Change the way we generate UUIDs to use uuid_generate_sha1()
from libuuid.
Fixes#2788.
Change-Id: Id750a7de74fb37bc3ab3ab06b3254b49d73f4be3
Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15935
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
The following patches will add mutex for bdev_nvme_delete() to improve
handling race conditions. This refactoring make such change easier.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I8971684a708bce89872f08f75db86eb3b723f380
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16821
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
If alternate paths and an active path are treated separately in
_bdev_nvme_delete(), it will be much easier to protect a path list
from delete operation by mutex.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ie3bed095fd92b80c0487ef7b136953ad03a174eb
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16820
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Factor out path deletion operation for one nvme_ctrlr into _bdev_nvme_delete().
_bdev_nvme_delete() traverses all remaining nvme_ctrlrs even after one
nvme_ctrlr was successfully deleted. To remember the successfule
deletion, use two return value variables, rc and _rc. For _rc returned by
_bdev_nvme_delete(), copy _rc to rc if _rc is zero, return _rc immediately
if _rc is not -ENXIO, or do nothing otherwise.
This improves the readability and makes us easier to add more changes.
Additionally, for _bdev_nvme_reset_io(), it is simpler to overwrite rc
to 0 if rc is -EBUSY rather than to return 0 if rc is -EBUSY. This is
very small change and hence done together.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I57eafd22918c8c976b9c51bedb9e4369976c1d5c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16819
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The next patch wants to use _bdev_nvme_delete() as a function name.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Iba103868e74795bf42c443a377c77e9c073329fb
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16818
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
This improves the readability and makes us easier to add more changes.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I55d7925d70f2a204f65a81f3fc44cf96b69c3ebe
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16709
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>
These functions:
_vbdev_lvs_grow_examine_finish
_vbdev_lvs_grow_examine_cb
_vbdev_lvs_grow_examine
are almost exact copies of:
_vbdev_lvs_examine_finish
_vbdev_lvs_examine_cb
vbdev_lvs_examine
Remove the duplicated grow functions. Factor out the common entry point
into _vbdev_lvs_examine() which accepts a callback to perform the
required action (spdk_lvs_load or spdk_lvs_grow).
Change-Id: I9805f29e22812051608873207401e3786dab7103
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16942
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>
Remove _vbdev_lvol_examine_close_cb() because it is identical as the
code at the end of _vbdev_lvs_examine_finish().
Remove the INFOLOG message because it is redundant (there's an ERRLOG
just before) and inconsistent with the lvolerrno != 0 case, where there
is no such message.
Change-Id: I8488a8b5fcbaf1895f4953081d98bc13f82be221
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16941
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
In the past, we didn't use the distinction between logical block size
and physical block size. Now it's possible to optionally set the
physical block size to be different then logical block size. It's useful
for NVMe 512e Advanced Format tests.
Change-Id: I1b596da471031ee90dafc6ba6276cebf769b5ea2
Signed-off-by: Panfil, Wojciech <wojciech.panfil@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16793
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
In the past we didn't use the distinction between logical block size and physical block
size in null bdev. Now we can optionally set the physical block size to
be different then logical block size. It's useful for testing NVMe 512e
Advanced Format scenarios.
Change-Id: Ib3713af9a4d0ce7fd322170b4d87100cfc91a103
Signed-off-by: Panfil, Wojciech <wojciech.panfil@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16792
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
When bdev_rados_cluster_init encounters an error, it shuts down the cluster
before returning, but since the pointer is still set, bdev_rbd_free will
attempt to shut it down again, which causes a crash.
Therefore, set the pointer to NULL after the first shutdown to indicate
that the cluster object does not exist anymore.
Change-Id: Ie403471e8aba881cb6380e74bd1a4ca8d67cbc68
Signed-off-by: Lukas Stockner <lstockner@genesiscloud.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16203
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
The spdk_bdev_ext_io_opts structure is used to pass extra options when
submitting a bdev IO request, without having to modify/add functions to
handle new options. Additionally, the structure has a size field to
allow adding new fields without breaking the ABI (and thus having to
bump up the major version of a library).
