This is a preparation to inject data corruption at completion for
read I/O.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I839f454d643254f2b805f3d4c65282deee037d71
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15003
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 bdev*_with_md APIs now allow to pass NULL md
pointer, so calling this function without checking
for metadata simplifies code
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: Ie4137f7a6a7628a13d14c7c9a5e9aa1ceb99d322
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15091
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: Paul Luse <paul.e.luse@intel.com>
Fixes commit c3a5848 where support of memory
domains was added without usage of the ext API
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: I7b318f515d7421b8876d4717c0ef293084401bbc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15089
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: Paul Luse <paul.e.luse@intel.com>
Fixes commit c3a5848 where support of memory
domains was added without usage of the ext API
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: Ia0d7132f11c233e334965669ab0d237c24074745
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15088
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
The following patches will support data corruption.
For write I/O, data corruption will be injected before submission,
and for read I/O, data corruption will be injected after completion.
To do these cleanly, use switch-case and reorder to process error
injection at submission.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I3b830b4331cb4c7d0794a555957cdcc73902c14f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15026
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Community-CI: Mellanox Build Bot
If we use error bdev in general use cases, the upper layer may submit
I/O commands other than read, write, unmap, or flush.
However, before this patch, the upper layer could submit only read,
write, unmap, and flush.
To improve the usability of error bdev, pass thorugh I/Os other than
read, write, unmap, or flush.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ia642b13771f42505055f1372733825153085b805
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15027
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: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
This will make it easier to add more parameters for error injection.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ie5b22c31b5ba9d8c256d369213fa8fb4b985fa26
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15025
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: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
This is a small clean up.
Use custom JSON decoders for the io_type and error_type parameters
in the bdev_error_injection_error RPC.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I528fe4a31fac7eddb8ec33594b90e107d71693be
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15024
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: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
If during a channel creation, an error happens, due to incorrect parameters
e.g. wrong pool / container name, or some other internal DAOS errors (like
reaching CART context limit), bdev_daos_io_channel_create_cb() signals
about such errors, however, spdk_io_device_register() does not takes them into account.
The device creation succeeds, returning successful RPC response and leaving bdev
in the bdev lists but it's completely unusable and not amendable.
This patch tries to detect it early and return an RPC error on failure.
Signed-off-by: Denis Barakhtanov <denis.barahtanov@croit.io>
Change-Id: I04758e6243566b4e619a1420aa7c01f6041441a6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15168
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>
Community-CI: Mellanox Build Bot
For write, verify DIF/DIX before submission and for read, verify
DIF/DIX after successful completion.
As same as the NVMe bdev module and the NULL bdev module, DIF/DIX
verification is done based on the DIF type and DIF insert/strip is
not supported.
In near future, the bdev I/O APIs bring an I/O flag to the underlying
bdev and the malloc bdev module will be able to decide DIF/DIX
verification based on the I/O flag.
One important feature is to setup protection information when
creating a malloc disk. Otherwise, all initial reads will fail
if protection information is enabled.
For users, add some explanation about the dif_type parameter
into doc/jsonrpc.md.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I93757b77c03cade766c872e418bb46d44918bee2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14985
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
The malloc bdev module supports both of interleaved and separated
metadata in this patch.
Different from the NULL bdev module, opts->block_size is a data block
size and a block size is caculated internally as a sum of
opts->block_size and opts->md_size if opts->md_interleave is true, or
opts->block_size otherwise. This will be more intuitive. Additionally,
opts->md_size accepts only either of 0, 8, 16, 32, 64, or 128.
Protection information (T10 DIF/DIX) will be supported in the
following patches.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Icd9e92c8ea94e30139e416f8c533ab4cf473d2a8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14984
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Community-CI: Mellanox Build Bot
Define a options structure, malloc_bdev_opts, and use it directly for
the bdev_malloc_create RPC. To do this, bdev_malloc.h includes
bdev_module.h instead of bdev.h to have the definition of the struct
spdk_uuid, and the struct malloc_bdev_opts has a instance of struct
spdk_uuid. Clean up file inclusion together. Furthermore, use
spdk_uuid_copy() to copy uuid from the malloc_bdev_opts to the malloc
disk rather than the = operator, and remove a duplicated size check.
These are helpful to add more parameters for creation.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ief25f12586c21b1666180ce10cfc6256ede8eba9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14982
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
If we use a custom decoder for malloc disk's uuid for the
bdev_malloc_create RPC, the code is simplified. Furthermore,
when we add an options structure, we will be able to include
the options structure into struct rpc_construct_malloc directly.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ib36fa628569f973218f2cc5ce65a51181cd9fb71
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15125
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
spdk_nvme_probe_poll_async() can only return 0 or -EAGAIN.
But the code currently indicates that other values might be
possible - so change the code to remove that confusion.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8e7b2e1183f6650043dd751d610d434d626efa7e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15110
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change 'bdev_nvme_compare_trids' to name 'bdev_nvme_check_secondary_trid'
and 'bdev_nvme_compare_namespaces' to 'bdev_nvme_check_secondary_namespace'
which better explain the aim of these function.
RPC bdev_nvme_attach_controller only response "invalid parameter"
if the path is not sucessfully added due to not meeting the conditions
in bdev_nvme_compare_trids. Add more log.
Change-Id: If9ba6ec1d397d49689aa2ed6ab74fbfa96e16afa
Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14251
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>
Community-CI: Mellanox Build Bot
A new `oclass` parameter allow to specify DAOS DFS object class that is
responsible for data redundancy and protection.
Examples of the object classes could be found here: https://github.com/daos-stack/daos/blob/master/src/include/daos_obj_class.h
The default value is OC_SX for the max IOPS.
Signed-off-by: Denis Barakhtanov <denis.barahtanov@croit.io>
Change-Id: Ia48681832458c2266eb7c3bcae0df2055e59e309
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/15006
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>
Community-CI: Mellanox Build Bot
Support Aio bdev 'readonly' option in RPC call. The read-only flag
can be dumped from the bdev info. Any writes on a read-only aio bdev
will be fail.
Signed-off-by: Yuhua <yuhua@smartx.com>
Change-Id: I939f72479f8953a3678a8df3083ecce0f96844fb
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14955
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
In a use case, a custom sock module supports zero copy for read.
The custom sock module wants to keep the recv_buf_size to be sufficiently
large, for example 16MB. However, most upper layers overwrite the recv_buf_size
by a smaller value via spdk_sock_set_recvbuf() later. This is not desirable.
To fix the described issue, change the meaning of impl_opts->recv_buf_size
to be the minimum size, and spdk_sock_set_recvbuf() uses the maximum value
among the requested size, g_spdk_sock_impl_opts->recv_buf_size, and
MIN_SO_RCVBUF_SIZE.
We may have to change the code to initially create a socket. However,
for most cases, the upper layer calls spdk_sock_set_recvbuf() anyway.
Hence this fix will be minimal and enough.
For the use case, it is enough to change recv_buf_size of the posix sock
module. However, the custom sock module may support I/O uring in future.
Hence, change I/O uring sock module together.
Additionally, for consistency, change the meaning of impl_opts->send_buf_size
to be the minimum size, and spdk_sock_set_sendbuf() uses the maximum value
among the requested size, g_spdk_sock_impl_opts->send_buf_size, and
MIN_SO_SNDBUF_SIZE.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I051ba7cb50bc9dcad229e922198b04fe45335219
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14915
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Community-CI: Mellanox Build Bot
If the module stop handler is asynchronous we must wait until it
finishes before unregistering the io_device.
Change-Id: I149b716d9f4b0c1680b3e43b395fc9ec5b90d70c
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14717
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Implement support for full stripe writes without parity calculation.
The size and alignment of write IOs must be a multiple of full stripe
size. To reflect this, the raid bdev's write_unit_size is set
accordingly. We rely on the bdev layer to split larger IOs based on
that.
