4926 Commits

Author SHA1 Message Date
Ivan Betsis
c818233b41 nvmf/rdma: Add WR batch rdma new transport option
With x86 and low queue depths with multiple QPs/initiators
there is a benefit from disable batch when we have randread IO pattern.

Testing environment: x86, Intel(R) Xeon(R) Silver 4116 CPU @ 2.10GH
Several results:
init_cores | QD | BS | Avg IOPs/BW without batch | Avg IOPS/BW with batch
  8 cores  | 4  | 4K |     1870087 / 7305        |     1594014 / 6226
  8 cores  | 8  | 4K |     1853573 / 7240        |     1576400 / 6157
  8 cores  | 16 | 4K |     1819643 / 7108        |     1569487 / 6130
  8 cores  | 32 | 4K |     1815467 / 7092        |     1569909 / 6132
 16 cores  | 4  | 4K |     1908018 / 7453        |     1566843 / 6120
 16 cores  | 8  | 4K |     1906081 / 7446        |     1562110 / 6102
 16 cores  | 16 | 4K |     1880706 / 7346        |     1555060 / 6074
 16 cores  | 32 | 4K |     1835878 / 7171        |     1548156 / 6046

Signed-off-by: Ivan Betsis <c_ivanb@mellanox.com>
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Change-Id: Icdbbbdf83f137eb4f05bd2063268ee2a7d87335a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/924
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
2020-10-21 02:25:32 +00:00
Shuhei Matsumoto
938d2ae254 test/nvme: Use spdk_nvme_detach_async() and spdk_nvme_detach_poll_async()
Use spdk_nvme_detach_async() and spdk_nvme_detach_poll_async() with
a local variable detach_ctx to detach multiple controllers.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I77cdc07ddfcd97569e31eeb245cd4e5a26289dbd
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4441
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-10-20 16:55:55 +00:00
Shuhei Matsumoto
7a85c283d9 test/app: Use spdk_nvme_detach_async() and spdk_nvme_detach_poll_async()
Use spdk_nvme_detach_async() and spdk_nvme_detach_poll_async() with
a local variable detach_ctx to detach multiple controllers.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I43428a41df2b6f26b62cf03990d35add9a3663d6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4440
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-10-20 16:55:55 +00:00
Shuhei Matsumoto
ea1bfd84cd lib/nvme: Make internal of spdk_nvme_detach() asynchronous
Add two new helper functions, nvme_ctrlr_detach_async() and
nvme_ctrlr_detach_poll_async() to make the internal of
spdk_nvme_detach() asynchronous.

Use callback function to remove controller from the attached list after
completing shutdown and before freeing to avoid conflict between
attach and detach.

Update MOCKs in the corresponding unit test cases.

The next patch will add two public APIs spdk_nvme_detach_async()
and spdk_nvme_detach_poll_async() based on this patch.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ifbdfec2a1facde9354007c6248f280e245a36eed
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4416
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-10-20 16:55:55 +00:00
Shuhei Matsumoto
c865839736 examples/blob_cli: Use spdk_bdev_create_bs_dev_ext() to pass bdev_name
Update a few print outputs to out not product name but bdev name
because bdev pointer is not available there after replacing
spdk_bdev_get_by_name() and spdk_bdev_open() by spdk_bdev_open_ext().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I624fea3a0a12c1049e950bddae8cea9f88b16db5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4702
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-10-20 15:27:38 +00:00
yidong0635
2e0dafb305 test/reset: put unregister_worker after unregister_controllers.
From the log we can see that it reports ns_ctx was freed before it
was used. In unregister_controller, it still need ns_ctx to do io_complete.

And now this app works as a signle worker to do something.
Just need to change the order, execute unregister_worker after
unregister_controllers.

Fixes issue #1626

tested on clearlinux.

Signed-off-by: yidong0635 <dongx.yi@intel.com>
Change-Id: I392ff168abb862ba236a24b775fb31bb341e2157
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4761
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-10-20 14:05:51 +00:00
Tomasz Zawadzki
20b7b660c9 test/lvol: rename lvol test script
After the large effort of moving lvol tests from
python to bash, the original lvol.sh was removed.
Only lvol2.sh remained.