It is also a part of spdk_bdev_io and there are several reasons for
removing it from that structure:
1. The size field only makes sense in structures that are passed
through pointers. And spdk_bdev_ext_io_opts is indeed passed as a
pointer to spdk_bdev_{readv,writev}_blocks_ext(), however it is
also embedded in spdk_bdev_io (internal.ext_opts_copy), which is
also part of the API. It means that each time a new field is added
to spdk_bdev_ext_io_opts, the size of spdk_bdev_io will also
change, so we will need to bump the major version of libspdk_bdev
anyway, thus making spdk_bdev_ext_io_opts.size useless.
2. The size field also makes internal.ext_opts cumbersome to use, as
each time one of its fields is accessed, we need to check the size.
Currently the code doesn't do that, because all of the existing
spdk_bdev_ext_io_opts fields were present when this structure was
initially introduced, but we'd need to do check the size before
accessing any new fields.
3. spdk_bdev_ext_io_opts has a metadata field, while spdk_bdev_io
already has u.bdev.md_buf, which means that we store the same thing
in several different places in spdk_bdev_io (u.bdev.md_buf,
u.bdev.ext_opts->metadata, internal.ext_opts->metadata).
Therefore, this patch removes all references to spdk_bdev_ext_io_opts
from spdk_bdev_io and replaces them with fields (memory_domain,
memory_domain_ctx) that were missing in spdk_bdev_io. Unfortunately,
this change breaks the API and requires changes in bdev modules that
supported spdk_bdev_io.u.bdev.ext_opts.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I49b7524eb84d1d4d7f12b7ab025fec36da1ee01f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16773
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>
Also deprecate the existing spdk_nvmf_request_data() API, which is
incompatible with iovecs.
Signed-off-by: John Levon <john.levon@nutanix.com>
Change-Id: I44df8ff30a431873a0c2f34b0cdb58df858fd7e3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16200
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>
It has been implemented in commit 56e2d632ce to reset all nvme_ctrlrs
of a bdev controller sequentially. Update the log.
Change-Id: Id87bf99d7e269c8ad0d6b2576e2329455601ec55
Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16653
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
With the introduction bdev module claims v2, existing consumers should
transition off of v1 claims. This transitions blob bdevs from v1
exclusive writer claims to v2 read write once claims.
Signed-off-by: Mike Gerdts <mgerdts@nvidia.com>
Change-Id: I1884585a540fa17ee341430e03de3c4f5d35322b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16168
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
We used hardcoded value set by bdev module, however
this value might be changed, so get a real value
from iobug config
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: Id15b602f699f3dd63aeff11fb063bb62c384663d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16601
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
For JSON RPC, boolean response with false value may not be regarded as error.
Previously many cases were replaced to use
spdk_jsonrpc_send_error_response() explicitly. Replace one of the
remaining cases in this patch.
rpc_blobfs_detect() uses boolean response for not only true but also
false, but it had a memory leak bug. Fix it together in this patch.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Iaff21115282f638038345daa986b5c743ba9a3ed
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16621
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
For JSON RPC, boolean response with false value may not be regarded as error.
Previously many cases were replaced to use
spdk_jsonrpc_send_error_response() explicitly. However, this pattern did
not become established and new bdev modules used
spdk_jsonrpc_send_bool_response() with false.
Once again, replace remaining cases in this patch.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ie8858bc8ff7c36bc3a829977044a91d459db76f2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16555
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The NVMe bdev module has been refined since the bdev_nvme_apply_firmware
RPC was added. It is enough to open any one NVMe bdev even if one NVMe
controller has multiple namespaces. Hence, let's remove
spdk_bdev_first/next() calls from rpc_bdev_nvme_apply_firmware() rather
than replacing these by spdk_for_each_bdev(). Additionally, not only
spdk_bdev_close() but also spdk_put_io_channel() and
spdk_jsonrpc_send_*_response() should be done on the original thread.
Hence, redirect to the original thread always when a NVMe command is
returned, and rename firm_ctx->thread by firm_ctx->orig_thread for
clarification. orig_thread will be better than comment.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I90b1986584b3926980fd265e4fded194eb5a2d00
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16541
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
It is enough to embed an instance of rpc_apply_firmware structure into
firmware_update_info structure.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I41a480a0b8cd56f4b537512d5f83c5cbd5eee718
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16540
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>
Previously, bdev_nvme_apply_firmware() used a temporary character array
to reduce the calls of spdk_jsonrpc_send_error_response().