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I6940280ad870f3bd678fd19346b06ba4bdadd52e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7702
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Let the raid modules create their own IO channels by implementing the
get_io_channel callback.
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Id4f6c90721474edd70a6e987c67f8f774737da27
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7700
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Move device cleanup to spdk_io_device_unregister() callback. This fixes
a case when the device would be freed before its last io channel was
closed, leading to use after free condition.
Repurpose raid_bdev_free() to actually free the bdev.
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Ib667b4d5ac1b34a0f2dda69f6b0775d9363dbfee
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11398
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Depend on bdev layer to send down chunk sized IOs, based on
optimal_io_boundary.
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: Iec45f4917117d35c3a9e807940e49091dfcba870
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7699
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Here we use vfu_tgt library and emulate a virtio-scsi device
as the next use case.
Compared with vhost-user-scsi, the packed ring is supported with this
patch.
Example usage method:
1. scripts/rpc.py bdev_malloc_create -b malloc0 $((512)) 512
2. scripts/rpc.py vfu_virtio_create_scsi_endpoint vfu.0 --cpumask 0x1 --num-io-queues=4 \
--qsize=128 --packed-ring
3. scripts/rpc.py vfu_virtio_scsi_add_target vfu.0 --scsi-target-num=0 --bdev-name malloc0
4. Start QEMU with '-device vfio-user-pci,socket=/spdk/vfu.0'
Change-Id: I8f35d1d21aaec34844d6ddb59dc997a64f141179
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12673
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Here we use vfu-tgt library and emulate a virtio-blk device
as the first use case of vfu-tgt library.
Usage example with QEMU:
1. build/bin/spdk_tgt
2. scripts/rpc.py bdev_malloc_create -b malloc0 $((512)) 512
3. scripts/rpc.py vfu_virtio_create_blk_endpoint vfu.0 --bdev-name malloc0 \
--cpumask=0x1 --num-queues=2 \
--qsize=256 --packed-ring
4. Start QEMU with '-device vfio-user-pci,socket=/spdk/vfu.0'
Change-Id: I45e45360c669584583b0b8a3f83250ab6c48efec
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12315
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Mellanox Build Bot
Previously SPDK use libvfio-user library to provide emulated NVMe
devices to VM, but it's limited to NVMe device type only. Here we
add SPDK vfu_target library abstraction based on libvfio-user which
supports more PCI device types.
We will add virtio-blk and virtio-scsi devices emulation based on
vfu_tgt library in following patches, actually this library can
support NVMe emulation too, due to the fact that the NVMe emulation
is already exist, so we will keep the NVMe emulation which based on
libvfio-user directly as it is.
Change-Id: Ib0ead6c6118fa62308355fe432003dd928a2fae9
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12597
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Fix for the issue 2702.
spdk_bdev plugin crashes while handling xnvme devices.
xnvme_queue_term gets invoked after the bdev_xnvme_free executes and
frees the xnvme structures. xnvme_queue_term references the xnvme->dev
structure, after it is freed, resulting in a segmentation fault.
Implemented a bdev_xnvme_destruct_cb, that frees the xnvme structures
after the xnvme_queue_term invokes and the device is fully unregistered.
Signed-off-by: Krishna Kanth Reddy <krish.reddy@samsung.com>
Change-Id: I9338c84baf4b61ec2e0d324e67bfefcb96485156
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14680
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: Konrad Sztyber <konrad.sztyber@intel.com>
Identify and properly handle conventional zones (in smr drives) by using
zone type and WP state. Bdevs supporting zoned devices(like uring, nvme and
vbdev_zone_block) now update the zone type information. As a result, the
fio plugin now uses this info instead of hard coding the zone type.
Also adds new WP state(ZONE_STATE_NOT_WP) for handling zones w/o WP.
Signed-off-by: Indraneel M <Indraneel.Mukherjee@wdc.com>
Change-Id: If031e0742d68c55c35e95ddc33d478939bbd52fe
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14572
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
Fixes#2708 for io_uring_cmd.
This is a minimal approach to enabling polling for bdev_xnvme. Ideally,
more would be done, however, there are several blockers to remove when
doing so. Thus, this commit only enables polling on
io_mechanism=io_uring_cmd.
Signed-off-by: Simon A. F. Lund <simon.lund@samsung.com>
Change-Id: Ifa604b52bb2b924fab4b559fae06f26a3574db42
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14679
Reviewed-by: Ben Walker <benjamin.walker@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>
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>
A new parameter io_drain_timeout has been added to spdk_bdev
structure. If this value is unset, the bdev reset behavior
does not change.
The io_drain_timeout controls how long a bdev reset must wait for IO
to complete prior to issuing a reset to the underlying device.
If there is no outstanding IO at the end of that period, the reset
is skipped.
Change-Id: I585af427064ce234a4f60afc3d69bc9fc3252432
Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14501
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
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>
Community-CI: Mellanox Build Bot
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>
After a controller was hot-removed, if a reset sequence started to
the controller, spdk_nvme_ctrlr_disconnect() failed and caused core
dump in debug mode.
When implemented, how to cause the failure and how to process the
failure were not clear. Hence assert was added to detect the
failure.
We know how we cause the failure now. Let's handle the failure
appropriately.
If spdk_nvme_ctrlr_disconnect() fails, we are on the nvme_ctrlr->thread.
Hence call bdev_nvme_reset_complete() with failure immediately.
Even if spdk_nvme_ctrlr_disconnect() completes synchronously, the
completion callback is executed asynchronously when polling an adminq.
Hence set the completion callback only if spdk_nvme_ctrlr_disconnect()
succeeds.
Fixes issue #2632
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I11f61853aba9eca2515592f964a291e59def7247
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13892
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: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
By a recent improvement, failure of I/O qpair creation is ignored
if the nvme_ctrlr is being reset or scheduled to reconnect.
However, failure of I/O qpair creation is not ignored if a new I/O
channel is allocated. It is normal to allocate a new I/O channel
when a nvme_ctrlr is being reset or scheduled to reconnect.
Fix this bug by relaxing the condition to ignore the result of
bdev_nvme_create_qpair() to if reconnect_delay_sec is non-zero and
bdev_retry_count is non-zero.
If reconnect_delay_sec is non-zero, reconnect will be tried sooner
or later, and if bdev_retry_count is non-zero, submitted IOs will be
queued until it succeeds.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Icf26e1ea65d292f9b8d24966abe25907d2cc33ec
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14446
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Add gathering of some performance counters and RPC for printing them.
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Signed-off-by: Kozlowski Mateusz <mateusz.kozlowski@intel.com>
Change-Id: I2e77d37fb66459240ff2e241f2b1f77c60f4eef4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13390
Community-CI: Mellanox Build Bot
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>
config_json callback is used to preserve all
bdevs that were created during application runtime.
xnvme bdev module was missing this callback.
While here, io_mechanism is now saved in the bdev_xnvme
structure for reference in the config_json.
Haven't seen an option to pull this from xnvme itself.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I1a88ad2bb761f589d214fec8f0690c38572824d6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14116
Reviewed-by: Michal Berger <michal.berger@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Ifba581c92269c675b03b67586b1fea0b096f9e95
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14511
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
If res = 0, do not pass this value directly to bdev io completion function,
otherwise it will be treated as a successful completion.
Fix issue: 2679
Signed-off-by: jun.ran <ranjunsh@163.com>
Change-Id: Ice525de1bb5b0ada9ac30d3b59e5c731419efe2f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14364
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>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Two functions have been added to implement bdev io type
SEEK_DATA and SEEK_HOLE. Blob functions to find next
[un]allocated io_unit are used
Signed-off-by: Damiano Cipriani <damiano.cipriani@suse.com>
Change-Id: Ic3be3c0c86bd3010a23ba2681f0f00c62abcaaba
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14362
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>
This will allow to have context per connection.
And free context when connection closes.