Just rename the script to its original name.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I5c0a239b01c111f0b11f554caaebfec372877c6d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4561
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>
2020-10-20 08:54:53 +00:00
Karol Latecki
af62eb57fc autopackage.sh: add flag for release builds
Using another flag for the conditional will let us
run release build test in selected job configurations
for per-patch testing on CI side, not just for nightly
tests.

Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: Ib9de1c98bf6d7380670f22321f2df7784f2517de
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4734
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>
2020-10-20 08:54:40 +00:00
Tomasz Zawadzki
6d86242dc5 subsystem/iscsi: remove legacy config support
This patch removes legacy config support in iscsi subsystem.
All options through the legacy config are already reflected in JSON.

Following RPCs are corresponding to removed legacy config sections:
Initiator groups - iscsi_create_initiator_group and iscsi_initiator_group_*
Subsystem options - iscsi_set_options
Portal groups - iscsi_create_portal_group
Target node - iscsi_create_target_node and iscsi_target_node_*

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I11326a84d4d580b19db422b8522198eea5a5be0d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4747
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-10-20 08:53:53 +00:00
Shuhei Matsumoto
2842056073 blobfs_bdev: Use spdk_bdev_create_bs_dev_ext() instead of spdk_bdev_create_bs_dev_from_desc()
Replace all calls of spdk_bdev_create_bs_dev_from_desc() and
spdk_bdev_open_ext() by calls of spdk_bdev_create_bs_dev_ext()
including unit tests.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Idb9dc5a10f6e221c26e82e0194930cb7a2071dae

Change-Id: I61e577db9e26ef3e1c3e2e4093ad66922a178f34
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4723
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-10-20 08:52:29 +00:00
Shuhei Matsumoto
b6cbf872eb bdev/lvol: Pass bdev name instead of bdev pointer to vbdev_lvs_create
Change the first parameter of vbdev_lvs_create() from bdev pointer
to bdev name, and then remove spdk_bdev_get_by_name() from
rpc_bdev_lvol_create_lvolstore().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I9b0e47f551657f6aa1235af37a8357b0af62d414
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4707
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: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-20 08:52:29 +00:00
Shuhei Matsumoto
3ea2bffb9e blob/bdev: Add function pointer get_base_bdev to struct spdk_bs_dev
spdk_bdev_create_bs_dev_ext() gets not bdev pointer but bdev name
as an argument, and hence vbdev_lvs_create() will get bdev name
accordingly.

However after completing spdk_bdev_create_bs_dev_ext(),
vbdev_lvs_create() has to get bdev pointer from the created bs_dev.

Hence add a function pointer get_base_bdev to struct spdk_bs_dev
and set it to bdev_blob_get_base_bdev() at initialization.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Idef0663ace85db0269442212014286669c150069
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4706
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: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-20 08:52:29 +00:00
Shuhei Matsumoto
6051368da9 bdev/lvol: Use spdk_bdev_create_bs_dev_ext() when creating lvol store
This is a drop-in replacement. The following patches will remove
spdk_bdev_get_by_name() from the operation to create lvol store.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I31688cf98625f1d13012281d89f06d343e2f2cef
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4705
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: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-20 08:52:29 +00:00
Shuhei Matsumoto
94d6e332bc ut/nvmf_ctrlr_discovery: Remove spdk_bdev_open() stub because it is not used
Remove the stub for spdk_bdev_open() and use the DEFINE_STUB_V macro
to the stub for spdk_bdev_close().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I84df06b4b73e1f5af5c2c8854f1613e8a413533b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4729
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: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-20 08:52:29 +00:00
Shuhei Matsumoto
6a684a349e ut/bdev_mt: Use spdk_bdev_open_ext() instead of spdk_bdev_open()
Replace all spdk_bdev_open() calls by spdk_bdev_open_ext() calls
in the multiple SPDK threads cases of the unit tests for lib/bdev.c.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I65591f12f8737bb8a0c1256fa84c5b6dac481150
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4728
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: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-20 08:52:29 +00:00
Shuhei Matsumoto
75dfecbb16 ut/bdev: Use spdk_bdev_open_ext() instead of spdk_bdev_open()
Replace most spdk_bdev_open() calls by spdk_bdev_open_ext() calls
in the unit test for lib/bdev.c.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ifbb8a7338b1d99808c96c87be1cfbee145b0d21f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4727
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: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-20 08:52:29 +00:00
Tomasz Zawadzki
cda1d2cf11 build: remove unused references to conf library
- Removed slew of conf.h includes
- No longer require mk vars that include conf

