In future patch in new spdk_bdev_open_ext function we will call
spdk_bdev_get_by_name function and after that call and before
calling old spdk_bdev_open routine bdev can be removed.
We need to add mutex which will prevent that. Any future code
should use this mutex when accessing the bdevs list to get
a bdev and perform some operation on it.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I785a1791346aebdd394fc51ad0e7fbfbabf317c9
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/458457
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
It looks like currently we only check bdev names for NULL, but
not for "empty" string.
For example this rpc command:
sudo scripts/rpc.py construct_aio_bdev aio_disk "" 512
Will result in construction of AIO bdev with empty name:
sudo scripts/rpc.py get_bdevs
[...]
"name": "",
"aliases": [],
[...]
Change-Id: I41204096c8cf210a4dc40a8225d1c9dad353f533
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460150
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
For devices that don't have a UUID, the UUID is generated at
registration time. That means that some devices will not have the same
UUID from run to run, but this seems no worse than having no UUID at
all.
Change-Id: Icf6b8517ffcffabafa2b73176dc03d896d0017fe
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459604
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
In file included from bdev_ut.c:43:
/root/yidong/spdk/lib/bdev/bdev.c:4373:9: warning: Access to field 'bdev'
results in a dereference of a null pointer (loaded from variable 'desc')
return desc->bdev;
^~~~~~~~~~
This is related to issue #822.
Change-Id: I8cd2bafadeff9846169bc9ca67b3c4110e9c0da8
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459529
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: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
When we run out of bdev_io's child iovs and we had
to round down I/O size to nearest block size boundary,
we used to decrease the existing child_iovcnt and
set a new "child_iov_run_out" flag to terminate the
uppermost splitting loop.
We can get rid of that new flag by just not decreasing
child_iovcnt when rewinding the last few iovs - it
will make the uppermost loop naturally terminate using
the existing checks.
Change-Id: Ie40c7ce135e7fb8fe284afdf7beeebd10af85cb7
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459911
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>
Here is the an example to describe existing issue:
There is a Write request with 64KiB data length, and this IO is cross the IO
boundary. We assume that the parent IO will have 2 children requests, one is
33KiB length, the other one is 31KiB. Here is the view of parent iovs, the
first 33KiB length data has 33 iovs:
iov.[0].iov_length = 1024;
.
.
iov.[31].iov_length = 256;
iov.[32].iov_length = 768;
.
.
iov.[64].iov_length = 1024;
In function _spdk_bdev_io_split(), then you can see that for the 33KiB length
child request, exiting code will run out of child child_iov space and return
error due to last one data buffer is not block size aligned.
Here we can rewind the existing offset to last block size aligned buffer to
avoid the error case, for backend which need aligned data buffer such as
AIO backend, the request will go through spdk_bdev_io_get_buf() again to
do the data copy, otherwise for those backend devices such as NVMe with
hardware SGL support, 256 data segment is fine for them.
Change-Id: I96ebdf29829d86f9b38fab28a7406eedc9fa44ef
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453604
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>
There is one existing example usage case to describe the issue:
Users(e.g. Vhost-blk target with Windows Guest) call spdk_bdev_readv_blocks()
to submit a 128KiB length data READ request, and the data buffer
provides by vhost isn't aligned, but the backend block device
requires aligned data buffer, so existing function call trace:
spdk_bdev_readv_blocks()-->
spdk_bdev_io_submit()-->
spdk_bdev_io_get_buf()
spdk_bdev_io_get_buf() will allocate buffer from large data
buffer pool for 128KiB length, of course, it will return error
with existing logic.
So here, no matter what the data length is, we can go through
the split process first for both READ and WRITE.
However, there is one scenario that for iSCSI READ request,
the iSCSI layer will not allocate data buffer for the request,
so for this case if the IO boundary is required we should keep
the logic as before.
Change-Id: I67661f5fa4c3c7c561b45c86146759aa3477adbf
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453133
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>
If bdev is configured to use separate buffers for metadata transfer,
but it doesn't support the write zeroes command, pass empty zeroed
buffer to make sure the metadata is cleared out as well.
Change-Id: If6f024266067e5764a28a276296f651d31da4792
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/457628
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
The function spdk_bdev_desc_get_bdev() was added,
but remained unused. Couple places done the exact same thing,
so now they just use it directly.
Change-Id: I018f57b7b4bcfe22ec6a97cf5261b9a257ba93de
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/456957
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>
_spdk_bdev_io_split() will be used to requests that have IO buffers.
Change-Id: I5ba0b83e47b84066e6c5032de2e02404155896d3
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/457549
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>
The function spdk_bdev_io_get_io_channel() was added,
but remained unused. Couple places done the exact same thing,
so now they just use it directly.
