Commit Graph

6081 Commits

Author SHA1 Message Date
Seth Howell
7463b0dea3 mk: standardize DIRS-x assignments.
Most of the assignments followed the DIRS-($(CONFIG_X)) pattern, but
there were a couple of assignments using a different pattern.

Change-Id: I7c80fec2813c32cb7676912d72805565f77b2e3d
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466469
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-29 20:16:18 +00:00
Shuhei Matsumoto
8a80461ac6 nvmf/tcp: execute buffer allocation only if request is the first of pendings
RDMA transport executes spdk_nvmf_rdma_request_parse_sgl() only if
the request is the first of the pending requests in the case
RDMA_REQUEST_STATE_NEED_BUFFER in the state machine
spdk_nvmf_rdma_requests_process().

This made RDMA transport possible to use STAILQ for pending requests
because STAILQ_REMOVE parses from head and is slow when the target is in
the middle of STAILQ.

On the other hand, TCP transport executes spdk_nvmf_tcp_req_parse_sgl()
even if the request is in the middle of the pending request in the case
TCP_REQUEST_STATE_NEED_BUFFER in the state machine
spdk_nvmf_tcp_req_process() if the request has in-capsule data.

Hence TCP transport have used TAILQ for pending requests.

This patch removes the condition if the request has in-capsule data
from the case TCP_REQUEST_STATE_NEED_BUFFER.

The purpose of this patch is to unify I/O buffer management further.

Performance degradation was not observed even after this patch.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Idc97fe20f7013ca66fd58587773edb81ef7cbbfc
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466636
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-29 18:17:38 +00:00
Shuhei Matsumoto
0f73c253b5 nvmf/fc: Replace FC specific get/free_buffers by common APIs
Use spdk_nvmf_request_get_buffers() and spdk_nvmf_request_free_buffers(),
and then remove nvmf_fc_request_free_buffers() and nvmf_fc_request_get_buffers().

Set fc_req->data_from_pool to false after spdk_nvmf_request_free_buffers().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I046a642156411da3935bc2fa2c2816fc2e025147
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465877
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-08-29 18:17:38 +00:00
Shuhei Matsumoto
9968035884 nvmf/tcp: Replace TCP specific get/free_buffers by common APIs
Use spdk_nvmf_request_get_buffers() and spdk_nvmf_request_free_buffers(),
and then remove spdk_nvmf_tcp_request_free_buffers() and
spdk_nvmf_tcp_request_get_buffers().

Set tcp_req->data_from_pool to false after spdk_nvmf_request_free_buffers().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I286b48149530c93784a4865b7215b5a33a4dd3c3
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465876
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-29 18:17:38 +00:00
Shuhei Matsumoto
85b9e716e9 nvmf/rdma: Replace RDMA specific get/free_buffers by common APIs
Use spdk_nvmf_request_get_buffers() and spdk_nvmf_request_free_buffers(),
and then remove spdk_nvmf_rdma_request_free_buffers() and
nvmf_rdma_request_get_buffers().

Set rdma_req->data_from_pool to false after
spdk_nvmf_request_free_buffers().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ie1fc4c261c3197c8299761655bf3138eebcea3bc
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465875
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-29 18:17:38 +00:00
Shuhei Matsumoto
cc4d1f82cc nvmf: Add spdk_nvmf_request_get/free_buffers() usable among transports
This patch adds new APIs spdk_nvmf_request_get_buffers() and
spdk_nvmf_request_free_buffers() to be used among transports.
Subsequent patches will replace transport specific APIs by them.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ib153e2c5806b7276915a0aa91179fe9dbcb2a1f0
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465874
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-29 18:17:38 +00:00
Shuhei Matsumoto
005b053a02 nvmf: Move data_from_pool flag to common struct spdk_nvmf_request
This is a prepration to unify buffer management among transports.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I6b1c208207ae3679619239db4e6e9a77b33291d0
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466002
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-29 18:17:38 +00:00
Shuhei Matsumoto
04ae83ec93 nvmf: Move allocated buffer pointers to common struct spdk_nvmf_request
This is a preparation to unify buffer management among transports.
struct spdk_nvmf_request already has SPDK_NVMF_MAX_SGL_ENTRIES (16) * 2
iovecs. Hence incresing the number of buffers twice will be no problem.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Idb525abbf35dc9f4b8547b785b5dfa77d106d8c9
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465873
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-08-29 18:17:38 +00:00
Mateusz Kozlowski
a3b7ae8ab6 lib/ftl: IO channel handling for nv cache
Moved scrubbing of nv cache to core thread. Added IO channel which is
used in user context, during shutdown of nv cache.

Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Change-Id: I88e680324e361bf7e0c0a9a9d29323f179c56e3b
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465932
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-29 18:10:19 +00:00
Evgeniy Kochetov
01887d3c96 nvmf/rdma: Fix data WR release
One of stop conditions in data WR release function was wrong. This
can cause release of uncompleted data WRs. Release of WRs that are
not yet completed leads to different side-effects, up to data
corruption.

The issue was introduced with send WR batching feature in commit
9d63933b7f.

This patch fixes stop condition and contains some refactoring to
simplify WR release function.

Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: Ie79f64da345e38038f16a0210bef240f63af325b
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466029
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-29 18:09:14 +00:00
Ziye Yang
d50736776c nvmf/tcp: Use a big buffer for PDU receving.
Purpose: Reduce the recv/readv system call.
Method: Use a big recv buffer to conduct the read.
Though it will introduce addtional buffer copy,
we hope that the overhead introduced by buffer copy will
be smaller compared with frequent recv/readv system call overhead.
And the design is to make a trade off between them.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I9286fd9cec0b512cea8e3f2c335c5bf862b98573
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464842
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-28 15:38:02 +00:00
Ziye Yang
ea5ad0b286 nvme/tcp: Change hdr in nvme_tcp_pdu to pointer
Purpose: Prepare the further optimnization in the
target side whening receving pdu headers, we expect
to use zero copy.

Change-Id: Iae7f9106844736d7160d39d0af1f5941084422ec
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465380
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: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-08-28 15:38:02 +00:00
Tomasz Zawadzki
1428692e1a lib/event: remove app.c dependency from loading json_config
Originally loading json_config using spdk_app_json_config_load_subsystem()
implied issuing start_subsystem_init RPC. This required a workaround
in the callback of RPC spdk_rpc_start_subsystem_init_cpl(), in order
to skip starting the app in json_config load path.

This made it difficult to load json_config without implicitly using
rest of the event framework. It will be usefull for example in
fio_plugin, which does not use the app.c API.

With change in this patch json_config load path directly calls
spdk_subsystem_init() C call.
Meanwhile start_subsystem_init RPC no longer needs a workaround
for json_config load path.

Change-Id: I535e079339cedaf0950767a8204002ab5885d8a5
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463978
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>
2019-08-28 15:26:12 +00:00
Tomasz Zawadzki
b85881ec7c lib/event: remove app.c dependency from subsystem initialization
This change adds return code to spdk_subsystem_init().
Making it's caller responsible for handling application
state - such as calling spdk_app_stop().

This change implies that start_subsystem_init RPC does not
stop the application on failure, only reports back the error.

Renamed g_app_start/stop variables to now more relevant
g_subsystem_start/stop.

Change-Id: I66a7da6ecfb234a569c65279cc4b210ddac53d2a
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464412
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>
2019-08-28 15:26:12 +00:00
Pawel Kaminski
139e4c0783 lib/rpc: Add include_aliases flag to rpc_get_methods implementation.
When getting the list of available RPCs from a tool like rpc.py,
aliases often should be hidden.
However, when getting the list of RPCs available
for loading from a JSON config file, aliases should be included.

Change-Id: Ie22d8b0ec2515d37dbfadf01b5cb709c160beb3e
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465656
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-08-28 15:19:17 +00:00
Konrad Sztyber
1f133d7279 lib/ftl: track defragged bands in ftl_reloc
Track the band under defrag inside the reloc module.  This allows for
multiple bands being defragged at the same time (e.g. extra one due to
write fault) as well as makes it easier to handle cases when relocating
a band that has no valid blocks.

Change-Id: Ia54916571040f5f4dfdb8f7cdb47f28435a466d8
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465937
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-27 18:55:40 +00:00
Seth Howell
407e88fd2a lib/mk: update OCF build.
The OCF build was broken by some of the recent changes
to the Makefiles. This change aims to fix that by separating out the ocf
environment from the ocf bdev.