Change these to call spdk_jsonrpc_send_error_response() directly.
This will simplify the next patch to replace spdk_bdev_first/next() by
spdk_for_each_bdev()ss.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I87ffc9416232dcaba30202ebbe0cb4b185a9563d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16539
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>
Support OCF is now winding down and will not see further updates.
Change-Id: Ica2026d3a9ad13daf677fcce2b7974eb333971fc
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16392
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
The gpt bdev module has an off-by-one error. When it
calculates the size of the partition, it simply does
"end - start", when really it should be "end - start + 1".
We cannot just fix it by changing the math here, any
consumers of the partition may have put down metadata
on the partition based on the old size.
So instead add a new SPDK partition type. SPDK will keep
the existing off-by-one behavior when it finds the old
partition type, but will use the correct math when finding
the new partition type.
Fixes issue #2801.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I48eb48c781f1968b59e52b4477ca45e9c81eac11
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16298
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Mike Gerdts <mgerdts@nvidia.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
This is required when volume is attached via different storage boxes
for example while migrating it.
Signed-off-by: Gili Buzaglo <gili.buzaglo@kioxia.com>
Change-Id: I680c781ae5de078972d6aef547804d60fff3c643
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16407
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
To allow SO_MINOR updates on LTS for the whole year it is supported,
the major version for all components needs to be increased.
This is to prevent scenario where two versions exists with matching
versions, but conflicting ABI.
Ex. Next SPDK release adds an API call increasing the minor version,
then LTS needs just a subset of those additions.
Increasing major so version after LTS, allows the future releases
to update versions as needed. Yet allowing LTS to increase minor
version separately.
Disabled test for increasing SO version without ABI change, as
that is goal of this patch. This check shall be removed with SPDK 23.05
release.
Looks like this was left over from prior LTS, to avoid that
make sure it is only skipped when running against v23.01.x as latest
release.
This patch:
- increases SO_VER by 1 for all components
- resets SO_MINOR to 0 for all components
- removes suppressions for ABI tests
Short reference to how the versions were changed:
MAX=$(git grep "SO_VER := " | cut -d" " -f 3 | sort -ubnr | head -1)
for((i=$MAX;i>0;i-=1)); do find . -name "Makefile" -exec \
sed -i -e "s/SO_VER := $i\$/SO_VER := $(($i+1))/g" {} +; done
find . -name "Makefile" -exec \
sed -i -e "s/SO_MINOR := .*/SO_MINOR := 0/g" {} +
Change-Id: I3e5681802c0a5ac6d7d652a18896997cd07cc8bf
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16419
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This was added during debug/development and
was not deleted by accident.
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: I146748151623a3ea4808c7b5cc34085d30ca81b4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16388
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
directly
This patch removes hardcoded compressdev code from the
vbdev module and instead uses the accel_fw. The port required
a few changes based on how things are plumbed and accessed,
nothing that isn't be too obscure. CI tests were updated to
run ISAL accel_fw module as well as DPDK compressdev with QAT.
Unit tests for the new module will follow in a separate patch.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I769cbc888658fb846d89f6f0bfeeb1a2a820767e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13610
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
ublk backend could support ublk driver with kernel. Specify
configuration parameter to start it up.
Signed-off-by: Yifan Bian <yifan.bian@intel.com>
Co-authored-by: Xiaodong Liu <xiaodong.liu@intel.com>
Change-Id: I55e7d757e04315b25e9bfab5fdcbb6621be3e29e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15680
Reviewed-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The mlx5 accel module supports crypto operations.
Data buffer is split into `block_size` chunks and each
chunk is enrypted individually.
mlx5 library contains some utility functions that will
later be used by other libraries, this lib will be
exntended later.
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: Iacdd8caaade477277d5a95cfd53e9910e280a73b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15420
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: Jim Harris <james.r.harris@intel.com>
All DPDK related code is removed, handling of
RESET command was sligthly updated.
Handling of -ENOMEM was updated for cases when
accel API returns -ENOMEM
Crypto tests in blockdev.sh were extended with more
crypto_bdevs to verify NOMEM cases - that failed
with original vbdev_crypto implementation
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: If1feba2449bee852c6c4daca4b3406414db6fded
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14860
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: Jim Harris <james.r.harris@intel.com>
Attempt to send any queued writes even if the socket is in a group. This
will not work if there is a send task already outstanding.