Fixes#2689
Change-Id: Ic4e9adfa3f1bd8574b9ccf75ff42c4f3bd442b26
Signed-off-by: Boris Glimcher <Boris.Glimcher@emc.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14443
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Adding `psk` field to `spdk_nvme_ctrlr_opts`
Adding `psk` parameter to `bdev_nvme_attach_controller` RPC
Change-Id: Ie6f0d8b04ce472e6153934e985c026acded6cdfc
Signed-off-by: Boris Glimcher <Boris.Glimcher@emc.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14046
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
the calculation (offset_blocks + num_blocks - 1) didn't check if num_blocks is 0
which it is in case of flush.
in flush case, offset_blocks was also 0, so we got (-1) and we got big unsigned number.
just replace it with (offset_blocks + num_blocks - (num_blocks > 0)) to solve the issue.
NOTE this is only fixing the wrong math, there might be more issues that outside the scope of this commit
for example, if flush(x, y) called, no bdev implementation really use those values, and all bdevs just flush the whole disk
also, a convention is that fluch(0, 0) should flush it all (but like I said before, all bdevs flush the whole disk anyway)
Change-Id: I7e991653bc3050349dc155365b2c37ecc2d6b24c
Signed-off-by: Amir Haroush <amir.haroush@huawei.com>
Signed-off-by: Shai Fultheim <shai.fultheim@huawei.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13579
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Trim is now also available as a management operation via RPC.
Signed-off-by: Kozlowski Mateusz <mateusz.kozlowski@intel.com>
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I05b778a611e9809a14bfed50b01986bb4649a35c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13379
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>
Adds ability to send trim commands to FTL - only 4MiB aligned requests (both
for offset and length of request) will be processed. During a trim
operation an L2P page (containing 1024 4B entries, 1 per user LBA; which
is where the 4MiB alignment comes from) will be marked as unmapped.
After this point any L2P access to that page will actually set the
entries themselves as FTL_ADDR_INVALID. This is done to make the trim as
fast as possible, since for large requests it's probable that most of
the L2P pages aren't actually in DRAM.
Signed-off-by: Kozlowski Mateusz <mateusz.kozlowski@intel.com>
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I4a04ee9498a2a6939af31b06f2e45d2b7cccbf19
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13378
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>
the current timeout parameter of the interface bdev_iscsi_set_opts is
duplicated with the timeout parameter of the JSONRPCClient parameter,
which may cause the iscsi timeout and JSONRPCClient parameters to
overwrite each other.
Signed-off-by: gongwei <gongwei833x@gmail.com>
Change-Id: I96604a7e1a495ac2e99518812297230680df42fd
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14306
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
These checked parameters are necessary themselves even for single path
configuration.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ie1eb2f51eeec1dbc634c6bae462a41d4c209d6ac
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12052
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: Dong Yi <yidong0635@126.com>
Community-CI: Mellanox Build Bot
Clean up the code by using a custom decoder. Use multipath mode to
follow doc/nvme_multipath.doc.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ie1f4109dae3a2929dcf933939a9c1b67bece0caf
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12051
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>
Community-CI: Mellanox Build Bot
Previously, reset just set a long timer to wait until all inflight
I/Os complete.
As already noted as a TODO item, check if any I/O is still inflight
before completing the reset by using a new API
spdk_bdev_get_current_qd().
The RBD bdev module can count outstanding I/Os itself but is not
efficient.
Signed-off-by: liu-darong <liu.darong@xsky.com>
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Iecaf90b06cae8e21198ec3822b978b54f5404d2b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13945
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: Dong Yi <yidong0635@126.com>
Reviewed-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
SSL_CTX isn't created in accept(), but when a socket on which accept()
is called is created, so it shouldn't be freed when accept() fails, as
this makes the socket unusable (any subsequent operations using SSL_CTX
would be using freed memory).
This caused the segfaults reported in issue #2681, where the second
connection would crash the application.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I1a01a748c5a34ce3dd0fd3c557b860c0ff314b85
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14355
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@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
Bumped up the priority of the posix and uring sock implementations to
make sure they are selected before SSL, when no impl is explicitly
specified.
Fixes#2681
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Ic8e1e2e13f7bce7ccd746f66087e348677df28d9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14354
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>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
hexlify and unhexlify utils from vbdev_crypto.h have been moved so that
they could be included and reused outside of vbdev_crypto module.
Signed-off-by: Blachut, Bartosz <bartosz.blachut@intel.com>
Change-Id: Ia074250176907f4803b84024239ecd4e9d8a5fc1
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14191
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
`v2c` helper function returns -1 on error, hovewer its return type was
char - which may cause an overflow situation on architectures where char
is interpreted as unsigned char, which was reported by the CI.
The return type has been changed to signed char.
Signed-off-by: Blachut, Bartosz <bartosz.blachut@intel.com>
Change-Id: I84f5784b2de7d681f78c69b5f3646e851e8dee88
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14273
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@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>
spdk_accel_module_finish
Also move it into the internal header that defines the interface used by
modules.
Change-Id: I3aeb41e643f27a69556099cb8d166f64c9e5d67f
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13917
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Writing to unallocated cluster triggers copy-on-write sequence. If
this cluster is backed by zeroes device we can skip the copy part. For
a simple thin provisioned volume copy this shortcut is already
implemented because `blob->parent_id == SPDK_BLOBID_INVALID`. But this
will not work for thin provisioned volumes created from snapshot. In
this case we need to traverse the whole stack of underlying
`spdk_bs_dev` devices for specific cluster to check if it is zeroes
backed.
This patch adds `is_zeroes` operation to `spdk_bs_dev`. For zeroes
device it always returns 'true', for real bdev (`blob_bs_dev`) always
returns false, for another layer of `blob_bs_dev` does lba conversion
and forwards to backing device.
In blobstore's cluster copy flow we check if cluster is backed by
zeroes device and skip copy part if it is.
Signed-off-by: Evgeniy Kochetov <evgeniik@nvidia.com>
Change-Id: I640773ac78f8f466b96e96a34c3a6c3c91f87dab
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13446
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
L2P cache allows for partial storing of L2P in memory, paging in and out
as necessary, lowering the total memory consumption.
Signed-off-by: Kozlowski Mateusz <mateusz.kozlowski@intel.com>
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Change-Id: I727fec9d2f0ade4ca73e872d62a2ec10cfdb0a88
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13353
Community-CI: Mellanox Build Bot
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>
Added a new RPC, vmd_rescan, that forces the VMD driver to do a rescan
of all devices behind the VMD. A device that was previously removed via
spdk_vmd_remove_device() will be found again during vmd_rescan.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Ide87eb44c1d6d524234820dc07c78ba5b8bcd3ad
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13958
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tom Nabarro <tom.nabarro@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Added new RPC, vmd_remove_device, that allows users to remove a PCI
device managed by the VMD library simulating a hot-remove.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Ifb84818ce8d147d1d586b52590527e85fe9c10de
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13957
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>
Reviewed-by: Tom Nabarro <tom.nabarro@intel.com>
The new name is consistent with the naming scheme of
<subsystem>_<action> that all of our other RPCs use.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I2cae7af5715add8eba26501cd192a6ac4884ec69
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13952
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Tom Nabarro <tom.nabarro@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This makes sure that if the app is killed before the subsystems have
been initialized (i.e. before framework_start_init is called), we don't
leak resources. Before this change, we initialized the VMD library and
registered the hotplug poller from the context of the RPC and we only
freed it in subsystem's fini(). However, if subsystems were never
initialized, we never freed them.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I56b746c46b94135ef56a478c5f80194ebe51a942
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13951
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: Tom Nabarro <tom.nabarro@intel.com>
bdev_nvme_create_bdev_channel_cb() did not initialized the multipath
policy of the newly created channel. 0 was active-passive and hence
multipath policy was always initialized to active-passive.