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ica7e8e8bf1d4a5d0b0200bfe689aa13afd77bfaf
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4746
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>
2020-10-20 02:42:16 +00:00
Tomasz Zawadzki
9103bca73b lib/event: remove deprecated ReactorMask from legacy config
Legacy INI configuration is being removed this release.
This patch removes one of its options and always uses the
SPDK_APP_DPDK_DEFAULT_CORE_MASK as default core mask.

That can only be overwriten by -m/--cpumask arguments in app.

In bdevperf there was no reason to set reactor_mask to NULL,
as that was then still using the defaults.

Meanwhile bdev_svc will now check if user provided different
string via command line args to know if it should
unaffinitize its thread.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Id882f8d7dbdd07b7743bd5981c37daa888b7872a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4619
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>
2020-10-20 02:42:16 +00:00
Tomasz Zawadzki
5b1e154a5c bdev: remove legacy config support
This patch removes legacy config support in bdev layer.
All options through the legacy config are already reflected in JSON.

Removed configuration can be set via `bdev_set_options` and
`bdev_set_qos_limit` RPC.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I24c365625540659cad425268d2aa41e3bf279d5d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4645
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>
2020-10-20 02:42:16 +00:00
Tomasz Zawadzki
ceea308887 lib/blobfs: remove legacy config support
This patch removes legacy config support in blobfs library.
Mostly reverting patch:
(97f3104) blobfs: Add conf parse for blobfs.

CacheBufferShift option in legacy config is not tested in CI,
and never received corresponding RPC.
If required the RPC can always be added later on.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I54e39f069047a243b2186ae5ea225ed452180488
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4668
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: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-20 02:42:16 +00:00
Tomasz Zawadzki
269efef886 bdev modules: remove legacy config support
This patch removes legacy config support in:
 crypto bdev module
- nvme bdev module
- ocf bdev module
- rbd bdev module
- pmem bdev module
- iscsi bdev module
- raid bdev module
All options through the legacy config are already reflected in JSON.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I00213365f52d3de1012493c14d4ea5fc537e595e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4673
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-10-20 02:42:16 +00:00
Changpeng Liu
6bd7bd0da2 vhost: deprecate internal vhost library support
The internal vhost library is used when DPDK's version
is older than 19.05 and the experiemntal vhost nvme
target.

For the CONFIG_INTERNAL_VHOST_LIB option, SPDK doesn't
enable this option by default over one year and CI
doesn't cover it either, so we may remove it with
this release.

As for the vhost-nvme target, since we are developing
a new vfio-user target solution, it's OK for us to remove
it now.

Change-Id: Ib2cce1db99cd09754307c2828b3187f2d4550304
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4562
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-10-20 02:42:16 +00:00
Darek Stojaczyk
c77c655987 json: add spdk_json_free_object()
After decoding a JSON object we had to free the parsed
strings one-by-one. Not anymore.

Change-Id: I819f1d533e397aa9babca58b5500c38ac01a963d
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/2753
Reviewed-by: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-10-19 10:02:10 +00:00
Michal Berger
f81cd2f3e2 make/check_so_deps: Speed up the confirm_deps()
Instead of iterating over each symbol, create a regex group including
all the symbols to lookup and pass it to grep.

Also, refactor some small pieces:
 - filter event_ dependencies within import_libs_deps_mk()
 - convert SPDK_LIBS to an array built up with extglob
 - drop DEP_LIBS
 - drop missing_syms (unused)

The overall improvement (this covers the execution of the subshell
within which confirm_deps() is called for each .so):

real    1m23.688s
user    4m16.196s
sys     8m3.110s

real    0m3.537s
user    0m13.450s
sys     0m18.486s

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: Id61c5f947cd116e0fa0107cc7c941beb2c0bdcb4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4632
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>
2020-10-19 10:00:44 +00:00
Michal Berger
d5f8983edd make/check_so_deps: Convert IGNORED_LIBS to assoc array
Also, move the check against IGNORED_LIBS to import_libs_deps_mk().