Change-Id: Id445340033898e9ae70a4bcfc799951110762d55
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465808
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>
2019-08-27 18:49:56 +00:00
Maciej Szwed
79ed1ba18d bdev: Add spdk_bdev_open_ext function
This patch adds new interface for opening bdev and
implements new style remove event. With that changes
user can be notified about different types of events
that occur in regards to bdev. spdk_bdev_open_ext
function uses bdev name as an argument instead of bdev
structure to remove race condition where user gets
the bdev structure and bdev is removed after getting
that structure and before open function is called.

spdk_bdev_open is now deprecated.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I44ebeb988bc6a2f441fc6a0c38a30668aad999ad
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/455647
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-08-26 19:07:56 +00:00
Shuhei Matsumoto
eab7360bcb nvmf/tcp: Factor out getting and filling buffers from nvmf_tcp_req_fill_iovs
This follows the practice of RDMA transport and is a preparation to
unify buffer allocation among transports.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ib85625f2a0eca01ef4028685dd838d6c41faad7b
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465872
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-26 19:04:24 +00:00
Shuhei Matsumoto
72c10f7094 nvmf/tcp: Use spdk_mempool_get_bulk in nvmf_tcp_req_fill_iovs
This follows the practice of RDMA transport and a preparation to
unify buffer management among transports.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I4e9b81b2bec813935064a6d49109b6a0365cb950
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465871
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-26 19:04:24 +00:00
Shuhei Matsumoto
8aac212005 nvmf/tcp: Pass number of alloc buffers s as param to nvmf_tcp_request_free_buffers
This is a preparation to the next patch to use spdk_mempool_get_bulk.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I28a5ad941004f139c9032d85c2ef92680081f1ce
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465870
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-26 19:04:24 +00:00
Shuhei Matsumoto
5437470cdc nvmf/fc: Factor out getting and filling buffers from nvmf_fc_request_alloc_buffers
This follows the practice of RDMA transport and  is a preparation to
unify buffer allocation among transports.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I3cd4377ae31e47bbde697837be2d9bc1b1b582f1
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465869
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-26 19:04:24 +00:00
Shuhei Matsumoto
71ae39594f nvmf/fc: Use buffer cache in nvmf_fc_request_alloc/free_buffers
FC transport can use buffer cache as same as RDMA and TCP transport
now. The next patch will factor out getting buffers and filling
buffers to iovs in nvmf_fc_request_alloc_buffers().

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I0d7b4552f6ba053ba8fb5b3ca8fe7657b86f9984
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465868
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-26 19:04:24 +00:00
Shuhei Matsumoto
fbb0f0faf9 nvmf/fc: Pass transport and num_buffers as params to nvmf_fc_request_free_buffers
This is a preparation to the next patch to use buffer cache in
FC transport.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I116b064ea0b0a437f9a3293a6f3d46a0e5fc8ecf
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465867
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-26 19:04:24 +00:00
Shuhei Matsumoto
e3b8c31d03 nvmf/fc: Use spdk_mempool_get_bulk in nvmf_fc_request_alloc_buffers
This follows the practice of RDMA transport and a preparation to
unify buffer management among transport types.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ic7dc8e6b826baf7f471d192630e8a048a35056ac
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465866
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.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>
2019-08-26 19:04:24 +00:00
Shuhei Matsumoto
c5b15dde18 nvmf/fc: Use common buffer pool for FC transport
NVMe-oF FC transport have used its own buffer pool and have not used
common buffer pool yet.

It looks that there is no particular reason to prevent FC transport
from using the common buffer pool.

This patch removes FC transport specific buffer pool and changes
FC transport to use common buffer pool instead. Add transport
as a parameter to nvmf_fc_request_free_buffers() because similar
APIs of RDMA and TCP transport do that.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Iae3a117466c21eaddbe78a8e8023d80ef37bb3e9
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465865
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.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>
2019-08-26 19:04:24 +00:00
Shuhei Matsumoto
cdf80adccc nvmf/fc: Check if buffer came from pool prior to nvmf_fc_request_free_buffers()
NVMe-oF FC transport have used its own buffer pool and have not used
common buffer pool yet.

It looks that there is no particular reason to prevent FC transport
from using the common buffer pool.