Fix the bug and add unit tests for verification.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I6e44108740da4b9ff72311ae4b5500558c65c5c3
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14225
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Admin passthrough supported retry and failover as same as I/O by
using the bdev_retry_count. However, doing retry or failover for
admin passthrough may have unexpected side effects and its value
is not clear. The safest way is to limit retry and failover for I/O.
If we need to support retry and failover for admin passthrough,
restore the code and add a new option bdev_admin_retry_count.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I680513a40a80041f6ea6f546c74c672f2a81812d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14227
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Abort is used usually for error cases. When abort is done, controller
may not be available. At completion, controller availability was checked
prior to aborted by request. Hence if abort is done when controller is
not available, the aborted request is retried.
Fix the case in this patch.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I3e7b356797dd50faed0e5113f6f7a47fea26d9cc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14098
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Adds API for fast shutdown - the ability for FTL to skip most
of the metadata persists made during clean shutdown, and relying
on their representation in shared memory instead. This allows for
faster update of SPDK (or just FTL, assuming no metadata changes),
with downtime reduction from 2-5 seconds to 500-1000 ms (for
14TiB+800GiB base and cache drives).
Signed-off-by: Artur Paszkiewicz <artur.paszkiewicz@intel.com>
Signed-off-by: Kozlowski Mateusz <mateusz.kozlowski@intel.com>
Change-Id: I5999d31698a81512db8d5893eabee7b505c80d06
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13348
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>
Enables the use of uring bdev with ZNS devices.
Uses BLKXXXZONE ioctls for implementing the zone operations.
Signed-off-by: Indraneel M <Indraneel.Mukherjee@wdc.com>
Change-Id: I440e316138182e25d89eb7224932e19bef9a005f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13550
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>
Here no need to define a variable only return.
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Change-Id: I6babb8ef94a9b111d5522f1e782cbd095c7da83a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14207
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: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: wanghailiang <hailiangx.e.wang@intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
If we use dd or bdevperf to run the xnvme bdev.
the destruct function of xnvme misses to free
dev while destructing bdev_xnvme.
xnvme_dev_close does free dev, and we can put it
in bdev_xnvme_free.
Meanwhile fixing cleanup for delete_xnvme_bdev.
This rpc for delete_xnvme_bdev doesn't really cleanup
to remove the bdev from the list and free the names.
Fixes issue: #2654
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Change-Id: I1c493cb8130b012d891ba8ee90cd0bfb127207d4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14177
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Found while debugging issue #2596, unfortunately this
is not the root cause of that issue.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I27501e283ce7c9bf7a431e8b48842c83f80792c8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14165
Community-CI: Mellanox Build Bot
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: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
This commmit introduces a new bdev type backed up by DAOS DFS.
Design wise this bdev is a file named as the bdev itself in the DAOS POSIX
container that uses daos event queue per io channel.
Having an event queue per io channel is showing the best IO throughput.
The implementation uses the independent pool and container connections per
device's channel for the best IO throughput.
The semantic of usage is the same as any other bdev type.
To build SPDK with daos support, daos-devel package has to be installed.
The current supported DAOS version is v2.X, please see the installatoin and
setup guide here: https://docs.daos.io/v2.0/
$ ./configure --with-daos
To run it, the target machine should have daos_agent up and running, as
well as the pool and POSIX container ready to use, please see the
detailed requirements here: https://docs.daos.io/v2.0/admin/hardware/.
To export bdev over tcp:
$ ./nvmf_tgt &
$ ./scripts/rpc.py nvmf_create_transport -t TCP -u 2097152 -i 2097152
$ ./scripts/rpc.py bdev_daos_create daosdev0 <pool-label> <cont-label>
1048576 4096
$ ./scripts/rpc.py nvmf_create_subsystem nqn.2016-06.io.spdk1:cnode1 -a -s
SPDK00000000000001 -d SPDK_Virtual_Controller_1
$ ./scripts/rpc.py nvmf_subsystem_add_ns nqn.2016-06.io.spdk1:cnode1
daosdev0
$ ./scripts/rpc.py nvmf_subsystem_add_listener nqn.2016-06.io.spdk1:cnode1
-t tcp -a <IP> -s 4420
On the initiator side, make sure that `nvme-tcp` module is loaded then
connect drives, for instance:
$ nvme connect-all -t tcp -a 172.31.91.61 -s 4420
$ nvme list
Signed-off-by: Denis Barakhtanov <denis.barahtanov@croit.io>
Change-Id: I51945465122e0fb96de4326db742169419966806
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12260
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>
This allows mapping an nvme_request back to the
nvme_bdev_io.
This requires bumping up the max number of arguments per
tracepoint. 5 was previously chosen as max since it
exactly fit in 64 bytes (1 cacheline) when all
arguments were stored as uint64_t, but now that we
support uint32_t arguments we can afford extra
arguments when some of them are uint32_t. I've
bumped it to 8 so we can avoid having to touch
this value multiple times if we find some cases
where we need 7 or 8 args.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ie2ef5e59d10549860b47542e68c1c34efa63047f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13995
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
This will allow us to map spdk_bdev_io events
to nvme_request events coming in a future patch.
Since we pass the nvme_bdev_io to the nvme driver
(not the spdk_bdev_io), we need to add tracepoints
for the nvme_bdev_io so that spdk_trace can
do the spdk_bdev_io->nvme_bdev_io->nvme_request
mapping.
An alternative would have been to pass the spdk_bdev_io
as the cb_arg to the nvme driver, but that change
seemed to invasive, and I think we will find other
uses for the nvme_bdev_io events anyways.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Id7519e689b01875093359f41a1ca2af912061a8b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13994
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
This is just a simple wrapper for now around the
calls to spdk_bdev_io_complete and its
nvme status variant. Upcoming patch will
add an spdk_trace_record to this function as well.
This avoids having to litter spdk_trace_record calls
in too many places.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Id2fb3aeb8b070ad6e09c1dfb9a30a61666a35688
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13993
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Community-CI: Mellanox Build Bot
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>
These hold a pointer to the channel which eliminates the need to look it
back up in the completion path.
Change-Id: Ie4fc98d92d6434262e64b9483ef8b3b0591d764a
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13914
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>
This expects the full size of the task for each module. This only worked
because the software module returned the right size.
Change-Id: I481cfad8b4bb9c3748301bdacd90e7f44fd2d878
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13913
Community-CI: Mellanox Build Bot
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>
These are 1:1 - they do not need to be separate objects.
Change-Id: I74ab52863f911d9be59ce98e1525302b5bd40846
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13910
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: Aleksey Marchuk <alexeymar@nvidia.com>
This change fixes the lower performance issue of the
xNVMe BDEV for libaio and io_uring backends. There is no
drop in the performance for the io_uring passthrough backend.
Signed-off-by: Krishna Kanth Reddy <krish.reddy@samsung.com>
Change-Id: I21de1b49a534cfc642d1873ef623271063da6af8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/14015
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Note, this change only sets defaults for the ID/KEY,
more specific use cases like NVMe/TCP may set the ID and KEY on a per connection basis.
Also simplify PSK identity string, that isn't NVMe focused.
NVMe libraries using this will need to construct more complicated
identity strings and pass them to the sock layer.
Example:
rpc.py sock_impl_set_options -i ssl --psk-key 4321DEADBEEF1234
rpc.py sock_impl_set_options -i ssl --psk-identity psk.spdk.io
./build/examples/perf --psk-key 4321DEADBEEF1234 --psk-identity psk.spdk.io
./build/examples/hello_sock --psk-key 4321DEADBEEF1234 --psk-identity psk.spdk.io
Change-Id: I1cb5b0b706bdeafbccbc71f8320bc8e2961cbb55
Signed-off-by: Boris Glimcher <Boris.Glimcher@emc.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13759
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
If a nvme_ctrlr is unregistered while I/O path caches are clearing, the
unregistration would fail. This race was not considered for a case that
a nvme_ctrlr is unregsitered when adminq poller started I/O path cache
clearing.