Signed-off-by: Michal Berger <michalx.berger@intel.com>
Change-Id: I190262f728118d65c35481e490ca094086760cfa
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4631
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>
2020-10-19 10:00:44 +00:00
Michal Berger
5d88afca2a make/check_so_deps: Use function to get the short name of the lib
Change-Id: I2def5ca17c8c34447a398a7d210b6dce6a50ecc4
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4630
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>
2020-10-19 10:00:44 +00:00
Michal Berger
4c859a6da5 make/check_so_deps: Drop replace_defined_variables()
This function was recursively greping through the .mk file to map all
ref variables $(...) to values they are set to. This was including
plenty of duplicate entries which then had to be sorted|uniqed.

Instead, and to avoid recurssion, import the entire .mk file into
Bash's environment. The mapping would look like so:

 JSON_LIBS := json jsonrpc rpc
 DEPDIRS-event_vmd := event vmd conf $(JSON_LIBS) log thread
 |
 v
 JSON_LIBS="json jsonrpc rpc"
 JSON_LIBS() { echo $JSON_LIBS ; }
 event_vmd="event vmd conf $(JSON_LIBS) log thread"
 |
 v
 event_vmd="event vmd conf json jsonrpc rpc log thread"

Change-Id: Ibfcd52438403cd7638e01d2d5642c08822f85106
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4629
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>
2020-10-19 10:00:44 +00:00
Michal Berger
7deb562547 make/check_so_deps: Fix a typo
/accesible/accessible/.

Change-Id: I79335935957f685ceb31ccfe0eca8ddd9edac306
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4628
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-10-19 10:00:44 +00:00
Michal Berger
5328d922d7 make/check_so_deps: Tell readelf to use wide output
Newer versions of readelf (e.g. from binutils v2.35) break the lines
in the following manner:

.... GLOBAL DEFAULT   14 restore_funcarra[...]

The symbol name is shortened, however, the way how it's indicated
with "[...]" may mess with any tools that look up this field with a
regex pattern - just like grep in the confirm_deps() test.

Currently, this test fails on clearlinux where the latest readelf
is shipped on board. To avoid it, make sure readelf returns full
name of the symbol with the --wide output.

Change-Id: Ief1a3dccde5481f603302ee714021dcebc20fc58
Signed-off-by: Michal Berger <michalx.berger@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4627
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-10-19 10:00:44 +00:00
Jim Harris
44ff994386 event: remove include of spdk_internal/thread.h
It's not needed.  Add it to one of the UT where it
is needed though.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I06628184c22df68deffce3ca0561878569ccf3f4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4717
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.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>
2020-10-19 10:00:29 +00:00
Jim Harris
fcaf67e238 test/rdma: fix array subscript violation in rdma_ut.c
Found by gcc 10.1.1.

Fixes issue #1623.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3b43b0ad1db5048cadaccc16e3c9a47b2592aa6e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4715
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2020-10-19 10:00:29 +00:00
Shuhei Matsumoto
229b996850 bdev/ocssd: Removed unused ioch parameter from bdev_ocssd_get_zone_info()
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I4a7a79892ca8d6010888e69d095e58c4b50bafce
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4526
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Mellanox Build Bot
2020-10-19 10:00:16 +00:00
Darek Stojaczyk
f766d1e478 nvmf: let transports parse transport opts from JSON themselves
There are more transport on the way and we don't want to add
all their various opts into the single, generic structure.
We'll pass the JSON structure to transports instead. Then
the transport code can custom pull from the JSON any param
it wants.

To complement that, transports will now also have their own
JSON config dump callback. This was only done in the generic
nvmf.c so far, with conditions for RDMA and TCP.

