Some data cannot be compresssed and if there is not room in
the output buffer for the uncompressed data and whatever
info the compress back end needs it will error out.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I4cb47e6cdb3facd3867d5dc4fb6f9352a307e33c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16098
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
We had it for compress but simply didn't think of a use case for
decompress. During the develpoment of the compressdev accel_fw
module it was discovered that compressdev does indeed provide the
uncompressed length on completion of decompress and the reducelib
uses it. So, add it here.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I2f6a8bbbe3ef8ebe0b50d6434845f405afa7d37d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16035
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Compression and decompression both start with an uncompressed file,
provided using the new -l command line option. The file is then
compressed in chunks according to the specified block size. Each
operation works on one chunk.
Change-Id: Ia7d3853627d938f73e6aa3ee09fccd11d9bca706
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Signed-off-by: Paul Luse <paul.e.luser@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14681
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
per Intel policy to include file commit date using git cmd
below. The policy does not apply to non-Intel (C) notices.
git log --follow -C90% --format=%ad --date default <file> | tail -1
and then pull just the 4 digit year from the result.
Intel copyrights were not added to files where Intel either had
no contribution ot the contribution lacked substance (ie license
header updates, formatting changes, etc). Contribution date used
"--follow -C95%" to get the most accurate date.
Note that several files in this patch didn't end the license/(c)
block with a blank comment line so these were added as the vast
majority of files do have this last blank line. Simply there for
consistency.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Id5b7ce4f658fe87132f14139ead58d6e285c04d4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15192
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>
Community-CI: Mellanox Build Bot
In prep for upcoming iovec based compression/decompression patches.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I413493f764bead9e56266e488b74f8bca979e225
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14633
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>
In prep for adding both src and dst iovec support for compression.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I704b8d2bd459de03deb7f8ee45d76261910a3727
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13746
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>
This is consistent with the use of terms in other parts of SPDK and fits
with the code living under module/
Change-Id: If182f7cf2d160d57443a1b5f24e0065f191b59b2
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13919
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The word engine was both used (interchangeably with module) to refer to
the things that plug into the framework and to the framework itself.
This patch eliminates all use of the word engine that meant the
framework. It leaves uses of the word that meant "module".
Change-Id: I6b9b50e2f045ac39f2a74d0152ee8d6269be4bd1
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13918
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
The public interface of lib/accel is now include/spdk/accel.h
Change-Id: Id94f623a494eb1b524b060f4413f633073ea7466
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13916
Tested-by: SPDK CI Jenkins <sys_sgci@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@nvidia.com>
In prep for the next few patches that will it back using a
different implmentation. For review purposes it will be much
easier to remove it first. The new implmentation will be nothing
like what was here before.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I3d14e524751442bfd5f0ade87333d879137b5d05
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13435
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Simplify things a bit for an upcoming patch. This also fixes an
annoyance when there's a submission error, previously the
outstanding IO assert would have hit in the completion routine
because of the previous location of the increment..
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ibfb914f10590f2370be58cabe06df466bbb3dc90
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12902
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Could have sworn this was in there but when we check for workload
selections we weren't printing usage and exiting when there was
an unknown selection.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Iadc02457d9a15602bb4138c611a982333a8a2b66
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12932
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: John Kariuki <John.K.Kariuki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Took a little bit of rework to both get the engine name and print
it before the results (as before).
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Iac38c30941eeae1501d58b0a28d241f7c2fad2d7
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12935
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
This has been implicitly required before, and all
in-tree apps (except accel_perf) set it, so let's
explicitly require it. This name gets used for
things like the shm name for spdk trace event file.
While here, add the name for accel_perf.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I47a22466550d4b31bacafee58d30339b4f22f4b4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13876
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Michal Berger <michal.berger@intel.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Many open source projects have moved to using SPDX identifiers
to specify license information, reducing the amount of
boilerplate code in every source file. This patch replaces
the bulk of SPDK .c, .cpp and Makefiles with the BSD-3-Clause
identifier.
Almost all of these files share the exact same license text,
and this patch only modifies the files that contain the
most common license text. There can be slight variations
because the third clause contains company names - most say
"Intel Corporation", but there are instances for Nvidia,
Samsung, Eideticom and even "the copyright holder".
Used a bash script to automate replacement of the license text
with SPDX identifier which is checked into scripts/spdx.sh.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iaa88ab5e92ea471691dc298cfe41ebfb5d169780
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12904
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: <qun.wan@intel.com>
By design there is a limit to how many channels the idxd driver
can suport based on how many DSA instances are available. When we
reach the limit we won't be able to get a channel. This fixes that
error path to fail gracefully instead of seg faulting.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I226f59913cb830eae0707623ae251ba19bce9aaf
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12218
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Decompress is not a selectable workload, only compress as it makes
no sense to decompress w/o a compressed buffer to start with. When
the verify option is selected with compress, decompress is used
on the compressed data and compared to the original buffer.
