This will become important later on.
Change-Id: I94e5af03359e476afbc68664e43f44269ad5974c
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448074
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>
When we have a shared receive queue, the number of outstanding items
associated with a completion queue is deterministic, and limited by how
many RECVs we have total in the SRQ. So, we can set the total size of
the Completion queue at the beginning of time and never resize it.
Change-Id: I787e4c5bbd52ac8948a323d1301f926f887cd91c
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447492
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>
Consolidating error paths is common practice in SPDK so do that here to
make the function more uniform and save space.
Change-Id: I98c5d5f7feeb688f1d8b24f4d2d3461a43d00c1d
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448191
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Array channels in the subsystem's poll group are indexed by
nsid - 1, so rename the previous num_channels to num_ms
makes more sense. Also embed the channels into a namespace
data structure here, and this can be reused in the following
patch.
Change-Id: If5d9aab4b1d5bcf7a3c22f29fa58d84752f0d4cc
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/446211
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 unifies the clean up path between SRQ and normal
operation.
Change-Id: I396d7e3749579f27b5bb1e89b9d6761a77ba5beb
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/446979
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Depending on whether SRQ is enabled, resources may be allocated
to the rqpair or to the rpoller. Create a struct to hold these
pointers that can be used in both locations to avoid duplicated
code.
Change-Id: I2c8fc59009201d9e41721e6462a81732b529a9e0
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/446978
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Eugene Kochetov <evgeniik@mellanox.com>
This wasn't used anywhere.
Change-Id: I405af3c808be284d19218f3f04c1e90e33e31de8
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/446977
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
The purpose is to use the single readv to read both
the payload the digest(if there is a possible one).
And this patch will be prepared to support the
multiple SGL in NVMe tcp transport later.
Change-Id: Ia30a5e0080b041a65461d2be13db4e0592a70305
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447670
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
We were only using one pd per device anywas, and this is necessary for
shared receive queue support.
Change-Id: I86668d5b7256277fe50836863408af2215b5adf9
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447385
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>
Both Mellanox and Soft-RoCE NICs work with this approach.
Change-Id: I7b05e54037761c4d5e58484e1c55934c47ac1ab9
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/446134
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>
Persist through power loss feature is not supported for now.
Change-Id: Id2a5088389dc28b9d28d88c04ff819d20ea11902
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/436940
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>
For number of registered controllers field in Reservation
Status Data Structure, we caculate all the controllers
in the subsystem which Host Identifier are same with
existing registrants.
Change-Id: Ib4de22c7020dbd8294f448f23c0c5c8c142629dd
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/436939
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>
The possible issue could be following if you shutdown NVMe-oF target
with TCP transport as an example,
=================================================================
==61022==ERROR: LeakSanitizer: detected memory leaks
Direct leak of 560 byte(s) in 1 object(s) allocated from:
#0 0x7ffff6efcfe0 in calloc (/lib64/libasan.so.3+0xc6fe0)
#1 0x4c6216 in spdk_nvmf_tcp_listen /home/ziyeyang/spdk/lib/nvmf/tcp.c:680
Indirect leak of 48 byte(s) in 1 object(s) allocated from:
#0 0x7ffff6efcfe0 in calloc (/lib64/libasan.so.3+0xc6fe0)
#1 0x4a77b8 in spdk_posix_sock_create /home/ziyeyang/spdk/lib/sock/posix/posix.c:291
After checking the issue, it seems that we did not call
spdk_nvmf_transport_stop_listen when removing the subsystem listener.
And this patch can solve this issue.
Change-Id: Ic75d99cb0c6a3ba1c47ac79a2d8e3887b0f6b012
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447020
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: yidong0635 <dongx.yi@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The reservation holder may release the reservation on
a namespace, release notification feature is supported
in comming patches.
Change-Id: If5d3158e691fcc782f7cf0b67a326bf62edf0531
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/436938
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>
Unregistering by a host may cause a reservation held by the host
to be released. If a host is the last remaining reservation holder
or is the only reservation holder, then the reservation is released
when the host unregisters. This may occur with Acquire/preempt
and Register/unregister commands.
