Revision tags: v25.01-rc1, v24.09, v25.01-pre, v24.09-rc1 |
|
#
cec5ba28 |
| 23-Aug-2024 |
Alexey Marchuk <alexeymar@nvidia.com> |
nvme/rdma: Register UMR per IO request
If accel sequence is supported, append a copy task even if there is no accel sequence. NVME RDMA driver expects that accel framework registers UMR for the data
nvme/rdma: Register UMR per IO request
If accel sequence is supported, append a copy task even if there is no accel sequence. NVME RDMA driver expects that accel framework registers UMR for the data buffer. This UMR allows to represent fragmented payload as a virtually contig one.
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com> Change-Id: I410f991959b08eab033105a7dbb4a9aaba491567 Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24709 Reviewed-by: Ben Walker <ben@nvidia.com> Community-CI: Community CI Samsung <spdk.community.ci.samsung@gmail.com> Reviewed-by: Jim Harris <jim.harris@nvidia.com> Community-CI: Mellanox Build Bot Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
show more ...
|
#
afdec00e |
| 06-Nov-2024 |
Shuhei Matsumoto <smatsumoto@nvidia.com> |
nvmf: Add hide_metadata option to nvmf_subsystem_add_ns
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com> Change-Id: I518c3cc5fdcb16b41f1e3bda1debf5cb3cc9c47b Reviewed-on: https://review.spdk.
nvmf: Add hide_metadata option to nvmf_subsystem_add_ns
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com> Change-Id: I518c3cc5fdcb16b41f1e3bda1debf5cb3cc9c47b Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/25413 Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Reviewed-by: Jim Harris <jim.harris@nvidia.com> Community-CI: Mellanox Build Bot Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Community-CI: Community CI Samsung <spdk.community.ci.samsung@gmail.com> Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
show more ...
|
#
e0d7428b |
| 23-Oct-2024 |
Atul Malakar <a.malakar@samsung.com> |
lvol: Add custom metadata page size to lvstore
Added new --md_page_size parameter to bdev_lvol_create_lvstore RPC. It facilitates user to pick a custom md_page_size, greater than phys_blocklen of th
lvol: Add custom metadata page size to lvstore
Added new --md_page_size parameter to bdev_lvol_create_lvstore RPC. It facilitates user to pick a custom md_page_size, greater than phys_blocklen of the underlying device.
This will allow functional testing of the large IU metadata changes on 4K IU NVMe SSDs.
Change-Id: Ib1bc68ba4d5b8a7db7f2befc1f616b342c01bc0f Signed-off-by: Atul Malakar <a.malakar@samsung.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/25304 Community-CI: Mellanox Build Bot Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Reviewed-by: Ben Walker <ben@nvidia.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Community-CI: Community CI Samsung <spdk.community.ci.samsung@gmail.com> Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Reviewed-by: Jim Harris <jim.harris@nvidia.com>
show more ...
|
#
637d0d0b |
| 21-Oct-2024 |
Michal Berger <michal.berger@intel.com> |
scripts/rpc: Fix conserve_cpu arg in bdev_xnvme_create()
Currently, there's no way to actually change this arg while calling this particular rpc. So make sure it's possible, and keep it as an option
scripts/rpc: Fix conserve_cpu arg in bdev_xnvme_create()
Currently, there's no way to actually change this arg while calling this particular rpc. So make sure it's possible, and keep it as an optional arg with default still set to False (as per b99b00e595).
Change-Id: I889179bfa46a6261d2e30eeba4a5a14395e756a5 Signed-off-by: Michal Berger <michal.berger@intel.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/25287 Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Reviewed-by: Pawel Piatek <pawelx.piatek@intel.com> Community-CI: Mellanox Build Bot Reviewed-by: Jim Harris <jim.harris@nvidia.com> Community-CI: Community CI Samsung <spdk.community.ci.samsung@gmail.com> Reviewed-by: Karl Bonde Torp <k.torp@samsung.com>
show more ...
