The only reason the qpair ever uses the port is to get to
the device attributes so skip the middle man.
Signed-off-by: Seth Howell <seth.howell@intel.com>
Change-Id: Ib14a97ceaa0c49176027d6c35c5cb2787a845cc1
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/478961
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: 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>
The call to update_ibv_state could result in a segfault if the other
thread had already freed the qp and was just spinning on handling the
rdma event. By not updating the qpair state here, I don't think that we
lose any information about the qpair state. Especiallyy since just a
little bit later we update the qpair state to be in error.
There is nothing in the man pages about the cm events changing the ib
state although I imagine they are closely related. I just say that
because I believe that's why the update was originally in that spot.
fixes: GitHub issue #1110
Change-Id: I3f87ff009bc2019464ed7c6920dd71e2b286b3fd
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477877
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
RDMA qpair might be destroyed by defunct timer, so it can have
active recv elements in incoming_queue. This queue is cleaned
incorrectly, so recv element for the destroyed qpair still may
be presented in the queue and be processed later. That leads
to undefined behaviour.
Fixes#1086
Change-Id: Ieae186b2d2dce4ec88ab886b26165f6ef98e8d05
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/477957
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
The following scenario might occur when nvmf_tgt is stopped:
1. nvmf_tgt receives SIGINT, changes state to NVMF_TGT_FINI_STOP_SUBSYSTEMS
2. In this state nvmf_tgt stops all subsystems and disconnects associated qpairs
3. In the case of RDMA qpair, its state will be changed to IBV_QPS_ERR.
Once qpair changes the state to IBV_QPS_ERR, RDMA device generates
LAST_WQE_REACHED event when there are no more WQE that can be sonsumed
from the SRQ by this qpair.
4. When all subsystems are stopped, some of qpair may still be alive since they
haven't received LAST_WQE_REACHED event yet.
5. nvmf_tgt stops all poll groups and forcefully destroyes any qpairs linked to them.
6. At this moment LAST_WQE_REACHED event might be generated and received in another thread.
Handler of this event sends a message with a pointer to qpair. The qpair itself may already
be destroyed.
7. Thread that owned qpair receives a message (LAST_WQE_REACHED) with a pointer to alredy destroyed qpair and
destroyes it for the second time when all pointer are invalid.
ibv events related to qpair should be handled by the thread that
owns this qpair. This commit adds a new structure that describes
ibv event, helper functions for sending the event and a list
of events per rdma qpair; add syncronization for LAST_WQE_REACHED event
Fixes#1075
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: I22bff89741708df2518760934ecb4e33fad49473
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/476712
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Community-CI: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell@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>
NVMF_REQ_MAX_BUFFERS is defined in nvmf_internal.h and not used in rdma
source code.
Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: I50f24c8fc4ea773378418f7803361d8592f961ae
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475529
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
It is valuable to have more detail status instead
SPDK_NVME_SC_INTERNAL_DEVICE_ERROR.
Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: Ifd003b490a7ae9af017645c97636ceaf2f93d4b0
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/476634
Community-CI: Broadcom SPDK FC-NVMe 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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
This issue was found by code inspection.
It only occurs when pdk_nvmf_transport_poll_group_create()
itself calls spdk_nvmf_transport_poll_group_destroy().
Other transports at this time do not show this issue.
spdk_nvmf_rdma_poll_group_destroy() depends on
rgroup being assigned a transport, which is only being
done on generic nvmf layer using
spdk_nvmf_transport_poll_group_create()
after successful spdk_nvmf_rdma_poll_group_create().
When failure occurs during create, such assignment was not
performed so any references to rtransport will segfault.
Reported-by: Jacek Kalwas <jacek.kalwas@intel.com>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Id54482d562bd6d7c71371306cf1de93bc05f4e8a
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/475002
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>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
This patch adds the following:
1. Change signature of nvmf_rdma_fill_wr_sge - pass ibv_send_wr ** in
order to update caller's variable, add a pointer to the number of extra WRs
2. Add a check for the number of requested WRs to nvmf_request_alloc_wrs
3. Add a function to update remote address offset
Change-Id: I26f6567211b3ebfdb4981a7499f6df25e32cbb3a
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470475
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>
RDMA WR has a predefined number of SGL entries (16) and with new logic added to
support DIF the number of entries required to process the request may exceed
this limit since IO unit buffers might be divided into several parts to remove
metadata chunks from the transmition. This change calculates and allocates
required number of WRs.