Change-Id: If59fe2fdaa69c8ad70f364618d6c281494ad6245
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/446821
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>
A registrant can obtain a reservation on a namespace by executing
acquire command. Acquire command is associated with specific namespace.
For now only Acquire and Preempt reservation acquire action is
supported, Preempt And Abort will be supported in future.
Change-Id: Ifcbb6b414827393ffc266ceada5982b743716321
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/436937
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>
Reservations can be used by two or more hosts to coordinate
acccess to a shared namespace, host must register to a namespace
prior to establishing a reservation. Unregistering by a host
may cause a reservation release, this feature will be supported
after reservation acquire patch.
Change-Id: Id44aa1f82f30d9ecc5999a2a9a7c20b2af77774a
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/436936
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>
Borrow the ideas from iSCSI and optimize
the nvme_tcp_build_iovecs function.
Change-Id: I19b165b5f6dc34b4bf655157170dec5c2ce3e19a
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/446836
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Not all RDMA drivers fail back the dummy recv and send operations that
we send to them when destroying a qpair. We still need to free the
resources from these qpairs to avoid eating up all of the system memory
after multiple connect and disconnect events. Since we won't be getting
any more completions, the best heuristic we can use is waiting a long
time and then freeing the resources.
qpair_fini is only called from the proper polling thread so we can safely
call process_pending to flush the qpair before closing it out.
Change-Id: I61e6931d7316d1e78bad26657bb671aa451e29f4
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/443057
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 <shuhei.matsumoto.xt@hitachi.com>
In the error path, we were first decrementing a variable and then
asserting that it must be >0. These operations should occur in the
opposite order.
Change-Id: I6cec544faf17bb75cbfca3d3a3c173dc5db14f99
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/446440
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: yidong0635 <dongx.yi@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
When the decision was made to uncouple the number of shared buffers from
the queue depth and allow the user to decide for themselves, the default
was also significantly lowered, which caused some issues when trying
torun performance tests (See https://github.com/spdk/spdk/issues/699).
While this is a user modifiable variable, it is still best to keep the
higher default value.
The original value was equivalent to max_queue_depth *
SPDK_NVMF_MAX_SGL_ENTRIES * 2 with the defaults for max_queue depth and
max_sgl_entries being 128 and 16 respectively. Hence 4096
fixes: 0b20f2e552d978d84780e0ab968bb7fa65f7707e
Change-Id: I809e97a10973093a2b485b85bca7160091166f70
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/446525
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>
I think this simplifies the process a little bit.
Change-Id: Icc87a59c9f6fd965ef35531975b7036d85c4bc95
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/445916
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>
We were only using one value from this array to tell us if the qpair was
idle or not. Remove this array and all of the functions that are no
longer needed after it is removed.
This series is aimed at reverting
fdec444aa8538aa6d782ad867821cf086e645e01 which has been tied to
performance decreases on master.
Change-Id: Ia3627c1abd15baee8b16d07e436923d222e17ffe
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/445336
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Since we no longer rely on the state queues for draining qpairs, we can
get rid of most of them. We cn keep just a few, and since we don't ever
remove arbitrary elements, we can use stailqs to perform those
operations. Operations on Stailqs carry about half the overhead as
operations on tailqs
Change-Id: I8f184e6269db853619a3581d387d97a795034798
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/445332
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>
This patch expose backend's bdev's PI setting to the corresponding
NVMe-oF Initiator by Ideintify command, and removes the check if
block size is 512 multiple.
These change enables NVMe-oF Initiator to send extended LBA payload.
Change-Id: Ia7aa8332d36f056872a515b6da90c83112edb909
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/445056
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>
If the current recv_state of qpair is same with the state to be set,
we will print error message. And checked the current code,
we should add a check to avoid this.
Change-Id: I49334f637c48e565e785d1fe6d0f000e18b2048a
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/445653
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: solve the coredump issue for the buffer
return later in spdk_nvmf_tcp_request_free_buffers.