|
#
008a6371 |
| 05-Jul-2024 |
Alexey Marchuk <alexeymar@nvidia.com> |
accel/mlx5: Initial implementation of mlx5 platform driver
Now we just execute all tasks one by one. The driver supports only limited scope of operations and disabled by default
Signed-off-by: Alex
accel/mlx5: Initial implementation of mlx5 platform driver
Now we just execute all tasks one by one. The driver supports only limited scope of operations and disabled by default
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com> Change-Id: I1478db685b1621a4610be1c80929d62d1106e908 Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24698 Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Ben Walker <ben@nvidia.com> Community-CI: Mellanox Build Bot Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com> Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Community-CI: Community CI Samsung <spdk.community.ci.samsung@gmail.com>
show more ...
|
#
42d1bd28 |
| 12-Aug-2024 |
Jim Harris <jim.harris@samsung.com> |
thread: add enable_numa parameter to iobuf_set_options RPC
This parameter does not yet actually enable per-NUMA node iobuf buffer pools. It only checks that the application was built with support fo
thread: add enable_numa parameter to iobuf_set_options RPC
This parameter does not yet actually enable per-NUMA node iobuf buffer pools. It only checks that the application was built with support for the number of NUMA nodes reported by the system.
Signed-off-by: Jim Harris <jim.harris@samsung.com> Change-Id: I1b9d11ccb8f6914280874a40754c51625d21645d Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24539 Reviewed-by: Ben Walker <ben@nvidia.com> Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Community-CI: Community CI Samsung <spdk.community.ci.samsung@gmail.com> Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Community-CI: Mellanox Build Bot
show more ...
|
#
3a02df0b |
| 30-Aug-2024 |
Jim Harris <jim.harris@samsung.com> |
event: add new 'mappings' parameter to static scheduler
This is useful for testing purposes, to place specific spdk_threads on specific cores. Specified core must be in the thread's cpumask.
Usage:
event: add new 'mappings' parameter to static scheduler
This is useful for testing purposes, to place specific spdk_threads on specific cores. Specified core must be in the thread's cpumask.
Usage:
scripts/rpc.py framework_set_scheduler --mappings='2:0,5:1'
This will move thread 2 to core 0 and thread 5 to core 1.
Note: checking for failure when setting core-limit parameter on static scheduler has been removed. The whole mechanism for determine which optional parameters are accepted for different schedulers needs to be rethought, the current mechanism is not really working.
Signed-off-by: Jim Harris <jim.harris@samsung.com> Change-Id: I16000805b8e2512f7ec6d84ee812d32bfcb2fd6d Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24766 Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Reviewed-by: Changpeng Liu <changpeliu@tencent.com> Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Community-CI: Mellanox Build Bot Reviewed-by: Anisa Su <anisa.su@samsung.com> Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
show more ...
|
#
92108e0a |
| 26-Jun-2024 |
Yoray Zack <yorayz@nvidia.com> |
fsdev/aio: add support for null IOs
This patch adds support for null IOs in the AIO fsdev by introducing a new RPC flag (--enable-skip-rw) during fsdev creation.
When enabled, the AIO fsdev will sk
fsdev/aio: add support for null IOs
This patch adds support for null IOs in the AIO fsdev by introducing a new RPC flag (--enable-skip-rw) during fsdev creation.
When enabled, the AIO fsdev will skip read/write operations, similar to how the null bdev operates in the bdev module.
This feature facilitates performance testing across the entire stack without actual data read/write operations. Implementing this within the fsdev/aio module, rather than creating a separate fsdev/null module, avoids unnecessary code duplication and keeps the AIO fsdev focused as a comprehensive example demonstrating various features, including null IO capability.
Change-Id: Id7e84711628f23e6faa9128f9e428f759e0032c9 Signed-off-by: Yoray Zack <yorayz@nvidia.com> Signed-off-by: Vishwanath Venkatesan <vvenkatesan@nvidia.com> Signed-off-by: Ben Walker <ben@nvidia.com> Signed-off-by: Anton Nayshtut <anayshtut@nvidia.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24563 Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Community-CI: Mellanox Build Bot Reviewed-by: Changpeng Liu <changpeliu@tencent.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Jim Harris <jim.harris@samsung.com> Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
show more ...
|
#
63e0c25d |
| 12-Sep-2024 |
Vasilii Ivanov <iwanovvvasilij@gmail.com> |
bdev: add reset_mode to bdev_get_iostat
In current implementation of resetting stats explicit bdev_reset_iostat call is needed. It is not optimal for usecases when stat is obtained periodically and
bdev: add reset_mode to bdev_get_iostat
In current implementation of resetting stats explicit bdev_reset_iostat call is needed. It is not optimal for usecases when stat is obtained periodically and then resetted, because some stats may be lost in between of get and reset. Introduce new option for bdev_get_iostat that allows to reset stat right after obtaining it.
