It's useful to add these APIs.
spdk_copy_iovs_to_buf and spdk_copy_buf_to_iovs.
It prepares that other ones can call these.
We don't need to define them in static state
repeatedly.
And add corresponding unit tests.
Change-Id: Ife40fec8d047a48af67b04e6c055e4932282abfb
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12075
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Calculation of the ANA log page size should use the
identify ctrl MNAN field
(maximum number of allowed namespaces)
not the NN (maximum valid nsid value).
An ANA-enabled controller must have a non-zero MNAN value,
see NVMe Base Specification, Figure 251,
therefore nvme_ctrlr_init_ana_log_page() may safely use MNAN.
Since NN might be much higher than MNAN,
ANA log size based on NN may results in a very large
log page and cause a failure to get ANA log,
e.g. if it is larger than the controller's MDTS.
Fix: replace cdata->nn with cdata->mnan
in nvme_ctrlr_init_ana_log_page()
Signed-off-by: Anton Eidelman <anton@lightbitslabs.com>
Change-Id: I2a522dca833a27dddad25848d7688efa23d23091
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/13039
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Jacek Kalwas <jacek.kalwas@intel.com>
DPDK CFLAGS get put into CFLAGS in mk/cc.flags.mk,
which for system package installed DPDK will include
extra paths like /usr/include/<arch-3-tuple>/dpdk.
If a Makefile adds its own CFLAGS before including
the .mk fragment that pulls in these CFLAGS, we won't
actually get those cc.flags.mk applied since they
are defined with ?=.
This may need to be revisited - using ?= for these
has evolved through several iterations of our SPDK
configured flag files - starting with commit
08ec96eb. But for now, let's just fix these few
Makefiles.
Fixes issue #2548.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I9863db1b37b31907b4088f58cc13b81ed1bb8632
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12982
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Many open source projects have moved to using SPDX identifiers
to specify license information, reducing the amount of
boilerplate code in every source file. This patch replaces
the bulk of SPDK .c, .cpp and Makefiles with the BSD-3-Clause
identifier.
Almost all of these files share the exact same license text,
and this patch only modifies the files that contain the
most common license text. There can be slight variations
because the third clause contains company names - most say
"Intel Corporation", but there are instances for Nvidia,
Samsung, Eideticom and even "the copyright holder".
Used a bash script to automate replacement of the license text
with SPDX identifier which is checked into scripts/spdx.sh.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iaa88ab5e92ea471691dc298cfe41ebfb5d169780
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12904
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: <qun.wan@intel.com>
There are a few places where a typo, extra character
or newline was added to the BSD 3-clause license text
which made it differ very slightly from the rest of
the license headers in the source tree. Remove those
differences in this patch, to help with automation of
SPDX identifier replacement in the next patch.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I542dc53cd252b1699253fd6dcc3ccac9643d7878
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12905
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
In autorun.sh it executes autotest.sh as root. But in autotest.sh and
test/unit/unittest.sh, when run git clean -f'*.gcda', it may show errors like:
08:03:54 -- unit/unittest.sh@277 -- # cd /home/jenkins/spdk_repo/spdk
08:03:54 -- unit/unittest.sh@277 -- # git clean -f '*.gcda'
fatal: unsafe repository ('/home/jenkins/spdk_repo/spdk' is owned by someone else)
The reason is the spdk source folder owner may not be root but we run the git
clean command as root. Fix it by using the folder owner's id to do
the git clean operation.
Signed-off-by: Rui Chang <rui.chang@arm.com>
Change-Id: Ifbd3098d4c32ffef5dcca738625302f63572e0c6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12693
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This SGL type was missed in the original commit
that added the pretty printing.
Fixes: 4d9ab1e9a1 ("nvme: pretty print dptr")
Reported-by: Ramanjaneya Burugula <burugula@gmail.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ibc655db4e65009071f39f55f691c94a094cea0bc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12705
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
This patch adds virtio_blk abstraction for custom transports,
with the 'vhost_user_blk' first one being used.
