Since a PDU can be sentout in many times, so this
function is called multiple times, so move the
caculation function in spdk_iscsi_conn_write_pdu
Change-Id: Ib4da4a74c17709d98e4b01c2e76428021afea947
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/429931
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
This function was always reporting true. Instead of grepping for the nic
name in the output, look for whether there is an rxe device assigned to
that nic.
Change-Id: Ic69868cfb0802a46c36b2fb83d01bca11ed9c181
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/431690
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Add missing wait in test/nvme/shutdown/shutdown.sh
Not waiting after connecting nvme device resulted in undefined behavior.
This patch uses new helper function - nvme_connect
Change-Id: Idb29c7f6b40ae4b3fa0eb68f7b8d5f86d9a4149f
Signed-off-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-on: https://review.gerrithub.io/428336
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
In cases we probe without a specific trid, the underlying
rte_bus_probe() in spdk_pci_enumerate() might fail to
initialize some devices, but still return with code 0,
That's technically correct, as we asked just to probe
devices on the bus and that's what it did. Some devices might
have been initialized, others not. In secondary process we
blindly assumed all devices were probed successfully, which
might have eventually led to assert failures, as current
process was not on the ctrlr->active_procs list.
To fix it, just add an additional check before attaching
the controller in secondary process.
Change-Id: If015b1e562052a9189ed1a48091b209bd2dd5f2a
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/431727
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 only detached the PCI device on the controller destruction,
which happens just once - in the primary process, but secondary
process needs the PCI detach as well.
Requesting to hotremove the NVMe PCIe controller in secondary
process is broken, because DPDK will still keep the device
reference and won't allow SPDK to hotplug it again.
Fix this by detaching the local PCI device whenever removing
a secondary process from spdk_nvme_ctrlr. This does require
an additional transport check in the generic NVMe layer, but
I found it an overkill to create a multi-process transport
abstraction just for this case.
Change-Id: I812dc1c878ade5b149556806228a2afcb49f0b17
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/431487
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This includes the NVMe-oF json_config and spdkcli tests
Change-Id: I5e4dad2c1bb68c4b7f36d50e937c56ef642f65b7
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/430166
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Current behaviour will match anything that contain address. Change this
to match whole address only.
Change-Id: I6343fb91ed624cba41adbc33d711fb48c2f167a1
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/431530
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>
Especially for rxe. We're not waiting for the queue pairs to get
cleaned up after disconnect, so this test fails due to running
out of qpairs sometimes.
Change-Id: Ib99133776d02743782ef1631e3880e4e6997c1b5
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/431372
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: Sasha Kotchubievsky <sashakot@mellanox.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
702 case are listed in NIGHTLY test and run PASS,
but it not listed in lvol.sh' usage().
It's easy to be confusing.Where is 702 case?
Change-Id: Iad376112510b277e8747798dde5ef0f12b42c2ec
Signed-off-by: WangHaiLiang <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.gerrithub.io/430905
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Paweł Niedźwiecki <pawelx.niedzwiecki@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>
Refactor the printout of autorun-spdk.conf and fix the path for
pkgdep.sh (the previous path was based on an old assumption)
Change-Id: Id95e0f80f835dd1b055a94a6bfdbffcce029b8af
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/430843
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Previously there was no consideration for IO that were outstanding
to the crypto device when handling a reset. This patch makes sure
that those IO are completed with FAIL status prior to completing
the reset that we pass down the stack.
It does so by sending down the reset first and in the completion
using spdk_for_each_channel and the poller to quiesce each channel
allowing the crypto side to complete all IOs before we finally
complete the reset IO after the last channel is quiesced.
Resets are tracked on a per bdev basis.
Addresses github issue #449.
Change-Id: Iadb07bada1fcaad33d9f224a60d983a7eb835236
Signed-off-by: paul luse <paul.e.luse@intel.com>
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/428552
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Also, remove bdev_svc memory limit to prevent it from hanging while
handling discover_bdevs calls.
Change-Id: I2868839f40931b964d49a90a86dfb391e2247e30
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/429535
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
This helps us avoid situations where other bdev modules will break the
rte_pci_bus mappings for qat devices before we have an opportunity to
initialize the qat pmd.
Also, update the blobstore match file to handle the possibility of using
a crypto driver and improve the json_config and spdkcli scripts to
handle allocating qat_crypto drivers.
Change-Id: I7359c67d1992df1d5bb85585eca6d5c342787649
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/430393
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.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>
By running random, 64KB, 70% write, and 30% read workload and periodical
TCP disconnection from the initiator, segmentation fault have occurred.
By investigation, when the last write task completed and dequeued
the primary write task in spdk_iscsi_task_cpl(), the primary write task
was already dequeued in spdk_clear_all_transfer_task().
This patch dequeues all primary write tasks after all outstanding
tasks complete.
After starting to exit the connection, the connection will not receive
any command. Hence waiting for completion of all pending tasks first will
avoid double dequeue safely.