Change-Id: Ifa332ce3a489256ccf2f5d0dd9c74a3215c544ce
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/456435
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>
The function spdk_bdev_io_get_thread() was added,
but remained unused. Couple places done the exact same thing,
so now they just use it directly.
Change-Id: Ia25abf57eb88c8df47c83e4edd761a9e02cc1618
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/456436
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>
This patch adds *_with_md family of functions allowing for IO with
metadata being transferred in a separate buffer.
Change-Id: I842d5a00a532cf5d0b0f0738535ea46903674140
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/451465
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>
Existing code in spdk_bdev_write_zeroes_blocks() will call spdk_bdev_free_io()
for the error case, which will cause assertion because the bdev_io isn't
submitted to the backend yet, so we will check the condtion first to
avoid the error case.
Change-Id: If27d78217f709a3315e74c00869d345abd6b9a69
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453491
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>
Move actual submission code to _spdk_bdev_io_do_submit, used by
both normal submission path and QoS path.
Previous patch(review.gerrithub.io/c/442127) adds the missing
bdev_io->internal.in_submit_request flag to QoS submission path.
But QoS submission path doesn't handle nomem_io yet.
This patch makes QoS submission path handle nomem_io in the same way
as the normal path and extracts actual submission code into do_submit
function, so that further modification of the submission logic will
apply to both paths automatically.
Change-Id: I41fa88d239c3a2bd9783d812826e32e7c887818d
Signed-off-by: lorneli <lorneli@163.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/455252
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
When parent IO was splitted into several children requests, SPDK
may return parent completion callback with error status before
all the children requests are finished.
Change-Id: I63221a0ae1a5925a7fcd9744b4f5d8079c641252
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/453611
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>
These two paths do the same thing, only spdk_bdev_io_get_buf tries to
allocate the buffer directly, while spdk_bdev_io_put_buf reuses the
returned buffer for one of the waiting requests.
Change-Id: I341a011f3a16a99de399c8b56fa73ccd9c7fe4fa
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/451466
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Previously whenever bdev module went through init>fini>init,
the async modules would trigger assert in spdk_bdev_module_action_done().
This was because starting value for action_in_progress was being
set only once - during registration of the modules.
With this change, modules are set as async just before their init start.
Change-Id: If177a8dc97812b1b264cb61d5ad202ce47fca3b5
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/454614
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>
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>
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>
For bdevs that don't support zero copy, emulate the
API using regular read and write operations.
Change-Id: Iabd7ff474bf740b096f38bd47196987cbd89e915
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/416465
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>
Add a ZCOPY operation to obtain buffers that represent
data regions on the backing block device.
Change-Id: Ie941c16ee051d0009e3888b52b8f41773bba47b3
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/386166
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: Jim Harris <james.r.harris@intel.com>
Bdev descriptors could be closed only from the same thread
that opened them. This restriction was suddenly introduced
at one point without making sure all the SPDK code respects
it. Vhost can still close descriptors from any arbitrary
thread and fixing that would require some more effort.
With this patch we remove the thread-specific assert from
spdk_bdev_close() and hence allow vhost to work properly
in debug builds. Vhost can still have a possible data
race with bdev hotremove notification, but let's get rid
of the abort() from the usual code path first.
Change-Id: I6fac66a5ebc907b1c5418fff618f0b64cd9b69f4
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/451561
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 used to wait only for those descriptors which
specified the hotremove notification callback. The
bdev could've been removed before the descriptor
was closed and the subsequent spdk_bdev_close would
simply segfault.
This patch modifies spdk_bdev_unregister to always
wait for all descriptors to be closed before actually
unregistering the bdev. This consolidates the bdev
unregister behavior for descriptors with and without
the hotremove callback.
Change-Id: I9b358209c6abd301b6fe8660e27bc6fa4ef485d6
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450175
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>
set_bdev_qos_limit RPCs must come after the RPCs that
create its bdev.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I7008745f9c56d9bc579decc7fe3c4d0d58950754
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/451414
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
spdk_dma_*malloc() is about to be deprecated.
Change-Id: Idb18f7ef44634deaf63139f0f872881c9cdaefac
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450256
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 API had good intentions, but as more complicated
use cases came up where base bdevs could come and go,
we've realized that the bdev layer will need another
mechanism to query bdev modules on these types of
relationships between a virtual bdev and its base
bdevs. We removed all code related to tracking
the array of base bdevs a long time ago.
Change all existing callers to use spdk_bdev_register.