Error handling section in spdk_nvmf_rdma_request_fill_iovs has been updated
to free allocated WRs
Change-Id: Ie5d659d8305a454949827d1f4aff6d871b7e825d
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470474
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 change helps to avoid passing the number of additional WRs to
spdk_nvmf_rdma_request_fill_iovs in the following commits and minimizes
changes in spdk_nvmf_rdma_request_parse_sgl
Change-Id: Id530d0996af661051d94930e3f776bad2dcc5771
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470473
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>
It can be useful for passing additional information about nvmf
target to a handler for new nvmf connections. Context can be
stored in globals as it is currently done in nvmf code. However
in case of multiple targets or languages where accessing global
state is challenging (i.e. Rust), this becomes inconvenient.
Change-Id: Ia6a2fdba4601531822b3e5fda7ac5ab89d46f6c5
Signed-off-by: Jan Kryl <jan.kryl@mayadata.io>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469263
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Use this function in nvmf_request_alloc_wrs and nvmf_rdma_setup_request
to eliminate code duplication
Change-Id: I771e0e899043049c90298e050d4353145e36f0d1
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/471034
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>
Delete a pointer to spdk_nvme_cmd as it is not used directly
Change-Id: I36a6a6d95c0707f446a0797a55a9e60c62f9503c
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470472
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>
Return -1 from spdk_nvmf_rdma_request_parse_sgl in the case of -EINVAL since 0 value
returned by spdk_nvmf_rdma_request_parse_sgl is treated as no memory case
Change-Id: I536592260a3bb658a1a4bc3a79c5b37fbacd3edc
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/470471
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>
The type of iovcnt of struct spdk_nvmf_request is uint32_t, and so
change the type of iovpos of struct spdk_nvmf_rdma_request from int
to uint32_t.
iovpos of struct spdk_nvmf_rdma_request is only incremented and
accessed. It is not used for comparison.
So to avoid rerunning CI, this fix is appended to the patch series.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I65fc5dfb7067f6e8f7cb1e555f010b246a72ec32
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469660
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
nvmf_rdma_fill_wr_sge() gets pointer to iovec at its head, but
nvmf_rdma_fill_wr_sgl() can pass it to nvmf_rdma_fill_wr_sge()
simply.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I16176d5d36ca9daf57640bfcbc49dfbf997afe54
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469639
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Pointers to struct spdk_nvmf_request and struct ibv_send_wr are
used in many lines of spdk_nvmf_rdma_request_parse_sgl().
Caching and using them simplifies and improves readability a little
for spdk_nvmf_rdma_request_parse_sgl().
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ib000c9d4e7fb7bb415f4ac4622b32b12cc787c80
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469537
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
spdk_nvmf_request_get_buffers()/_multi() may return not only -ENOMEM
but also -EINVAL, but spdk_nvmf_rdma_request_fill_iovs() and
nvmf_rdma_request_fill_iovs_multi_sgl() had returned -ENOMEM
regardless of the actual return value. Fix them in this patch.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ic19593ffa9c0731f63d198d4ae16feb3bb47f57c
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469378
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This patch is the end of the effort to unify buffer allocation
among NVMe-oF transports.
This patch aggregates multiple calls of spdk_nvmf_request_get_buffers()
into a single spdk_nvmf_request_get_buffers_multi().
As a side effect, we can move zeroing req->iovcnt into
spdk_nvmf_request_get_buffers() and spdk_nvmf_request_get_buffers_multi()
and do it in this patch.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I728bd330a1f533019957d58e06831a79fc17e382
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469206
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This patch is close to the end of the effort to unify buffer allocation
among NVMe-oF transports.
Merge each transport's fill_buffers() into common
spdk_nvmf_request_get_buffers() of the generic NVMe-oF transport.
One noticeable change is to set req->data_from_pool to true not in
each specific transport but in the generic transport.
The next patch will add spdk_nvmf_request_get_multi_buffers() for
multi SGL case of RDMA transport.
This relatively long patch series is a preparation to support
zcopy APIs in NVMe-oF target.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Icb04e3a1fa4f5a360b1b26d2ab7c67606ca7c9a0
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469205
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This patch merges nvmf_rdma_fill_wr_sgl_with_md_interleave()
into nvmf_rdma_fill_wr_sge(), and then removes
nvmf_rdma_fill_wr_sgl_with_md_interleave().
