1048 Commits

Author SHA1 Message Date
Jim Harris
4aac975b35 nvme: make nvme_qpair_enable just set the is_enabled flag
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I6782f311156dba87875a754fc64525f5ad7d06ea

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453748
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-05-14 08:48:11 +00:00
JinYu
040801010a unit/nvme: add spdk_nvme_connect unit test case
cover the opts_size examination

Change-Id: I8058f1db98713b5f19151b1b127180ae5ec58b96
Signed-off-by: JinYu <jin.yu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453944
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-05-13 23:04:04 +00:00
paul luse
7b641c757d bdev/compress: change how we manage mbufs
In working on a future patch to queue compress operations, I found
some corruptions in our mbuf pool stemming from an inconsistency
in using mbuf macros when constructing a compress operation and
how we allocated and freed both the pool and the mbufs.

This also fixes an issue that I hadn't addressed yet with freeing
chained mbufs.  Use of the mbuf macro to free them instead of the
generic spdk functions takes care of that for us.

Change-Id: I7b29a0d740ab745574698c721d575d8a735ad5cb
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453028
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-05-13 15:41:35 +00:00
paul luse
024e89afb3 bdev/compress: Populate params structure on load
On init, we pass reducelib the address of our params structure
so that the volume size is updated accordingly.  On load however,
there was nothing to set the volume size so any load of a previously
created compress volume would result in a 0 length bdev.

Change-Id: I7643c79fa2e664115fd25df064ff1c74d82e358b
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452906
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-05-13 15:41:35 +00:00
Ben Walker
59467b3a39 nvme: Support multiple spdk_nvme_connect to same device
Change-Id: I0b3e5d263ab15798302a2a32dfe860f29641fc06
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453009
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-05-13 15:40:36 +00:00
Darek Stojaczyk
376d893a20 vhost: introduce vsession->started
We used to rely on lcore >= 0 for sessions that are
started (have their pollers running) and in order to
prevent data races, that lcore field had to be set from
the same thread that runs the pollers, directly after
registering/unregistering them. The lcore was always
set to spdk_env_get_current_core(), but we won't be able
to use an equivalent get_current_poll_group() function
after we switch to poll groups. We will have a poll group
object only inside spdk_vhost_session_send_event() that's
called from the DPDK rte_vhost thread.

In order to change the lcore field (or a poll group one)
from spdk_vhost_session_send_event(), we'll need a separate
field to maintain the started/stopped status that's only
going to be modified from the session's thread.

Change-Id: Idb09cae3c4715eebb20282aad203987b26be707b
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452394
Tested-by: SPDK CI Jenkins <sys_sgci@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>
2019-05-10 22:31:41 +00:00
GangCao
40a9098fe9 ut/iscsi: add test case for portal groups destroy
Add the UT test case to cover below function:
spdk_iscsi_portal_grps_destroy()

Change-Id: I910b1066ff306039af8d4634122f894ffb3d66e1
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453499
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-05-10 22:26:46 +00:00
Konrad Sztyber
8c6f63a3f1 lib/ftl: name ftl_io's LBA / iovec unions
Replaced the unnamed unions with named ones. It makes the assignments
easier (it allows for direct assignment instead of having to choose the
correct union member).

Change-Id: I130233a096070092275a040e73cbaf36106ae1ab
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453682
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-05-10 22:20:57 +00:00
Ben Walker
dcb8ba7b8e thread: Add a cleanup function for threads
This reduces some repeated code. I could have made both paths
call spdk_thread_exit(), but I want to add some stronger checks
around the tls_thread there eventually that wouldn't be valid
in the other path.

Change-Id: I61e1484536d8aef05f120d9ed394312b41f8445a
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453575
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-05-09 04:35:10 +00:00
Ben Walker
835d21a2d0 thread: Allow thread schedule callback to fail
Change-Id: Id391c2c03804dda0ad354d98dfe0a75fb4d3d324
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453012
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-05-08 21:56:59 +00:00
JinYu
743081c22b unit/nvme: add FC and TCP in trid trtype test case.
Add two trtype test and increase code coverage.

