That's what the library expects.
Fixes#2904.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I6d636f7effa2c9f22ff7a189ca7a569ae500eff4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16767
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
To be backwards compatible, we allow users to pass options with both the
underscores and hyphens, e.g. `bdev_get_bdevs --timeout-us 100` and
`bdev_get_bdevs --timeout_us 100` are equivalent. However, python's
argparse allows users to pass option values after equals sign and we would
also replace any underscores in those values (e.g. `bdev_get_bdevs
--name=bdev_null0` would become `bdev_get_bdevs --name=bdev-null0`).
This patch fixes that.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I82d3adb39167ff5e20451e8ab7de7bb50edb670e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16334
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>
This is done to calculate readings with better precision and fix
the case where calculation of total reading from given entity would
fail if it was < 1 (as bc drops the leading 0, leaving e.g. .42).
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: I68f2df89c340dba28d15c4aaac3e106c9f8057d4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16586
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The goal of a platform driver is to execute chained accel operations in
the most efficient way possible. A driver is aware of the hardware
available on a platform and can execute several operations as a single
one. For instance, if we want to do DMA and then encrypt the data, the
driver can do both at the same time, if the hardware is capable of doing
that.
Platform drivers aren't required to support all operations. If a given
operation cannot be executed, the driver should notify accel to continue
processing a sequence, via spdk_accel_sequence_continue(), and that
operation will processed by a module assigned to its opcode.
It is required however, that all platform drivers support memory
domains, including the "virtual" accel domain. A method for allocating
those buffers will be added in the following patches.
This patch only adds methods to register and select platorm drivers, but
doesn't change the way a sequnce is executed (i.e. it doesn't use the
driver to execute it).
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I97a0b07e264601ab3cf980735319fe8cea54d38e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16375
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: Ben Walker <benjamin.walker@intel.com>
Replace spaces with undescores for each sensor name
to avoid dealing with filenames with spaces later.
Change-Id: I2115cc14a15a53a7d92a7dae5cb6d1bfa7fb4402
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15352
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jaroslaw Chachulski <jaroslawx.chachulski@intel.com>
Reviewed-by: Michal Berger <michal.berger@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Allow adjusting number of CQ entries for SPDK
transport layer.
When testing with RDMA iWARP protocol it is
neccessary to adjust the number of CQ entries
manually as iWARP does not support CQ resize.
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: I03c1a3f20fa64a90995428e693c57b48b0a06bcb
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16509
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>
Do not overwrite extra_params when io_uring fio
engine is selected; append number of poll queues
to params list instead.
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: I5609e3ad4009df74bc2b02b5c5407548d1d69f3b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16507
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 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>
For each NIC reduce number of configured ADQ tc
entries. Use only these ports which are actually
associated with NIC's IP address instead of using
all port numbers in use by Target's subsystems.
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: I90934db594be0412b0fb7fb2b26684733df7711a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16379
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>
Add all subsystem ports to created traffic class
instead of just one hardcoded port number.
Change-Id: I702948958213eb920e56db4593f26f0ce122a8c0
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15596
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jaroslaw Chachulski <jaroslawx.chachulski@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Pawel Piatek <pawelx.piatek@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Move ADQ traffic classess configuration after
Target has been configured. ADQ TC configuration
will rely on information generated by configuring
the target (e.g. port numbers).
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: I5f5c438525d742ceab473c28afdb68d39ff019b8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15595
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Pawel Piatek <pawelx.piatek@intel.com>
Reviewed-by: Jaroslaw Chachulski <jaroslawx.chachulski@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Initial ADQ configuration in script was created based
on "Nov 2020 ADQ with SPDK Configuration Guide".
Update using latest June 2022 guide version.
- Channel inline flow director configured using
"devlink" for each TC separately instead of
using ethtool setting
- Disable channel packet inspect optimize priv flag
- Enable busy poll private flags
- Run NIC IRQ affinity script again after creating
TC's
- net.core.busy_poll and net.core.busy_read now both
set to 1
- Set acceptor_poll_rate when creating transport layer
Change-Id: I05b2d0aa2ddd5fc249889fb5e5d6118963367b36
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15584
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jaroslaw Chachulski <jaroslawx.chachulski@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 could export a backend device as ublk block device (/dev/ublkb*).
A rpc method is used to add ublk device and it should be done
after creating ublk target. Corresponding, ublk_del_dev is
used to delete the specified ublk device.
Signed-off-by: Yifan Bian <yifan.bian@intel.com>
Co-authored-by: Xiaodong Liu <xiaodong.liu@intel.com>
Change-Id: I3a4ba8d8dc5f5ad241511ccbc9d3336b582a6dc5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15976
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Add rpc methond for ublk target creation and destruction. Before to
add ublk device, need to initialize ublk target to create ublk
threads, corresponding an rpc methond to destroy ublk target is
also added. It will deinitialize ublk target and release all ublk
devices.