Change-Id: Icc0b5884e3d247042194ad26b30340ceb824886c
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15212
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Add RPC bdev_nvme_get_path_iostat to show I/O statistics for IO paths
of the NVMe bdev.
Change-Id: I22e5ad112d5cfa6d96cf246dcd0e511ae71dc839
Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14745
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Handling for scalar dst buffers were removed in 1866faffe, and all
buffers are now described by iovecs. The dst field was removed from
spdk_accel_task, so we also need to remove any references to that field
from dpdk_compressdev. This patch fixes the build with compressdev
enabled.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I21fbbb45a15e7250944753e445dede7d586bf35b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16349
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Michal Berger <michal.berger@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@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>
From an earlier comment on the original patch that introduced the
module. Stop using the thread to associate the device_qp and
simply link it into the chan.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ib55979247d9bdacdc868bdb9dea97e1941e1e8ab
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15832
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>
This is the port of the vbdev compress logic into the accel
framework. It includes just one enhancement, to only fill each
mbuf in either src or dst array with max "window size" param to
avoid QAT errors. Note that DPDK ISAL PMD was not ported as we
have native ISAL compression in accel now.
Note: ISAL w/DPDK is still built w/this patch, that can't be
removed until the vbdev module moves to accel fw as it still
depends on DPDK ISAL PMD.
Follow-on patches will include addition C API for PMD selection,
this patch just gets equivalent functionality going. Upcoming
patches will also convert the vbdev compress module to use the
accel framework instead of talking directly to compressdev.
More patches will also address comments on vbdev common code
that addressed here would make the review challenging.
This patch also fixes a bug in the ported code that needs to
be fixed here to pass CI. Capability discovery was incorrect
causing all devices to appear to not support chained mbufs,
with the mbuf splitting code this is important to get right.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I7f526404819b145ef26e40877122ba80a02fcf51
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15178
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>
We will be creating a new accel module for DPDK
compressdev. We can heavily leverage all of the
code from the existing vbdev_compress.c file. So
just copy that file exactly to start, and then the
next patch will contain only the deltas for removing
the bdev/reduce plumbing and adding the accel
plumbing.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I4f6ca1c2dad92eb8dd38b351602b65b8cb4ee4e8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15829
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Community-CI: Mellanox Build Bot
We may need to process multiple events to get all of
the events associated with a newly published service,
so a 1 second poller is actually a bit too long since
we will only get one event per poll iteration. Shorten
it to 100ms instead.
It doesn't appear there is any easy way to use the avahi
API to help with this, maybe we could have some context
variable used to detect if an event was processed or not,
and call avahi_simple_poll_iterate() multiple times if
necessary. This might be something worth investigating
in the future.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ifea7a99dc8b8b501392e29276b20528a873b1ae1
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16327
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Boris Glimcher <Boris.Glimcher@emc.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Make vbdev_crypto_destruct() return 1 to signal that program
execution should wait for spdk_bdev_destruct_done() function,
which is added inside _device_unregister_cb().
This change is related to _vdev_dev_get() not being able
to find the devices, when called from _cryptodev_sym_session_free(),
as it uses device driver name, which might already be freed.
This occurs only during bdev module finish, when crypto bdevs
are being unregistered and vbdev_crypto_finish() proceeds to
call bdev name deletion without waiting for the unregister
callbacks to complete, which ultimately results in reading
freed pointers.
This only happens when code execution takes path for DPDK 22.11+.
Change-Id: Id9a43d07c90aef7a82867383fd77354ac521a3e7
Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16290
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Currently delete_crypto_disk() calls spdk_bdev_unregister_bdev_by_name()
and immediately after exiting that function, it proceeds to bdev name
deletion. This causes callbacks triggered by above call to run with
references to bdev names that are partially unavailable due to free()
functions in vbdev_crypto_delete_name().
Add an intermediate callback that will call vbdev_crypto_delete_name()
and then the original callback that was sent as an argument to
delete_crypto_disk(). That way we are sure that bdev name deletion
is performed right after bdev unregister.