Change-Id: I59543dc6aa56529b05bb7ac5717d9ba7004b8b72
Signed-off-by: JinYu <jin.yu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453626
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-05-08 21:27:32 +00:00
Jim Harris
fabd7fbb41 nvme: remove qpair_disable
This transport function is a complete nop now, so
remove it.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I5cc6ac75795a3cf5311f24e2ac293fb53d4b9f8c

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453487
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-05-08 01:44:20 +00:00
Jim Harris
783a2a20f1 nvme: add transport_qpair_abort_reqs
This will allow us to move more of the reset-related
functionality to the common layer, as part of enabling
resets for fabrics controllers.

The transport qpair_enable and qpair_fail functions
acted similarly - so those are both removed now and
replaced with this new qpair_abort_reqs function.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I9486630ad5b807239b0b5bcde50e8cfd313695d3

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453486
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-05-08 01:44:20 +00:00
Jim Harris
74aa552ef9 nvme: make helper function to abort outstanding err reqs
The nvme_qpair_disable functions will be going away in
an upcoming patch, so move this one bit of functionality
into a helper function in advance.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I61c2de535c2230b988d56dea13b00f39cb59dcfa

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453483
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-05-08 01:44:20 +00:00
Jim Harris
f366e261a6 nvme: abort aers at common layer
We submit AERs to all controllers - both pcie and
fabrics.  But currently we only manually abort the
aers when disabling the qpair for pcie.  Make this
common instead by creating a new transport function
for aborting aers.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I1e926b61b8035488cdc6e8cb4336b373732f985e

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453482
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-05-08 01:44:20 +00:00
Jim Harris
14e67af3c5 nvme: rename reinit_io_qpair to reconnect_qpair
This better explains what the function is doing,
and makes the name more general so we can use it
for the adminq as well.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I6b55761cb141a9a79cdef876be47995d8813b312

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453480
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-05-08 01:44:20 +00:00
wuzhouhui
ab3f35b226 lib/notify: rename spdk_notify_get_events to spdk_notify_foreach_event
And change type name of callback as well. The new name is more accurate.

Change-Id: I13b63f7d33f60ecea7fdf6e50f57aa6a391a4562
Signed-off-by: wuzhouhui <wuzhouhui@kingsoft.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453151
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-05-07 06:11:27 +00:00
Ben Walker
df9129300c thread: Call spdk_thread_lib_init in unit tests
Change-Id: Ib05b9f2ea6582a96b0719a2834c2ad6896fb744e
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453011
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-05-06 17:34:31 +00:00
Darek Stojaczyk
78326e722f blobfs: remove trace short names
They were removed from the trace API and BlobFS doesn't
compile right now.

Change-Id: Ie98339f19353e4db901af551c706f57c18b89fc5
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452863
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-05-02 09:57:57 +00:00
Mike Carlin
a6524cd1f8 raid bdev: Change product_name to "Raid Volume"
The product_name for raid bdevs was "Pooled Device" which was a legacy
naming convention that hadn't been cleaned up yet. This changes the
naming to be up to date with the current naming scheme.

Signed-off-by: Mike Carlin <mikefcarlin@protonmail.com>
Change-Id: I9092a2b793e48bb9ec0349087a31fdcde17ed9cd
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452269
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-05-02 09:02:52 +00:00
Jim Harris
617184be3b trace: remove short_name
This was not used by any of the trace register descriptions.
Let's remove it rather keeping it around if we don't need it.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Idda809e2911db5be555ff6aa13695484a14bf665

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452734
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2019-05-02 08:41:56 +00:00
Jim Harris
af25204404 bdev/nvme: always enable FTL
FTL doesn't have any kind of special package requirements.
It is getting pretty good traction in the community, so
let's enable it by default.

Note that we will disable FTL on FreeBSD.  FTL uses
CIRCLEQ which is not available on FreeBSD.  Let's not
spend time trying to get FTL to work on FreeBSD until
there's a demand to do so.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I15525b6c4e6ee52f49adf74d55f9484fe08a6dcc

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452752
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-05-02 08:41:56 +00:00
Ben Walker
8df1f6b220 iscsi: Rename spdk_iscsi_conn_migrate to spdk_iscsi_conn_schedule
This function is in charge of scheduling new connections
onto cores. It used to be used to dynamically migrate
connections, but we no longer do that.