In nvmf_rdma_fill_wr_sgl(), pass DIF context, remaining data block
size, and offset to nvmf_rdma_fill_wr_sge() in the while loop.
For non DIF case, initialize all of them by zero.
In nvmf_rdma_fill_wr_sge(), classify non-DIF case and DIF case
by checking if DIF context is NULL.
As a minor change of wording, remaining is sufficiently descriptive
and simpler than remaining_io_buffer_length and so use remaining.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I55ed749c540ef34b9a328dca7fd3b4694e669bfe
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469350
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This patch separates filling wr->sg_list from filling req->iov
in nvmf_rdma_fill_buffers_with_md_interleave() and create an new helper function
nvmf_rdma_fill_wr_sgl_with_md_interleave() to fill wr->sg_list by adding iovcnt to
struct spdk_nvmf_rdma_request.
The subsequent patches will merge nvmf_rdma_fill_buffers() into
spdk_nvmf_request_get_buffers().
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I03206895e37cf385fb8bd7498f2f4a24797c7ce1
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469204
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This patch separates filling wr->sg_list from filling req->iov
in nvmf_rdma_fill_buffers() and create an new helper function
nvmf_rdma_fill_wr_sgl() to fill wr->sg_list by adding iovcnt to
struct spdk_nvmf_rdma_request.
The next patch will do the same change for
nvmf_rdma_fill_buffers_with_md_interleave().
The subsequent patches will merge nvmf_rdma_fill_buffers() into
spdk_nvmf_request_get_buffers().
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ia4cdf134df39997deb06522cbcb6af6666712ccc
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469203
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
When buffer replacement succeeds, only iov_base has to be updated.
This change is small but will be helpful to disaggregate buffer
allocation and filling WR SGL.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ifc72fd783b515dfaecac04939c183097f939e29b
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469202
Community-CI: Broadcom SPDK FC-NVMe 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: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Factor out setup WR operation from nvmf_rdma_fillbuffers_with_md_interleave()
into a function nvmf_rdma_fill_wr_with_md_interleave().
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I92689daa7dcc93aaa68ecf5706d4e1b75d7fabae
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469066
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This patch
- applies nvmf_rdma_get_lkey(),
- changes pointer to struct iovec from iovec to iov,
- changes pointer to ibv_sge from sg_list to sg_ele, and
- passes DIF context instead of decoded data block size and metadata size
- use cached pointer to nvmf_request to call
- change the ordering of operations to setup sg_ele slightly
for nvmf_rdma_fill_buffers_with_md_interleave().
Name changes are from the previous patch.
They are for consistency with nvmf_rdma_fill_buffers() and a
preparation for the next patch.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I942fb9d07db52b9ef9f43fdfa8235a9e864964c0
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469201
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This reduces the diff in the next patch.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I85dccdc1a1a5a51777934121f50a6af97feda5a5
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469480
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Factor out getting lkey and checking translation length in
nvmf_rdma_fill_wr_sge() into a function nvmf_rdma_get_lkey().
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I495ba9ae4a48b4aa7dc35a0bd72708753846dfdc
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469349
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Cache pointers to iovec and ibv_sge at the head of the function
and use them throughout.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I493759bf3989ced4390d077280cd44c122847d08
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469348
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Factor out setup WR operation from nvmf_rdma_fill_buffers() into a
function nvmf_rdma_fill_wr_sge().
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I813f156b83b6e1773ea76d0d1ed8684b1e267691
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468945
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
The subsequent patches unifies getting buffers, filling iovecs, and
filling WRs in a single API. This is a preparation.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I077c4ea8957dcb3c7e4f4181f18b04b343e9927d
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468953
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
This is a preparation to unify getting buffers, filling iovecs,
and filling WRs in a single API in RDMA transport and then to unify
it among RDMA, TCP, and FC transport.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ia69d4409c8cccaf8d7298706d61cd4e2d35e4406
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468944
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
This patch makes multi SGL case possible to call spdk_nvmf_request_get_buffers()
per WR.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I977ebb0c6b2a67218c9b6fc20dc26a93a6ec770b
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468943
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
This patch makes multi SGL case possible to call spdk_nvmf_request_get_buffers()
per WR.