Changes also included making the src buffer for compress semi-random
for more real life comp/decomp speed. Additionally some error handling
was fixed up in the event the we get an error because ISAL isn't
configured, before it would crash, not it exits nicely.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ic1f323579ed5c6950bdb0e95513bfd2f6593b5d9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12303
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
In support of upcoming patches and to greatly simplify things,
the capabilites enum which held bit positions for each opcode
has been removed. Only the opcodes enum remains and thus only
opcodes are used throughout. For the capabiltiies bitmap a helper
function is added to convert from opcode to bit position. Right
now it is used in the IO path but in upcoming patches that goes away
and the conversion is only done at init time.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ic4ad15b9f24ad3675a7bba4831f4e81de9b7bc70
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11949
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
First in a series of patches that will enable multiple engines
to exist at once and choose the best one based on their priorities
and capabilites, the public API will no longer be needed.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ia87b83aa2263745a94a822a160b6e97bb2e0dc19
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11948
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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>
This patch is just plumbing the flags param. Use of it for PMEM
will come in upcoming patches.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I620df072aaad3f8062a0312bbea3da1bc3f911b9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9281
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
We encountered a coredump in running accel_perf with only one
ioat/idxd device enabled:
accel_perf: accel_engine.c:973: accel_engine_create_cb:
Assertion `accel_ch->engine_ch != NULL' failed.
Aborted (core dumped)
In identify_accel_engine_usage, we try to get an accel channel,
read capabilities of it, and free it. However, the hw destory_cb
is not yet called before running _init_thread because the hw destroy_cb
is delayed by accel_engine_destroy_cb, which is already a delayed
event itself. So, we simply check the first available channel's
capabilities in _init_thread to avoid such partial-free error.
Signed-off-by: Wenliang Wang <wangwenliang.1995@bytedance.com>
Change-Id: I96ae0408568ed6cd2cb9b74fde406a821943616e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10426
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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>
It's being added to the low level library perf tool which makes
more sense as the accel_fw provides queueing thus allowing any
queue depth. When using the low level lib you are limited to
a small number reported by HW unless you use batching then you
can get quite a bit more.
Future patches will remove batch from the accel_fw, this is just
the accel_perf tool.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I3775b9ecdf353f730c7f3e2c06bb45a8873e61f8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9845
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Monica Kenguva <monica.kenguva@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Some were still using 0, -1 and/or count values.
Signed-off-by: paul Luse <paul.e.luse@intel.com>
Change-Id: Ic161b5436c55f229f1f1a557d29e395bf8d4f660
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8584
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Wrong opcode was used when deciding whether a dst buffer is needed
or not. Also on freeing we were freeing src instead of the vector
parts of the task.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I33eb9408ee20eca6c44911b4567d0367528347de
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9189
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Monica Kenguva <monica.kenguva@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Previously the accel_perf tool would look at whether it had HW
or SW commands to know whether to execute the callback right away
or schdule to avoid blowing the stack (SW calls are sync).
Moved this to the SW module (part of the accel engine) so the
caller doesn't have to worry about. Allowed for a few simplifcations
in the tool as well.
Also, instead of using send_msg to call the completion we add it to
a list in the sw module that a new poller uses to perform the
completions as this is more efficient the sending a message to the
same thread.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ifc6c5b8635f51e3fa1a825c8573378b3752d7d91
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9171
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
In accel_done function, we use g_using_sw_engine to
determine to directly call _accel_done or use thread message
passing way.
However when we get the capability and determine the
value of g_using_sw_engine in mulitple cases. We do not
protect the value of g_num_workers. Then if we use CPU mode
to do test, g_using_sw_engine will not set to be false
in racing condition. Since the value of g_num_workers can be
> 1 when we do the check, i.e., it is a TOC2TOU issue.
The solution is that we check the g_using_sw_engine in
accel_perf_start function.
Fixes issue #2084
Change-Id: I55c18e0443120adb698d5bd27d4522df09f6dcab
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9151
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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: Ben Walker <benjamin.walker@intel.com>
For all CRC related functions. Does not need to be DMA'able memory
as DSA returns the CRC to it's completion record and the lib
copies it to this address. Done for consistency as this element
was added as part of adding the copy+CRC API.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Iefedcbc0a1c4e211eeb8aaf5c52f2881e9173bad
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8230
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
For COPY+CRC operations, we allocate a destination buffer for each
task that's big enough to hold the copied input data for all stages
of the chain. For example, if the operation is 4 stages of 4K input
buffers, the destination will be 16K in size.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Id32a98c1dbada2881a8423c050e892d5c37bf6cc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8204
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Faced the following warnings during the compilation:
accel_perf.c:222:17: warning: ‘argval’ may be used uninitialized in this function [-Wmaybe-uninitialized]
222 | g_crc32c_seed = argval;
And this patch can be used to fix this issue.
