This allows us to hide the implementations of
g_subsystems and s_subsystems_deps within the
libraries themselves.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I60716b9465b58d6cdb3a43262a7ded844bd80eda
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1786
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
This is part of a larger effort to remove the g_subsystems and
g_subsystems_deps variables from the spdk_event map file. The
implementation of those variables should be internal to the
library.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: I3c2c04933859c6c484a903e666df10f810b26709
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1785
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Also, increment the library version since some non-public symbols have been removed.
Please note, SPDK_LOG_BLOBFS is included in the map file because it is used by the
blobfs_bdev module.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Ib05c0b6630951d97b1a5b2931746471eeb9d9630
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1702
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
All of the error cases for spdk_nvme_transport_id_parse_trtype
were covered earlier, so just make this an assert.
fix kw warning 12653.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: If0eea934764b35d097887b98b0441ae5d7dd3e4f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1953
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
With the advent of custom transports, it is impossible
for this call to fail.
fix kw warning #12653
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Ib1f9d0992e2def9eafd8696310b6c79ab6ac8c78
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1952
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Since the related feature is already contained in
spdk_sock_listen and spdk_sock_connect functions,
we no longer need this function.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I1eafff0d139fa266a355fbee2bf0fc3947db69fc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1876
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI
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>
Do large reads from the socket and buffer into a pipe.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ibce74917a1cd7248ff1a325204c0d338cc6a3470
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1349
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
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>
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>
We will be create fine name for each poller but it will need large
effort. Replacing spdk_poller_register by the macro SPDK_POLLER_REGISTER
will provide better name than function address with minimum effort.
Following patches may improve function name for clarification.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: If862a274c5879065c3f7cb04dcb5ca7844523e68
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1781
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: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Community-CI: Broadcom CI
Cache the return value of spdk_io_channel_get_thread() to orig_thread
and use it in the function. This will clarify the logic and improve
readability a little by reducing line length. Besides, in
vbdev_compress_submit_request(), spdk_io_channel_get_thread() can be
replaced by spdk_get_thread() and do the replacement in this patch.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Id0fadb5dae9b78ecade99c5deb650849bf6257ab
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1453
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Previously only bdev_close() had been ensured to execute on the
correct thread.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ie3019bd1206060a86ec3c598795255c4c4357b0f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1696
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom CI
Not only bdev_close() but also TAILQ_REMOVE and bdev_module_release_bdev()
are better to be executed on the correct thread for
vbdev_compress_destruct_cb().
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I0810ecc4149747315e6ec290437ba40fb4b71686
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1694
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
vbdev_reduce_init_cb() had ensured only closing bdev was done on
the correct thread. I/O channel should have been released on the
same thread.
Fix this potential issue. reduce_errno and vol cannot be passed
through message because message can have a single parameter.
So set vol before sending message and use vol as reduce_errno.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I923a9e3148db0f5413a6903d62f869eec122dcca
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1693
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Factor out setup source and destination mbufs operation from
_comppress_operation() into a helper function _setup_compress_mbufs().
Setup source mbufs and setup destination mbufs are identical except
for total_length, and so this refactorinng is possible.
This refactoring will improve readability and clarify the logic
a little.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ia0a230c2d5e74aec917580aae969b49266178191
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1683
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
This request was getting leaked previously.
Change-Id: I6e7dc24c92d7bae7a8df54025d61eb391a569df9
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1591
Community-CI: Broadcom CI
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>
If thread A is the first to grab a channel, the poller will be on thread
A. But then if the shutdown happens such that thread B is the final
channel to release it's channel, it will attempt to free the lun poller
from thread B and crash.
Change-Id: I354f9f28d55e5e82cb6c737c734acadbd80e283d
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1590
Community-CI: Broadcom CI
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>
Save cache device name in metadata section to
check if names agree during auto creation on examine.
This change prevents accidental creation of ocf devices.
Consider example in which vbdev_split is used as cache:
1) bdev_malloc_create -b Malloc0 ...
2) bdev_malloc_create -b Malloc1 ...
3) bdev_nvme_attach_controller -b nvme ...
4) bdev_split_create nvme 2
5) bdev_ocf_create ocf0 wt nvmen1p0 Malloc0
6) bdev_ocf_create ocf1 wt nvmen1p1 Malloc1
7) *shutdown*
8) *startup*
9) bdev_nvme_attach_controller -b nvme
Now ocf0 bdev gets created with cache = nvmen1 (not nvmen1p0)!
This is because nvmen1 and nvmen1p0 have the same metadata.
The result is rather unexpected,
so we would like to verify that cache device
is the one used during creation.
Name is not an ideal way to verify that,
but it should work for most cases.
This change is related to issue #1320
Change-Id: I19ce97163090c5c5b3324eaed90b3134011bb3fb
Signed-off-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1544
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>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Currently run count of poller has been incremented per execution.