This patch has an unrelated fix to clear req->iovcnt in
reset_nvmf_rdma_request() in UT. We can do the fix in a separate patch
but include it in this patch because it is very small.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: If6e5af0505fb199c95ef5d0522b579242a7cef29
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468942
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This patch matches the ordering of single SGL case and multi SGL
case for parsing SGL.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Iea026b48e8957e140b71db7afaf8aca88634dc33
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468941
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
In nvmf_rdma_requst_fill_iovs_multi_sgl(), length of descriptors
are accumulated into req->length. However, req->length was not cleared
when nvmf_rdma_fill_buffers() fails in the middle. This patch fixes it.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I80a55d90d09c8af46d570e017d342afd69f41996
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469199
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: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
wr->num_sge has to be used in spdk_nvmf_rdma_request_fill_iovs(),
and memset() can be used instead of clearing each variable.
Besides, holding cached pointer to the current WR simplifies the
code a little and so is done together in this patch.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Iebda158f85e3a0e3046686f76991217fa7297c24
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/469198
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
The current connection scheduling mechanism (RoundRobin) doesn't take into account the qpair type and assigns each new qpair to the next poll group. As a side effect there might occur a disbalance when some poll group handles more IO qpairs than others. In RDMA transport it is possible to get the qpair type before the controller creation using a private data from the rdma_cm event, this allows to schedule admin and IO qpairs in the balanced way.
Change-Id: I90c368a41c4cd0f5347a83cab7511e4494f05b29
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468993
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>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Operations with poll groups list must be protected by rtransport->lock.
Make rtranposrt->lock recursive to avoid unnecessary mutex operations when
the poll group is being destroyed within spdk_nvmf_rdma_poll_group_create
Change-Id: If0856429c10ad3bfcc9942da613796cc86d68d8d
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468992
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.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>
This issue can be reproduced on fedora30.
Add assert here is enough to fix this kind of warning.
Error log:
rdma.c:3070:20: warning: Access to field 'data_buf_pool' results in a
dereference of a null pointer (loaded from field 'transport')
spdk_mempool_put(group->transport->data_buf_pool, buf);
^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
1 warning generated.
This is to fix issue #965.
Change-Id: Ifb742ab914ee9a0381dca0bb769ba8aa564c816f
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468908
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Update transaction length wrt to medata size
Change buffers handling in the case of enabled DIF - add function nvmf_rdma_fill_buffer_with_md_interleave to split SGL into several parts with metadata blocks between them in order to perform RDMA operation with appropriate offsets
Add DIF generation before executing bdev IO operation
Add parsing of DifInsertOrStrip config parameter.
Since there is a limitation on the number of entries in SG list (16), the current approach has a limitation on the max transaction size which depends on the data block size. E.g. if data block size is 512 bytes then the maximum transaction size will be 512 * 16 = 8192 bytes.
In adiition, the size of IO buffer (IOUnitSize conf param) must be aligned to metadata size for better perfromance since metadata is treated as part of this buffer. E.g. if the initiator uses transaction size = 4096, data block size on nvme disk is 512 then IO buffer size should be aligned to (512 + 8) which is 4160. In other case an extra IO buffer will be consumed which will increase the number of entries in SGL and in iov.
Change-Id: I7ad2270fe9dcceb114ece34675eac44e5783a0d5
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465248
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Now code always return 0 , do this like nvme_rdma_mr_map_notify.
That callback can get the right return.
Change-Id: Ief2924e14321b2062f6001e7ae3f50d507206594
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/468663
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: Changpeng Liu <changpeng.liu@intel.com>
It is a very rare thing for a buffer to be split over two memory
regions. In fact, it is only possible in dpdk versions where
--match-allocations is not passed as a startup parameter to dpdk but
dynamic memory allocation is enabled.
By adding a small helper function, we avoid failing an I/O because it
was assigned one of these improperly aligned buffers. Also, we try to
remove the buffer from circulation so that it doesn't get picked up
again by another request.
Also, add a unit test to catch this case.
Change-Id: Ia09865c2f77160a960571665b29c4533b11758ae
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/467446
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: Paul Luse <paul.e.luse@intel.com>
Just cleaning up a few things like variable names and ordering to make
the whole function more readable.