Fixes #3525
Change-Id: I77a5ea9310718c25e678336e2450a04fb582c050 Signed-off-by: Vasilii Ivanov <iwanovvvasilij@gmail.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24900 Community-CI: Mellanox Build Bot Reviewed-by: Jim Harris <jim.harris@samsung.com> Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com> Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
show more ...
|
#
8d3f8fb8 |
| 01-Jul-2024 |
Konrad Sztyber <konrad.sztyber@intel.com> |
bdev/nvme: add method for changing DH-HMAC-CHAP keys
This method will change the keys on all multipath controllers and force reauthentication on all qpairs. The high level flow looks like this:
1
bdev/nvme: add method for changing DH-HMAC-CHAP keys
This method will change the keys on all multipath controllers and force reauthentication on all qpairs. The high level flow looks like this:
1) Set the keys on the first multipath controller. 2) Authenticate admin qpair. 3) Go over all IO channels and authenticate IO qpairs on each one. 4) If there's no next multipath controller, we're done, otherwise set keys on that controller and go to 2).
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com> Change-Id: Iec0de19f1a9326cf32c9b27acaab117100616770 Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24236 Community-CI: Mellanox Build Bot Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Jim Harris <jim.harris@samsung.com> Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
show more ...
|
Revision tags: v24.05, v24.09-pre, v24.05-rc1 |
|
#
fe7bb7bd |
| 10-May-2024 |
Alexey Marchuk <alexeymar@nvidia.com> |
accel/mlx5: Add statistics
Collect statistics per accel opcode, per mlx5 operation, polling and nomem statistics The statistics can be retrieved per channel, per device per channel and accumulated p
accel/mlx5: Add statistics
Collect statistics per accel opcode, per mlx5 operation, polling and nomem statistics The statistics can be retrieved per channel, per device per channel and accumulated per module
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com> Change-Id: I082e1556295071d0243037fd810bb6ade752c352 Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/23141 Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com> 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: Konrad Sztyber <konrad.sztyber@intel.com>
show more ...
|
#
ddd4603c |
| 06-Aug-2024 |
Yankun Li <845245370@qq.com> |
bdev/compress: Supports the specified compression algorithm
compress bdev Indicates that compression uses the synchronization mechanism and only deflate is supported. However, for some business scen
bdev/compress: Supports the specified compression algorithm
compress bdev Indicates that compression uses the synchronization mechanism and only deflate is supported. However, for some business scenarios, it is more concerned with compression performance than compression rate. So we provide extensions that support multiple compression algorithms
Change-Id: I36b93875eed3069aa0c74843d98e4a0c90412b9e Signed-off-by: Yankun Li <845245370@qq.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24452 Reviewed-by: GangCao <gang.cao@intel.com> Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Community-CI: Mellanox Build Bot Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
show more ...
|
#
698b2423 |
| 05-Jul-2024 |
Shuhei Matsumoto <smatsumoto@nvidia.com> |
rpc: Add nvmf_subsystem_set_ns_ana_group RPC
Add nvmf_subsystem_set_ana_group RPC to change ANA group ID of a namespace in a subsystem dynamically.
Probably, we can change ANA group ID safely witho
rpc: Add nvmf_subsystem_set_ns_ana_group RPC
Add nvmf_subsystem_set_ana_group RPC to change ANA group ID of a namespace in a subsystem dynamically.