Added spdk_virtio_blk_transport_ops describing the nessecary
callbacks to be implemented by each transport.
Please use SPDK_VIRTIO_BLK_TRANSPORT_REGISTER to register the transport.
Transports can use virtio_blk_process_request() to process the
incoming I/O from their queues.
virtio_blk_create_transport RPC was added to create one of the
registered transports, possibly with custom JSON arguments.
Added 'transport' argument to vhost_create_blk_controller RPC,
to specify which transport should create the controller.
By default the vhost_user_blk transport is used.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ic9d93a6e0f483796eb56b7174a678e41a6ea4808
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/9540
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
As of right now the UT always used the empty struture of
struct spdk_vhost_dev_backend during the test. This meant
VHOST_BACKEND_BLK.
alloc_vdev() will require further changes to test both types
of backends. So for now change it to VHOST_BACKEND_SCSI,
since it currently does not touch any fields outside of the
struct spdk_vhost_dev.
Meanwhile next patch will do so for blk backend.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ib5af7520bc8a21a7af03b810d4cc42726797a331
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12749
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Vhost library was not initialized as part of the test,
it will become necessary later in the series.
Suite startup/cleanup have no matching CUnit test case,
so only assert() can be used. Rather than CU_ASSERT().
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ieaa3d2f6b6f1899105362181f285f585ff9724d7
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/10945
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
If compress driver doesn't support SGL input of output
then we need to copy user's buffers into reduce internal
buffers
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I0c07243a5b668d0e0adcc153e5b573f59c26ab64
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12281
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reduce library allocates one big chunk of memory and
then splits it between requests. The problem is that
a chunk of memory assigned to a request may cross huge
page boundary and if compress driver doesn't support
SGL input of output, operation will be failed.
To avoid this problem, align buffer start on 2MiB
and check each chunk of memory if it crosses huge page
boundary.
Fixes issue #2454
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: Ie730b8ba928f27a43bde1222b6c18d29b797575a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12249
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
ext_io_opts uses the size member to allow backwards
compatibility however currently we only check if it is
below or equal the current size of the opts struct and
that it is not 0. size is only used when we copy opts
because of split or push/pull.
This patch introduces size checks to allow safe access
to e.g. metadata and memory domain pointers of the user
provided opts pointer. The minimum size of the struct
passed is now the size of the initial version of
spdk_bdev_ext_io_opts. To not introduce additional
checks when opts are consumed by a bdev module we
now always copy if the size is smaller than the
current opts struct size.
When introducing new members to opts additional
checks might be needed if those are directly accessed
through the passed pointer or bdev_io->internal.ext_opts.
Change-Id: Ibd181a5840a3d5022018a9f61403df961ffd6e1d
Signed-off-by: Jonas Pfefferle <pepperjo@japf.ch>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12550
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
During ctrlr reconnection, spdk_nvme_ctrlr_reconnect_poll_async()
is executed by a non-timed poller.
We should poll adminq more often during ctrlr disconnection too.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ib1f5b41015aed20deda8df6f2c837981ac233c04
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12615
Reviewed-by: Dong Yi <dongx.yi@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
As described in the NVMe specification, a controller level reset
includes the following actions:
- the controller stops processing any outstanding admin or I/O
commands;
- all I/O SQs and CQs are deleted.
In a full controller reset sequence for a PCIe controller, if we do
a controller level reset first, we can abort outstanding commands
after the hardware has actually been stopped.
For NVMe-oF controller, each I/O qpair is an independent network
connection and is disconnected safely. We do not want to change
NVMe-oF controller.
Fixes the issue #2360
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: If05febac74705bfd3df5abd15064c1203126e027
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12447
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
As described in the previous patches, we need to delete all I/O
SQ/CQs before aborting trackers when disconnecting a controller.
The following patches reorder the operations. This patch changes
adminq disconnection to initiate a Controller Level Reset and
adminq completion processes it if ctrlr->is_disconnecting is true.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I64f06bae2ce8a9127124029fd042db0028198e3c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12560
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
When a new cluster is added to a thin provisioned blob,
md_page is allocated to update extents in base dev
This memory allocation reduces perfromance, it can
take 250usec - 1 msec on ARM platform.
