Commit Graph

4786 Commits

Author SHA1 Message Date
Changpeng Liu
0f15edee2d nvmf: factor out namespace change helper function
Change-Id: Iaeaf308bc2135cf94a3e1fd94c3c5d56f8a2f86e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405130
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2018-04-03 17:29:56 -04:00
Changpeng Liu
763ab88884 nvmf: add Namespace attribute notice support
Users can use RPC to add/remove a namespace to/from
existing NVMe controller, SPDK NVMeoF target will
generate an asynchronous event as an indication to
host when asynchronous event request is available.

While here, we also set the event with invalid log
identifier, so that the host doesn't need to clear
the event. Users can use Set Feature to disable
such event.

Change-Id: I93c4d752f552d3c86c53e80877aa61c093e167cc
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/398759
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>
2018-04-03 17:29:56 -04:00
Shuhei Matsumoto
22b8b92275 bdev/error: Add config of error vbdev when the base bdev of it doesn't exist
Currently construct_error_bdev() fails if the base bdev doesn't exist.
This patch add configuration of the error vbdev for the base bdev instead,
and the configuration will be parsed at examine() when the base bdev is
created.

This will improve the usability of error injection for bdev and will be
usable for the upcoming JSON config file.

Change-Id: I550b7f6c74fd8ab6cbd424a192f12a0c0099028e
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403914
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>
2018-04-03 15:33:14 -04:00
Yanbo Zhou
070e72eda7 include/env.h: add comments for public APIs
Change-Id: Ic661748435a5fcd2ec233802366f6870b072e6df
Signed-off-by: Yanbo Zhou <yanbo.zhou@intel.com>
Reviewed-on: https://review.gerrithub.io/403444
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-03 15:26:10 -04:00
xuhuagen
a04b77e6bd rpc: rpc method 'load_config' should need 2 parameters.
Change-Id: I7a47d2187d135353d7f843a815fcbbb87ac4523b
Signed-off-by: xuhuagen <huagenx.xu@intel.com>
Reviewed-on: https://review.gerrithub.io/406138
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>
2018-04-03 15:23:12 -04:00
Dariusz Stojaczyk
3cb775b9ae virtio: don't silence vhost-user errors
All errors were being silenced in an upper virtio layer.
This patch makes them properly propagate further.

Change-Id: I289c810ff0f670c4ba1fbcf0804089639fa561a8
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/405918
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>
2018-04-03 15:22:49 -04:00
Dariusz Stojaczyk
91bdec96c7 virtio/vhost_user: set NEEDS_RESET status bit if necessary
This protects against brute-force initialization that virtio
is not really prepared for. Most importantly, this behavior
makes us Virtio spec compliant (3.1 Device Init.).

Change-Id: I6d26f3d8b5cce488a71068777531b78538489662
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/405917
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>
2018-04-03 15:22:49 -04:00
John Kariuki
8ac087613c bdev/passthru: read/write access
Change-Id: I541b5846f2c1c4acd2c7a6771147738112c8f803
Signed-off-by: John Kariuki <John.K.Kariuki@intel.com>
Reviewed-on: https://review.gerrithub.io/406118
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-03 15:15:30 -04:00
Karol Latecki
d798ac57a7 autorun_post: save aggregated test completion list to file
First save the list of run / not run tests to file for
easier re-use later and then print to screen.

Change-Id: I1cb4ea057a75f08cac43853299f509d03b299709
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/405222
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>
2018-04-03 15:12:50 -04:00
xuhuagen
dd8b1719d2 rpc: rpc method 'get_rpc_method' does not need argument
Change-Id: I5e64a938e5df21f773476a7f96fea0a4a8a205c1
Signed-off-by: xuhuagen <huagenx.xu@intel.com>
Reviewed-on: https://review.gerrithub.io/406123
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>
2018-04-03 15:04:16 -04:00
Daniel Verkamp
08ec96eb70 configure: capture environment variables in config
Capture the current value of CFLAGS, CXXFLAGS, LDFLAGS, and DESTDIR in
the CONFIG.local output from configure.