As a bug fix, control ANA log page updating and I/O path cache clearing
separately by adding a new flag io_path_cache_clearing.
Fixes issue #2617
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Id58684caf9b2a10fa68bdb717288ff2bd799c3f7
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13924
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: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Instead of passing each parameter to create a module, just have the user
make one and pass it in. This makes it easier to change the module
definition later.
Change-Id: I3a29f59432a6f0773129d7b210fbc011175b2252
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13909
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Parameter `num_queues` for virtio_scsi PCI device means
maximum number of queues, it SHOULD include the `eventq`
and `controlq`, while for `vhost_user` RPC call, it means
the number of IO queues, so here we use it as `max_queues`
in lib/virtio and add the fixed number queues for `vhost_user`
SCSI device.
Also fix `vhost_fuzz` to get `num_queues` earlier than
negotiate the feature bits.
Change-Id: I41b3da5e4b4dc37127befd414226ea6eafcd9ad0
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13791
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>
VHOST_USER_F_PROTOCOL_FEATURES is used for `vhost_user` transport,
so unmask it for PCI devices.
Change-Id: If84d6c0ee7558886f14647dad07e41530e306206
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13790
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>
While running into this function, even the subsystem can't be
destroyed due to error subsystem state, it's better to continue
the execution.
Continue to fix#2590, QEMU is stuck for the failure case, and
nvmf target should process such error because it may support other
normal subsystems at the same time.
Change-Id: Ib05e24996378b52070d2b760519f476f9b2d7e76
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13839
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Sometimes VM may get a kernel panic when starting, and SPDK CI will kill
`nvmf_tgt` after 60 seconds, and for this exception, SPDK will raise an
assertion when destroying the subsystem, while here, we remove this
assertion and print the error information.
CI will still mark this case as a failed case, then we can use this error
information to understand error subsystem state in vfio-user.
Fix issue #2590.
Change-Id: I20b16f9e96a566730eca2dd9ea165645bd9160bd
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13773
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: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Failed rpc response will be sent when rescan successfully.
Signed-off-by: Chuanwei Ji <chuanwei.ji@jaguarmicro.com>
Change-Id: I99a2491ec76b63cb01fb384e621b41b10ee0ed83
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13711
Community-CI: Mellanox Build Bot
Reviewed-by: Qingmin Liu <qingmin.liu@jaguarmicro.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Both PCIE and VFIO-USER can use the same APIs to get IO queue
pair statistic data, so merge them here.
Change-Id: Iadf9ead2bd5abaf11d2ef5d1884acb67369f85bb
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13538
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: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Some of the options in sock_impl_opts could be different for different
sockets (even if they're using the same impl). However, outside of a
few selected options (recv_buf_size, send_buf_size), there was no
interface to change them.
This change will allow users to change impl_opts on a per-socket basis
when creating a socket. Sockets created through accept() inherit
impl_opts from the listening socket.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I7628ae19def25cef6ffa62aa54bd34e446632579
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13661
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>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
It'll make it possible to change some of the impl_opts options on a
per-socket basis, as well as make it easier to use fields common to all
implementations in the generic layer.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Id3b5e0a0b302fdecc2387d07fb87b75b487dc5c5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13659
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>
This RPC prints only cntlid, to identify a controller
it is needed to issue bdev_get_bdevs and find more info
using cntlid. Printing the controller's trid helps to
identify the controller faster.
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com>
Change-Id: I97325b822528ef9e71afbe2ff1c30b3bce2ae203
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13655
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
This implementation of xNVMe BDEV module supports the char-device / ioctl-over-uring,
along with the "regular" io_uring, libaio, POSIX aio, emulated aio (via threadpools) etc.
Code changes done :
a. Addition of xNVMe submodule to SPDK
b. Modification of RPC scripts to Create / Delete xNVMe BDEVs
c. Implementation of xNVMe BDEV module
Signed-off-by: Krishna Kanth Reddy <krish.reddy@samsung.com>
Change-Id: If814ca1c784124df429d283015a6570068b44f87
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11161
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Both get_opts and set_opts use very similar macros to achieve almost the
same thing, so it makes sense to extract it to a separate function.
Additionally, it'll be also useful in subsequent patches introducing
per-sock impl_opts, as there will be more places when we want to copy
impl_opts.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I8ab27298d62ea0118463ee945c708acd91aa5104
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13658
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: Aleksey Marchuk <alexeymar@nvidia.com>
nvme_ctrlr_init_ana_log_page() had used cdata->mnan as active ns count
to allocate a buffer and read a ANA log page into the buffer.
However, cdata->mnan was larger than the real active ns count and caused
an issue when the corresponding NVMe-oF target set the bit 18 of the SGL
support field in the Identify Controller Data structure.
We still need to use cdata->mnan to allocate the buffer because
number of namespaces may be increased dynamically after initialization.
Hence, rename nvme_ctrlr::ana_log_page_size to
nvme_ctrlr::max_ana_log_page_size and calculate and use the active ns
count to read the ANA log page. Check if the current ana_log_page_size
is not larger than nvme_ctrlr->max_ana_log_page_size.
Fixes issue #2584
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ieb10b9c793c4f48ffd88d517c0e9a55184b7d935
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13653
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Other parts have changed these since readv and writev
support ext_opts.
And change corresponding unittest.
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Change-Id: I79260a7e6110aa46df2016e579f1da5c241c9844
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13620
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 <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Instead, we pass MSG_DONTWAIT flag to all recvmsg()/sendmsg() calls.
That way, the IOs remain non-blocking, but the socket is marked as
blocking allowing us to pass flags like MSG_WAITALL, which only make
sense if a socket is in blocking mode.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Ic52162e84aa14efaf6ad0fb3343d289822758e81
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12592
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
It'll make it possible to reuse this code for asynchronous read
requests.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I56dab62587884e2e37fad11b5f0d12df92e175ea
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12590
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
This function processes and completes asynchronous write requests, so it
makes sense to rename it. This is done in preparation for handling
asychronous read requests.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I3f36631dc24a3170204aaaba56f4968be0672fe5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12172
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This task is used to receive the socket's error queue to check for
completed zero-copy write requests. The rename is done in preparation
for adding a read task that will actually receive the data from the
socket.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I61bf45e210bb09bd89f3161a75478b41bd8eb070
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12171
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This patch defines a new function, spdk_sock_readv_async(), which allows
the user to send a readv request and receive a callback once the
supplied buffer is filled with data from the socket. It works simiarly
to asynchronous writes, but there can only be a single outstanding read
request at a time.
For now, the interface isn't implemented and any calls will return
-ENOTSUP. Subsequent patches will add support for it in the uring
module and as well as emulation in the posix module.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I924e2cdade49ffa18be6390109dc7e65c2728087
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12170
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Treat it as zero if the user doesn't provide it. This will make it
consistent with other RPCs and the behavior of that command in
scripts/rpc.py.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Ic5505f853bc203fb1144ba3f1f44c736563a3677
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13529
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
The bdev_lvol_grow_lvstore will grow the lvstore size if the undering
bdev size is increased. It invokes spdk_bs_grow internally. The
spdk_bs_grow will extend the used_clusters bitmap. If there is no
enough space resereved for the used_clusters bitmap, the api will
fail. The reserved space was calculated according to the num_md_pages
at blobstore creating time.
Signed-off-by: Peng Yu <yupeng0921@gmail.com>
Change-Id: If6e8c0794dbe4eaa7042acf5031de58138ce7bca
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9730
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>
Reserve space for used_cluster bitmap. The reserved space is calculated
according to the num_md_pages. The reserved space would be used when
the blobstore is extended in the future.