Change-Id: I8e2b6b756be3a6e096675acc81cdb93fb6a7e350
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/430397
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Forcing bdev_svc to use a single hugetlbfs file causes the crypto bdev
to fail to properly allocate qpairs for qat devices. The qpairs come
back from the dpdk function queue_dma_zone_reserve misaligned.
Change-Id: Ib0c95856031ca89f6528ea6d39ef68e03e2f9009
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/430372
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: Ben Walker <benjamin.walker@intel.com>
The memory restrictions were causing issues with allocating crypto bdev
qpairs when using qat.
Change-Id: I1e8a9799006293cb54f8959cfd24e38c4dee6d0f
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/430104
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.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>
This script should be called when testing the crypto module. It will
configure any qat cards with class code 37c8 for use with the spdk
crypto bdev module.
Change-Id: I233069fbe9ba3c7a6463f52443234f9fe2c9a1f7
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/428549
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
nvmf_create_transport can be run both before and after the subsystems
have been initialized. Therefore, we don't need the --wait-for-rpc
argument in most cases. This eliminates the need for calling
start_subsystem_init.
Change-Id: I35560fb968159b4796b1022b1de9cca4dfc5feeb
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/429983
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: Ben Walker <benjamin.walker@intel.com>
We need additional mocks for structures that were added
in the most recent DPDK release to make our unit tests
build properly.
Change-Id: If6e471528d4cb1dce24fb5d910e9e545fcdaa0f6
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/429987
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Change-Id: I94a59e240744acceca138d56bd141e9aec2e6270
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/429875
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Piotr Pelpliński <piotr.pelplinski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
When trying to run the blockdev.sh test against a crypto bdev using qat,
I consistently got allocation failures on the malloc disks. I believe
that this is because the qat pmds require some amount of dma safe
memory. While the requirement is not huge, it is enough to fragment the
hugepages and make it impossible for us to allocate 7 contiguous 64MiB
buffers. The tests passed when this number was reduced to 32 MiB.
Change-Id: I66716a918123bc69e8b5d19412ac1f9c0b3dd462
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/429534
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@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>
In JSON RPC the ID is optional. Method is mandatory but user might want
to produce the name later or by using
spdk_json_write_named_string_fmt(). This patch also changes the argument
order.
Change-Id: Ifbd35b8c93e684d15731c4ba1d18bf68d1e8a068
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/429254
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
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>
If JSON structure is not known it is hard to use it with current API. To
address this gap lets add API that will give more flexibility the user.
This patch also adds proper unit tests.
Change-Id: I82eb8c8d4a562ee4c9eb5b72c69fe36004dc576e
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/424009
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>
In the case that the subsystem in the related poll group has
NULL IO channel assigned due to some problem like out of resource,
for example, the NVMe SSD hardware itself has limited number
of IO qpairs. The subsystems in the particular poll group
could have zero valid channels. In this case, the creation of
assoicated poll group will fail and when adding the new qpair
to the specified poll group, needs to have a check and pick the
available poll group.
Change-Id: Iedee2a6375e48eb7bf899cfb0542c565c7ebd231
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/423646
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This is inspired by pkg-config dicussion for SPDK packaging. For now it
used during nvme-cli building to remove greps on current configuration
just to discover proper LDFLAGS.
Change-Id: I18b3e7690dc27b8c418cb897e57e224850fa7435
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/428335
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Fix variable name added in patch:
https://review.gerrithub.io/#/c/spdk/spdk/+/429049/
Change-Id: I0349dfd16f784a0cc92ff64beae3389c1de8b55c
Signed-off-by: Pawel Niedzwiecki <pawelx.niedzwiecki@intel.com>
Reviewed-on: https://review.gerrithub.io/429485
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This will resolve out-of-space errors that have cropped
up as SPDK continues to grow. There's no need to copy
*.o files to the mounted filesystem - we 'make clean'
right after the rsync anyways.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I6844183c527953fd4b3329f04171f05e503b04dc
Reviewed-on: https://review.gerrithub.io/429517
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Change-Id: I189ad8889c74937bf43bcf2c3029416ddb94976d
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/425705
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I875cc9d6a6bd1e9e9ac25ca9103a2070226ac236
Reviewed-on: https://review.gerrithub.io/428877
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This function doesn't return error code
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I67a8fa7393990470e509baa8934e78bc6f6a6c9e
Reviewed-on: https://review.gerrithub.io/429441
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
The RAID module is no longer marked experimental and
is now built by default. Using '--with-raid' was giving
us an additional deprecation message:
> --with-raid option ignored and is now deprecated.
> RAID module is always enabled.
Change-Id: If9cc65a4900fc93d07fa88a3ebe3498001916285
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/429179
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: Ben Walker <benjamin.walker@intel.com>
When running these tests, we want to set the transport opts, not
necessarily the target opts. This will also open us up to doing broader
tests in the future against different transports.
