The purpose is to reduce the duplicated functions
in posix and uring implmentation.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ia0568b2490d362e7e78fa59b3ca88a60313ba0bd
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5284
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Since spdk_sock_group_poll should do level trigger to
the callback func registered in spdk_sock_group_add_sock,
if there is data in pipe, but not event occurs, poll func
should still reap sock who has data in pipe.
Change-Id: If3a983f80fd04708e45ad0398c7d34018ec52bc7
Signed-off-by: Liu Xiaodong <xiaodong.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5072
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
By design the opts for each implementation
can not match spdk_sock_impl_opts.
During get_opts for specific implementation
only used fields are filled.
Yet iterating over all spdk_sock_impl_opts fields
would yeild garbage values for unset fields.
This is the case right now when doing save_config RPC
with uring enabled. A garbe value for enable_zerocopy_send
is returned.
sock.c:829:62: runtime error: load of value 165, which is not a valid value for type '_Bool'
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ie0512a7dffc36c8ff89256d08f8a2f4fefcf9e83
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4699
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
This patch is used to enable placement_id getting
in sock layer and also add the rpc support.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I70de57b0ed392a0aefce9d3ff1f61ef924015a87
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4146
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The pipe buffer has obvious performance influence on arm64. The
following is my test result with 1core, we can also enable it
on arm64 currently like the posix socket. And later we can find
the optimal pipe size that won't cause a degradation for large
payloads.
randwrite randread
512 byte 61% 97%
4096 byte 84% 16%
16384 byte -13% -17%
Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Change-Id: Ib4df60751c5e06ef9bd7fc7bb7efafa5ad4de211
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3329
Tested-by: SPDK CI Jenkins <sys_sgci@intel.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: Aleksey Marchuk <alexeymar@mellanox.com>
For some exceptional cases (e.g.,
https://github.com/spdk/spdk/issues/1486),
we may detect POLLERR or other events. So for those events,
we can just ingore it, but not use SPDK_UNREACHABLE.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I073575408783ff75e50b40d45ddf09388a2cab96
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3262
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
If the socks parameter(passed in uring_sock_group_impl_poll) is NULL,
we do not need to handle the sock_flush and prep the pollin task,
otherwise it will cause the assert issue when we reap the task when
we handle the nvmf_shutdown_tc3 issue.
Because in uring_sock_group_impl_remove_sock, we finally
set sock->group = NULL. Without this patch,
when we call uring_sock_group_impl_poll in this function,
pollin_task or write_task are prepared, then in the next round,
we will reap those tasks again.
PS: Error info can be found in
https://ci.spdk.io/results/autotest-per-patch/builds/19186/archive/nvmf-tcp-vg-autotest/build.log
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I7e6deaa05e958b52e71e0bbf0ccdd20e35583685
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3031
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
According to the description of io_uring_queue_exit:
Tear down function for io_uring. Unmaps all setup shared ring buffers
and closes the low-level io_uring file descriptor returned by the kernel.
So we should remove the close operatoin on ring fd.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I910c6e8acd935925b7985c2aa750df385004eb55
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/2922
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Thus, we can make sure that when read data is larger than
the pipe size, it will not read the data into the pipe.
Change-Id: I87f3b03fd9b81eb693e9eae0fea9eef7d1b9eaa8
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/2450
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
When the initiator terminates the connection suddently, we
found the keep alive timeout issue, e.g.,
nvmf_ctrlr_keep_alive_poll: *NOTICE*:
Disconnecting host from subsystem nqn.2016-06.io.spdk:cnode1 due to keep alive timeout.
The root cause is that we did not closes the connection on our target side on time
whening using uring sock, and this patch can fix the issue.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I295f58bbdbae0ac3f5308f6eadef6a75c5ad07d8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/2544
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
This reverts commit 79215d80c1.
Reason: Find the bugs while using batched. For example, if
we fetch 3 CQEs, A, B, C and put it in a cqes[] array.
Then we leverage io uring cqe seen to handle, Then we handle the
CQE A, then invokes the call back related with A. In A's call back,
it may also call the reap function (sock_uring_group_reap),
then the CQEs will be handled again. Thus the CQEs B and C can be already
handled. Then we will handle B or C again, then it triggers the error.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I67ece3b24e677b88d66d08722b00539693b42e1e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/2543
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>
Purpose: This can improve the performance.
Change-Id: I3f5526ab8716cb0771b5e193afa9a0dbffec5cc0
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1929
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
We should add the cancel task feature in uring if
sock is removed from the group.
This issue is detected after the group polling
feature is added in NVMe tcp initiatator side. Before
the patch, SPDK NVMe initiator side will not use
group polling feature. After the group polling
feature added in the iniatiator side, we should add this
patch.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I012b403a9f57a5a8ee96c83471b775f0d99b9eb6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/2049
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>
Purpose: prepare for the next patch
Change-Id: Iae6a3d7a2c90a78c7dd1e510e718e4e1c07b3f32
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/2048
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Port the similiar code from posix sock module if a sock
is removed and added to a new group.
Change-Id: I306bed3c90f79ee06a363fbab02c776e756cda2f
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/2047
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Purpose: This is used to make users can specify
some options on the socket, e.g., the different priority for the socket.
While creating sockets, the priority needs to be set before connect()
and listen system calls, so better to add one parameter in spdk_sock_opts
which can contain options (e.g., priority) in spdk_sock_listen_ext and
spdk_sock_connect_ext functions.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Signed-off-by: Sudheer Mogilappagari <sudheer.mogilappagari@intel.com>
Change-Id: I406238e9da7abd69f937b7072535a19124ed0169
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1874
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI
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>
Since the related feature is already contained in
spdk_sock_listen and spdk_sock_connect functions,
we no longer need this function.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I1eafff0d139fa266a355fbee2bf0fc3947db69fc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1876
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Do large reads from the socket and buffer into a pipe.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ibce74917a1cd7248ff1a325204c0d338cc6a3470
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1349
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This patch is used to add the async network I/O support in
sock layer. If code is configured with I/O uring, --with-uring,
we can use io uring in Linux (version >=5.4-rc3).
PS: We also make VPP's default priority > uring, because
for the iSCSI or sock test linked with VPP. It tests VPP with
a given address (which is not a special VPP can only open address),
so using uring can also listen those address succefully. And if we make
uring with priority > VPP, actually, VPP will not tested in those cases.
Additionally, the current CI pool is not ready for test, we need
wait for the CI system ready. And I test on my local platform, it works.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ie8ee3c8ddf8d2a7264f2b382376733e002816dcc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/952
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