This patch extract checking fc_req->data_from_pool from
nvmf_fc_request_free_buffers() to make the transition easier.

fc_req->req.iovcnt and fc_req->req.data should be cleared regardless
of fc_req->data_from_pool. Hence extract them into callees.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I36420f0e573d1ec3f9f3a75f6b2ced82ade89dd3
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465864
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.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>
2019-08-26 19:04:24 +00:00
Shuhei Matsumoto
cbd3500019 nvmf/fc: Use common setting to FC specific data buffer pool
NVMe-oF FC transport have used its own buffer pool and have not used
common buffer pool yet.

It looks that there is no particular reason to prevent FC transport
from using the common buffer pool.

This patch adjust the setting of the FC transport specific buffer pool
to the common buffer pool to make the transition easier.

Large alignment requirement consumes more memory but is acceptable.
Cache size calculation looks dated.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Id3224b65f39187c4d8e99c00cf54b1cfdd902250
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465863
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-26 19:04:24 +00:00
Jim Harris
32e22643ef nvme: add NVME_QUIRK_DELAY_BEFORE_INIT quirk
Currently we *always* wait 2 seconds before starting
controller initialization during attach.  This
works around an issue where some older Intel NVMe SSDs
could not handle MMIO writes too soon after a PCIe
FLR (which would be triggered when VFIO was enabled).

After further discussion with Intel experts, we know
the SSD models that exhibit this issue.  So we can
quirk this so that only the older SSDs incur the extra
delay.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ieb408c24f6afd5bd5147d1c87239aa20f2d13511

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466064
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: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-08-26 17:35:06 +00:00
Darek Stojaczyk
d1d69a169c vhost: remove session type checks
When rte_vhost tells us to start a session with given
vid, we lookup the corresponsing session object from
an spdk-internal session list and tell it to start
polling without even specifying any backend. The vsession->vdev->type
checks could only fail as a result of some spdk data
corruption, so replace those with just asserts now. This
code path could have never been hit in our tests anyway.

Change-Id: I97c6cbe7088f338b684d291c93cbc59c44cfdc4e
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466042
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-26 17:24:04 +00:00
Darek Stojaczyk
bfaa737dff vhost/blk: unify error message format
Error messages are extremely chaotic, so unify them to
a single format:

<session name>: <error string>

Change-Id: I9b4c29321700b485e0e7eb71a73ea094cf02f000
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466041
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-08-26 17:24:04 +00:00
Darek Stojaczyk
cf86621327 vhost/scsi: unify error message format
Error messages are extremely chaotic, so unify them to
a single format:

<session name>: <error string>

Some messages were slightly reworded to make them more clear.
I believe it would make sense to replace some of those ERRLOGs
with TRACELOGs, but that's not going to change now.

Change-Id: I32fa38b3bf26998b418b8b9e68c88ec5022c973f
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466040
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-08-26 17:24:04 +00:00
Darek Stojaczyk
e5d7a44581 vhost: introduce session names
We currently don't have any way to differentiate different
sessions e.g. in error messages. Whenever there's an error
in some session, we just print the device name.

We now introduce vsession->name with the following format:
<device name>s<dpdk connection id>

Note that it's still impossible to know exactly which
qemu process corresponds to which session in spdk, but
there's not much we could do in that matter right now.
In spdk we don't even have the accepted connection fd.

Change-Id: I666aa60c5e36bf3d56f68133042af2afc8cc5e85
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466039
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-26 17:24:04 +00:00
Darek Stojaczyk
f12ac17189 vhost: change vsession->id to uint64_t
This id is assigned from a global increment-only counter
whose type is uint64_t. I believe the original intent
was to use uint64_t for vsession->id as well, let's fix
it now to avoid wrapping errors.

Change-Id: I9cae87e6c74400590a1dc1b1f91d51e4a4c13499
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Acked-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466038
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@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>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-23 22:34:02 +00:00
Darek Stojaczyk
3b6f69c8f5 vhost: remove unnecessary membarrier on I/O completion
We've recently switched from manually calling eventfd_write()
to rte_vhost_vring_call(), which besides writing to the
eventfd, always calls a full memory barrier in the upstream
rte_vhost lib. With upstream rte_vhost we're actually
calling two memory barriers on I/O completion - one in
spdk code, one inside rte_vhost_vring_call().