This allows sequences like this to work:

  CFLAGS='-O3' ./configure
  make

Change-Id: I1112577a94e35b948e8761b920a5bd2e4fcb10a9
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405692
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-03 15:02:21 -04:00
Changpeng Liu
90c0e24410 vhost_user_nvme: add vhost user nvme target to SPDK
Similar with exist vhost scsi/blk target, this commit introduces
a new target: vhost nvme I/O slave target, QEMU will present an
emulated NVMe controller to VM, the SPDK I/O slave target will
process the I/Os sent from Guest VM.

Users can follow the example configuation file to evaluate this
feature, refer to etc/spdk/vhost.conf.in [VhostNvme].

Change-Id: Ia2a8a3f719573f3268177234812bd28ed0082d5c
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/384213
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>
2018-04-03 15:01:24 -04:00
Daniel Verkamp
20e69cf6b1 test/vm_setup.sh: add nvml-tools for pmempool
Change-Id: I964c45f652c6a24a05300d63f9c417e0f26e97e9
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405919
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
2018-04-03 14:14:29 -04:00
Daniel Verkamp
5d0b4b270e test/nvmf: remove nvmf_tgt+pmem test
This has been replaced with a pmem component-level test.

Change-Id: I3c433d9edbb4c4f0ff26d7716cd11ee9df5c0ad7
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405910
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
2018-04-03 14:14:29 -04:00
Daniel Verkamp
6b5a1d6c24 bdev/pmem: add conf support to test in blockdev.sh
The long-term plan is to use the JSON-based configuration format, but
for now, we need a config file section to be able to test a bdev module
in blockdev.sh.

Change-Id: I2a69f7172693ed6d4939a3b938747e2a1c62ff83
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405908
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2018-04-03 14:14:29 -04:00
Changpeng Liu
998b961e75 nvmf: set the subsystem state to inactive when removing it
Since the function call will remove all the active I/O channels,
the pollers don't need to submit all the pending I/O requests any
more.

Change-Id: I93e7b070f5c74b10f67bd1248fa515a29dca5620
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/403759
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>
2018-04-03 14:12:24 -04:00
Daniel Verkamp
e134fa47c2 app: set default print log level INFO, log NOTICE
This causes INFO logs to be printed to screen, but only NOTICE and more
critical logs to be sent to syslog.

Change-Id: I1371cd1485348da82d073d7f929d90609adbc3d8
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405932
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2018-04-03 13:52:35 -04:00
Slawomir Mrozowicz
5f9ba5b837 rpc: fix initiator address verification
In function verify_iscsi_connection_rpc_methods fixed
initiator address verification. It was used addres for target. From now
it is used separate addres for initiator.

Change-Id: I46ee7ab758b24342b6a25553a62a517914e9b70e
Signed-off-by: Slawomir Mrozowicz <slawomirx.mrozowicz@intel.com>
Reviewed-on: https://review.gerrithub.io/405582
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
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>
2018-04-03 13:30:52 -04:00
suman chakraborty
bc9423e229 Segfault occurs during connect to the subsystem when a namespace is added with a nsid smaller than the nsid previously added
Change-Id: I74c7b32e1713d683e5d80818724ed3b19f3dac64
Signed-off-by: suman chakraborty <suman.chakraborty@wdc.com>
Reviewed-on: https://review.gerrithub.io/405373
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>
2018-04-03 13:26:14 -04:00
Shuhei Matsumoto
af7cbd44b0 event/app: Refactor initialization of trace in spdk_app_start()
Refactor spdk_app_start() in lib/event/app.c to support JSON config file.

Change-Id: I259f17dd2b2a9c886bae729b40792f04aa638c3a
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/405364
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>
2018-04-03 13:21:22 -04:00
Shuhei Matsumoto
93cb4a311a event/app: Refactor initialization of app environment in spdk_app_start()
Refactor spdk_app_start() in lib/event/app.c to support JSON config file.