Change-Id: I1503cdb43ddd73e063d6e57e9ff0cf2a06e79728
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/467445
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
IB Architecture Specification vol.1 rel.13. in ch.10.3.1 "QUEUE PAIR
AND EE CONTEXT STATES" suggests the following destroy procedure for
QPs associated with SRQ:
- Put the QP in the Error State;
- wait for the Affiliated Asynchronous Last WQE Reached Event;
- either:
* drain the CQ by invoking the Poll CQ verb and either wait for CQ
to be empty or the number of Poll CQ operations has exceeded CQ
capacity size; or
* post another WR that completes on the same CQ and wait for this WR
to return as a WC;
- and then invoke a Destroy QP or Reset QP.
Without the drain step it is possible that LAST_WQE_REACHED event is
received and QP is destroyed before the last receive WR completion is
polled from the CQ.
In SPDK there is no risk of resource leakage in this case. So, instead
of draining we can destroy QP and then just ignore receive completions
without QP and post receive WRs back to SRQ.
Fixes#903
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: Ice6d3d5afc205c489f768e3b51c6cda8809bee9a
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465747
Reviewed-by: Seth Howell <seth.howell@intel.com>
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>
This unifies buffer management among transports further and is a
preparation to make buffer allocation asynchronous.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I8c588eeac4081f50fe32605feb7352f72c628d95
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466847
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Most variables related with I/O buffer are in struct spdk_nvmf_request
now. So we can pass nvmf_request instead of nvmf_rdma_request to
nvmf_rdma_request_fill_buffers and do it in this patch.
Additionally, we use the cached pointer to nvmf_request in
spdk_nvmf_rdma_request_fill_iovs which is the caller to
nvmf_rdma_request_fill_buffers in this patch.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ia7664e9688bd9fa157504b4f5075f79759d0e489
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466212
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: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Use spdk_nvmf_request_get_buffers() and spdk_nvmf_request_free_buffers(),
and then remove spdk_nvmf_rdma_request_free_buffers() and
nvmf_rdma_request_get_buffers().
Set rdma_req->data_from_pool to false after
spdk_nvmf_request_free_buffers().
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ie1fc4c261c3197c8299761655bf3138eebcea3bc
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465875
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This is a prepration to unify buffer management among transports.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I6b1c208207ae3679619239db4e6e9a77b33291d0
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466002
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This is a preparation to unify buffer management among transports.
struct spdk_nvmf_request already has SPDK_NVMF_MAX_SGL_ENTRIES (16) * 2
iovecs. Hence incresing the number of buffers twice will be no problem.
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Idb525abbf35dc9f4b8547b785b5dfa77d106d8c9
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465873
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
One of stop conditions in data WR release function was wrong. This
can cause release of uncompleted data WRs. Release of WRs that are
not yet completed leads to different side-effects, up to data
corruption.
The issue was introduced with send WR batching feature in commit
9d63933b7f.
This patch fixes stop condition and contains some refactoring to
simplify WR release function.
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: Ie79f64da345e38038f16a0210bef240f63af325b
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466029
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
From rdma_cma.h "Users must destroy any QP associated with an
rdma_cm_id before destroying the ID."
Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: I5ed0c25221c5401cdde8b31a4e217b9d79e7caaa
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464290
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
We should be checking directly against the base of the iov when doing
memory map translations. The current behavior is to check against the
starting address of the buffer which is a close address, but not exactly
the same.
Change-Id: I7f65224a6836a814708438f2866d84ae22882216
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463893
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: <jiandong.zheng@broadcom.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
In case of failure during resource allocation within poll_group_create
there is a lack of return statement which could lead to NULL ptr
dereference.
Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: I84abe64a1843117d76b97e62656bdfc4fe2b35d8
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463195
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
NVMf statistics functions use spdk_get_io_channel function to get a
poll group. It increases reference counter in io channel and causes
problems on application exit. spdk_put_io_channel calls were added to
release the channel.
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: I832d1eae346c3bc3858ed0ed063ff7a7a897a2f5
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463389
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>
This patch adds measurement of time request spends from the moment it
was polled till completion.
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: I1fcda68735f2210c5365dd06f26c10162e4ddf33
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/445291
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 patch adds statistics for pending state in NVMf RDMA subsytem
which may help to detect lack of resources and adjust configuration
correctly.
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: I9560d931c0dfb469659be42e13b8302c52912420
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452300
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
RDMA polling statistics: number of polls and number of completion
entries returned.