Document spdk_vbdev_register as deprecated for now,
and change its implementation to just call
spdk_bdev_register for simplicity sake.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3b40ed96480c0fa7184db42953a9f4e4c167fed1
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450076
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
When bdev is registered it will send "bdev_register" notification and
"bdev_unregister" when unregister is complete.
Change-Id: I3b37a4cb766a473f3da63a571036add366e78fa5
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448839
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>
As the bdev_io maybe NULL, so put the assignment after assert(bdev_io != NULL).
Change-Id: I58d6fcf97931b2f431ad5680b87b098e0c9a5e9b
Signed-off-by: JinYu <jin.yu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/449296
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: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Currently if module claims a bdev in examine_config,
it cannot start asynchronously. This patch changes this
behaviour by calling examine_disk on modules which previously
claimed bdev trough examine_config.
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I85b603590c6dab50e59ef7e68f292cb9abc47d98
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/448132
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Increase the size of small and large buffers in the bdev layer
to store DIF. Increase is the amount necessary to store 16 byte
metadata to the block formatted with 512 + 16. 512 + 16 is the
current maximum ratio of metadata per block.
This change will be done in the iSCSI library in the next patch
and other libraries may be done later.
Hence add and use an new macro SPDK_BDEV_BUF_SIZE_WITH_MD(x) for
convenience.
Change-Id: I4b5498f56c9baf3e3ed93dd1c757998d7ce65141
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/444558
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Unregister calls are not guarded. Fix this by chekcing status before
doing unregister.
Change-Id: I593e27efdae17f6d89362fd8e4edccf2af2b7281
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/445894
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Retry mechanism will stuck if there is no outstanding
IO after completion with ENOMEM. This should never
happen.
Change-Id: I58ebf8cc8a498231beef43ac20f58eeaad89afda
Signed-off-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/446610
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>
The calling of spdk_bdev_finish is in wrong place,
the bdev subsystem recycling will be called by
_spdk_subsystem_fini_next. If we call spdk_bdev_finish
here, it will be called twice, so it is unnecessary.
And this patch will be used to address the issue
reported in:
https://review.gerrithub.io/#/c/spdk/spdk/+/447613/
Change-Id: I03dff8b84bd0d7b49675ce8300b3da623963e140
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447731
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.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>
iSCSI target will need to get data block size except for metadata.
Other SPDK application may need to get the same information
future. Hence this patch adds an new API spdk_bdev_get_data_block_size
to bdev layer. In the header file, spdk_bdev_get_data_block_size
is located next to spdk_bdev_is_md_interleaved to avoid confusion
by new users.
Change-Id: I0fd2a6d0bcf6a4c18c583f70d96cc5035fc57fe9
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/445082
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: wuzhouhui <wuzhouhui@kingsoft.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
If success is false in each bdev module's spdk_bdev_io_get_buf_cb,
call spdk_bdev_io_complete with SPDK_BDEV_IO_STATUS_FAILED, and
then return.
Change-Id: I6f106d8d39a3616f7305201fa2efc4805d4d00ee
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/446046
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
When the specified buffer size to spdk_bdev_io_get_buf() is greater
than the permitted maximum, spdk_bdev_io_get_buf() asserts simply and
doesn't call the specified callback function.
SPDK SCSI library doesn't allocate read buffer and specifies
expected read buffer size, and expects that it is allocated by
spdk_bdev_io_get_buf().
Bdev perf tool also doesn't allocate read buffer and specifies
expected read buffer size, and expects that it is allocated by
spdk_bdev_io_get_buf().
When we support DIF insert and strip in iSCSI target, the read
buffer size iSCSI initiator requests and the read buffer size iSCSI target
requests will become different.
Even after that, iSCSI initiator and iSCSI target will negotiate correctly
not to cause buffer overflow in spdk_bdev_io_get_buf(), but if iSCSI
initiator ignores the result of negotiation, iSCSI initiator can request
read buffer size larger than the permitted maximum, and can cause
failure in iSCSI target. This is very flagile and should be avoided.
This patch do the following
- Add the completion status of spdk_bdev_io_get_buf() to
spdk_bdev_io_get_buf_cb(),
- spdk_bdev_io_get_buf() calls spdk_bdev_io_get_buf_cb() by setting
success to false, and return.
- spdk_bdev_io_get_buf_cb() in each bdev module calls assert if success
is false.
Subsequent patches will process the case that success is false
in spdk_bdev_io_get_buf_cb().
Change-Id: I76429a86e18a69aa085a353ac94743296d270b82
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/446045
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
There are some cases that virtual bdev open and close
the device and QoS will be disabled at the last close.