Add the num_md_pages_per_cluster_ratio parameter to the
bdev_lvol_create_lvstore API. Then calculate the num_md_pages
according to the num_md_pages_per_cluster_ratio and bdev total size, then
pass the num_md_pages to the blobstore.
Signed-off-by: Peng Yu <yupeng0921@gmail.com>
Change-Id: I61a28a3c931227e0fd3e1ef6b145fc18a3657751
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9517
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>
In SPDK, declarations have the return type on the same line. Definitions
have the return type on a separate line. Astyle has an option for
enforcing this. Unfortunately, it seems to have two bugs:
1) It doesn't work correctly at all on C++ files.
2) It often fails on functions that return enums, or long type names
Deal with 1) by adjusting the check_format.sh script to only tell astyle
to fix return type line breaks for C files and not C++. Deal with 2) by
adding a few typedefs to work around the problem.
Change-Id: Idf28281466cab8411ce252d5f02ab384166790c6
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13437
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Adding more unit tests using standard openssl
The unfortunate small sleep is needed due to issue:
https://www.mail-archive.com/openssl-users@openssl.org/msg02937.html
Change-Id: I6f55453f12371bec6a402ba4c1d20e21aed73cf4
Signed-off-by: Boris Glimcher <Boris.Glimcher@emc.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12625
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
Added new `ssl` based socket implementation.
For now we are using hard-coded PSK and only support TLS 1.3
One can use it via sock_set_default_impl RPCs
Nvme/TCP published secure channel specification (TP 8011)
Which is based on TLS 1.3 and PSK.
So this is a primary but not the oly use case.
Before any SSL connection can be established
we need to create SSL context.
The context should be client/server aware.
Similar to regular sockets, to establish connection
server must call SSL_accept and client must call SSL_connect.
For now I'm using PSK and not certificates since
we aim this for NVMe/TCP TP-8011 which supports only PSK.
Adding certificates later on will be very easy.
The complication with SSL state machine during accep and connect
comes with returned SSL_ERROR_WANT_READ or SSL_ERROR_WANT_WRITE.
According to documentation, call have to be repeated in this case.
Using openssl here for TLS from user space.
openssl also has support for kTLS.
Will be part of the next changes.
openssl doesn't have implemetation for iovec
only basic SSL_read and SSL_write.
So adding here SSL_readv and SSL_writev wrappers.
Tested using:
./build/examples/hello_sock -N ssl -H 127.0.0.1 -P 12345
./build/examples/hello_sock -N ssl -H 127.0.0.1 -P 12345 -S
Also tested using:
nvmf_tgt + sock_set_default_impl + perf
Signed-off-by: Boris Glimcher <Boris.Glimcher@emc.com>
Change-Id: Ie730077c5c581b7e112c18f5f9e1b683015e7b4b
Signed-off-by: Boris Glimcher <Boris.Glimcher@emc.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12327
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>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
reactor_run() decides whether to start gather_metrics
based on non-zero scheduler period.
The default of 1 sec was set during initialization,
in scheduler_subsystem_init().
This resulted in unessecary operations each second,
even if only 'static' scheduler is used.
This patch moves setting default scheduling period to
respective schedulers.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I953aee271a959b6314c8e83434c922dba9638de4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9492
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Calculation of the ANA log page size should use the
identify ctrl MNAN field
(maximum number of allowed namespaces)
not the NN (maximum valid nsid value).
An ANA-enabled controller must have a non-zero MNAN value,
see NVMe Base Specification, Figure 251,
therefore nvme_ctrlr_init_ana_log_page() may safely use MNAN.
Since NN might be much higher than MNAN,
ANA log size based on NN may results in a very large
log page and cause a failure to get ANA log,
e.g. if it is larger than the controller's MDTS.
Fix: replace cdata->nn with cdata->mnan
in nvme_ctrlr_init_ana_log_page()
Signed-off-by: Anton Eidelman <anton@lightbitslabs.com>
Change-Id: I2a522dca833a27dddad25848d7688efa23d23091
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13039
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
rte_power was added to DPDK long time ago,
but some of the DPDK packages do not include it.
For those cases just skip building components that depend on in.
This change still allows to use dynamic scheduler, since
the dpdk_governor usage is optional.
Fixes#2534
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ied88edc8d58aae07d1384c1c40203fc80b919d80
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12993
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
dpdk_governor and gscheduler use rte_power,
which is only available on Linux and when
DPDK env is used.
Rather than repeat those checks in each mk or Makefile,
added DPDK_POWER flag directly to DPDK env.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I438caad8d333a4df697a79aa45de2930cce71d23
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12992
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: John Kariuki <John.K.Kariuki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@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>
We cannot try to set multipath policy on a non-nvme bdev.
While here, make the error messages match what we use for
setting preferred path.
Fixes issue #2543.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I823077f92634ee3c16e77e7e0d67eb343ec3584e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12916
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: <qun.wan@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
From aio_abi.h, io_event.res is defined __s64, negative
errno is assigned to io_event.res for error situation
in Linux Kernel.
But from libaio.h, io_event.res is defined unsigned long,
so convert it to signed value for error detection.
Fixes issue #2325
Change-Id: I99f8b03e8bfedfa260fe91f3e9e8ef0e5ecd0b77
Signed-off-by: Liu Xiaodong <xiaodong.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12882
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.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>
There are a few places where a typo, extra character
or newline was added to the BSD 3-clause license text
which made it differ very slightly from the rest of
the license headers in the source tree. Remove those
differences in this patch, to help with automation of
SPDX identifier replacement in the next patch.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I542dc53cd252b1699253fd6dcc3ccac9643d7878
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12905
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
These were deprecated in 2019, it's time to remove
support for them now.
Change-Id: I5a715e9b9e991c6febec5e505384728281eee8b7
Signed-off-by: wanghailiangx <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12773
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
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>
These were deprecated in 2019, it's time to remove
support for them now.
Change-Id: Ia28abb9b724c9589e1da66f0f22a1ba95d96f5dc
Signed-off-by: wanghailiangx <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12776
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
These were deprecated in 2019, it's time to remove
support for them now.
Change-Id: I9e203a52877802127df8144e68090d7975f9d200
Signed-off-by: wanghailiangx <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12772
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
And associated RPC to enable.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I06785bcd8b8957293ad41d13bab556fe62f29fd5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12765
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: Jim Harris <james.r.harris@intel.com>
These were deprecated in 2019, it's time to remove
support for them now.
Change-Id: I25aea510648a55d751db3740b36fb9924d1f52ed
Signed-off-by: wanghailiangx <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12747
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Misc internal IDXD changes needed to support the upcoming addition
of IAA.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Idb180088af545b174ed33a4f8ee113e58640477f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12764
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
IDXD has always been used everywhere but technically it stands for
the driver, not the HW (Intel Data Streaming Accelerator Driver)
where the X comes from "Streaming Accelerator" somehow. Anyway, the
underlying hardware is just DSA. It doesn't matter much now but
upcoming patches will add support for a new HW accelerator called
the Intel In-Memory Analytics Accelerator which we'll call IAA and
it will use the same (mostly) device driver (IDXD) as DSA. So, calling
the HW what it is will lessen confusion when adding IAA support.
This patch just does renaming for the accel_fw module and associated
files (RPC, etc).
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ib3b1f982cc60359ecfea5dbcbeeb33e4d69aee6a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11984
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
We explicitly refer to 2MiB huge pages when a buffer
spans huge page boundary. That is not correct since
it may happen even with 1GiB huge pages.
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reported-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ief72b677ccf3d8c1d9835bb8b74621f2b349175a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12250
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>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Separate out SCSI and BLK vhost subsystems to later add
virtio_blk transport abstraction.
This allows for further changes to the vhost_blk, not
affecting vhost_scsi.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Id1ecfeafeb936809a479a43c321e13f75cb3d5ad
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9539
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: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Maximum Data Transfer Size indicates the maximum data transfer size
for a command that transfers data between memory and the controller.