Change-Id: I73112f82c371592456c65355f53f7970878a59c3
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/429049
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: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I90f68e9dbe00854f569f6574b9c89508f89caa43
Reviewed-on: https://review.gerrithub.io/428876
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
It's a C libary for client to call rpc method.
Change-Id: I5378747bd9dab83a41801225ba794b3910d1f5a5
Signed-off-by: Liu Xiaodong <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/424061
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The problem with registering the entire hotplugged memory
region is that it won't necessarily be unregistered in one
go. Registering each hugepage separately solves that
problem.
This puts a limitation on the number of pages that can
be allocated when using RDMA. We'll hopefully lift this
limitation sometime in future - probably levereging
ibv_rereg_mr, but for now we'll have to resort to either:
a) using 1GB hugepages
b) preallocating memory (with [-s|--mem-size <size>] app
param) as it will be registered as just one region no
matter what size it is. This memory won't be returned
to the system until the SPDK app exits.
Change-Id: I6de997fb4901b772730ba6fe995dcc0640b85749
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/428716
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.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>
All mem_maps will still receive separate unregister
notification for each registered region, but the
public memory unregister API is more flexible now.
This follows the VFIO_TYPE1v2_IOMMU interface, which
allows the same.
Change-Id: Ifc008afdc6bff39d9b3b4c892c379ade10c3098e
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/428715
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.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>
Added sanity checks to prevent unregistering a memory
range that wasn't registered as a one, complete region.
Change-Id: I819b57560b2e48b0802113ffff9f72949d7a148a
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/425556
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>
Removed the reference count from the registrations map.
Although technically supported, registering a single memory
region more than once had a lot of unhandled cases and could
easily lead to a segfault.
RDMA maps require all memory to be unregistered in the same
chunks the memory was registered, which is often impossible
to achieve if a region was registered more than once:
1. register region 0x0 - 0x3 -> it gets mapped to
a single ibv_mr
2. register region 0x1 - 0x2 -> nothing happens, this region
is already registered
3. unregister region 0x0 - 0x3 -> 0x0-0x1 gets unregistered as
one region. 0x2-0x3 gets
unregistered as another
(leading to segfault in the
the current RDMA implementation)
The problem is that the last two regions share the same ibv_mr,
which SPDK tries to free twice. The second free causes a segfault.
vtophys map handles this case by registering each 2MB chunk
separately, but this solution cannot be applied for RDMA, as
NICs put a limitation (~2048) on the number of regions registered.
Another option is to keep a refcount of each ibv_mr allocated,
and free it only when the entire region was unregistered from the
SPDK mem map. This is however very tricky and RDMAmojo mentions
that freeing a memory buffer before unregistering its ibv_mr
may lead to a segfault.
Change-Id: I545c56e24ffa55bda211dea22aeb8a55d9631fe5
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/426085
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>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Prevents us from unregistering two or more separately
registered regions with a single notification.
This fixes an ibv_mr leak in RDMA. When multiple registrations
were unregistered with a single notification, only the first
ibv_mr one would be freed and the remaining memory would
possibly still remain DMA-able.
As of now, unregistering multiple complete regions with
a single unregister call is not possible. It will be
implemented later, after the rest of the code is cleaned up.
Change-Id: I7d61867fa61fd7a4a8a644ff45cab17125d63e1b
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/425555
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Moved them from test/env/vtophys to test/env/memory
because that's where they should land in the first
place. Our memory ut already test allocating a mem_map,
so just extend them with an extra test case now. Since we're
a unit test rather than a fully-fledged SPDK app, we can
simplify the code a lot now - we no longer have any memory
(hugepages) registered at the beginning of our test case,
hence we no longer need to alloc multiple dummy mem maps to
iterate through all registrations - we can simply hardcode
and predict which registrations are there.
Change-Id: I82cd00ea2ad2370bdc63846874885f8c55e11d53
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/428714
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.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>
Purpose: We need to get the port info in other applications
(e.g., NVMe-oF TCP/IP transport)
Change-Id: I3a4636e764e44425436bb064cb0062c6f3e44035
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/428313
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Large read I/O will be typical in some use cases such as
web stream services. On the other hand, large write I/O
may not be typical but will be sufficiently probable.
Currently when large I/O is submitted to the RAID bdev,
the I/O will be divided by the strip size of it and then
divided I/Os are submitted sequentially.
This patch tries to improve the performance of the RAID bdev
in large I/Os. Besides, when the RAID bdev supports higher
levels of RAID (such as RAID5), it should issue multiple
I/Os to multiple base bdevs by batch fasion in the parity
update. Having experience in batched I/O will be helpful
in the future case too.
In this patch, submit split I/Os by batch until all child IOVs
are consumed or all data are submitted. If all child IOVs are
consumed before all data are submitted, wait until all batched
split I/Os complete and then submit again.
In this patch, test code is added too.
Change-Id: If6cd81cc0c306e3875a93c39dbe4288723b78937
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/424770
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Chandler-Test-Pool: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