Since we may have only 1 outstainding cluster
allocation per io_channel, we can preallcoate md_page
on each channel and remove dynamic memory allocation.
With this change blob_write_extent_page() expects
that md_page is given by the caller. Sicne this function
is also used during snapshot deletion, this patch also
updates this process. Now we allocate a single page
and reuse it for each extent in the snapshot.
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I815a4c8c69bd38d8eff4f45c088e5d05215b9e57
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12129
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
To fix issue: #2484
When unregistering the bdev, will send out the message
to each thread to abort all the IOs including IOs from
nomem_io queue, need_buf_small queue and need_buf_large queue.
The new SPDK_BDEV_STATUS_UNREGISTERING state is newly
added to indicate this unregister operation.
In this case, the bdev unregister operation becomes the
async operation as each thread will be sent the message
to abort the IOs and as the last step, it will unregister
the required bdev and associted io device.
On the other hand, the queued_resets will be handled
separately and not aborted in the bdev unregister.
New unit test cases are also added:
enomem_multi_bdev_unregister: to abort the IO from
nomem_io queue during the unregister operation
bdev_open_ext_unregister: to handle the events and
async operations from the unregister operation
Change-Id: Ib1663c0f71ffe87144869cb3a684e18eb956046b
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12573
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Reviewed-by: Dong Yi <dongx.yi@intel.com>
By default, failback to the preferred I/O path is done automatically
if it is restored. Some users may want to keep using the backup I/O
path even if the preferred I/O path is restored. In this case,
bdev_nvme_set_preferred_path can be used to do manual failback.
We may be able to clear/fill I/O path cache more strictly but it will
be complicated and have bugs. This patch does the minimal change,
just skips an apparent case.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: I78fe5faee6ff04e88ae3d7c6be6da1c20637c912
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12431
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
The new blobstore ext API is used when the user
provides ext_io_opts in bdev layer.
To store blobstore ext_io_opts, vbdev_lvol reports
non-zero get_ctx_size in bdev module interface.
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I64076b5369533be0c1d69ca48aef9d70a9abe488
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11373
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
These function accept optional spdk_blob_ext_io_opts
structure. If this structure is provided by the user
then readv/writev_ext ops of base dev will be used
in data path
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I370dd43f8c56f5752f7a52d0780bcfe3e3ae2d9e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11371
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Introduce spdk_blob_ext_io_opts structure which
is used in the new *_ext functions.
Zeroes dev is updated with implementation of
readv_ext which uses memory domains memzero
or regular memset().
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: Id94542196eff999827bf00591fd43804256fccb4
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11369
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
In the following patches, nvme_ctrlr_process_init() will be used to
disable the controller when disconnecting the admin qpair for PCIe
transport. In this case, we will have to exit nvme_ctrlr_process_init()
after CSTS.RDY is 0. However, spdk_nvme_ctrlr_reset() and
spdk_nvme_ctrlr_reconnect_poll_async() have to continue
nvme_ctrlr_process_init() until the controller becomes ready.
To differentiate stop and continue clearly, add a new state
NVME_CTRLR_STATE_DISABLED to enum nvme_ctrlr_state.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ic0a5fb7114d4eeb1cefec28bc404184768fb0a96
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12613
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
We enable multiple engines by:
* getting rid of the globals that point to the one available HW
and one available SW engine
* adding a submit_tasks() entry point for the SW engine so that
it is treated like any other engine allowing us to just call
submit_tasks() to the assigned engine for the opcode instead of
checking what is supported
* changing the definition of engine capabilities from
"HW accelerated" to simply "supported"
* during init, use a global (g_engines_opc) that contains engines
and is indexed by opcode so we know what the best engine is for each
op code
* future patches will add RPC's to override engine priorities or
specifically assign an opcode(s) to an engine.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I9b9f3d5a2e499124aa7ccf71f0da83c8ee3dd9f9
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11870
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
The NVMe bdev module supported active-passive policy for multipath mode
first. By this patch, the NVMe bdev module supports active-active policy
for multipath node next. Following the Linux kernel native NVMe multipath,
the NVMe bdev module supports round robin algorithm for active-active
policy.