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: Iabcf2cb6f6a35f595b89b58cdfcd177a637dda13
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/445289
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 patch adds transport part to nvmf_get_stats RPC method and basic
infrastructure to report NVMf transport specific statistics.
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: Ie83b34f4ed932dd5f6d6e37897cf45228114bd88
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452299
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>
qpair structure is freed and an error code is returned to the caller in the case of failed qpair initialization in function spdk_nvmf_rdma_qpair_initialize (e.g. bad return value of rdma_create_qp).
The return code is handled by nvmf_tgt_poll_group_add function which destroys the qpair for the second time.
This patch fixes#857
Change-Id: I0773652ecccbbd634ad272106e0a93c1e591d7d2
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462011
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Lorne Li <lorneli@163.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Func spdk_nvmf_rdma_destroy_defunct_qpair is a "last chance option"
to destroy qp manually if some driver/hardware doesn't drain qp's
failed wr as expected.
There's a probability that ibv_poll_cq polls wr of the destoryed qp
after spdk_nvmf_rdma_destroy_defunct_qpair's execution. Although in
practice the risk of this situation is minimal(if not non-existent),
add a log here so that we could detect this situation easily.
Change-Id: Ifa9534397513bcea34c18fbb8168eef8f53599c1
Signed-off-by: lorneli <lorneli@163.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462441
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@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>
Currently rqpair will be destroyed directly in ibv_poll_cq path
if it has been drained, regardless of whether there are outstanding
I/Os issued to bdev layer. So after outstanding I/Os completing,
spdk_nvmf_rdma_close_qpair will be called from nvmf layer, accessing
a destroyed qp.
This path defers qp destruction in nvmf_rdma_destroy_drained_qpair
func until nvmf layer closes qp.
Fixes 851
Change-Id: I8bcce66f8053ddb105702ac603d5d73af54bdcfc
Signed-off-by: lorneli <lorneli@163.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461237
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Seth Howell <seth.howell@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>
spdk_dma_*malloc() is about to be deprecated.
Change-Id: I5bcac50baca785255eb068086e67c07d120b042f
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459432
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
No need to have it under lock. Additionally in case of failure
there was a lack of rdma_destroy_id(). This is addresed within this
change as well.
Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: Idbb36d51ad4ef7ef81051463f56efc87ef00c966
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462054
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
In case of failure during pd or map allocation freeing list of devices
was missing.
Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: If62f7b072f3894fd1a7e856c19b4ea51646dd20e
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462079
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
In case of pd allocation by nvmf hooks there is a lack of null
check as oposed to pd allocation by ibv_alloc_pd.
Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: Iead6e0332bdee3da4adb6e657af298215c4e2196
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461576
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Vhost testing crashed from Nightly testing, because a member
access within null pointer of type 'struct ibv_send_wr'.
Change-Id: If8f34f23864883ea73516d2d1fe3b30137c04316
Signed-off-by: Hailiang Wang <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/458913
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>
Unsetting this flag will decrease the number of WRs retrieved during CQ polling and will decrease
the oeverall processing time. Since RDMA_WRITE operations are always paired with RDMA_SEND (response),
it is possible to track the number of outstanding WRs relying on the completed response WR.
Completed WRs of type RDMA_WR_TYPE_DATA are now always RDMA_READ operations.
The patch shows %2 better peformance for read operations on x86 machine. The performance was measured using perf with the following parameters:
-q 16 -o 4096 -w read -t 300 -c 2
with nvme null device, each measurement was done 4 times
avg IOPS (with patch): 865861.71
avg IOPS (master): 847958.77
avg latency (with patch): 18.46 [us]
avg latency (master): 18.85 [us]
Change-Id: Ifd3329fbd0e45dd5f27213b36b9444308660fc8b
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/456469
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This matches the Linux kernel target. Users can
still decrease this default when creating the
transport (i.e. -p option for nvmf_create_transport
in rpc.py).
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Icad59350a2cd35cfc4ad76d06399345191680c05
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/454820
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
We could run into issues with this if we were using an arbitrarily large
amount of cores to run SPDK.
Change-Id: Ia7add027d7e6ef1ccb4a69ac328dbdf4f2751fd8
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452250
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 will help us not iterate through the whole list of connections when
only some of them have pending recvs.
Change-Id: I681bc98befbdda4e77ef333b7a086c08b2708eb3
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/449266
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>
This will help save MMIO overhead. Especially in the SRQ case.
