bdev claim
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>
2017-10-11 12:13:38 -04:00
Pawel Kaminski
96bd19093b test/vhost: Fio tests for vhost initiator.
Change-Id: Iad11eef12c0f7f80c26264f65a38df798eae1a27
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/378071
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>
2017-10-11 11:10:13 -04:00
Dariusz Stojaczyk
ad9e7060ed env: add SPDK_ENV_LCORE_ID_ANY
Added a copy of DPDK's LCORE_ID_ANY.
It's returned by some env functions,
e.g. spdk_env_get_current_core.

Change-Id: I19079a5bd714e32c309e5078e8de97ff1849c0aa
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382025
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-10 17:41:12 -04:00
Dariusz Stojaczyk
6c0233c0a5 bdev_virtio: slight cleanup
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>
2017-10-10 17:41:12 -04:00
Seth Howell
3da8f166d4 env_dpdk/init: remove shared memory files at exit
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>
2017-10-10 17:40:23 -04:00
Ziye Yang
36f9d416a1 fio_plugin: update the README
Describe the phenoemon for peformance difference
between fio + spdk plugin and spdk nvme perf
on multiple NVMe SSDs while both using single
cpu core.

Change-Id: I80c2cfd51cd1d8ec28a11a1a8653469cfc3335eb
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/379573
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-10 16:45:00 -04:00
Tomasz Zawadzki
526d759a2d vbdev/unit: destroy bs_dev during unload
If there is no lvol on lvol store in destroy bs_dev in
vbdev unit tests.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I5b4783c98bb1b6bba011118f46f708ad0f0fb222
Reviewed-on: https://review.gerrithub.io/382018
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-10 16:41:40 -04:00