If keep this statement, we cannot return the buffer
to the polling group.
Change-Id: Ib5c95ba54b37540950e654110fe6317cab507076
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/c/445435
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Error logs in nvmf_rdma_dump_request lead to report error about
address points to the zero page, add judgement to return.
this issue occurs in heavy load fio testing.
Change-Id: I50302be88b3af53f718e3800aa16df7c506ca4e8
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Reviewed-on: https://review.gerrithub.io/c/441110
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
From TP8000 spec 7.4.7,
"In response to a C2HTermReq PDU, the host shall terminate the connection.
If the host does not terminate the connection in an implementation specific
period that does not exceed 30 seconds, the controller may terminate the
connection on its own".
It means that the timeout is designed for: when the target is
sending out C2hTermReq, if the host does not terminate the connection,
the target should terminate the connection.
PS: For detecting the malicous connection without sending response
(such as no response of R2T PDU) which should be another patch.
Change-Id: I586dbb235d99aeab5d748a19b9128cd8b0cef183
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/c/440831
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: Jim Harris <james.r.harris@intel.com>
The persistence feature can't support for now, but as the features
are mandatory for reservation, so add the two function here, and
we can enable it with future patches for power loss persist feature.
Change-Id: Ic358eda00058809bbfd6984b0861f8b6b5aabecd
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/438213
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
When this structure was brought up to the generic layer, the tcp
transport was using max_io_size and the rdma transport was using
io_unit_size. In the interest of conserving memory, we should use
io_unit_size instead of max_io_size.
Change-Id: I2633306fcbfd8c3d557445959c745cb2d9a0999e
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/442778
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
We should never be going over these limits in the respective transports,
but add asserts to check this during testing.
Change-Id: Ifcaa82ccf58546a38020b31df54ee5d1d9822b8b
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/442777
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This intermediate state is unused and meaningless. the qpair transitions
into this state right before calling a synchronous operation and then
transitions to active as soon as that operation completes successfully.
If the operation did not complete successfully, we were leaving qpairs
in this weird intermediate state when for all intents and purposes they
had reverted to an uninitialized state. Keeping qpairs in the
uninitialized state until they have been added to a poll group creates a
meaningful distinction between states that can be actionable from the
transport level.
Change-Id: I6de9bc424b393b6fff221aa2f4212aaa91488629
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443471
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>
Connections in the uninitialized state haven't been added to a poll
group yet, so submitting dummy requests to them will be pointless since
they will never be polled. We need to reject the connection and destroy
the qpair immediately.
Change-Id: Id5dd711882e1ae7c13ae32c06da2285186b00a1b
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443470
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 there are multiple events/conditions that can trigger a qpair
disconnection, we need to funnel them to a single point of entry. If
more than one of these events occurs, we can ignore all but the first
since once a disconnect starts, it can't be stopped.
Change-Id: I749c9087a25779fcd5e3fe6685583a610ad983d3
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443305
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
For devices that support fewer SGE elements than our default values, we
need to adjust the I/O unit size so that we don't ever try to submit
more SGLs than we are allowed to.
Change-Id: I316d88459380f28009cc8a3d9357e9c67b08e871
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/442776
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>
This value was not being decremented when we got SEND completions for
write operations because we were using the recv send to indicate when we
had completed all writes associated with the request. I also erroneously
made the assumption that spdk_nvmf_rdma_request_parse_sgl would properly
reset this value to zero for all requests. However, for requests that
return SPDK_NVME_DATA_NONE rom spdk_nvmf_rdma_request_get_xfer, this
funxtion is skipped and the value is never reset. This can cause a
coherency issue on admin queues when we request multiple log files. When
the keep_alive request is resent, it can pick up an old rdma_req which
reports the wrong number of outstanding_wrs and it will permanently
increment the qpairs curr_send_depth.
This change decrements num_outstanding_data_wrs on writes, and also
resets that value when the request is freed to ensure that this problem
doesn't occur again.