Change-Id: I483ce5c3c63596f54d44220ca61c5e97c3807faf
Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16253
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
It was found that if system has no crypto devs,
we exit earlier from init function and don't register
io_device. Later in fini function we may try to unregister
invalid io_device
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: I23ac9674c02d4fe97f01c66928a5ec5a2b39ec47
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16321
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>
This patch is a combination of commits which update vdev_crypto:
110d8411e bdev/crypto: do not create mempool for session private data
495055b05 bdev/crypto: update rte_cryptodev usage for DPDK 22.11
02caed6b5 bdev/crypto: remove mempool usage matching < DPDK 19.02
5887eb321 bdev/crypto: do not track type of crypto session
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: I30c4f76e4e7b4865a7daa638d357888bb5e02071
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16039
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
The io paths' stat will get lost when they are destroyed. Record
the stat in the nvme_ns structure.
Change-Id: I12fc0b04fac0d59e7465fe543ee733f2822a9cdb
Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14744
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Added helper functions nvme_ns_alloc() and nvme_ns_free().
This is a preparation for next patch where we will allocate or free
I/O statistics of nvme_ns when this nvme_ns is allocated or freed.
Change-Id: I54b0dba61bd19923178ba4bed97677cf628ba509
Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16300
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Currently we have stat per bdev I/O channel, but for NVMe bdev
multipath, we don't have stat per I/O path. Especially for
active-active mode, we may want to observe each path's statistics.
This patch support IO stat for nvme_io_path. Record each nvme_io_path
stat using structure spdk_bdev_io_stat.
The following is the comparison of bdevperf test.
Test on Arm server with the following basic configuration.
1 Null bdev: block size: 4K, num_blocks:16k
run bdevperf with io size=4k, qdepth=1/32/128, rw type=randwrite/mixed with 70% read/randread
Each time run 30 seconds, each item run for 16 times and get the average.
The result is as follows.
qdepth type IOPS(default) IOPS(this patch) diff
1 randwrite 7795157.27 7859909.78 0.83%
1 mix(70% r) 7418607.08 7404026.54 -0.20%
1 randread 8053560.83 8046315.44 -0.09%
32 randwrite 15409191.3 15327642.11 -0.53%
32 mix(70% r) 13760145.97 13714666.28 -0.33%
32 randread 16136922.98 16038855.39 -0.61%
128 randwrite 14815647.56 14944902.74 0.87%
128 mix(70% r) 13414858.59 13412317.46 -0.02%
128 randread 15508642.43 15521752.41 0.08%
Change-Id: I4eb5673f49d65d3ff9b930361d2f31ab0ccfa021
Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14743
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>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Support to specify rr_min_io for multipath round-robin policy,
which makes I/O switches to another io path after rr_min_io I/Os are
rounted to current io path.
Change-Id: I09f0d8d24271c0178ff816fa63ce8576b6e8ae47
Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15445
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>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Added helper function bdev_nvme_clear_current_io_path for clearing
current_io_path.
The next patch will clear a new variable of the nvme_bdev_channel
when clearing current_io_path. It is convenient to add a helper
function to clear current_io_path.
Change-Id: I7d445638648ea232fedcbf16736e9c4c73cc9c71
Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15681
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Support selecting io path according to number of outstanding io of
each path in a channel. It's optional, and can be set by calling
RPC "bdev_nvme_set_multipath_policy -s queue_depth".
Change-Id: I82cdfbd69b3e105c973844c4f34dc98f0dca2faf
Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14734
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
When we submit more tasks than supported by qp,
extra tasks are queued on io_channel. Later completion
poller tries to resubmit these tasks one by one. That
is not efficient since every enqueu_burst may cause
doorbell updates in HW.
Instead add a check for qpir capacity and submit
appropriate number of requests. If qpair is full,
tasks are queued in dedicated list. This approach
should remove or minimize the need to resubmit
individual crypto operations.
This also handles a case where there are no entries
in global pools (crypto_ops or rte_mbuf)
Fixes issue #2756
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: Iab50e623e7a82a4f5bef7a1e4434e593240ab633
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15769
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>
Previously vbdev_crypto used DPDK directly and
the restriction on max IO size was propagated to
generic bdev layer which split big IO requests.
Now, when DPDK code is a standalone accel module,
this restriction on max IO size is not visible to
the user and we should get rid of it.
