Commit Graph

11938 Commits

Author SHA1 Message Date
Ben Walker
bc2fdcb280 bdevperf: Separate job construction for -C from normal mode
Make these two separate code paths so normal mode doesn't need
to do an spdk_for_each_channel and iterate every thread just
to get to the single thread it wants to build a job on.

Change-Id: Ibe57b3f3d4f990550ef4f5da93cb8ca54ae3ab85
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1510
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-04-17 07:40:47 +00:00
Vitaliy Mysak
d7a3a052ab ocf: update ocf submodule to v20.3
New OCF version is ready, so update our submodule.
There were a lot of API changes so
we need to adjust our bdev/ocf and lib/ocf_env code.

Description of code changes:
- env: added small functions like ENV_BUILD_BUG_ON, env_vzalloc_flags
- env: added "destroy" method for all locks
- env: added "execution context" interface
- cache/core "id" field made private
- signature of "ocf_io_configure" changed
- "io->volume" field made private

List of changes to OCF is available at
https://github.com/Open-CAS/ocf/releases
But no new features were implemented for our
OCF module since 19.6

Change-Id: I1ac2b6db0aad2a9840e4fa73d65608c5638fcb23
Signed-off-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1801
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-17 07:32:48 +00:00
Vitaliy Mysak
e316ec90b2 lib/env_ocf: fix locks implementation
Some of the locks implementation in our OCF env
is different from suggested posix implementation (ocf/env/posix),
which leads to deadlocks in OCF v20.3

This patch copies correct implemention from example
posix env.

Change-Id: Ib3bb1cf3532b9e5ebc450a1569c620d95efe6704
Signed-off-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1867
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-17 07:32:48 +00:00
Maciej Wawryk
6ec892634e scripts/perf: Enable percentile 999 measurements in fio config
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: I32c534196108c4795bcd6cd8392e3a1b0a5dd6e9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1842
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
2020-04-17 07:31:55 +00:00
Michal Berger
dcae88350e test/lvol: Rewrite clear_method_none and clear_method_unmap to Bash
These are the final test cases from the series of ports, thus clean up
the python script and its lib as well.

Change-Id: I9923fc93fbeb8c2d54dd2dad5acae41eaf5cfff5
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/934
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-04-16 09:45:30 +00:00
Michal Berger
75b782be4f test/lvol: Add function for calculating ceiling integers
This is meant to reassemble python's math.ceil() that was used
throughout the test_cases.py in couple of places.

Change-Id: I0d7d13ffd1121b12d58f00fb6ca59d76a237802e
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/933
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2020-04-16 09:45:30 +00:00
Michal Berger
e5497fd293 test/lvol: Rewrite unregister_lvol_bdev to Bash
This test case covers unregistering of all bdevs by removing malloc
device under the lvol store with snapshots|clones present (test case
no. 553).

Change-Id: I7e706230c5156b5a072e73c774da492597a53379
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/892
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-04-16 09:45:30 +00:00
Michal Berger
4605ac90b0 test/lvol: Rewrite bdev_lvol_delete_lvstore_with_clones to Bash
This test case covers removal of the lvol snapshot while having a
snapshoted clone on top (test case no. 552).

Change-Id: I0674877bb3c39fa360c886f1b82f77e675109484
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/878
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-04-16 09:45:30 +00:00
Michal Berger
a0d55c607a test/lvol: Rewrite delete_lvol_bdev to Bash
This test case covers proper order of lvol snapshot, clone removal (
test case no. 551).

Change-Id: I0faccaba0c2a097e2b6d03bc0446d1fbc1ef1891
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/870
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-04-16 09:45:30 +00:00
Michal Berger
100339aaf6 test/lvol: Rewrite delete_lvol_store_persistent_positive to Bash
This test covers lvol store removal from the underlying aio device (
test case no. 255).

Change-Id: I1e514abc0d0cc601996c6744dd65279d0865cf93
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/866
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-04-16 09:45:30 +00:00
Michal Berger
12ded5af6d test/lvol: Rewrite destroy_resize_logical_volume_positive to Bash
This test covers several instances of bdev resizing (test case
no. 254).

Change-Id: I31cd2d807a19e0452801ffe4721b8c154daa204b
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/779
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-04-16 09:45:30 +00:00
Ben Walker
d3f661cfd7 nvme/pcie: Don't store cmb.end
This isn't actually necessary.

Change-Id: Ic229b44f4eaf628a468fa8c2fa526162e426ec57
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/789
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-16 08:14:18 +00:00
Ben Walker
9ad044c464 nvme/pcie: Make signature of nvme_pcie_ctrlr_alloc_cmb more like other
alloc functions

Make the signature look more like spdk_dma_malloc and family.