Change-Id: Iedcbdeef5cc48c9aab4137735c1eae8daeb63950
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/405363
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-04-03 13:21:22 -04:00
Tomasz Zawadzki
c99069fd46 test/iscsi: change target IP for calsoft tests
Target IP for Calsoft tests was hardcoded in config file.
Now it will be based on iSCSI tests common configuration.

Change-Id: Ic8db40b02d2be59f5fac5cb4503cc0c80b24cd91
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/405865
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2018-04-03 13:11:17 -04:00
Karol Latecki
8d27c02378 scripts/rpc.py: move exit on error to rpc.py
Moving exit in case of error to rpc.py
By using exceptions in  client.py it is easier to use it
as module in other scripts.

Change-Id: Ic9ecef481ef5b6a169e1293b3dcf859ffbbe0e89
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/405739
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>
2018-04-03 11:59:33 -04:00
GangCao
3bce351916 iscsi: enable per-core cache for PDU data-out pool
With the preferred per core operation for the lockless
consideration, having some per core cache instead of
the shared gloal cache will help the performance.

Change-Id: Ib3cfaac5bad7062b15643d5b151d4c7c6051ddf1
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/404533
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>
2018-04-03 11:57:17 -04:00
Tomasz Zawadzki
583bc2efad vpp/doc: getting started guide for VPP
Change-Id: I269f11461696625f583cb31a01d87a0411d12dcc
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/404316
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-04-02 20:02:30 -04:00
Ziye Yang
6d4e6ffd08 nvmf: add the assert in ctrlr_delete_qpair
Change-Id: I4c23f83ebaf80f1b62fb4c1144ff864bdfd6efbe
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/406014
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>
2018-04-02 19:57:05 -04:00
Liang Yan
f0979076d6 autobuild: Fix typo in autobuild.sh
Change-Id: I6a63d70060cbaa3416cb6980092113b88baf593d
Signed-off-by: Liang Yan <liang.z.yan@intel.com>
Reviewed-on: https://review.gerrithub.io/406024
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>
2018-04-02 17:59:32 -04:00
Ed Rodriguez
06fbf4b34b nvme: Use active namespace list for enumerating namespaces
- Add support for multi page CNS 0x2
 - Use CNS value 0x02 (SPDK_NVME_IDENTIFY_ACTIVE_NS_LIST)
   to query active namespaces
 - Add an API to iterate the active list

Change-Id: Iea524881fa6e3610a7d85ab02a2005a92fd633df
Signed-off-by: John Meneghini <johnm@netapp.com>
Reviewed-on: https://review.gerrithub.io/401957
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>
2018-04-02 17:17:40 -04:00
Seth Howell
397521bdb9 autotest_common.sh: handle ceph luminous in rbd_setup
unlike previous implementations of ceph, luminous (which ships with
fedora 27) does not create a default pool for us. In case we are on a
system using luminous, we need to create that pool ourselves.

Change-Id: I183dc4fff6b92f7b270bd5a5d05947f0d99e9d04
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/405703
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>
2018-04-02 16:58:18 -04:00
Daniel Verkamp
7b4bc2a243 nvme/identify: print ASCII strings with helper
SN, MN, and FR are ASCII strings as defined by the NVMe spec; use the
new print_ascii_string() helper function to print them.  This trims the
trailing spaces and prevents accidentally printing any control
characters to the screen if the device provides an invalid ASCII string.

Change-Id: Ifaf383a79e13be62625250e7e79a305ebaa3612b
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405926
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>
2018-04-02 15:44:35 -04:00
Daniel Verkamp
8e56cd4131 env_dpdk: track PCI devices internally for vtophys
Replace the use of the private rte_pci_bus list with our own internal
list of PCI devices inside SPDK.  This fixes linking against the shared
library version of DPDK.

Change-Id: Ia69555e4e7caa1a40974b7969d48773e36ae0fd7
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405937
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>
2018-04-02 14:03:05 -04:00
Daniel Verkamp
75ed184a79 env_dpdk: use public function to check VFIO status
DPDK 17.11 added a public API, rte_vfio_is_enabled(), that we can use
instead of declaring and using pci_vfio_is_enabled().  This removes one
of the remaining non-public DPDK symbols we are currently using, getting
us closer to building against the shared library version of DPDK.