To remove this limitation, allow to submit crypto
operations for part of logical blocks in big IO,
the rest blocks will be processed when all submitted
crypto ops are completed.
To verify this patch, add a functional test which
submits big IO verify mode
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: I0ee89e98195a5c744f3fb2bfc752b578965c3bc5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15768
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>
All operations are using iovecs to describe their buffers and only
encrypt/decrypt additionally used nbytes to store the total size of a
src buffer. We don't really need this value in the generic accel code,
so we can let modules calculate it, if necessary. That way, we won't
waste cycles calculating it if a module doesn't use it and it makes the
code a bit easier, as we won't have to deal with the fact that nbytes is
only valid for certain operations.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I29252be34a9af9fd40f4c7fec9d0a0c1139c562d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16306
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Also, since this was the last operation using dst and nbytes, these
fields were removed from spdk_accel_task.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I0d6b090e101c016d1bdcbe7a3bee7d6f691f1c9e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15943
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Also, since this was the last operation using src, remove this field
from spdk_accel_task.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I55fd98697ef4f92a13dd0563b4adf9ccb0af171b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15942
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Implement the resize function for RAID0. raid0_resize() calculate the
new raid_bdev's block count and if it is different from the old block
count, call spdk_bdev_notify_blockcnt_change() with the new block count.
A raid0 bdev always opens all base bdevs. Hence, if the size of base
bdevs are reduced, resize fails now. This limitation will be removed
later.
Add a simple functional test for this feature. The test is to create
a raid0 bdev with two null bdevs, resize one null bdev, check if the
raid0 bdev is not resize, resize another null bdev, check if the raid0
bdev is resized.
test/iscsi_tgt/resize/resize.sh was used a reference to write the test.
Using jq rather than grep&sed is better and hence replace grep&sed by jq
of test/iscsi_tgt/resize/resize.sh together in this patch.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I07136648c4189b970843fc6da51ff40355423144
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16261
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Also, make it possible to remove copy operations following a fill
operation if they're using the same buffers.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I7da195ce80650a02c5db99d9400ee692f797b1f8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15940
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Also, replace src2 with an iovec + iovcnt and rename it to s2 to
keep the naming consistent with the source buffer (s).
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I44787128377addd514818ec5aaec084b1a31f0c3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15939
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Also, replace dst2 with an iovec + iovcnt and rename it to d2 to
keep the naming consistent with the destination buffer (d).
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Ib394c127eeb5890451535ff485f96f7edd2897a4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15938
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
This patch is first in the series of patches aimed to make all accel
operations describe their buffers with iovecs. The intention is to make
it easier to handle tasks in a generic way.
It doesn't mean that we change the API - all function signatures are
preserved. If a function doesn't use iovecs, we use the aux_iovs array.
However, this does mean that each accel module that provides support for
a given operation will need to be adjusted to use iovecs.
Additionally, update the unit test checking copy elision to verify the
buffers of the copy operation that is left.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I9e6d8d1be3b8b9706cb4a6222dad30e8c373d8fb
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15937
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Factor out block count calculation of raid0 bdev into a helper
function raid0_calculate_blockcnt(). This helper function will be used
to support resize in the following patches.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ie99d8686897f1249f48ef8985cb1c8347028fccf
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16283
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The new flag is used in the data processing path.
Change-Id: I93dfc00003d370f8505cc3d334aea161024e2435
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16265
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Non-optimized path was not cached for active/active policy unexpectedly.
Fix the bug in this patch.
This will simplify the code and will be helpful to add more algorithms a
little.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I233d9fa6eca73b1e0fb850c7ea4b3474aff6fc1d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16190
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>
Reviewed-by: Richael <richael.zhuang@arm.com>
Unify _bdev_nvme_find_io_path() and bdev_nvme_find_next_io_path()
into _bdev_nvme_find_io_path() by modifying nvme_io_path_get_next().
For active/passive policy, _bdev_nvme_find_io_path() is called only if
nbdev_ch->current_io_path is NULL. Hence, the prev parameter is not
necessary anymore.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: If61b8a24b768a1d571c0033b91d9d9bd487b5cf7
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16189
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>
Reviewed-by: Richael <richael.zhuang@arm.com>
nbdev_ch->current_io_path is NULL at initialization.
bdev_nvme_find_io_path() calls _bdev_nvme_find_io_path() if
nbdev_ch->current_io_path is NULL. If there is no optimized path,
nbdev_ch->current_io_path is not filled. Hence, as long as there is no
optimized path, bdev_nvme_find_next_io_path() is never called.