Change-Id: I2fa04a7dfb43bf9fae7902376ba5ba6d18744469
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452727
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-05-02 08:33:48 +00:00
Anil Veerabhadrappa
2061874474 lib/nvmf: Validate requested SQ size for both admin and IO queue
During connect call based on queue type (AQ or IOQ), SQ size should be
validated against max sq size for that particular queue type.

Change-Id: I977d7556e4d04e37004d16c87efffd3b467fa62c
Signed-off-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452376
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-05-01 18:51:28 +00:00
JinYu
50a130c6da nvmf: add keep alive unit test
Add the KATO==0 uint test of keep alive feature.
1, If subsystem == nvme && KATO == 0, it means initiator don't want
to enable keep alive feature, the keep_alive_poller would not be registered.
2, If subsystem == discovery, KATO must be 0.

Change-Id: I212b344e235e94d5f34168d43d45766283773446
Signed-off-by: JinYu <jin.yu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/451819
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-05-01 18:44:29 +00:00
Jim Harris
f71fed216c blobfs: add trace events
For now, just do events for open, close and start/end
for writing the length xattr.  These will be useful for
debugging the intermittent RocksDB failures.

Note these events may only be recorded on the polling
SPDK thread.  SPDK events cannot be recorded on
non-SPDK threads (i.e. RocksDB user or background threads).

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I72fb302db23b399f583f56194c237340587f3027

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452262
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-05-01 17:10:43 +00:00
Jim Harris
dd1c38cc68 trace: allow arg1 to represent a string
This requires changing arg1_is_ptr to arg1_type.
We will use this to print the first 8 characters of
a blobfs filename when collecting event trace data.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I1b321d99145e82b42dcf6d901ce9d6298158edae

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452259
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-05-01 17:10:43 +00:00
Tomasz Zawadzki
b5f96b0ea5 ut/blobstore: write and allocate clusters from multiple threads
This patch verifies that functionality of only releasing cluster
that was originaly claimed in race thread condition.

Change-Id: I4d60ffdb4fd6612d61a761835aae2fd1bf81b7fd
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452626
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-04-30 14:43:09 +00:00
Wojciech Malikowski
049624823b lib/ftl: Rely on internal IO position during ftl_io_done()
Change-Id: I7a7667e1c4e6321150e5bc8eb4287fb61847ccb5
Signed-off-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450174
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Young Tack Jin <youngtack.jin@circuitblvd.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-04-24 23:24:21 +00:00
Maciej Szwed
e6100af425 blobstore: block simultaneous operations on blobs
Block operation that should not be done simultaneously.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I3cab510377a49be4e5847ba37a6218f0025c0db6

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450014
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-04-24 22:43:47 +00:00
paul luse
933270eafd bdev/crypto: add new uninit call needed for dpdk 19.02
This patch won't fix issues related to the need for the latest
ipsec with 19.02 but it is needed for that patch to pass.

Change-Id: I8e2d984d85b355d88edfb9c90c159c8aa0a5362d
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/451788
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-04-24 22:00:10 +00:00
Konrad Sztyber
ef5ede4b51 lib/ftl: allow parent/child relations between IOs
Extended the IO descriptors with the ability to group them together in a
parent / child(-ren) relationship. It allows to delay parent completion
until all children are done and enables the children to have additional
context in their completion routines (as opposed to having a single IO
describe all requests).

Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I6ad111dc231813e397697109a333e2a5d7f5941d
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/449068
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-by: Young Tack Jin <youngtack.jin@circuitblvd.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-04-24 21:57:06 +00:00
Ben Walker
5d0b5e2ce9 thread: Add cpumask parameter to spdk_thread_create
Allow users to optionally specify an affinity mask when
creating a thread. This isn't currently used, but we want
the API to be in its final form for the next release.