Change-Id: I6fb70cf6de4763450f97961f41ccdce3acec2e63
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/449265
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>
By creating a list of qpairs, we can avoid looping over every connected
qpair to process sends each time we poll.
Change-Id: If24bbc363176f52fbfb756d56719edd885a21a11
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/449264
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>
By batching ibv sends each time we poll, we can reduce the number of
MMIO writes that we do.
Change-Id: Ia5a07b0037365abfa8732629c34d34a9ed49ac70
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/449253
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>
There are cases where srq can be a detriment. Add a flag to allow users
to disable srq even if they have a piece of hardware that supports it.
Change-Id: Ia3be8e8c8e8463964e6ff1c02b07afbf4c3cc8f7
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452271
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>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This restriction helps reduce the amount of padding when
printing out the event trace, allowing it to fit in a
small number of columns.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ifa31e5a6967c7b9bc7028069effb71533f80596f
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452736
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This was not used by any of the trace register descriptions.
Let's remove it rather keeping it around if we don't need it.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Idda809e2911db5be555ff6aa13695484a14bf665
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452734
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: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
We can use the rpoller->srq to check if a qpair is valid when processing
recv completions.
Change-Id: I6aa360adc48a3312ddcf79f10e2a65b502a7314f
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452247
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: Jim Harris <james.r.harris@intel.com>
Mempools are based off of a ring structure which allocates its elements
as a power of two. It also only exposes n-1 elements to the user. So
when we create a mempool with 2^n elements in it, we have to allocate a
ring with 2^n+1 entries. By decreasing the number of elements in these
key mempools by 1, we can save a decent amount of memory.
Change-Id: I942c9dd4cf59096969bc2559fb46fd2084a07f09
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448875
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
It used to be that we would get async events very infrequently. However,
with the introduction of SRQ, this number has gone up tremendously.
Change the way we report our these events so that we don't spam/confuse
people running the target.
Change-Id: I33070281fa854cbc17784d61bbbb870196ca8780
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452159
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>
If there are outstanding recvs for a qpair when it is destroyed, we need
to clear the qpair from it before reposting it. Otehrwise, we have a
potential heap-use-after-free of double free (depending on whether the
recv completion is in error state or not).
See github issues #730
Change-Id: Ic2009c761cbcc5e89174f62fbd0872d0489c67ca
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452122
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>
We were setting this value in the target from our initiator, but it
turns out the rdma_conn_params struct is responsible for setting the
opposite side so we need to add it in the target side when accepting
connections.
Also, add a test to demonstrate target functionality when we overwhelm
the SRQ. It is useful to note that performance really tanks when you
start overwhelming the srq so it may be useful to use this test case to
check performance gains in edge cases over time.
Change-Id: Iac541bd9fc1d82eca9f21e7abc3f625663a6c460
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/451678
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 incrementing over the end of the descriptor list and assigning
undefined values to the rsp opcode in SEND_WITH_INVAL case. We were only
hitting this error when mixing sgl and inline requests in the same
workload. We were just by chance hitting a four bit value that was set
to all 1s from the in capsule data from the last request.
Change-Id: Ied06356f3d22fa34a2cd869dfad6bdca8720791d
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450873
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>
This was not being properly set in the multi-sgl path.
Also add a verification step to the fio configuration file to prevent
against future regressions.
Change-Id: I510b6acd92bc2fbc9b6fbec1d59945cc53584ad3
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450305
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>
Rqpair qp and resources maybe not be created, if rqpair fail to
initialise. For example, in function new_qpair, the code run to
spdk_nvmf_qpair_disconnect, but rqpair is initialised in
poll_group_add.
Fix#557 segmentaion fault(core dump)
Change-Id: I1892e6d13e2d53dd5a7c4856d775f9b3b85da961
Signed-off-by: JinYu <jin.yu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450986
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Hailiang Wang <hailiangx.e.wang@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
If rsp->status.sc != SUCCESS and xfer == DATA_CONTROLLER_TO_HOST,
We would not send the data WR, so clean the num_outstanding_data_wr.
Fix#728
Change-Id: I32259788e495ed76f8f02a9d871bd56356d93dc4
Signed-off-by: JinYu <jin.yu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450726
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@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>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Should speed up operations, and allows us to remove the 16 byte link
object from the request structure.
Change-Id: Ie62df1f44d22580a7a7ae41c498295841d1e3064
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448080
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