However, bdev_nvme_find_next_io_path() fills nbdev_ch->current_io_path
even if the found path is non optimized.
This is a contradiction and a bug.
To fix this bug, as a preparation, refactor _bdev_nvme_find_io_path() to
cnosolidate bdev_nvme_find_next_io_path() and _bdev_nvme_find_io_path()
into a single function because bdev_nvme_find_next_io_path() and
_bdev_nvme_find_io_path() were almost identical.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I7bc4107ce6ae6f116dee03c9bb67d9e4061ce775
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16188
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>
Reviewed-by: Richael <richael.zhuang@arm.com>
When an I/O gets an I/O error, the I/O path to which the I/O was
submitted may be still available. In this case, the I/O should be
retried to the same I/O path. However, a new I/O path was always
selected for an I/O retry.
For the active/passive policy, the same I/O path was selected naturally.
However, for the active/active policy, it was very likely that a
different I/O path was selected.
To use the same I/O path for an I/O retry, add a helper function
bdev_nvme_retry_io() into bdev_nvme_retry_ios() and replace
bdev_nvme_submit_request() by bdev_nvme_retry_io(). bdev_nvme_retry_io()
checks if nbdev_io->io_path is not NULL and is available. Then, call
_bdev_nvme_submit_request() if true, or call bdev_nvme_submit_request()
otherwise. For I/O path error, clear nbdev_io->io_path for
clarification. Add unit test to verify this change.
Linux kernel native NVMe multipath already takes this approach. Hence,
this change will be reasonable.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I7022aafd8b1cdd5830c4f743d64b080aa970cf8d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16015
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Richael <richael.zhuang@arm.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The following patches will clear bio->io_path when the error is a
network path error. As a preparation, cache bio->io_path to a local
variable io_path.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I0a25f4a70dd1064702b2037283bddd6e789dfae1
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16014
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>
This is in the same effort as gathering all retry functions into the
same place. This will make the following patches easier.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: If2a017ebda45eb1eaf0dc93b15d02b4122dc3be0
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15958
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>
Relocate abort_retry_ios() in a file to gather all retry functions
in the same place.
I/O retry is very complex and an improvement will be added in the
following patches. This will make the following patches easier.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I84751bd078db4aef753dcc533320cee9aa09c9b2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15957
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>
The following patches will change I/O retry to use the same io_path if
it is still available. However, bdev_nvme_submit_request() always calls
bdev_nvme_find_io_path() first. For I/O retry, if possible, we want to
skip calling bdev_nvme_find_io_path() and use nbdev_io->io_path instead.
To reuse the code as much as possible and not to touch the fast code
path, factor out request submit functions from
bdev_nvme_submit_request() into _bdev_nvme_submit_request().
While developing this patch, a bug/mismatch was found such that
bdev_io->internal.ch was different from ch of
bdev_nvme_submit_request(). Fix it together in this patch.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Id003e033ecde218d1902bca5706c772edef5d5e5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16013
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>
The new module replaces functionality in vbdev_crypto.
This module is bdev agnostic, so some inernal parts
were reworked.
io_channel: contains a qp of every configured DPDK PMD
crypto key: for mlx5_pci we register a key on each available
device since keys are bound to Protection Domain.
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: If1845cb87eadacbb921c593ba82207a97f2209a3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14859
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
This patch is just a copy of vbdev_crypto.c and the
corresponding UT file. It makes it easier to review
the next patch which adds accel operations
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: Ib88b45d573b011b1acb35da9bf4dab922d8fb183
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16182
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
* generic metadata support for raid modules
* raid is not created when metadata formats for base bdevs differ
Signed-off-by: Krzysztof Smolinski <krzysztof.smolinski@intel.com>
Change-Id: Ifaf9cfc4f2472c3820da1070deda758c5334edb2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13549
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>
This adds a log message indicating that an lvstore is being unloaded due
to its base device being hot removed.