Change-Id: I6a31acf3b9edd136924b6e53b9a23c699429b9dc
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/788
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-04-16 08:14:18 +00:00
Ben Walker
7b28450b3f nvme: Allow users to reserve the CMB for data without mapping it
Separate these two operations into different functions. It is
possible that a CMB may not be visible from the CPU, but still
be present and have data transferred to it by some other DMA
engine. Generalize the API to handle that case.

Change-Id: Ifcd282af0db734fe4a6ef2283ae8e8933d017809
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/787
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-16 08:14:18 +00:00
Ben Walker
6a7aa72edc nvme: Only memory map CMB if user requests it
We only need to register the memory for the CMB if the user
plans to map it for use with data. Delay the operation until then.

This also gives us a way to support unmapping the CMB.

Change-Id: I6121ae2cc3f6f44efae8b52b6582ff9f68432bc8
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/786
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-04-16 08:14:18 +00:00
Ben Walker
265a8436f4 nvme: Change mapping semantics of controller memory buffer
Instead of creating an allocator where the driver manages the space,
now, since using the CMB for queues and data has already been
disallowed, just create functions to map and unmap the entire CMB.
The user can manage the space.

Change-Id: I023994deda3b517e14d2ba464c7375bf22b58456
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/785
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
2020-04-16 08:14:18 +00:00
paul luse
3429f97a89 scripts/setup: add support for IDXD (aka DSA)
Add bin/unbind support between the kernel idxd driver
and VFIO. UIO not tested but tested this extensively
on a system with valid idxd kernel driver and VFIO.

Future patches in this series add the actual idxd
low level library and bdev accel plug-in module. See
those patches for more details on idxd.

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I09dd00b1aedcf88577335bde79d31cfd50ac4cde
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1721
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2020-04-16 08:10:33 +00:00
paul luse
2a0c66d03d examples/accel/perf: Add support for fill operation
Usable with both ioat and upcoming idxd modules.

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ie25743854aa6a05d1b5f580ea64fb5c7d7c722d1
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1720
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>
2020-04-16 08:10:33 +00:00
Shuhei Matsumoto
33a2974768 lib/scsi: Remove spdk prefix from private functions
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I89aa5dc10150cff74a420ccf8c3842bd12e84f3c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1825
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>
2020-04-16 08:09:14 +00:00
Shuhei Matsumoto
18dec40111 lib/scsi: Remove spdk_ prefix from internal APIs
Remove spdk_ prefix from the name of internal APIs.

Add single underscore as the prefix of the function name to the
private functions if we see any conflict as a result of this change.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: If0eabffbdb750db02866c1aa2b29b0c89fab1040
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1824
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>
2020-04-16 08:09:14 +00:00
Maciej Wawryk
6ee4bdab18 test/vm_setup: Add nbd install for Centos8
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: Ie687d29841ed41c88e26cef803bd23be8c009833
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1499
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2020-04-16 08:08:40 +00:00
Maciej Wawryk
6fed4f6110 test/vm_setup: Update yum repository before install packages in Centos8
There is fail during install using vm_setup.sh:
    Error: Failed to synchronize cache for repo 'AppStream'
adding yum update on instalation begining fix this issue.

Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: I92a3298d332ffe94c63a4f007e480a0c4d529b00
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1498
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-04-16 08:08:40 +00:00
Maciej Wawryk
36b7098a84 scripts/pkgdep: Fix failing symlink creation during python instalation
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: Ida6bfaf9ed21c5349a3107e033391f8d30a9ff93
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1497
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2020-04-16 08:08:40 +00:00
Pawel Kaminski
d841706a0b test/vm_setup: Install necessary packages for freebsd
Also remove unnecessary code in fio install.

Change-Id: I31ceb89254657002771e0012379e6fb7da4e6ce0
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1142
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2020-04-16 08:08:40 +00:00
Karol Latecki
485d615d7e scripts/vagrant: disable default synced folder
Disable default synced folder. We have our own set of
directories to synchronize so this is not needed.

Change-Id: Ie52e38af94fc2c403e3d3f095071833b9df09c9c
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1158
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-16 08:08:02 +00:00
Karol Latecki
3a06abc9d9 scripts/vagrant: enable hugepages backing for VM memory
Change-Id: I66c1c965d9de8b4e9625c1f1850cbb28d11138ad
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1684
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Maciej Wawryk <maciejx.wawryk@intel.com>
2020-04-16 08:08:02 +00:00
Karol Latecki
7fe1b36a36 scripts/vagrant: select tool for synced folders
In order to have all the boxes fully functional we
need to select the proper tool for synced folders.

FreeBSD boxes fail to set proxy properly via vagrant-
proxyconf plugin, so they fail to install rsync and sshfs
clients. NFS is pre-installed so we can use it.