Change-Id: I33115a8d56cec829b1c51311a318e0333cc64920
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Signed-off-by: jiaqizho <jiaqi.zhou@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/2761
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2020-10-19 09:55:05 +00:00
Changpeng Liu
da58e37709 test/memory_ut: fix clang compilation error
clang reports the following error:

memory_ut.o: In function `vtophys_notify':
/home/spdk/lib/env_dpdk/memory.c:1025: undefined reference to `rte_eal_iova_mode'
/home/spdk/lib/env_dpdk/memory.c:1137: undefined reference to `rte_eal_iova_mode'

Fix issue #1613

Change-Id: Ia7e3e6c1f6f63bf664d6b76ebdc070c2cba76b2d
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4686
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
2020-10-19 09:54:32 +00:00
Shuhei Matsumoto
7a85820db3 bdev/zone: Use spdk_bdev_open_ext() instead of spdk_bdev_open()
This is just a drop-in replacement.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I018ef60648122aa672430bb62dc7b1a2e1cd5d7c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4648
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2020-10-16 23:12:03 +00:00
Shuhei Matsumoto
d8a1892422 bdev/raid: Use spdk_bdev_open_ext() instead of spdk_bdev_open()
This is a drop-in replacement. Update unit test together, and the
idea of the update was from the unit test for zone bdev module.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ia8d0644f42b9d0a0ad502eebbe3e414abd1de4cf
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4591
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-16 23:12:03 +00:00
Shuhei Matsumoto
491e6c4309 bdev/crypto: Open base bdev first using spdk_bdev_open_ext()
vbdev_crypto_claim() gets bdev name instead of bdev pointer
as a parameter, and open the corresponding base bdev first using
spdk_bdev_open_ext().

The purpose is to fix the race condition due to the time gap
between spdk_bdev_get_by_name() and spdk_bdev_open(). A bdev pointer
is valid only while the bdev is opened.

Resize event is not supported for now.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ia0e1ce2ce696f431bb26af94729931c3ffb9a9d0
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4588
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-16 23:12:03 +00:00
yidong0635
9714818d04 test/bdev_ut: fix warning about unitialize value.
gcc version 10.1.1 20200619 releases/gcc-10.1.0-223-gf8e16e23d0
(Clear Linux OS for Intel Architecture)

Issue reports:

  CC test/unit/lib/nvme/nvme_ns_cmd.c/nvme_ns_cmd_ut.o
bdev_ut.c: In function ‘bdev_io_alignment_with_boundary’:
bdev_ut.c:2146:2: error: ‘buf’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
 2146 |  free(buf);
      |  ^~~~~~~~~
bdev_ut.c: In function ‘bdev_io_alignment’:
bdev_ut.c:2008:2: error: ‘buf’ may be used uninitialized in this function [-Werror=maybe-uninitialized]
 2008 |  free(buf);
      |  ^~~~~~~~~

Signed-off-by: yidong0635 <dongx.yi@intel.com>
Change-Id: I6d1bbf74b230b7bc51646454ddba0db4792f5900
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4693
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>
2020-10-16 08:15:57 +00:00
Jin Yu
1903dd1049 test: add packed ring test in blk device
Add an integrity test for the packed ring.
SPDK vhost blk has already supported this format.

Change-Id: I38329d837e0a5c6d4e12b30c7c99e02536ed8ac9
Signed-off-by: Jin Yu <jin.yu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4595
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
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>
2020-10-16 08:15:51 +00:00
Tomasz Zawadzki
b850710af6 test/vhost: remove unused bdev_pci.conf
This config file was not used in any tests.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I8e32346dcb05fd68f7f64d2a7b4907bb8d80a5d2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4618
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: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-16 08:15:26 +00:00
Tomasz Zawadzki
562598c9de test/vhost: remove test for incorrect legacy config
Legacy configuration is being removed, no need to test it.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I38eb9f5b77e0457516a03b30d33dc5a11ef35d1b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4617
Community-CI: Mellanox Build Bot
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: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-16 08:15:26 +00:00
Tomasz Zawadzki
d48992413c perf/nvme: simplify discover_bdevs()
This function does need to handle legacy configs and
it's single use did not request any wait_for_spdk_bdev.