Change-Id: I7bd05e921ece6d8d5f61775bd14286f6a58f267f
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/451683
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-04-23 20:22:55 +00:00
Darek Stojaczyk
283abcb9a2 bdev: temporarily allow bdev descriptors to be closed from any thread
Bdev descriptors could be closed only from the same thread
that opened them. This restriction was suddenly introduced
at one point without making sure all the SPDK code respects
it. Vhost can still close descriptors from any arbitrary
thread and fixing that would require some more effort.

With this patch we remove the thread-specific assert from
spdk_bdev_close() and hence allow vhost to work properly
in debug builds. Vhost can still have a possible data
race with bdev hotremove notification, but let's get rid
of the abort() from the usual code path first.

Change-Id: I6fac66a5ebc907b1c5418fff618f0b64cd9b69f4
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/451561
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-04-23 17:06:37 +00:00
Darek Stojaczyk
f93b6fb0a4 bdev: defer unregister untill *all* descriptors are closed
We used to wait only for those descriptors which
specified the hotremove notification callback. The
bdev could've been removed before the descriptor
was closed and the subsequent spdk_bdev_close would
simply segfault.

This patch modifies spdk_bdev_unregister to always
wait for all descriptors to be closed before actually
unregistering the bdev. This consolidates the bdev
unregister behavior for descriptors with and without
the hotremove callback.

Change-Id: I9b358209c6abd301b6fe8660e27bc6fa4ef485d6
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450175
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-04-23 17:06:37 +00:00
Gregory Shapiro
14032a984c NVMF: Add model number as parameter to construct_nvmf_subsystem (-d option).
Change-Id: Ia1a458a0ac1c5a17d2955a3f31c6dfe77538eb17
Signed-off-by: Gregory Shapiro <gregory.shapiro@kaminario.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/438562
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-04-23 16:51:16 +00:00
Changpeng Liu
3b214eb8f3 UT/nvmf: add controller reservation notification log unit tests
Change-Id: I98dba9998e412db101437e9276648dac6eba2de5
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450490
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-04-23 16:30:24 +00:00
Changpeng Liu
4fa486a1e3 nvmf: add asynchronous event for reservation notificaiton
Now Host can get an asynchronous event notification when
registrants were unregistered/preempted or reservation was
released from the associate namespace, Host can send
get log page to clear related log pages and reservation
report to get the full overview of current reservation
configuration.

Change-Id: Idc57c19812490c7536503308989871515e9f2361
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/439935
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-04-23 16:30:24 +00:00
Shuhei Matsumoto
56d8b78576 lib/scsi: Make spdk_scsi_dev_destruct asynchronous
This is the end of the patch series. After this patch,
delete_target_node RPC will wait for the completion of
removal of the SCSI device and then free the iSCSI target.

SCSI device holds passed callback and calls it in free_dev().
free_dev() is ensured to be called after all iSCSI sessions
are closed. So iSCSI target resource can be freed safely
after that.

Change-Id: I25921b4014207092b7b3845dfeae58bcdffa2edc
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450607
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-04-22 18:22:59 +00:00
Shuhei Matsumoto
9470d65e8d lib/scsi: Add lun to the names of descriptors and callback for LUN
The next patch will add the function ponter typedef
spdk_scsi_dev_destruct_cb for SCSI device destruction.
Hence add lun to the names of descriptors and callback for SCSI
LUN for clarification.

This patch doesn't change any behavior.

Change-Id: I73f2bce9129f7a6f16770ab6ed18428b16589108
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450883
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-04-22 16:00:42 +00:00
Shuhei Matsumoto
a5478cefbd lib/iscsi: Exit related connections at the start of target node destruction
When any iSCSI target is destructed, if the target exits all corresponding
connections first, destructing SCSI device will be easier.

Hence, iscsi_tgt_node_destruct() starts exiting all corresponding
connections. Then it destructs SCSI device immediately if no active
active connections, or waits for the completion if there is any
active connection for the target.