Change-Id: Idf4ee66d4868cf542521fa2896ed8c609d42ee29
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405921
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>
2018-04-02 14:03:05 -04:00
Pawel Wodkowski
60e8667261 bdev/split: move config scaning to vbdev_split_init
By this we are abble to produce proper RPC config in next patches.

Change-Id: I1ae9e81bf50bc4fb5e6a9cf7bf9b84df7e6377d1
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/403842
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-30 20:47:08 -04:00
Daniel Verkamp
d2e7daa435 nvmf: add stubs for all mandatory Get/Set Features
Most of these don't actually do anything useful yet, but they are all
required by the NVMe 1.3 specification.

The features are also rearranged in numeric order to make it easier to
match up the cases in the switch statements to the specification.

Change-Id: I5f70ecb0bb38b9e1d8287d32fc2e03bca5f1f8a6
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/403903
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>
2018-03-30 20:18:54 -04:00
Pawel Niedzwiecki
c9253b8f23 test/vhost: shorten tests by reducing file size on fio tests
There are timeouts in NIGHTLY_TEST mainly caused by long duration
of spdk_vhost.sh --fs-integrity-blk test. It could be shorten by
reducing file size in fio test

Change-Id: Ic99f6f3ce52ed8bf1fafc75bb0f908d9df0d0d4e
Signed-off-by: Pawel Niedzwiecki <pawelx.niedzwiecki@intel.com>
Reviewed-on: https://review.gerrithub.io/405587
Reviewed-by: Karol Latecki <karol.latecki@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>
2018-03-30 20:15:16 -04:00
Dariusz Stojaczyk
afd264b3f4 include/linux: update virtio_config.h
Updated to Linux 4.9.0. This introduces e.g.
VIRTIO_CONFIG_S_NEEDS_RESET flag that's required
for the next patch.

Change-Id: I562d0b9d9a3cb18fd484dda52fb447087062da47
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/405916
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>
2018-03-30 19:34:22 -04:00
Dariusz Stojaczyk
9728d6b054 virtio: check if setting status bits succeeded
This is required by the Virtio spec. (3.1 Device Init.)
It will also help us with vhost-user error handling.
set_status() doesn't have a way to return an error, so
its internal failures were silenced until now. When we
exceeded max memory region count (8) we only printed
an error message without failing any SPDK initialization.
This patch fixes that. It also removes not-particularly-
useful comments in virtio_dev_reset().

Change-Id: Ibe0010c493ef4e12e1fdd0a1679bf706f298d97e
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/405915
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>
2018-03-30 19:34:22 -04:00
Dariusz Stojaczyk
c2520346bf bdev/virtio/blk: fix memory leaks on device init failure
Change-Id: I43dfe7f7067a7344922f4dfbdce34b72754b9c0a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/405914
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>
2018-03-30 19:34:22 -04:00
suman chakraborty
5e98dfd126 nvmf: add capability to add namespaces dynamically during active connection
1) The user should provide MaxNamespaces during the construction of the subsystem
2) The namespace which is added should have nsid less than or equal to MaxNamespaces
3) If the user does not provides MaxNamespaces then the exsisting behaviour continues where the nisd can grow dynamically when it is not connected.

Change-Id: I54769d9669575a5f6bf56fe5a262191ac51c474d
Signed-off-by: suman chakraborty <suman.chakraborty@wdc.com>
Reviewed-on: https://review.gerrithub.io/405375
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>
2018-03-30 19:24:29 -04:00
GangCao
3709dfd674 bdev: update the function to get the QoS setting
Instead of accessing the qos_channel pointer on the bdev,
always have the QoS parameter on the allocated memory of
qos_channel structure.

The bdev->qos_channel is set to NULL in the destroy operation,
and the destroy is through the async message which could
be executed later after the poller function within which
the bdev->qos_channel is accessed (thus a NULL pointer
dereferenced).