Signed-off-by: Mike Gerdts <mgerdts@nvidia.com>
Change-Id: Ic80c19888edad4bb5ca613a23440aef01de8c6a2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14966
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Error counters for NVMe error was added in the generic bdev layer but
we want to know more detailed information for some use cases.
Add NVMe error counters per type and per code as module specific
statistics.
For status codes, the first idea was to have different named member
for each status code value. However, it was bad and too hard to test,
review, and maintain.
Instead, we have just two dimensional uint32_t arrays, and increment
one of these uint32_t values based on the status code type and status
code. Then, when dump the JSON, we use spdk_nvme_cpl_get_status_string()
and spdk_nvme_cpl_get_status_type_string().
This idea has one potential downside. This idea consumes 4 (types) *
256 (codes) * 4 (counter) = 4KB per NVMe bdev. We can make this smarter
if memory allocation is a problem. Hence we add an option
nvme_error_stat to enable this feature only if the user requests.
Additionally, the string returned by spdk_nvme_cpl_get_status_string()
or spdk_nvme_cpl_get_status_type_string() has uppercases, spaces, and
hyphens. These should not be included in JSON strings. Hence, convert
these via spdk_strcpy_replace().
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I07b07621e777bdf6556b95054abbbb65e5f9ea3e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15370
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Fix for the issue 2803.
Reporting an error when deleting xnvme bdev.
bdev_xnvme_destruct gets invoked from the fn_table->destruct prior to
the xnvme_bdev_unregister_cb while deleting the xnvme bdev.
Hence removed the duplicate invocation of bdev_xnvme_destruct in
the function xnvme_bdev_unregister_cb.
Additionally, fixed the hang issue when the bdev_xnvme_delete
gets called multiple times for a xnvme bdev.
Signed-off-by: Krishna Kanth Reddy <krish.reddy@samsung.com>
Change-Id: Ie36a84987ace20d324b7a139ca67fd60bf46e25b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16144
Reviewed-by: Ye Chen <yex.chen@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
* added raid1 module functions
* raid1 logical volume can be created using standard SPDK RPC
* strip size parameter not supported by raid1
Signed-off-by: Krzysztof Smolinski <krzysztof.smolinski@intel.com>
Change-Id: Id3ee1ba0ec28540ca8eb67b04c3ff655a16b1f19
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13444
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>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Attribute base_bdevs_max_degraded of raid_bdev_module struct is
replaced with more generic structure allowing implementation of
raid levels for which constraint is by number of operational
drives instead of maximum number of failed drives.
Signed-off-by: Krzysztof Smolinski <krzysztof.smolinski@intel.com>
Change-Id: Ie7079993d27d32118b865c3aabd92252a2807b94
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14411
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>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
All operations which affect the state of the raid bdev should be
performed on this thread.
Remove the thread pointer from struct raid_base_bdev_info because it is
no longer necessary.
Change-Id: I59678de7dff5c5388cb75449019ae765bdac1fbc
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14509
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
It will be used for allocating buffers from accel domain and
allocating bounce buffers to push/pull the data from memory domains for
modules that don't support memory domains.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Idbe4d2129d0aff87d9e517214e9f81e8470c5088
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15745
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>
To achieve the highest possible IO-rates and lowest latency, then CPU
cycles must be spent processing IO. This commit introduces three
different techniques dependendent on the 'io_mechanism' used.
For 'libaio', xNVMe is instructued via 'opts.poll_io' to not wait for
completions, thus xnvme_queue_poke() returns immmediatly, the user can
then call xnvme_queue_poke() as frequently as desired. This requires
xNVMe v0.5.0. Earlier versions will ignore 'opts.poll_io' for 'libaio'.
For 'io_uring', xNVMe is instructed via 'opts.poll_io' to enable
IORING_SETUP_IOPOLL.
For 'io_uring_cmd', xNVMe is instructued via 'opts.poll_sq' to enable
IORING_SETUP_SQPOLL, this sets up a kernel-side thread reaping
completions from user-space on the ring. Note that 'io_uring_cmd'
requires liburing >= 2.2.
This commit enables the above by default. The above can be disabled by
setting 'conserve_cpu' to true on the bdev-setup.
Signed-off-by: Simon A. F. Lund <simon.lund@samsung.com>
Change-Id: Id54f1e59733ce9ae3b174ad4562904d868d4ef4f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14678
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>