Remove those arguments.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ic988762c7ca622ff538aeb7bd2bb529e6e6d56e4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4616
Community-CI: Mellanox Build Bot
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: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-16 08:15:26 +00:00
Tomasz Zawadzki
e251e40422 test/vhost: remove unused vm_check_virtio_location()
This function relied on legacy config to work and was unused,
thus is removed in this patch.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Id11dbbcba3dc5b4981c03eca945c7d40fb0f7ce6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4615
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: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-16 08:15:26 +00:00
Tomasz Zawadzki
b7db237d09 test/blob: move blobiowait test to JSON config
Legacy config will be soon removed, change to JSON config.

While here, removed superflous sourcing of nvmf common and
-r on rm for a file.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ifd45c644192b57661131e0b3e369e389a4500432
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4614
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>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-16 08:15:26 +00:00
Tomasz Zawadzki
7f139e549b lib/blob: extent_page shall never occupy md page 0
Search for md_page to be used as extent page started
from 0, which is completely valid md_page.

This page can be free when for example blob with id 0
was deleted and some other requested a new page for extent.

There are already existing blobs that have extents
pointing to 0, which means unallocated.
Unfortunetly it means 0 can never mean md page 0.
If that already occured for someone, this extent page was already
lost during blob/bs reload and nothing can be done.

With this in mind following assumptions are made for extent pages:
- 0 means unallocated extent page
- UINT32_MAX means we ran out of md pages, and should not be persisted
- [NEW] extent page can never occupy md page 0

That last one is new addition in this patch.
bs_allocate_cluster will now always try to find md page from 1 or higher.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ia17ce5bbca2fab4fb4487e4e263f3a0aa120bf17
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4314
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
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>
2020-10-16 08:15:16 +00:00
Tomasz Zawadzki
63e257ed34 lib/blob: update pages array during blob load
When loading a blob and parsing its metadata,
the array of pages was not updated.
Serialization was unaffected, since the current pages
array is unused there.
Behavior was working correctly for first page,
but did not for any blob with more than one page.

Unfortunetly blob_persist_zero_pages() never zeroed out
the pages, neither blob_persist_zero_pages_cpl()
released the md pages.

Resulting in md pages being claimed even after blobs
deletion.

This patch now fills out the active pages array with
the appropriate page numbers from metadata.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I6ff1f4fe95684119d283c2471fdbbea464da8151
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4504
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
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>
2020-10-16 08:15:16 +00:00
Shuhei Matsumoto
aec30063e3 bdev/compress: Pass bdev name instead of bdev pointer to _prepare_for_load_init()
This patch removes the call of spdk_bdev_get_by_name() from
create_compress_bdev() by calling spdk_bdev_open_ext() and then passing
bdev descriptor to _prepare_for_load_init().
vbdev_init_reduce() returns the return code of spdk_bdev_open_ext()
directly if it is error to process the ENODEV case correctly.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ie80ce4104ceaa5726db976e33cd35352d5c91703
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4571
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
2020-10-16 08:14:34 +00:00
Tomasz Zawadzki
4e8e97c886 log: remove internal log.h header
There is nothing left here, so remove it.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ib947d42bc577dbebb4650b1be885e05a80f8f8cf
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4541
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Community-CI: Broadcom CI
2020-10-15 08:23:39 +00:00
Tomasz Zawadzki
8a76c2484a event/app: allow to enable log flag for release builds
Log flags could also report on SPDK_LOG_INFO level by using
SPDK_INFOLOG() macro. Yet this did not result in additional
log due to check for debug build.

This patch allows release builds to use that flag.
Meanwhile the -L option besides turning on particular log flag
changes print log level to SPDK_LOG_DEBUG.

Applied changes to serveral applications to follow the
behaviour of event framework.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ib0d6cce33263c350d6d83300d60e7d15bdfe4b64
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4557
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2020-10-15 08:23:39 +00:00
Shuhei Matsumoto
779a6bdf82 bdev/compress: Replace spdk_bdev_open() by spdk_bdev_open_ext()
This patch is just a drop-in replacement.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Iffb253ba3a46f03f9927c4ba4206376509cbb5fc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4566
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Community-CI: Mellanox Build Bot
2020-10-14 08:07:06 +00:00