It will be helpful for us to know how poller is busy by adding busy
count which is incremented only when some work is done.
spdk_thread_poll() has used the same timestamp in it, and so this is
the maximum we can do for now.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I0adfbf9a62c959499978124ecc97d377c96c3769
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1713
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
When the socket is migrated from one polling group to another
(e.g., iSCSI target example), we should add it into pending_recv_list
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I56d34000344ae452a25b82952c831f09e0266d66
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1448
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>
Following the idea of thread CPU stats, add reactor CPU stats.
Reactor CPU stats accumulates run time of spdk_thread_poll() calls
to idle TSC or busy TSC according to their return codes.
Add necessary unit tests.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I1a1391e79d74387c68f1651a61c8900e4c6faf66
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1501
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
The code used to do this but it was removed when the buffering was
shifted down to the posix layer. Add a way for users of sockets
to still properly size the buffers.
This also means that by default, the receive buffering is not enabled
on sockets. That matches the behavior of the previous release.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: I20ce875be2efd841fe3a900047b4655a317d7799
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1560
Community-CI: Broadcom CI
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>
This change is aimed at fixing github issue #1312 where we are
apparently calling the nvme_bdev_ctrlr_destruct function more than
once.
In the previous implementation, if a controller was resetting for more than
one iteration of the poller, a second iteration of the poller would get
registered.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Ica01ecb21d76ea4f60624efd780bf4eea957c277
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1611
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reorder vbdev_redoce_load_cb() so that normal case comes first,
orphaned case comes second, and other error cases come at last.
This will simplify the code and improve readability a little.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ieb79364f0b3996600e8ff7ec340101877527cac2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1477
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>
Move queue insertion to the end to avoid removal in error cases.
spdk_bdev_module_examine_done() is duplicated with the caller in
error cases and so remove it.
I/O channel is not got in this function and so remove
spdk_put_io_channel() in error cases.
move up spdk_bdev_close() to call at error_bdev_register or
error_claim label.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I34a1459dcb0d3e0a2018f5b50db5be3ac44b6049
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1469
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: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
In comp_bdev_ch_create_cb(), list head comp_bdev->pending_comp_ios and
comp_bdev->queued_comp_ops should be initialized only when
comp_bdev->ch_count is 0. Besides, extra brackets for if condition
can be removed.
In _comp_bdev_ch_destroy_cb(), comp_bdev->ch_count is not necessary
to check if it is 0 again.
Fix these.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I71786423a77819c41419c51a4cfcad71b85a0b39
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1444
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>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
When reduce volume is unloaded at compress bdev removal, the callback
to unload did not get base bdev's I/O channel on the same thread
that opened base bdev.
Hence spdk_put_io_channel() hit assert later.
This patch fixes the bug by sending message to get I/O channel.
Fixes issue #1307.
Besides, add assert to _delete_vol_unload_cb() to detect the unexpected
complex cases. Fix will be added later.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: If4983c2e06d7b0b7618f38fb80f3aa73effe4b83
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1426
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: Paul Luse <paul.e.luse@intel.com>
Introduce context structure to ensure the callback function to
bdev_compress_delete() runs on the original thread.
The time to free comp_bdev and the time to call the callback function
to bdev_compress_delete() are different. Hence it is necessary to
allocate context separately.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I534f5673b58d2a0321ee752534c3ea10fb37b11d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1472
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>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Commit 8c1d107 added a new erase API and renamed the original
API with "secure_" prefix according to the specification, as the
secure one will not cryptographically erase user data, due to
the limitation from the drive, only the secure API can be
supported, so changing the caller to use the original again.
Change-Id: I25cb054e728065d9ae9c6c30aa0ab374d60cf6f6
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1519
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>
The statement in line 1199 is may not be correct:
Actually, it should be following two cases
to pendinging_recv into false;
1 posck->recv_pipe == NULL
2 psock->recv_pipe != NULL & avalable_bytes == 0;
So this patch can fix this issue.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ie612f781b0848e1f0ab1b48dc8c45e39862b772a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1446
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Collect elapsed time of each SPDK thread and add it to output of
framework_get_reactors RPC.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I9e2f0487de81720327428cda5738284a4ce2c557
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1278
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Actually we can just use one API to finish the requirement.
Change-Id: Ia0d3d589755e8c92f636d3d090ec642299511401
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1280
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>
This will eliminate one calloc() and add one small code cleanup.
Change-Id: I3d67f2b073a46e04304ae5342974afecf532794b
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1233
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>
The revert asynchronous API doesn't run as the *real* asynchronous
way, because the drive can only support synchronous module and only
1 session is supported. The reason why we added this API is that
RPC call has the default timeout value here, while the revert may
take over several minutes, the API itself doesn't short the revert
action, so just remove it and use the synchronous API instead.