In this case, assign the memory address of the allcoated
qos_channel to the function as the parameter to solve
this issue.

Change-Id: I2fdb53cb0a6a29fb41ab28362f8e068d21ee5d12
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/405438
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2018-03-30 17:43:25 -04:00
Ed Rodriguez
c540ca01a3 test: nvmf host test script modifications to support fc hardware
This problem was discovered after an lpfc card was installed
  in one of our CIT tetbeds. When an lpfc card is installed the
  modprobe call in identify_kernel_nvmf.sh will load lpfc
  as a side effect of loading nvmet. When this happens, you
  can't unload nvmet until lpfc is unloaded.

Change-Id: I2cf63ea7d20b7dc15d73c7a8c8502fb05bef29f8
Signed-off-by: John Meneghini <johnm@netapp.com>
Reviewed-on: https://review.gerrithub.io/405518
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>
2018-03-30 17:39:53 -04:00
Daniel Verkamp
cdaf4fd922 nvme/rdma: re-use memory registrations if possible
We don't need to re-register memory with the same ibv protection domain
more than once; maintain a global list of already-registered PDs and
reuse the existing registration for other queues.

Change-Id: I7ec9c35ed93083faa00cca4cb5c61104200a4c66
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405702
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-30 17:37:15 -04:00
GangCao
898bbb660b bdev: properly handle the io_outstanding count for QoS bdev channel
Change-Id: If9e52b9a16ffff7bd4263bfca85bf7cbaf53984c
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/405868
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>
2018-03-30 17:32:01 -04:00
Shuhei Matsumoto
cf4cf8d52a event/app: Refactor read global params of config file in spdk_app_start()
Refactor spdk_app_start() in lib/event/app.c to support JSON config file.

Change-Id: Ia2b36e517b59b6ac1ffb12cb818efc8064fae495
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/405362
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>
2018-03-30 17:31:04 -04:00
Shuhei Matsumoto
a4c86be7f0 event/app: Refactor check config file operation in spdk_app_start()
Refactor spdk_app_start() in lib/event/app.c to support JSON config
file.

Change-Id: I157573eea48b774579158f41a9010e5faa1a3de5
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/405361
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>
2018-03-30 17:31:04 -04:00
Daniel Verkamp
85f316b183 scripts/rpc.py: pass named args to nbd.py
Change-Id: I4703c813d80b805c7b747fc5ee8bc91ef3e20717
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405506
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-30 16:48:47 -04:00
Daniel Verkamp
94c0ce5503 scripts/rpc.py: fix help string for subsystem RPCs
These had an extra double quote at the beginning of the help string,
which showed up in the rpc.py -h output.

Change-Id: Iaa8ac94e3beb445091dcce41ffea90dde6c0fa22
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405505
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-30 16:48:47 -04:00
Daniel Verkamp
81088b8779 scripts/rpc.py: re-order delete_bdev function
The get_bdevs_config argparse and wrapper got inserted between the
delete_bdev wrapper and its argparse code.  Move the delete_bdev
function down so it is next to the parser setup for that method.

Change-Id: Ib0af5c3c89ce332ef689d44321f8724116a1241a
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405503
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-30 16:48:47 -04:00
Daniel Verkamp
3eaf92650b scripts/rpc.py: pass named args to subsystem.py
As an example of how we want the Python wrappers for the RPC interface
to look, convert the methods in scripts/rpc/subsystem.py to have
explicitly named arguments and pass the JSONRPCClient object explicitly.

Change-Id: I9d2e194ce7fde535d323383925f7825ab93909de
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405500
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-30 16:48:47 -04:00
Daniel Verkamp
96dc91d608 scripts/rpc.py: pass client as separate parameter
Split client out of the args object and pass it as the first parameter
to all RPC methods instead.  This is a step toward decoupling the
rpc/*.py interface from the argparse front end.

Change-Id: Ib030862e0c79112e5c9acdde295d68983126a987
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/405502
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-03-30 16:48:47 -04:00