The multipath policy, active-passive or active-active, is managed per
nvme_bdev. The multipath policy is copied to all corresponding
nvme_bdev_channels.
Different from active-passive, active-active caches even non_optimized
path to provide load balance across multiple paths.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ie18b24db60d3da1ce2f83725b6cd3079f628f95b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12001
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
If we specify a preferred path manually for each NVMe bdev, we will
be able to realize a simple static load balancing and make the failover
more controllable in the multipath mode.
The idea is to move I/O path to the NVMe-oF controller to the head of
the list and then clear the I/O path cache for each NVMe bdev channel.
We can set the I/O path to the I/O path cache directly but it must be
conditional and make the code very complex. Hence, let find_io_path() do
that.
However, a NVMe bdev channel may be acquired after setting the preferred
path. To cover such case, sort the nvme_ns list of the NVMe bdev too.
This feature supports only multipath mode. The NVMe bdev module supports
failover mode too. However, to support the latter, the new RPC needs to
have trid as parameters and the code and the usage will be come very
complex. Add a note for such limitation.
To verify one by one exactly, add unit test.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ia51c74f530d6d7dc1f73d5b65f854967363e76b0
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12262
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: <tanl12@chinatelecom.cn>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@nvidia.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
spdk_bdev_get_acwu() is a 1-based number, so we need
to subtract 1 from it before assigning the value to
nsdata->nacwu.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I32708b28a35670cba6013a48b79389fa48226285
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12399
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
When sending a fused compare and write command, we pass a callback
bdev_nvme_comparev_and_writev_done that we expect to be called twice
before marking the io as completed. In order to detect if a call to
bdev_nvme_comparev_and_writev_done is the first or the second one, we
currently rely on the opcode in cdw0. However, cdw0 may be set to 0,
especially when aborting the command. This may cause use-after-free
issues and this may call the user callbacks twice instead of once.
Use a bit in the nvme_bdev_io instead to keep track of the number of
calls to bdev_nvme_comparev_and_writev_done.
Signed-off-by: Alex Michon <amichon@kalrayinc.com>
Change-Id: I0474329e87648e44b08998d0552b2a9dd5d34ac2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12180
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This patch adds an extra spdk_thread_send_msg() call to destroy a qpair
to make sure that it isn't freed from the context of a socket write
callback. Otherwise, spdk_sock_close() won't abort pending requests,
causing their completions to be exected after the qpair is freed.
Fixes#2471
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Change-Id: Ia510d5d754baccca1e444afdb10696ab9b58e28b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12332
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
There is a race condition when a bdev is unregistered while reset is
submitted from the upper layer very frequently.
spdk_io_device_unregister() may fail because it is called while
spdk_for_each_channel() is processed.
spdk_io_device_unregister io_device bdev_Nvme0n1 (0x7f4be8053aa1)
has 1 for_each calls outstanding
To avoid this failure, defer calling spdk_io_device_unregister() until
reset completes if reset is in progress when unregistration is ready
to do, and then reset completion calls spdk_io_device_unregister()
later.
A bdev cannot be opened if it is already deleting. So we do not need
to hold mutex.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ida1681ba9f3096670ff62274b35bb3e4fd69398a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12222
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Previously, if a namespace is in ANA inaccessible state, I/O had been
queued infinitely. Fix this issue according to the NVMe spec.
Add a temporary poller anatt_timer and a flag ana_transition_timedout for
each nvme_ns.
Start anatt_timer if the nvme_ns enters ANA transition. If anatt_timer
is expired, set ana_transition_timedout to true. Cancel anatt_timer or
clear ana_transition_timedout if the nvme_ns exits ANA transition.
nvme_io_path_become_available() returns false if ana_transition_timedout
is true.