Change-Id: I5866af97c946a0a58c30507499b43359fb6d0f64
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443811
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The typical rdma qpair disconnect function goes through the function
_nvmf_rdma_disconnect_retry. When this function was introduced, it was
discovered that we could receive a qpair disconnect event for a given
qpair before that qpair had been assigned to a poll group. In order to
ensure that the disconnect procedure completed properly, we waited on
the current thread in _nvmf_rdma_disconnect_retry for the qpair to be
assigned a poll group before we finally disconnected. see rdma.c:2250.
Since _nvmf_rdma_disconnect_retry was not necessarily called from the
poll group's thread, we relied upon the assumption that the group
variable would never be set back to NULL. See the comment on rdma.c:
2243.
However, in _spdk_nvmf_qpair_destroy we were setting the group back to
NULL. This operation can result in the following set of operations
across multiple threads that prevent a qpair from ever being fully
destroyed.
1. thread 1: receive a disconnect event - call nvmf_rdma_disconnect
2. thread 1: from nvmf_rdma_disconnect call
spdk_nvmf_rdma_qpair_inc_refcnt - setting rqpair->refcnt to 1.
3. thread 2: call spdk_nvmf_rdma_poller_poll.
4. thread 2: in spdk_nvmf_rdma_poller_poll reap a completion with an
error status which causes us to call spdk_nvmf_qpair_disconnect -
rdma:2846
5. thread 2: spdk_nvmf_qpair_disconnect calls _spdk_nvmf_qpair_destroy which sets
qpair->group = NULL
6. thread 1: from nvmf_rdma_disconnect we call
_nvmf_rdma_disconnect_retry which checks if qpair->group == NULL. If
that is the case, we assume that the qpair has not been assigned a group
yet and send ourself a message to call _nvmf_rdma_disconnect_retry again. see rdma.c:2253
7. thread 2: from _spdk_nvmf_qpair_destroy we call
spdk_nvmf_transport_qpair_fini which results in a call to
spdk_nvmf_rdma_close_qpair. which sends dummy send and recvs to the
qpair.
8. thread 2: we call poller_poll and get completions for both the send
and recv dummy requests. This results in a call to
spdk_nvmf_rdma_qpair_destroy.
9. thread 2: spdk_nvmf_rdma_qpair_destroy checks rqpair->refcnt and when
it sees that it does not = 0 (see step 2 above) it returns without
freeing the resources. see rdma.c:629
10. thread 1: we keep churning in _nvmf_rdma_disconnect_retry sending
ourselves messages because rqpair->group is going to be null. Thread 1
never reaches line 2257 where it sends a message to call
_nvmf_rdma_qpair_disconnect. _nvmf_rdma_qpair_disconnect is the function
that decreases the rqpair->refcnt and allows us to make forward progress
on destroying the qpair.
I encountered this issue while trying to disconnect from our target
using the kernel initiator with an x722 NIC. I think the timing on this
bug comes out with that specific configuration because come of the calls
in the disconnect path on thread 1 fail causing it to take longer giving
a chance to the second thread to delete the qpair.
There are really two issues at play here. We don't have a single point
of entry for disconnecting RDMA qpairs, and we rely on the qpair->group
variable never being set back to NULL. This patch addresses the second
issue, and the next patch in the series addresses the first.
Change-Id: I65395d0bbb67edfa7bad2ddc70906606c3d83781
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443304
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: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
This doesn't fix any bug, but it makes more sense to leave the qpair
in the NVME_TCP_PDU_RECV_STATE_AWAIT_PDU_READY state until it
receives at least one byte.
Change-Id: Ic5f34a733a80b58f65a1334fae7e07dbded2b3d0
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/441811
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
The management channel was used in the RDMA transport prior
to the introduction of poll groups and made its way over to
the TCP transport when it was written. Eliminate it in favor
of just using the poll group.
Change-Id: Icde631dd97a6a29190c4a4a6a10a0cb7c4f07a0e
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/442432
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
