We were only using one value from this array to tell us if the qpair was
idle or not. Remove this array and all of the functions that are no
longer needed after it is removed.
This series is aimed at reverting
fdec444aa8 which has been tied to
performance decreases on master.
Change-Id: Ia3627c1abd15baee8b16d07e436923d222e17ffe
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/445336 (master)
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447620
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>
Not doing so can cause us to hit asserts during the shutdown path. This
should fix an intermittent failure we are seeing on the test pool where
we hit the assert rdma_req->state != RDMA_REQUEST_STATE_FREE in
spdk_nvmf_rdma_request_process.
Note that this problem doesn't cause any data corruption when debug is
not enabled, it just causes us to probcess a subset of commands through
the state machine one extra time suring qpair shutdown.
Change-Id: Ibc36bfea87ec4089b8e2c7a915f48714fddb0b09
Signed-off-by: Seth Howell <seth.howell@intel.com>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447852
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Since there are multiple events/conditions that can trigger a qpair
disconnection, we need to funnel them to a single point of entry. If
more than one of these events occurs, we can ignore all but the first
since once a disconnect starts, it can't be stopped.
Change-Id: I749c9087a25779fcd5e3fe6685583a610ad983d3
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443305 (master)
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447619
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 is a holdover from before poll groups were introduced.
We just need a per-thread context for a set of connections,
so now that a poll group exists we can use that instead.
Change-Id: I1a91abf52dac6e77ea8505741519332548595c57
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/442430 (master)
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447618
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
When an operation fails, we shouldn't pass a handle or
a 'valid' blob ID to the caller's completion function.
The caller *should* ignore it when bserrno != 0, but
it's best to not take that chance.
Fixes#685.
Note: #685 seems to have a broader issue related to
a possibly locked NVMe SSD in the submitter's system.
This only fixes the assert() that was hit.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3fb3368ccfe0580f0c505285d4b1e9aca797b6a6
Reviewed-on: https://review.gerrithub.io/c/445941 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447449
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>
This is fix for https://github.com/spdk/spdk/issues/523
Fio hangs on pthread_exit(NULL) from spdk thread.
This happens because, pthread_exit tries to dlopen glibc and hangs on
__lll_lock_wait. This patch prevents unmapping of glibc in fio_plugin
and phtread_exit does not need to dlopen it again.
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I5078cc55e24841675d6ef4ecba43879dc3f73a4f
Reviewed-on: https://review.gerrithub.io/c/443912 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447586
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: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
VMWare Workstation NVMe emulation does not seem to write the
SHST_COMPLETE bit within 10 seconds, resulting in an ERRLOG
during detach/shutdown. So add a quirk to cover these VMWare
SSDs. But rather than squashing the ERRLOG completely for
these SSDs, just add a message instead indicating this is
somewhat expected on these VMWare emulated SSDs.
Fixes issue #676.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3dfcb631feda639926fd712f1f41abb66cbf2096
Reviewed-on: https://review.gerrithub.io/c/445942 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447591
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>
The -i option for uname is not portable, -m is a better choice.
Fixes#648
Signed-off-by: gila <jeffry.molanus@gmail.com>
Change-Id: I2287e652e8d3243df2bf101c1cfbdc6aedf643f1
Reviewed-on: https://review.gerrithub.io/c/443315 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447596
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>
Add a memory barrier for arm64 to prevent possible reordering
of tracker and cpl access,
because arm64 has less strict memory ordering behavior than x86.
Change-Id: I0a8716f7bfeffb0bbce27ee3174e214c8e4566b4
Signed-off-by: heyang <heyang18@huawei.com>
Reviewed-on: https://review.gerrithub.io/c/442964 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447592
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>
Checking version of libibverbs is error prone as custom version might be
installed that implements needed features but version number is not
incremented. Instead test if we can compile with needed features.
Fixes#524
Change-Id: I18e9ca923eea92b124e95a5f660955a01afad5c4
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443387 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447587
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>
Add a CLEAN_FILES macro that shared_lib/Makefile can use
to add to the list of files to be cleaned.
Fixes#663.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I12982e0989e02a69aaea4e470777301280090096
Reviewed-on: https://review.gerrithub.io/c/444427 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447583
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>
When we were trying to push a newly allocated string
into the arg array and the array realloc() failed,
the string we were about to insert was leaked.
Change-Id: I31ccd5a09956d5407b2938792ecc9b482b2419d1
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/445149 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447580
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
This patch refactors driver init and in doing so eliminates the mem
leak described in the GitHub issue. Also it is now consistent with
how the pending compression driver does init.