Add unit test case to verify these addition.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ic76933242046b3e8e553de88221b943ad097c91c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/12194
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Monica Kenguva <monica.kenguva@intel.com>
This reduces a lot of casting.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: Ibc04f422858642d0e20c9b020bb6c5d1b70256fe
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11534
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
The code to handle the lingering qpair when deleting it was really
complicated.
The RDMA transport can connect or disconnect qpair asynchronously.
Then we can include the code to handle the lingering qpair into the
code to disconnect qpair now.
If the disconnected qpair is still busy, defer completion of the
disconnection until qpair becomes idle.
If poll group is not used, we can complete disconnection immediately
because cq is already destroyed.
The related data and unit test cases are not necessary anymore.
So delete them in this patch.
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Change-Id: Ic8f81143fcad0714ac9b7db862313aa8094eeefb
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11778
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Add three states, INITIALIZING, EXITING, and EXITED to the rqpair
state.
Add async parameter to nvme_rdma_ctrlr_create_qpair() and set it
to opts->async_mode for I/O qpair and true for admin qpair.
Replace all nvme_rdma_process_event() calls by
nvme_rdma_process_event_start() calls.
nvme_rdma_ctrlr_connect_qpair() sets rqpair->state to INITIALIZING
when starting to process CM events.
nvme_rdma_ctrlr_connect_qpair_poll() calls
nvme_rdma_process_event_poll() with ctrlr->ctrlr_lock if qpair is
not admin qpair.
nvme_rdma_ctrlr_disconnect_qpair() returns if qpair->async is true
or qpair->poll_group is not NULL before polling CM events, or polls
CM events until completion otherwise. Add comments to clarify why
we do like this.
nvme_rdma_poll_group_process_completions() does not process submission
for any qpair which is still connecting.
Change-Id: Ie04c3408785124f2919eaaba7b2bd68f8da452c9
Signed-off-by: Shuhei Matsumoto <smatsumoto@nvidia.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11442
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
spdk_vhost_dev structure should only contain generic fields
that are to be used by either vhost, vhost_blk or vhost_scsi
layer.
The vhost_user backend can hold its properties in
spdk_vhost_user_dev, which is maintained within rte_vhost.
Both structures contain references back to each other.
The reference in spdk_vhost_dev is a void pointer to
allow future transports to keep the reference
to their own structures.
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I68640c524426d885c20242146365ba242fa9df8e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11813
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
In support of upcoming patches and to greatly simplify things,
the capabilites enum which held bit positions for each opcode
has been removed. Only the opcodes enum remains and thus only
opcodes are used throughout. For the capabiltiies bitmap a helper
function is added to convert from opcode to bit position. Right
now it is used in the IO path but in upcoming patches that goes away
and the conversion is only done at init time.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ic4ad15b9f24ad3675a7bba4831f4e81de9b7bc70
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11949
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Patch for not running tests if ASAN and
Valgrind options are both enabled.
Fixes#2422
Signed-off-by: Kamil Godzwon <kamilx.godzwon@intel.com>
Change-Id: I50c91bede687f0aee571c1f2540530a7fafcb49c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11998
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Previously spdk_vhost_dev_backend held callbacks
for vhost_blk and vhost_scsi functionality, along
with ones that are called by the vhost_user backend.
This patch separates out those callbacks into two
structures:
- spdk_vhost_dev_backend - to be implemented by vhost_blk
and vhost_scsi
- spdk_vhost_user_dev_backend - is only implemented by
vhost_user backend, callbacks for session managment
specific to that transport
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I348090df5dddeb2b1945b082b85aec53d03c781b
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11812
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
there is no group
The real implementation handles this by returning -ENOENT, so do the
same in the test.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: I405b6f60bf4dcdb22c57e48bbaf66d57522a49c5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11508
Community-CI: Mellanox Build Bot
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Count disconnecting a queue pair as activity so that the unit test
poll_threads() calls don't bail out until the disconnectedd_qpair_cb is
called at least once.
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: Idc437d6c589dbf133bfcbb5edba1087f928a718c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/11507
Community-CI: Broadcom CI <spdk-ci.pdl@broadcom.com>
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