Probably, we can change ANA group ID safely without pausing subsystem. However, we pause subsystem as same as other configuration changes for now.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com> Suggested-by: Leonid Chernin <leonidc@il.ibm.com> Tested-by: Leonid Chernin <leonidc@il.ibm.com> Change-Id: I6fa4a9560ef75cdf3abb9428849ee2ffcea85136 Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24060 Community-CI: Mellanox Build Bot Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com> Reviewed-by: Jim Harris <jim.harris@samsung.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
show more ...
|
#
2186fc03 |
| 11-Sep-2024 |
Zhangfei Gao <zhangfei.gao@linaro.org> |
accel/dpdk_compressdev: Support uadk compress pmd
Add support of UADK Compress Poll Mode Driver to accel/dpdk_compressdev.
build: ./configure --with-dpdk-uadk --with-dpdk-compressdev make
./build
accel/dpdk_compressdev: Support uadk compress pmd
Add support of UADK Compress Poll Mode Driver to accel/dpdk_compressdev.
build: ./configure --with-dpdk-uadk --with-dpdk-compressdev make
./build/bin/spdk_tgt -m 0xf0 --wait-for-rpc
./scripts/rpc.py compressdev_scan_accel_module -p 3 ./scripts/rpc.py accel_assign_opc -o compress -m dpdk_compressdev ./scripts/rpc.py accel_assign_opc -o decompress -m dpdk_compressdev ./scripts/rpc.py framework_start_init ./scripts/rpc.py accel_get_opc_assignments
Change-Id: I202c17c3a936208901a3bdc6bb2a11ddc88875f7 Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/23738 Reviewed-by: Changpeng Liu <changpeliu@tencent.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Community-CI: Mellanox Build Bot Reviewed-by: Jim Harris <jim.harris@samsung.com>
show more ...
|
#
8a4b7226 |
| 12-Jun-2024 |
Konrad Sztyber <konrad.sztyber@intel.com> |
nvmf/auth: add method for changing keys
This allows users to change the DH-HMAC-CHAP keys without removing/re-adding hosts to a subsystem. That means that keys can be changed without terminating ex
nvmf/auth: add method for changing keys
This allows users to change the DH-HMAC-CHAP keys without removing/re-adding hosts to a subsystem. That means that keys can be changed without terminating existing connections.
Once the keys are changed, new connections, as well as reauthentication requests on the already established connections, will be required to use the new keys.
Change-Id: I09e112ae73e4afebd452a3ebd19264cc8217d1f8 Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/23822 Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com> Reviewed-by: Jim Harris <jim.harris@samsung.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Ben Walker <ben@nvidia.com> Community-CI: Mellanox Build Bot
show more ...
|
#
b2b3fa9e |
| 28-Aug-2024 |
Mateusz Kozlowski <mateusz.kozlowski@solidigm.com> |
scripts/rpc: Add optional print for uuid in bdev_null/malloc_create
These are tagged as optional in the parsing of the argument, adding the info to the help, so the user doesn't feel the need to fil
scripts/rpc: Add optional print for uuid in bdev_null/malloc_create
These are tagged as optional in the parsing of the argument, adding the info to the help, so the user doesn't feel the need to fill this in when creating a new instance.
Change-Id: I7bd18a58d9c38d243445dd843128026cc7f5dbd3 Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@solidigm.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24721 Reviewed-by: Jim Harris <jim.harris@samsung.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Community-CI: Mellanox Build Bot
show more ...
|
#
e5693d68 |
| 12-Aug-2024 |
Mateusz Kozlowski <mateusz.kozlowski@solidigm.com> |
bdev/aio: Add UUID to the bdev_aio_create function
Adds an optional UUID to the RPC call. The parameter is persisted upon save_config call. This allows for the bdev to have a consistent UUID and mea
bdev/aio: Add UUID to the bdev_aio_create function
Adds an optional UUID to the RPC call. The parameter is persisted upon save_config call. This allows for the bdev to have a consistent UUID and means it can be used with RAID bdev.
Change-Id: If6e7ab1fb327a958bba5a6aa583ba5a4943105f8 Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@solidigm.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24502 Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Community-CI: Mellanox Build Bot Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Reviewed-by: Jim Harris <jim.harris@samsung.com>
show more ...
|
#
496d6e76 |
| 23-Aug-2024 |
Jim Harris <jim.harris@samsung.com> |
rpc: add 'subsystems' parameter to save_config
This faciliates saving a config from an application like nvmf_tgt for later use with bdevperf.
bdevperf doesn't have nvmf or nbd subsystems, so reusin
rpc: add 'subsystems' parameter to save_config
This faciliates saving a config from an application like nvmf_tgt for later use with bdevperf.