The revert action will erase all the users data and bring the drive
back to the factory state, it should run in the synchronous mode,
so just remove the asynchronous API and we can increase the timeout
value when using RPC to call this API.
Change-Id: I08a082edea6385e378399423bbb229d05f8bc262
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1232
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>
Sending large amounts of data from host to the controller with 1s
admin polling time, take a lot of time (e.g. 1M firmware file in 4k
chunks takes ~17min).
Reducing this time to 10ms whole operation takes about 3s.
Change-Id: I2dabe9f60acab57e348c34bfabc3cc7479dedec9
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1393
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
This patch is used to add the async network I/O support in
sock layer. If code is configured with I/O uring, --with-uring,
we can use io uring in Linux (version >=5.4-rc3).
PS: We also make VPP's default priority > uring, because
for the iSCSI or sock test linked with VPP. It tests VPP with
a given address (which is not a special VPP can only open address),
so using uring can also listen those address succefully. And if we make
uring with priority > VPP, actually, VPP will not tested in those cases.
Additionally, the current CI pool is not ready for test, we need
wait for the CI system ready. And I test on my local platform, it works.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ie8ee3c8ddf8d2a7264f2b382376733e002816dcc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/952
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This will be used by upcoming spdk_top application.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I066567f0f14d70e6744821e8e805934a3d790882
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1235
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>
This will allow us to keep track of compatibility issues on a
per-library basis.
Change-Id: Ib0c796adb1efe1570212a503ed660bef6f142b6e
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1067
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>
At startup, use g_num_poll_groups and spdk_env_get_core_count()
to detect completion and move to the next state. By returning
completion message to the init thread, we can avoid using any
atomic operation.
At shutdown, the last patch did most of the necessary change.
This patch adds spdk_thread_exit() to the callback.
To maintain the original behavior, number of threads created is
the number of cores that SPDK app uses.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Signed-off-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Change-Id: I2cd4757fcb6a43002423486d80b6dbee77532ead
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/497
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Previously NVMe-oF target had requested each thread to destroy
its poll group, but had moved to the next state without waiting
for completion.
To create and destroy poll group threads dynamically, NVMe-oF
target have to know the completion of poll group destroy.
The reason is as follows.
spdk_thread_exit() requires that each poll group thread to unregister
its pollers, but poller unregistration is done asynchronously, and
releaes its I/O channels, but I/O channel release is done
asynchronously.
This patch does the following.
To avoid using mutex, add the init thread.
spdk_for_each_thread() requires completion callback but the
completion callback is usable only if each message handler is
synchronous. spdk_nvmf_poll_group_destroy() is asynchronous now.
So replace spdk_for_each_thread() by parsing g_poll_groups and
sending message to each corresonding thread.
Then add comletion callback nvmf_tgt_destroy_poll_group_done() to
spdk_nvmf_poll_group_destroy().
nvmf_tgt_destroy_poll_group_done() sends message to the init
thread.
The init thread executes _nvmf_tgt_destroy_poll_group_done().
_nvmf_tgt_destroy_poll_group_done() decrements g_num_poll_groups
and move to the next state if it becomes zero.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I97eb90b9dbff29d7702b20cf7ac233d39d7216b6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/496
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
The next patch will create poll group threads dynamically for
NVMe-oF target, and will need to wait for completion of poll group and
I/O channel destroy. This is a preparation for the next patch.
Add callback function and its argument to spdk_nvmf_poll_group_destroy(),
and to struct spdk_nvmf_poll_group, respectively.
The callback has not only cb_arg but also status as its parameters even
if the next patch always sets the status to zero. The reason is to follow
spdk_nvmf_tgt_destroy's callback and to process any case that the status
is nonzero in future.
spdk_nvmf_poll_group_destroy() sets the passed callback to the passed
poll group.
Then spdk_nvmf_tgt_destroy_poll_group() calls the held callback in the
end.
This change will ensure all pollers are being unregistered and
all I/O channels are being released.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ifb854066a5259a6029d55b88de358e3346c63f18
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/495
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Do large reads from the socket and buffer into a pipe.
Change-Id: I0a1bc5b356cb8c403048ab3b22a159332f085e6b
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/447
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>
Default was 8 which meant max of 8 bdevs. Bump it up to 64.
Fixes issue #1232
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I966e90de5c27910df0e4da0d1062d9d1665f8de6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1063
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
The adminq poller could get a failure if the ctrlr has
already been hot removed, which starts a reset.
But while the for_each_channel is running for the reset,
the hotplug poller could run and start the destruct
process. If the ctrlr is deleted before the for_each_channel
completes, we will try to call spdk_nvme_ctrlr_reset() on
a deleted controller.
While here, also add a check to skip the reset if the
controller is already in the process of being removed.
Fixes#1273.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I20286814d904b8d5a9c5209bbb53663683a4e6b0
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1253
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: Aleksey Marchuk <alexeymar@mellanox.com>