SPDK NVMe driver will split IO request based on MDTS and stripe
boundary, however, if user submited a big enough IO size, SPDK
NVMe driver will run out of requests data structure and return
-EINVAL as the error code, it's OK for application who call SPDK
NVMe driver directly.
SPDK bdev module also will do similar split based on `max_segment_size`
and `max_num_segments`, but we don't set them for bdev/nvme driver,
once there was a big enough IO request, the NVMe driver will return
-EINVAL to bdev module, here we set `max_segment_size` based on MDTS
and set `max_num_segments` based on number of requests of NVMe
controller.
Fix#2403.
Change-Id: Ic6e14a0b12413783597122285ac648b87e1f1e16
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12186
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
During ctrlr reconnection, spdk_nvme_ctrlr_reconnect_poll_async()
is executed by a non-timed poller.
We should poll adminq more often during ctrlr disconnection too.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ib1f5b41015aed20deda8df6f2c837981ac233c04
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12615
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
As described in the NVMe specification, a controller level reset
includes the following actions:
- the controller stops processing any outstanding admin or I/O
commands;
- all I/O SQs and CQs are deleted.
In a full controller reset sequence for a PCIe controller, if we do
a controller level reset first, we can abort outstanding commands
after the hardware has actually been stopped.
For NVMe-oF controller, each I/O qpair is an independent network
connection and is disconnected safely. We do not want to change
NVMe-oF controller.
Fixes the issue #2360
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: If05febac74705bfd3df5abd15064c1203126e027
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12447
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
These were deprecated in 2019, it's time to remove
support for them now.
Change-Id: Ic80ce74344b24814dad792cfff6a4791d0430527
Signed-off-by: wanghailiangx <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12741
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
It's now possible to specify a time to wait until a connection to the
discovery controller and the NVM controllers it exposes is made.
Whenever that time is exceeded, a callback is immediately executed.
However, depending on the stage of the discovery process, we might need
to wait a while before actually stopping it (e.g. because a controller
attach is in progress). That means that a discovery service might be
visible for a while after it timed out.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I2d01837b581e0fa24c8e777730d88d990c94b1d8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12684
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Currently this should be a no-op as the log_page is always freed in
discovery_remove_controllers(), but it'll make it easier to handle cases
when we want to stop the discovery service while it's attaching NVM
controllers. We'll be relying on this in the subsequent patch adding
attach timeout to start_discovery().
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Ia03fde92bf5ae5590bca507b7a0f963885d85f4f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12721
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: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
By default, failback to the preferred I/O path is done automatically
if it is restored. Some users may want to keep using the backup I/O
path even if the preferred I/O path is restored. In this case,
bdev_nvme_set_preferred_path can be used to do manual failback.
We may be able to clear/fill I/O path cache more strictly but it will
be complicated and have bugs. This patch does the minimal change,
just skips an apparent case.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I78fe5faee6ff04e88ae3d7c6be6da1c20637c912
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12431
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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>
Using stop_discovery() will also free the entry contexts tied to that
discovery service. It's not a big deal to leave them, as module_fini is
usually called on app shutdown, but this gets rid of asan reporting
memory leaks.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I81fc843708694791a5846c24cbde4b32e0fa7287
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12683
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
It was never freed, so we leaked it.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I9e17d043ebd0d8d11bb776cb2676ac7f53f8ee41
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12682
Community-CI: Mellanox Build Bot
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: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
For now, it's only called from a single location,
bdev_nvme_stop_discovery, but it'll make it possible to stop the
discovery from other places.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I3ba447f30fd8ed23c392d008b3d03cdad30cdb33
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12681
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: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
If the trid is not zeroed out, trid.trstring might contain garbage
value, which means that nvme_probe_internal() might not populate it
based on trtype and will use that garbage value to get a transport,
leading to the following failure:
```
nvme.c: 834:nvme_probe_internal: *ERROR*: NVMe trtype 3 () not available
```
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I56bc6502d285ee5ce094184e00d3297f6332e8c0
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12680
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: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Moved assigning ctx->start_cb_fn before it's checked for NULL to set
ctx->wait_for_attach, otherwise it was always false.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I819d9e326dbb36f943279c3714695ae604dd64b2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12628
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 <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Check that we're not already connected to a discovery service that has
the same address (or has a referall to) as the service we're trying to
start.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I84863fd959f62b30e9a348f69d10c7f1edffda7a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12627
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Otherwise, we'll try to use the same name to create the bdevs.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: I38cfb9073f343a7bf3966754008065c7ab89e609
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12626
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Replaced the TODO comment with an error handing in case SPDK fails to
allocate memory for the IO request. Returning the proper error code
will use the bdev's no memory retry mechanism to handle the failure.
Signed-off-by: Gal Hammer <gal.hammer@huawei.com>
Signed-off-by: Shai Fultheim <shai.fultheim@huawei.com>
Change-Id: I151668f26b7f122dca95eaf65934be675e601952
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12372
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Rafal Stefanowski <rafal.stefanowski@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The new blobstore ext API is used when the user
provides ext_io_opts in bdev layer.
To store blobstore ext_io_opts, vbdev_lvol reports
non-zero get_ctx_size in bdev module interface.
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I64076b5369533be0c1d69ca48aef9d70a9abe488
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11373
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
Queued vectored IOs use extended API -
if ext_opts is NULL there is no difference
between regular and extended blob API
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I091f36d81dab04bcd483ea61e667a368441d70e4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11372
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Introduce spdk_blob_ext_io_opts structure which
is used in the new *_ext functions.
Zeroes dev is updated with implementation of
readv_ext which uses memory domains memzero
or regular memset().
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: Id94542196eff999827bf00591fd43804256fccb4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11369
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
The following patches will swap the ordering of destroying I/O qpairs
and disconnecting a controller for PCIe transport to fix a github issue.
Setting callback and calling spdk_nvme_ctrlr_disconnect() have been
executed in two cases now.
After the following patches, these will be executed in three cases.
Factoring out these into a helper function will be rewarded.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I8597908d7fd8acc6dc62ec442ba2e8c4c08f11a4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12562
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: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
The following patches will swap the ordering of destroying I/O qpairs
and disconnecting a controller for PCIe transport to fix a github issue.
For PCIe transport, destroying I/O qpairs will be as the completion
callback to controller disconnection. To do this easier, factor out
destroying I/O qpairs into a helper function.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I96bb6d0487fc67b71c759ee64200bd7fb71aceb1
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12561
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: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
The RPC returns a list of active discovery service connections. Each
discovery service is described by a name, its trid, and a list of
discovery service trids it refers to.
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Ifa4b9501dd353e7b4948ad830575a6c94dafd86b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12380
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
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>
We enable multiple engines by:
* getting rid of the globals that point to the one available HW
and one available SW engine
* adding a submit_tasks() entry point for the SW engine so that
it is treated like any other engine allowing us to just call
submit_tasks() to the assigned engine for the opcode instead of
checking what is supported
* changing the definition of engine capabilities from
"HW accelerated" to simply "supported"
* during init, use a global (g_engines_opc) that contains engines
and is indexed by opcode so we know what the best engine is for each
op code
* future patches will add RPC's to override engine priorities or
specifically assign an opcode(s) to an engine.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I9b9f3d5a2e499124aa7ccf71f0da83c8ee3dd9f9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11870
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
The NVMe bdev module supported active-passive policy for multipath mode
first. By this patch, the NVMe bdev module supports active-active policy
for multipath node next. Following the Linux kernel native NVMe multipath,
the NVMe bdev module supports round robin algorithm for active-active
policy.
The multipath policy, active-passive or active-active, is managed per
nvme_bdev. The multipath policy is copied to all corresponding
nvme_bdev_channels.