Other boxes, like generic/fedora*, have issues using NFS
so we need to use sshfs/rsync instead.

Change-Id: Ic191b5a80dbd43479943c1739971abdff39baf41
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1581
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-16 08:08:02 +00:00
Karol Latecki
a0e6c88daa test/vhost: run fio bdev plugin in test VMs
Allow to run fio bdev plugin with attached virtio
devices. This might allow to get better performance
results when running performance tests.
Fio is not run in client-server mode due to problems
experienced when running fio plugin that way.

These changes are not generic and will not work
in the CI out of the box. New VM image must be crafted
in order to run fio in this mode. VM must have compiled
SPDK and FIO binary already in place.

Change-Id: I2e957e1e3a573cc899fcfbe5918193e1af6a9a63
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1605
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-16 08:07:47 +00:00
Maciej Wawryk
451c9e7b69 scripts/perf: Add frequency-info after changing cpu frequency
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: Icf45fbdff547fcf45c361b1d9c95b352756ad126
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1775
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-16 08:07:14 +00:00
Karol Latecki
49cb486296 doc: add Vhost 20.01 performance report link
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: I440bc0fba95de14f657e5db418cdabea76693540
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1840
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-04-16 07:45:18 +00:00
Seth Howell
ba870c2e99 lib/blob: remove some unused internal APIs
spdk_bs_sequence_unmap and spdk_bs_batch_to_sequence were
unused.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I4edc45948941ba700bea353c20ddb4e3f2fa15a4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1701
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
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>
2020-04-15 22:10:08 +00:00
Seth Howell
ad7fdd12b1 lib/blob: remove spdk_ from non-public APIs
We have an unofficial naming convention that the
spdk_ namespace is reserved for public API functions only.
This patch is attempting to bring the blob library into compliance
with that naming convention.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Ie298e41d1b741dae01744826c208378ee60f9d0a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1700
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom CI
2020-04-15 22:10:08 +00:00
Seth Howell
75365cfa60 lib/blob: add a map file.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I72da725f82dfa3eeb2c0ec6614ecc9ffb0b852a8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1682
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Community-CI: Broadcom CI
2020-04-15 22:10:08 +00:00
Seth Howell
869ad9c488 lib/bdev: add a map file.
Also update the so minor version. Apparently spdk_bdev_module_list_find
was not declared global even though it matches the spdk_* regex for the
generic spdk map file. My guess is this is because it isn't actually
used in any file other than bdev.c even though it is declared in
include/bdev_module.h

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I5c4e9ed06130e5d1dcc7235b5c2588f7b98a3ab3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1681
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Community-CI: Broadcom CI
2020-04-15 22:10:08 +00:00
Seth Howell
4021f34520 test/make: fix the confirm_abi_deps test.
I reversed the arguments to abidiff when I first submitted
this test which was causing additions to be reported as removals
and vice versa.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Iac50243f7cda7c1f9c2302af13a34eca844e0689
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1705
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-04-15 22:10:08 +00:00
Seth Howell
3509378604 test/autobuild: verify external code can link to libs
This test helps ensure that nothing about the way we build our shared
objects changes in a way that breaks external applications or bdev
modules trying to link to SPDK.

Change-Id: I45ac36a2afc873b04eb237f4e633a9d84066737c
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/435
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
2020-04-15 22:10:08 +00:00
Seth Howell
ae1dc68f39 test/autobuild: move ocf_precompile to new location.
This is needed so that we maintain proper configuration when
I add a new test that confirms our ability to run an application
that links dynamically to our shared libraries.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I9a8796c75280a5265579dc3c4a58955e1f82d049
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1813
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2020-04-15 22:10:08 +00:00
Shuhei Matsumoto
1fbc628e7a lib/scsi: Delete unused struct spdk_lun_db_entry
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I95f1b7445e55efe2aec5ab819eaef1d3e25b2507
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1821
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: Paul Luse <paul.e.luse@intel.com>
2020-04-15 07:40:06 +00:00
Shuhei Matsumoto
799e0a84af lib/scsi: Merge append and execute SCSI task into a single function
Both for SCSI IO task and management task, append and execute
operations bad bbeen separated into different functions.

Append operation was for LUN reset, and separating into two different
functions was for clarification and readability.

LUN reset is sufficiently stable now.

Merging append and execute SCSI task into a single function is good
as API and enables us to do optimization.

For SCSI management task, merge spdk_scsi_lun_append_mgmt_task into
spdk_scsi_lun_execute_mgmt_task() simply.