In this case, when a new bdev open operation comes again,
the QoS needs to be enabled again.
Change-Id: I792e610f4592bad1cac55c6c55261d4946c6b3e2
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/c/442953
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Currently struct bdev_io holds io_channel that the I/O was submitted
on through bdev_io::bdev_channel, but bdev_io::bdev_channel is private
in bdev.c and cannot be referenced in other files.
Hence add an new API spdk_bdev_io_get_io_channel API to get io_channel
coniveniently.
Change-Id: Ic2e2fde845d324f7a1637e3c75080727a62de5ec
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/443843
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This patch is for DIF check types.
Add enum spdk_dif_check_type to DIF library.
Add a field dif_check_flags to struct spdk_bdev and add
spdk_bdev_is_dif_check_enabled to bdev APIs.
Added enum is intended to improve usability. If no enum, the
caller will have to get raw data of flags and mask each bit.
Change-Id: Ia46a37a9684dc968dcc51963674f0a9963e0cd4d
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/443339
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This patch is for DIF settings.
Add fields dif_type and dif_is_head_of_md to struct spdk_bdev and
add APIs spdk_bdev_get_dif_type and spdk_bdev_is_dif_head_of_md to
bdev APIs.
The fields dif_type and dif_is_head_of_md are added to the JSON
information dump.
Change-Id: I15db10cb170a76e77fc44a36a68224917d633160
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/443184
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>
To support DIF, bdev will need to expose the following information:
- Metadata format
- Block size
- Metadata size
- Metadata setting (interleave or separate)
- DIF settings
- DIF type 1, 2, or 3
- DIF location
- DIF check types
- Guard check
- Reference tag check
- Application tag check
This patch is for the metadata format. Subsequent patches will do for the DIF
setting and DIF check types.
Add fields, md_len and md_interleave, to struct spdk_bdev and add APIs,
spdk_bdev_get_md_size and spdk_bdev_is_md_interleaved, to bdev APIs.
The fields, md_len and md_interleave, are added to the bdev JSON infomation dump.
DIF will be used only in the NVMe bdev module and the upcoming virtual
DIF bdev module first. But additional required storage by md_len and md_interleave
will be very small and they are simple. Hence add them to struct spdk_bdev simply.
Change-Id: I4109f6a63e6f0576efe424feb0305a9a17b9b2e8
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/443183
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This function gets used as a function pointer, which
seems to keep the compiler from trying to inline the
function. Stack manipulation was showing up in the
perf profile pointing to this. Marking the function
as inline gets it actually inlined in the hot I/O
path.
Improves bdevperf microbenchmark from 78M to 85M IO/s.
Cores are virtually identical - 11.4M on core 0 and
10.4-10.6M on remaining cores.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iadced071dfc07fc09db6da3571c930988b2dc3fd
Reviewed-on: https://review.gerrithub.io/c/443278
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 keeps the hottest structures at the head of the
cache and helps improve performance.
Improves microbenchmark (8 null bdevs on 8 lcores,
bdevperf seq read with qd=1) from 67M to 78M on my
Xeon E5-v3 system. Core 0 performance remains about
the same (10.7-10.8M) but others cores improve from
around 8.0M each to 9.4M.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ia3ccf94ab39b6f911127f0bd1016e352027b11fc
Reviewed-on: https://review.gerrithub.io/c/443277
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>
Unmap, discard, write zeros will be sent down from
higher stack. Remove these IOs for the QoS limit.
Change-Id: Ieb3cc19f31c43f8ddf8f8d2fd338f442ef48b679
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/c/442673
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Liang Yan <liang.z.yan@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
_spdk_bdev_io_submit uses the bdev_io->internal.in_submit_request
flag to ensure we unwind in cases where the I/O is completed
inline (i.e. malloc or null bdevs). But when an I/O gets queued
for QoS, and then we iterate through the queued I/O in
_spdk_bdev_qos_io_submit(), this flag was not getting set
when those I/O would get submitted to the underlying bdev. This
would allow for _spdk_bdev_qos_io_submit recursion, resulting
in all kinds of different types of memory corruption.
Fixes#613.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I29263f4e7b2ead60f08b60474d210defa803348c
Reviewed-on: https://review.gerrithub.io/c/442127
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Liang Yan <liang.z.yan@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
This patch adds the support of read and write separate
bandwidth rate limits control with the configuration file.
Below is the example (in MiB) for the configuration section:
[QoS]
Limit_Read_BPS Malloc0 100
Limit_Write_BPS Nvme0n1 200
Change-Id: I0221516ce70c3fbb07b9e80c1c814ed5ba271c88
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/c/416672
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