Change-Id: I84ee542d629ff5d9e6a2873c0035bea81b376150
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8538
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Chengqiang Meng <chengqiangx.meng@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: wanghailiang <hailiangx.e.wang@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
For benchmarking purposes, we may want to use a
relatively low queue depth but spread the operations
across a wider range of memory. A new -a option is
added where the user can specify an "allocate depth"
to do exactly that. In this case, more tasks (and
their associated buffers) can be allocated than we
have actual queue depth. Then when we pick a new
task for the next operation, it will use a different
memory range and avoid always using the same buffers
over and over again.
If not specified, we just allocate the same number
of tasks as the queue depth, which is the current
behavior.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I78042d905fd49d130c4a318e2c19eb11b84ff726
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8451
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
When a task completes, always put it back in the task
pool (using TAILQ_INSERT_TAIL) and then use _get_task
to get a task for the next submission. Currently this
will just allocate the task that was just put into
the TAILQ. But an upcoming patch will allocate
more tasks than we have queue depth, and this patch
will ensure all of those tasks get used evenly.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ia6247a76ba60337fe6da3189e6c305f4dfb0a041
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8450
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Previously we would only assign the worker in _get_task().
But future patches will use _get_task() for each I/O,
not just during startup.
Also increment the current_queue_depth during startup
only, rather than every time _get_task() is called.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I2713591d36b8353eaab8119ee230261f40857019
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8449
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Community-CI: Mellanox Build Bot
Getting/putting the channel races with getting real IO channels
causing issues with an upcoming design. Avoid it entirely by using
the first worker channel to get the capabilties.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I750a8d59e294f4cda9f71f3327afc03e15342768
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8170
Community-CI: Mellanox Build Bot
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>
This results in a significant performance improvement when using
HW offload engines.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I54d3e39f186c9f878fcf8bed8e9242e29d1e1bf1
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/8162
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: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
This is useful for applications even if they elect not to use the SPDK
event framework.
This doesn't shift everything in one go - just the subsystem
initialization logic. Configuration file loading also needs to move
in a separate patch later.
Change-Id: Id419df1045442d416650ed90e5ee78adfdd623d7
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6641
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
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: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Not only in accel_perf, but also in test event_perf.
Remove them.
Fixes#1895
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Change-Id: I2af1d9f6f077f3ae775af994567804633fc8f050
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7370
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>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
This patch added the chained crc32 support API for both batched
and non batched mode usage. And also update the accel_perf
program in order to use the revised accelerated crc32 function.
For example, you can use the following command:
./build/examples/accel_perf -C 4 -q 128 -o 4096 -t 5 -w crc32c -y
In this command, "-C 4" means that caculate the chained
crc32 for an iov array.
(even if you do not have the accelerated DSA hardware)
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ifede26f9040980b5791da8e5afef41177eede9f6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6457
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This patch provides two new accelerated crc32c function interface.
And the next patch will be used to add the real support of chained crc32c feature.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I3f8dd55c3da636e29e5fb02fc229b51f05653cd6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6456
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
For use by test scripts to know when there was a non-fatal error.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I1c5e37edb13570aec1e186fe534ed6780a6de0c5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6324
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>
Community-CI: Mellanox Build Bot
Useful for DSA, for example, where we might need more than one
thread hitting a single DSA device at a time. Previously you'd
have to do this by using multiple cores.
Note: the -n option was removed and replaced with -T, it was
a carry over from the ioat perf tool that this was modeled after.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I44840655dc297cdc3116ca7b67718444b0800ab3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6333
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>
Community-CI: Mellanox Build Bot
As reactors no longer have a thread created with them.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ie9e9411c52c215b8cffd894fef6394448ae8167d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6312
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>
This function is used to eliminate the duplicated code.
Also rename _free_task to _free_task_buffers to make
it easy to understand the code.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I2ef9dbbb81c12c229952f5590f616a17dc2fe087
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6128
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Mellanox Build Bot
When the task is allocated from _get_task function,
the task is removed from the tasks_pool in non batched mode.
So in _accel_done function, when the is_draining flag is true
and it is not a batched mode, we should add task back to the pool.
If not, the the memory related resource allocated by the task will
not be freed.
PS: In _check_draining function, the related resource of task
in the tasks_pool will be freed. However, if the task is not
added back, the resource free will not work as expected.
PS: The issue is reported by ASAN.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I981117037fba8e111987c771cae65bc06a734a6f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6097
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Mellanox Build Bot
Previous version just used batching for initial queue depth loading
as an example of how to batch. This version adds a new param -b that
allows the caller to either disable or set a specific batch value
for use during the entire run. For example Q depth 128 with a batch of
64 will always send IO in batches of 64 so in effect once the Q depth
has been met the tool will wait until the Q depth has dropped enough
to send another 64. This will allow for a more accurate measurement
of batching performance vs sending IO one at a time.
Also added clarrifying note on usage the Q depth is per core, not
spread over all cores.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ieb1df5f668ae9c7b37b0d789fceab1138044a5e6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5489
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>
Community-CI: Mellanox Build Bot