For SCSI IO task, merge spdk_scsi_lun_append_task into
spdk_scsi_lun_execute_task() and do a small optimization.
The refined spdk_scsi_lun_execute_task() adds the IO task to the
pending list if there is any pending management task, executes all
existing penging IO tasks first and then the IO task if there is any
pending IO task, or executes the IO task directly otherwise.

Update unit test accordingly.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I26ffc4f4f62747d8cdecb90690f26cd58a9c17f7
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1817
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-15 07:40:06 +00:00
Shuhei Matsumoto
2aa74d8ba9 lib/scsi: Inline _scsi_lun_execute_mgmt_task() into the caller function
Inline _scsi_lun_execute_mgmt_task() into the caller function
spdk_scsi_lun_execute_mgmt_task() as another preparation to the following
patches to avoid using double underscores as the prefix of the
function name.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I3c282fff133dfe7afc70c374a2186c14d1eb766c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1829
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>
2020-04-15 07:40:06 +00:00
Shuhei Matsumoto
2144f0b4c3 lib/scsi: Separate pending task and outstanding (submitted) task into different functions
This is a preparation to the following patches to optimize task
submission and remove the spdk_prefix from internal or private
functions.

To avoid using double underscores as the prefix of the function name,
separate pending task check and outstanding task check into
different functions.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ieda54507bf4c781b60fa05d03cd32ca25948e430
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1826
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>
2020-04-15 07:40:06 +00:00
Changpeng Liu
30e42bcecf nvme/opal: remove the device mutex lock finally
We can remove the device lock from now because all the APIs are executed
base on session, the controller can return error if there are multiple
sessions, actually most drives can only support one active session.

Change-Id: I9d5f4dc01a50ec95ef97b38c9e079ef95f37e4de
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1741
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2020-04-15 07:39:10 +00:00
Changpeng Liu
e51a2aaf3f nvme/opal: use asynchronous security send/receive transport APIs
opal_send_recv() is a wrapper implementation to use the asynchronous
security send/receive APIs, it can be used in a session context, but
from the view of one session, the opal_send_recv() is still executed
synchronously, but if the drive can support more than one session,
opal_send_recv() can be called from different sessions or threads.

Change-Id: I3a4b2ec14cb7706c39565a6b4fb8a3a4862f3d4c
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1670
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2020-04-15 07:39:10 +00:00
Changpeng Liu
71327bfef8 nvme/opal: move the command finalization to generic_pw_cmd()
opal_cmd_finalize() is part of OPAL command construction, so move it
to the common password construction function.

Change-Id: I65ecf1c9181e622f344f7e9284058e2472accd31
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1669
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2020-04-15 07:39:10 +00:00
Changpeng Liu
2728b774aa nvme/opal: merge two revert tper command function into one
Also rename it with *build* which is more meaningful.

Change-Id: I6e81e1b641ffdd04a7420e93e67448dc430f5168
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1668
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2020-04-15 07:39:10 +00:00
Seth Howell
4f7f0f0986 autotest_common: move config_params to a function.
This accomplishes a couple of things:

1. Now we don't perform these checks every single time
we source autotest_common.sh (some 140 times)

2. We have some flexibility in changing parameters either
during a test or when trying to do a specific compilation
and calling this function to get the updated parameters.

Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Ibbe2dc9113a56f651d41216e8557708824652442
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1784
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-04-15 07:39:00 +00:00
Seth Howell
b6eb4c8bb6 autopackage: with-lto should be enable-lto.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I9604b32cc45e2d0a5ca03a9ca41fc5a8b62d7842
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1846
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-04-15 07:39:00 +00:00
Pawel Kaminski
fbedb897bd test/openstack: Change http to https for cirros server.
Extend build timeout, enable image volume cache and
change max spdk queue depth on local.conf.

Change-Id: I1dcacd8fbfbfabcba1d017d950dd09ce8ee68076
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/762
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-15 07:37:25 +00:00
Pawel Kaminski
15df89808a test/openstack: Use nvmf_tgt wrappers instead of spdk_tgt app
This is for the sheer convenience and cleanup purposes.

Change-Id: I526c4fb682eef94fbfae20b1d5a03dcf325ff647
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/761
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-15 07:37:25 +00:00
Michal Berger
5000bd4885 test/nvmf: Don't inherit last exit status from errexit
If return is called without specifying the exit status while being
used in the trap context, it inherits the exit status code from the
last cmd that triggered the errexit (i.e. the cmd which was run right
before the trap). In this particular case it may be quite unexpected
since return is called after successful execution of the modprobe,
implying the overal success of the function. However, as set -e is
called right before return, the function returns with a != 0.

To avoid this behavior, explicitly return from the function with 0.

Change-Id: I8b21e7aa6cd5628f14b66e559d05b4d0a20e2050
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1807
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-04-15 07:37:25 +00:00