bdevperf doesn't have nvmf or nbd subsystems, so reusing the nvmf_tgt config file as-is just generates a lot of annoying NOTICELOGS that confuse users. We can instead instruct users to do the following to create the json config file for bdevperf:
# scripts/rpc.py save_config -s bdev > bdevperf.json
Signed-off-by: Jim Harris <jim.harris@samsung.com> Change-Id: Ia0dfc83d16c3a6f5b3ad48f466ecabcf9a470ac8 Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24665 Community-CI: Mellanox Build Bot Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com> Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
show more ...
|
#
e591409f |
| 19-Aug-2024 |
Hadi Moshayedi <hadi@ubicloud.com> |
lvol: fix parameter name of bdev_lvol_set_parent[_bdev].
In `vbdev_lvol_rpc.c` we use `parent_name` for parent name parameter of bdev_lvol_set_parent and bdev_lvol_set_parent_bdev. Docs missed this.
lvol: fix parameter name of bdev_lvol_set_parent[_bdev].
In `vbdev_lvol_rpc.c` we use `parent_name` for parent name parameter of bdev_lvol_set_parent and bdev_lvol_set_parent_bdev. Docs missed this.
As a follow up, this patch also changes the corresponding names in lvol.py and rpc.py to match the names in the json-rpc protocol.
Change-Id: I9837f579c550a0f3d61e41a3dda265b7fe9623cc Signed-off-by: Hadi Moshayedi <hadi@ubicloud.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24598 Reviewed-by: Jim Harris <jim.harris@samsung.com> Reviewed-by: Damiano Cipriani <damiano.cipriani@suse.com> Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com> Community-CI: Mellanox Build Bot Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
show more ...
|
#
462fd69e |
| 14-May-2024 |
SeungYeon Shin <yss9509@naver.com> |
lib/event: Add support for core isolation in scheduling
Added new 'scheduler_set_options' RPC. 1. isolated_core_mask: Users are allowed to select cores to isolate during scheduling 2. scheduling_cor
lib/event: Add support for core isolation in scheduling
Added new 'scheduler_set_options' RPC. 1. isolated_core_mask: Users are allowed to select cores to isolate during scheduling 2. scheduling_core: Users are allowed to select main core of scheduling This RPC can only be called before SPDK subsystems have been initialized. These parameters can only be set once.
The following options are for general mechanisms. For example, dynamic scheduler now allows specific cores to be isolated from scheduling through the newly added isolated_core_mask. This means that no threads can enter or leave the cores designated as isolated cores.
Core isolation can be useful in the following situation: The user may want the main core to be dedicated to orchestration tasks(such as RPCs, etc.) and does not want any IO work to be assigned to it while running dynamic scheduler. These changes allow user to dedicate main thread for RPC, assign nvmf poll groups to non-main thread cores, and then ensure that dynamic(or any other) scheduler will not place any other spdk_threads on the main core.
Change-Id: Idb5e564150d014cec7106d48d609d83490561a94 Signed-off-by: SeungYeon Shin <syeon.shin@samsung.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/23156 Reviewed-by: Jim Harris <jim.harris@samsung.com> Community-CI: Mellanox Build Bot Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
show more ...
|
#
78467a35 |
| 16-Jul-2024 |
Karl Bonde Torp <k.torp@samsung.com> |
bdev/nvme: add support for unrecognized csi
The intention is to enable the use of namespaces with unsupported/custom NVMe command sets, e.g. KV, without having to implement support for a specific cs
bdev/nvme: add support for unrecognized csi
The intention is to enable the use of namespaces with unsupported/custom NVMe command sets, e.g. KV, without having to implement support for a specific csi.
These namespaces only support NVMe passthrough.
Change-Id: I5d13dc5ae749f428ea399cff929cb53c38493335 Signed-off-by: Karl Bonde Torp <k.torp@samsung.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24190 Community-CI: Mellanox Build Bot Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Jim Harris <jim.harris@samsung.com> Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
show more ...
|
#
60241941 |
| 04-Jul-2024 |
Karl Bonde Torp <k.torp@samsung.com> |
nvmf: add support for a passthrough subsystem
The intention is to enable the use of unsupported/custom NVMe command sets, e.g. KV, without having to implement support for a specific csi.
Only names
nvmf: add support for a passthrough subsystem
The intention is to enable the use of unsupported/custom NVMe command sets, e.g. KV, without having to implement support for a specific csi.