Fixes#633
Change-Id: Ia2d55d9e98fb9470ff8f9b34aeb4ee9f3d0478f5
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/442896 (master)
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447607
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
The ioctl NBD_SET_SOCK can return EBUSY on conditions not
only the kernel module hasn't loaded entirely yet, but
also the nbd device is setup by another process, which will
lead the poller's infinite polling.
This patch will wait only 1 second if device is busy.
Change-Id: I8b1cfab725cba180f774a57ced3fa4ba81da2037
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/444804 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447598
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>
Use NBD_SET_SOCK to check whether the nbd device is setup
by other process or whether nbd kernel module is ready
before other nbd ioctl operations. This can avoid bad
influence to the nbd device setup by other process.
Change-Id: Ic12acbfddb8c4388e25731c39159b1ce559b8f23
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/444805 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447597
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>
When hotplug feature is enabled by NVMe driver, users may
call delete_nvme_controller() RPC to delete one controller,
however, the hotplug monitor will probe this controller
automaticlly and attach it back to NVMe driver. We added
a skip list, for those user deleted controllers so that
NVMe driver will not attach it again.
Fix issue #602.
Change-Id: Ibbe21ff8a021f968305271acdae86207e6228e20
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/444323 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447595
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>
A new module switch which was missed at here.
Change-Id: If1784ace13657756d8034cd04e594af5b1799381
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Reviewed-on: https://review.gerrithub.io/c/444820 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447594
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>
Previously, we can -p + hex value(e.g., 0x1) to assign the master core
and start the NVMe-oF or iSCSI target app.
However now it is not supported and prints error. I checked
the code, it only supports transformation with Decimal format,
so chaning the base to 0 to make it supporting other formats.
Change-Id: I82510ba0cef47b5593484b4fd3490f85c93cf6a5
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/444830 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447593
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>
We started to use iptables in patch 21bd94275
(libsock: add functional tests) but never added
the package dependency.
Change-Id: I651f2545a11f546f8b47f9759fbaed3a141f0928
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443597 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447590
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Make modyfication of global allocator index tread safe
by using atomic operation
This patch also changes mempool size to be 2^n - 1
which makes it more efficient
Change-Id: I5b7426f2feef31471d3a4e6c6d2c7f7474200d68
Signed-off-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-on: https://review.gerrithub.io/c/442695 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447588
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>
Added check before write submission to indicate if
LBA was update in meantime. In such case don't set band's
metadata and rwb entry cache bit. Previous implementation
invalidates such address during write completion and could
cause that inconsistent lba map was stored into disk.
Change-Id: I4353d9f96c53132ca384aeca43caef8d11f07fa4
Signed-off-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/444403 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447582
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>
Recently, we started setting the list of RDMA wr in the parse_sgl
function. This meant that we started using a variable we hadn't before
which was uninitialized in the unit tests which caused a valgrind error.
Change-Id: I3f76ce1dcf95d1d41fe8b3f96e878859036a5031
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443791 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447450
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>
The match file is hardcoded to $(FP)G. If using xxTB volume NVMe
SSD, this test case will fail. So using $(S) to cover larger
volume NVMe SSD.
Change-Id: Id046cadfbc5236cd8f480981fa337d2ee9a68bf4
Signed-off-by: Liang Yan <liang.z.yan@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447130 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447472
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>
Removing band from "free list" is moved from FTL_BAND_STATE_OPENING
to FTL_BAND_STATE_PREP state's change actions.
This will fix race condition when one band is prepared (erased)
and write pointer is trying to get next active band.
Change-Id: I9e4fe9482a01ee732271736e4a0e6fcedf2582d8
Signed-off-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/445118 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447461
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>
Older versions of QEMU (<= 2.11) expose the VGA BIOS
hole (0xA0000-0xBFFFF) by specifying two separate memory
regions - one before and one after the hole. This results
in the "size" not being a 2MB multiple. But the underlying
memory is still mmaped at a 2MB multiple - so that's what
we should be checking to ensure the memory is hugepage backed.
Fixes#673.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I1644bb6d8a8fb1fd51a548ae7a17da061c18c669
Reviewed-on: https://review.gerrithub.io/c/445764 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447457
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
We have conflict to handle the NVMf subsystem shut
down. The situation is that:
If there is shutdown request (e.g., ctrlr+c),
we may have subsystem finalization and subsystem
initialization conflict (e.g., have NVMf subsystem fini and
intialization together), we will have coredump
issue like #682.
If we interrupt the initialization of the subsystem,
following works should do:
1 Do not initilize the next subsystem.
2 Recycle the resources in each subsystem via the
spdk_subsystem_fini related function. And this patch will
do the general thing, but will not consider the detailed
interrupt policy in each subsystem.
Change-Id: I2438b4a2462acb05d8c8e06dfff3da3d388d4b70
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/446189 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447459
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>
OpenSUSE releases (OpenSUSE Leap and Tumbleweed) now use
/etc/SUSE-brand than /etc/SuSE-release as SUSE identification.