Signed-off-by: Yifan Bian <yifan.bian@intel.com>
Co-authored-by: Xiaodong Liu <xiaodong.liu@intel.com>
Change-Id: I5db0cf9cc68745440df999169aa1c61111010e02
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15962
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: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Xiaodong Liu <xiaodong.liu@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>
The configuration is generated based on existing host's NUMA
topology (as seen via sysfs) instead of a total number of cpus as
it was done before. New logic attempts to load balance VMs and
their cpus based on nvme drives' NUMA location. If there is no
enough cpus left under the target node, all remaining nodes are
checked. For the sake of the performance, cpus are not mixed
between different numa nodes.
Disk map is created by mapping VMs to existing nvme drives
based on their NUMA location. Extra VMs are assigned in bus
order of the nvme drives.
SPDK cpus are split by matching the VM-to-nvme NUMA ratio.
Static list can be defined as well to override this behavior.
https://trello.com/c/HSoRtQkO/401-deprecate-vhost-performance-python-helper-script
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: Ia63c6f9a472a685d252efd110eaba7b114a87d2c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12401
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: Karol Latecki <karol.latecki@intel.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>
Recent changes done to iobuf and accel framework
require us to adjust iobuf pool sizes when running
tests with high number of NVMe-oF subsystems.
Change-Id: I72ce6e71446bea0af44bdad6258e7d7f5d765656
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16288
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
This is meant to improve performance of the heaviest checks, like
the shellcheck one, where instead of running against the contents of
the entire repo simply go through files that are meant to be
committed.
This mode has to be requested through the environment via the
CHECK_FORMAT_ONLY_DIFF.
For now, get_diffed_dups() is hooked into least performant
checks (permissions, shfmt, shellcheck).
Also, the git grep command in the main check_permissions() is dropped
as the idea of piping its output to git ls-files was faulty - the git
ls-files does not read its arguments from the stdin.
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: I098dcbbe18c08c08a8216857c7cf2c80c4021d31
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16049
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.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>
This patch adds virtio_blk_get_transports matching the
virtio_blk_create_transport RPC. Allowing for querying
existing virtio_blk transports and displaying their options.
Signed-off-by: Krystyna Szybalska <krystyna.szybalska@gmail.com>
Change-Id: I0ec49c5f2ad11962feb5087dd376407ad125c349
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16303
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.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>
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>
Each fio job section will get unique CPU cores
assigned based on the number of numjobs value.
In case of high number of fio jobs or high numjobs
parameter value we might eventually run out of
CPU cores to assign. Allow regenerating list
of available CPU cores. This allows to run the
test, but as a result CPU cores might be shared
between fio threads.
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Change-Id: I69b1713e640d9343d68b26317f4caccdcec3cddd
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16240
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>
Allow user to specify the way IRQ alignment for
network interfaces used in test should be done.
Change-Id: Ib835d2ac2bc0c7b79474e617de32b96a483e436b
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15737
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Fio "numa_cpu_nodes" parameter (which tells fio
which NUMA node to use to pick cpus for the job)
seemed promising, but manually adjusting
"cpus_allowed" seems to have better results.
Change-Id: I113566ad0dd1d32fb5a1e989725b257e3ccff4c0
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14842
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>
This will enable NVMe mDNS discovery implementation
and testing in future patches.
Signed-off-by: Parameswaran Krishnamurthy <parameswaran.krishna@dell.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ic8de8e463b07b5b9d260781175d117766acdab9e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16254
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Boris Glimcher <Boris.Glimcher@emc.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This application has not been maintained for at least
two years, let's just remove it rather than updating
it. Original intent was to monitor iSCSI I/O
processed on each core, if we decide it's important
to still provide this kind of analysis for iSCSI it
would be better to incorporate it into spdk_top
instead most likely.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I4093ab1357ccc06c8a6770f7f87238b510bb20d4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16219
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@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 is done to make clear what data is included with the core dump.
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: I67f7da7f342354df4688147eaf56283b33ba2863
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15996
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>
As stated in the core(5) the RLIMIT_CORE is not enforced when kernel
is piping core to the collector, hence it will be written out even
when it's set to 0. Instead of playing nice and checking the validity
of RLIMIT_CORE, simply ignore it and apply our own limit (2GB).
This is done for convenience and to make sure that any changes to the
way how given distro applies limits (see fedora37) to the processes
doesn't affect our core collection.
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: Iab8757f548f2a4f0f4b27b4ce66b0a4a84ed2579
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15994
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.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
* 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>
Some Ceph builds, as seen under fedora37, have their default
osd_class_dir parameter set improperly to a relative path. As a
result, Ceph is not able to open and load .so libs that are part
of rados-classes. Example of an error seen in the ceph logs:
could not stat class lib64/rados-classes/libcls_rbd.so: (2) No such file or directory
To workaround it, always slap "/" at the beginning of the path.
Signed-off-by: Michal Berger <michal.berger@intel.com>
Change-Id: I08c2c94f7469748489ef4a9f0e65f3faccbecfb7
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/16064
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Kamil Godzwon <kamilx.godzwon@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@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>