Only namespaces supporting NVMe passthrough for both I/O and admin commands can be added to the passthrough subsystem.
I/O commands and admin commands with a specified NSID will be sent via the passthrough path.
Admin commands meant for the controller will be handled by the subsystem as usual.
Change-Id: I5c47ffcee8834187d3e0bcc1f60388c03256c46f Signed-off-by: Karl Bonde Torp <k.torp@samsung.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24057 Reviewed-by: Jim Harris <jim.harris@samsung.com> Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com> Community-CI: Mellanox Build Bot Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
show more ...
|
#
e892af6b |
| 02-May-2024 |
Alexey Marchuk <alexeymar@nvidia.com> |
accel/mlx5: Allow to split crypto op by num of blocks
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com> Change-Id: Idfa18001c423ed493cb2a846d99bd5d69808be40 Reviewed-on: https://review.spdk.io/ge
accel/mlx5: Allow to split crypto op by num of blocks
Signed-off-by: Alexey Marchuk <alexeymar@nvidia.com> Change-Id: Idfa18001c423ed493cb2a846d99bd5d69808be40 Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/23115 Community-CI: Mellanox Build Bot Reviewed-by: Ben Walker <ben@nvidia.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
show more ...
|
#
ff89983c |
| 06-Aug-2024 |
Yankun Li <845245370@qq.com> |
script/rpc.py: Provide necessary params for bdev_compress_create
Must provide base bdev name and pm path for bdev_compress_create
Change-Id: Ib9b099df3b395b42c561444345dd9d5c50179798 Signed-off-by:
script/rpc.py: Provide necessary params for bdev_compress_create
Must provide base bdev name and pm path for bdev_compress_create
Change-Id: Ib9b099df3b395b42c561444345dd9d5c50179798 Signed-off-by: Yankun Li <845245370@qq.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24451 Reviewed-by: GangCao <gang.cao@intel.com> Reviewed-by: Jim Harris <jim.harris@samsung.com> Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com> Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com> Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
show more ...
|
Revision tags: LTS, v24.01, v24.05-pre, v24.01-rc1 |
|
#
4d453b24 |
| 03-Jan-2024 |
Anton Nayshtut <anayshtut@nvidia.com> |
module/vfu_device: vfu_virtio_fs introduced
This patch set implements the virtiofs vfio-user device based on SPDK fsdev + FUSE dispatcher.
Steps to run w/QEMU:
1. Run target:
build/bin/spdk_tgt
module/vfu_device: vfu_virtio_fs introduced
This patch set implements the virtiofs vfio-user device based on SPDK fsdev + FUSE dispatcher.
Steps to run w/QEMU:
1. Run target:
build/bin/spdk_tgt -S /tmp/vfio-sockets
2. Create an fsdev and a corresponding vfu endpoint:
spdk_rpc.py fsdev_aio_create aio0 /tmp/vfio-test spdk_rpc.py vfu_virtio_create_fs_endpoint vfufs.0 --fsdev-name aio0 \ --tag vfu_test --cpumask=0x1 --num-queues=8 --qsize=256 --packed-ring
3. Run the QEMU with:
-device vfio-user-pci,socket=/tmp/vfio-sockets/vfufs.0
Then inside the VM:
$ mkdir /tmp/zzz $ modprobe -v virtiofs $ mount -t virtiofs vfu_test /tmp/zzz
NOTE: as the implementation is based upon the nutanix/libvfio-user library ([1]) similar to vfu_virtio_blk and vfu_virtio_scsi. It requires an QEMU version that supports the vfio-virtio-pci devices. More information can be found in the libvfio-user README ([2]).
[1] https://github.com/nutanix/libvfio-user [2] https://github.com/nutanix/libvfio-user/blob/master/README.md
Change-Id: I182119aced0640d6f9290802d91f93b27294f468 Signed-off-by: Anton Nayshtut <anayshtut@nvidia.com> Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/24086 Tested-by: SPDK CI Jenkins <sys_sgci@intel.com> Reviewed-by: Ben Walker <ben@nvidia.com> Reviewed-by: Jim Harris <jim.harris@samsung.com> Community-CI: Mellanox Build Bot
show more ...
|