Different from active-passive, active-active caches even non_optimized
path to provide load balance across multiple paths.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ie18b24db60d3da1ce2f83725b6cd3079f628f95b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12001
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
If we specify a preferred path manually for each NVMe bdev, we will
be able to realize a simple static load balancing and make the failover
more controllable in the multipath mode.
The idea is to move I/O path to the NVMe-oF controller to the head of
the list and then clear the I/O path cache for each NVMe bdev channel.
We can set the I/O path to the I/O path cache directly but it must be
conditional and make the code very complex. Hence, let find_io_path() do
that.
However, a NVMe bdev channel may be acquired after setting the preferred
path. To cover such case, sort the nvme_ns list of the NVMe bdev too.
This feature supports only multipath mode. The NVMe bdev module supports
failover mode too. However, to support the latter, the new RPC needs to
have trid as parameters and the code and the usage will be come very
complex. Add a note for such limitation.
To verify one by one exactly, add unit test.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ia51c74f530d6d7dc1f73d5b65f854967363e76b0
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12262
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: <tanl12@chinatelecom.cn>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
ACWU and NACWU are 0-based values. But spdk_bdev_get_acwu()
specifies the compare-and-write-unit in terms of blocks
(i.e. 1-based). So the bdev/nvme module needs to add 1
to this value before registering the bdev.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I7c19975a2bd8c09bb65374838fe20aad690d1ecf
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12384
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
When sending a fused compare and write command, we pass a callback
bdev_nvme_comparev_and_writev_done that we expect to be called twice
before marking the io as completed. In order to detect if a call to
bdev_nvme_comparev_and_writev_done is the first or the second one, we
currently rely on the opcode in cdw0. However, cdw0 may be set to 0,
especially when aborting the command. This may cause use-after-free
issues and this may call the user callbacks twice instead of once.
Use a bit in the nvme_bdev_io instead to keep track of the number of
calls to bdev_nvme_comparev_and_writev_done.
Signed-off-by: Alex Michon <amichon@kalrayinc.com>
Change-Id: I0474329e87648e44b08998d0552b2a9dd5d34ac2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12180
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: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Add an new RPC bdev_nvme_get_io_paths to query all active I/O paths.
One io_path belongs to One nvme_bdev_channel.
Each nvme_bdev_channel is associated with one nvme_bdev.
If the RPC bdev_nvme_get_io_paths has a bdev name as a parameter
it can use spdk_for_each_channel() simply for the corresponding
nvme_bdev.
However, users will want to know I/O paths of all nvme_bdevs like
the RPC bdev_get_bdevs.
One io_path has one nvme_qpair. One nvme_qpair belongs to one
nvme_poll_group. By relying on these relationships, the RPC
bdev_nvme_get_io_paths traverses all nvme_poll_groups by using
spdk_for_each_channel() to g_bdev_nvme_ctrlrs.
The RPC bdev_nvme_get_io_paths has two modes, display all or
the specified NVMe bdev's active I/O paths.
The specified bdev name is used just for comparison and empty
array is returned if no matched io_path is found.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I4a0dbf3ef7aaa9a7b7345fc03dc493cc6d37bc99
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12146
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
NVMe bdev name already includes the name of the NVMe bdev controller and
the NSID. CNTLID will be a good ID to identify a namespace from a NVMe
bdev when multipath is configured. However, the query RPCs,
bdev_get_bdevs and bdev_nvme_get_controllers had not returned such
information.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I2f2e355ff13f69ced616be803a3152c838cdc980
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12276
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Previously, if a namespace is in ANA inaccessible state, I/O had been
queued infinitely. Fix this issue according to the NVMe spec.
Add a temporary poller anatt_timer and a flag ana_transition_timedout for
each nvme_ns.
Start anatt_timer if the nvme_ns enters ANA transition. If anatt_timer
is expired, set ana_transition_timedout to true. Cancel anatt_timer or
clear ana_transition_timedout if the nvme_ns exits ANA transition.
nvme_io_path_become_available() returns false if ana_transition_timedout
is true.
Add unit test case to verify these addition.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ic76933242046b3e8e553de88221b943ad097c91c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12194
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Monica Kenguva <monica.kenguva@intel.com>
g_kernel_mode is a bool everywhere it is used but was written as a U32
in write_config_json routine.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I16b68b88a259df0d8240b64464729bd4a0ef84ec
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12275
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: <wayne.gao@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
We may fail creating qpair when adding io_path while creating a bdev_channel
if connection is down. But if we enable I/O error recovery, we can retry
creating qpair later.
So let nvme_qpair_create() succeed if the ctrlr is being reset or
I/O error recovery is enabled even if creating qpair failed.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I7d4ff036187bb79ada258cfc299582b4d287018b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12288
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: <tanl12@chinatelecom.cn>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Previously, only if admin qpair gets error, bdev_nvme_failover() was
called.
However, I/O qpair may get error earlier than admin qpair. In this case,
bdev_nvme_failover() was called but reset was already in progress. So
bdev_nvme_failover() returned without doing anything.
bdev_nvme_reset_complete() executes bdev_nvme_failover() if reset
failed. However the test time of test/nvmf/host/failover.sh was very
short. Timeout came before trying bdev_nvme_failover().
We can replace other bdev_nvme_reset() calls by bdev_nvme_failover()
but this patch focuses on the critical case.
Fixes issue #2128.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I68f54bbf54f92343aa56ae41f2b4cd92421c4bbb
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12295
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: Aleksey Marchuk <alexeymar@mellanox.com>
Due to the same reason as transport_ack_timeout for
RDMA transport, TCP transport also needs ack timeout.
This timeout in msec will make TCP socket to wait for
ack util closes connection.
Signed-off-by: zhangduan <zhangd28@chinatelecom.cn>
Change-Id: I81c0089ac0d4afe4afdd2f2c7e5bff1790f59199
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12214
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@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>
The raid bdev may receive IO requests after the raid layer
invokes spdk_bdev_unregister function. This patch moves the
raid_bdev->module->stop to the raid_bdev_destruct function.
Then there will be no IO after the raid_bdev->module->stop
is invoked.
Below is a way to reproduce this issue:
(1) create a malloc bdev
sudo ./scripts/rpc.py bdev_malloc_create --name malloc0 128 4096
(2) create a concat bdev base on the malloc bdev
sudo ./scripts/rpc.py bdev_raid_create --name concat0 \
--raid-level concat --base-bdevs malloc0 --strip-size-kb 4
(3) create a lvstore base on the concat bdev
sudo ./scripts/rpc.py bdev_lvol_create_lvstore \
--cluster-sz 4194304 --clear-method unmap concat0 lvs0
(4) remove the concat bdev
sudo ./scripts/rpc.py bdev_raid_delete concat0
In the step(4), the spdk app will crash because an IO request
is sent to the concat bdev after the concat_stop is invoked.
Signed-off-by: Peng Yu <yupeng0921@gmail.com>
Change-Id: I76d6964ee9528d4590ed86e9c5c28d53e85da32f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12221
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This was neither set nor used.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: I3119135843c5fc0b8724e593db40df46e6b5bdb0
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12097
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: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The concat module can combine multiple underlying bdevs to a single
bdev. It is a special raid level. You can add a new bdev to the end of
the concat bdev, then the concat bdev size is increased, and it won't
change the layout of the exist data. This is the major difference
between concat and raid0. If you add a new underling device to raid0,
the whole data layout will be changed. So the concat bdev is extentable.
Change-Id: Ibbeeaf0606ff79b595320c597a5605ab9e4e13c4
Signed-off-by: Peng Yu <yupeng0921@gmail.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11070
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: Jim Harris <james.r.harris@intel.com>
vbdev_gpt reports memory domains of its base
bdev if the base bdev is not configured to check
DIF refence tag since in that case bdev_part will
remap reftags thereby it will touch metadata.
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: Ie1fee7f267c318b3cede47fbbbe9f7639571bdeb
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11050
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: Shuhei Matsumoto <smatsumoto@nvidia.com>