According to this change, This commit intends to update
scripts/pkgdep so that it could install packages for OpenSUSE.
Tested on OpenSUSE Leap 15.0 and latest Tumblweed.
Change-Id: I878b6671753084ef718e1f7630a42520a72ea151
Signed-off-by: Zhu Lingshan <lingshan.zhu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/446504 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447458
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 fixes potential memory leak in spdk_app_parse_args() when
white or blacklist of devices is defined.
Change-Id: Ia586d77c67dbe6c664447f8431e1a7a30d624ae1
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/440982 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447456
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>
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 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447455
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>
In some situation, the script needs to try more times to kill
spdk_tgt. So increase the loop count.
Change-Id: I5c3596b0bae8ee965bb0b3532ba100dfd0aec82d
Signed-off-by: Liang Yan <liang.z.yan@intel.com>
Reviewed-on: https://review.gerrithub.io/c/445436 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447453
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Since we no longer rely on the state queues for draining qpairs, we can
get rid of most of them. We cn keep just a few, and since we don't ever
remove arbitrary elements, we can use stailqs to perform those
operations. Operations on Stailqs carry about half the overhead as
operations on tailqs
Change-Id: I8f184e6269db853619a3581d387d97a795034798
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/445332 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447466
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
When the decision was made to uncouple the number of shared buffers from
the queue depth and allow the user to decide for themselves, the default
was also significantly lowered, which caused some issues when trying
torun performance tests (See https://github.com/spdk/spdk/issues/699).
While this is a user modifiable variable, it is still best to keep the
higher default value.
The original value was equivalent to max_queue_depth *
SPDK_NVMF_MAX_SGL_ENTRIES * 2 with the defaults for max_queue depth and
max_sgl_entries being 128 and 16 respectively. Hence 4096
fixes: 0b20f2e552
Change-Id: I809e97a10973093a2b485b85bca7160091166f70
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/446525 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447465
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
For devices that support fewer SGE elements than our default values, we
need to adjust the I/O unit size so that we don't ever try to submit
more SGLs than we are allowed to.
Change-Id: I316d88459380f28009cc8a3d9357e9c67b08e871
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/442776 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447464
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>
In the error path, we were first decrementing a variable and then
asserting that it must be >0. These operations should occur in the
opposite order.
Change-Id: I6cec544faf17bb75cbfca3d3a3c173dc5db14f99
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/446440 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447463
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 value was not being decremented when we got SEND completions for
write operations because we were using the recv send to indicate when we
had completed all writes associated with the request. I also erroneously
made the assumption that spdk_nvmf_rdma_request_parse_sgl would properly
reset this value to zero for all requests. However, for requests that
return SPDK_NVME_DATA_NONE rom spdk_nvmf_rdma_request_get_xfer, this
funxtion is skipped and the value is never reset. This can cause a
coherency issue on admin queues when we request multiple log files. When
the keep_alive request is resent, it can pick up an old rdma_req which
reports the wrong number of outstanding_wrs and it will permanently
increment the qpairs curr_send_depth.
This change decrements num_outstanding_data_wrs on writes, and also
resets that value when the request is freed to ensure that this problem
doesn't occur again.
Change-Id: I5866af97c946a0a58c30507499b43359fb6d0f64
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443811 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447462
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>
perf application can't generate IO for NVMe namespace with
more than 4G size.
Example of error:
"Attached to NVMe over Fabrics controller at 1.1.75.1:1023:
nqn.2016-06.io.spdk.r-dcs75:rd0
WARNING: controller SPDK bdev Controller (SPDK000DEADBEAF00 ) ns 1 has
invalid ns size 0 / block size 4096 for I/O size 4096
WARNING: Some requested NVMe devices were skipped
No valid NVMe controllers or AIO devices found"
ns_size variable is uint32_t, spdk_nvme_ns_get_size function
returns uint64_t. Result can exceed the maximum size of
uint32_t and ns_size remains 0.
The issue introduced by commit: f2462909
Change-Id: Idc6dd8688d5d6268bda1a1d6b06a611643af6155
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/443996 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447451
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>
On VM these tests takes ages.
Change-Id: Id4799e2d226e59b430e899983a6470080b5c37dc
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443795 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447149
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: Jim Harris <james.r.harris@intel.com>
iter_pci_dev_id abd iter_pci_dev_id functions should
not return BDF for devices that are not ment to be used
in tests.
Note that not all tests are ready for this change as they
discover functions on its own. Lets this changed in
separate patch.
Change-Id: I45a59ec121aa81e9f981acae7ec0379ff68e520a
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/443767 (master)
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/447148
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: Jim Harris <james.r.harris@intel.com>