Change-Id: Ibd4a29789faecfefccefa1153a519c43d040a00d
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450737
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-04-22 16:00:42 +00:00
paul luse
766c536184 bdev/compress: add missing mocks and re-enable UT build for comp
Disabled temporarily earlier to get to basic functionality, circling
back now to begin work on UT again.

Change-Id: Ie7606f91072257f392727bdecc5f1eac26380453
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/451063
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-04-22 15:44:38 +00:00
Seth Howell
ae694fced8 rdma_ut: add test cases for rdma multi-sgl parsing.
Change-Id: I3ed0b87cdb3496f5096ed5b86e5a8a350064f212
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450306
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-04-19 17:29:45 +00:00
Changpeng Liu
b62dca9308 UT/nvmf: add nvmf reservation notification unit tests
Change-Id: I7bceb437a6e68e8a933587f71f35a6a66fccce9b
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/439932
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-04-12 01:25:39 +00:00
Changpeng Liu
78bfb2a1d0 nvmf: generate reservation notification log pages
A host can use the Asynchronous Event Command to be notified of
the presense of one or more avaiable reservation notification
log pages.  A reservation notificaton log page should be created
whenever an unmasked reservation notification occurs.

Change-Id: I8b83e5319725286dd0a5efc1b22d8ac4673e31e1
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/439931
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-04-12 01:25:39 +00:00
Shuhei Matsumoto
8cc7b0bc4d lib/iscsi: Set destructed at the start of target node destruction
Add the flag destructed to struct spdk_iscsi_tgt_node and
iscsi_op_login_check_target() refers it and returns
ISCSI_LOGIN_TARGET_REMOVED if it is true.

When destructing iSCSI target node, it will be nice if iSCSI library
can stop further connections are created but, connections are not
associated with any target node until processing login. Hence stop
creating sessions instead.

Additionally, when destructing iSCSI target node, if the flag destructed
is already set, return immediately, and the flag destructed does not
affect discovery session.

Change-Id: Ic73bdd93f2ca7d5ca1d2f897d5046cbc51650d5f
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450881
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-04-11 18:33:18 +00:00
Shuhei Matsumoto
d09eff6a0f lib/iscsi: Make two helper functions from private to public in iSCSI library
These change will be used in the next patch.

Change-Id: Ifdb4ccf20049b46e850122a4021cbbe7441e1270
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450736
Tested-by: SPDK CI Jenkins <sys_sgci@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>
2019-04-11 18:33:18 +00:00
Shuhei Matsumoto
5f51f0aff6 bdev/raid: Add callback parameters to remove_base_devices()
This is a preparation to add completion callback to the
destroy_raid_bdev RPC.

Newly added callback parameters are passed to spdk_bdev_unregister()
in the end. This patch adds just parameters and the next patch will
utilize them.

Change-Id: Ic239c55872c0c69f3d1625eaccdb91a32a9d4d30
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450572
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-04-10 20:41:57 +00:00
Shuhei Matsumoto
1ba9859353 bdev/raid: Change the prefix of names of lists from g_spdk_ to g_
Configuration lists in RAID bdev are unlikely to be exposed outside
of the RAID bdev module. Hence simply the prefix g_ will be enough
to clarify they are global data structure in RAID bdev module.

Change-Id: I9df88db8fa651d5af7d771d88ff04bb5997079c9
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450563
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-04-09 18:20:40 +00:00
Darek Stojaczyk
bb64a7e511 ut/bdev_mt: fix io_channel leak in "unregister_and_close"
We didn't call teardown_test() in "unregister_and_close"
test case, causing the subsequent test case to fail
to register the same io_channel. This didn't cause any
issues, as spdk_io_device_register() silently returned
if the same io_device was already registered. However,
there was an extra error message printed and this patch
gets rid of it.

```
  Test: unregister_and_close ...passed
  Test: basic_qos ...thread.c: 850:spdk_io_device_register: *ERROR*:
io_device 0x55555576e4e0 already registered (old:0x555555770ab0
new:0x55555d7a14d0)
passed
```

Change-Id: Ib554612df8985c9d99b46b71bb76020f52565362
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450111
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-04-05 16:21:58 +00:00