The spdk barrier was only required for our internal rte_vhost
lib, whose rte_vhost_vring_call() implementation (that we
wrote) did not have such membarrier inside. So now we'll
add this membarrier there, and remove the same barrier
from spdk code.

This doesn't change any code flow for the internal rte_vhost
lib, but optimizes I/O path for the upstream version.

Change-Id: I68738d7feb9159f718b0e60ac7eed1fafd4836b9
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466037
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-08-23 22:34:02 +00:00
Shuhei Matsumoto
703a5473f7 iscsi: Restore the previous bug fix for LUN hot plug
One recent commit destroyed the critical bug fix for LUN hot plug.
Hence this patch restores the critical bug fix. Simple revert is
not possible because connections are assigned to poll groups
instead of cores now. But we can revert easily because earlier
version of the recent patch did that.

Fixes #925

The github issue was caused by commit 8cf1945432.
The bug fix restored by this patch is commit 1f6a78620d.
The reference we can follow to create this patch is earlier version
of commit fb641c4b54.

Reported-by: yidong0635 <dongx.yi@intel.com>

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Change-Id: Ie1ba14a59ce48149a8474cbffc56aa08adc1fc4d
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466108
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-23 18:09:16 +00:00
Ben Walker
6aff44ccbb event: Move spdk_reactors_fini higher up in file
Change-Id: I07a96c0a4eaabd762da684a577381ec95410d32d
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465992
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-08-23 17:51:26 +00:00
Ben Walker
2139bfa91f event: Move spdk_reactors_init up in file
Begin organizing file so setup operations appear
at the top.

Change-Id: I7411b4bf20480c8aeb40bc21b521e5d359f8da1f
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465991
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-08-23 17:51:26 +00:00
Seth Howell
9d14641dd5 mk: add a lib deps file.
By adding this file and modifying the way we define a couple of
variables in the makefiles, we can actually avoid having to redefine
the library dependencies on a per file basis.

Change-Id: Ieab4aa1021b0341fc21e3b65677a9ad7f70559c2
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466063
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: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-08-23 17:48:35 +00:00
Tomasz Zawadzki
cfc0fbf11e bdev: fix error path for allocating qos paramters
Every exit path in spdk_bdev_set_qos_rate_limits() should
go through _spdk_bdev_set_qos_limit_done() as soon as
ctx is allocated and qos_mod_in_progress set to true.

This patch fixes one path were it did not occur.
With this change qos_mod_in_progress is set to false,
when failure in allocating qos parameters occurs.

Change-Id: I04a45dfdcde9160fd2701b44f5fde26fb0245177
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465659
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-08-23 17:31:52 +00:00
Ben Walker
fd0f036480 event: Relax restriction on g_reactors not being NULL
There is a case in vhost where this occurs. Until that is
sorted out, just make this a warning.

Change-Id: Id021791e8cbddf3023e0cb1b8c52a733b3578a7d
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/466075
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-22 21:14:11 +00:00
Seth Howell
f196669374 lib/copy: move ioat subdir to module directory.
Change-Id: I29b31344a11efd2430e0f77062fb98fa0ab1c71e
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465458
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.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>
2019-08-22 16:29:49 +00:00
Seth Howell
7392cdeff7 lib/blob: move bdev subdir under module directory.
Change-Id: Ifb9a1df919d32a98c328101029cc22e91915a977
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465457
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.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>
2019-08-22 16:29:49 +00:00
Seth Howell
c77565ee04 lib/sock: move subdirs to module/sock
Rounding out the module concept of SPDK libraries.

Change-Id: I2b316153809ae9f73361648fe505274a59d0bdb3
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465456
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.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>
2019-08-22 16:29:49 +00:00
Seth Howell
f34fa35a52 lib/event: move rpc and subsystems dirs to module
These directories fit in with the module concept we are forming inside
of SPDK. Essentially modules are derivative or specialized libraries that
rely on a general or core library.

Change-Id: Ib40f05422f144ff8fd579f47a3867ef4412b3372
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465455
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: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-22 16:29:49 +00:00
Seth Howell
07fe6a43d6 mk: move the bdev modules under module directory.
This is more accurate to what they are, and will make defining library
dependencies much simpler. This change in directory does not affect the
final placement of naming of libraries at the end of time.

Change-Id: Ic48a9233dff564e39ce357a9ea0a111ea2b6414b
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465454
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-22 16:29:49 +00:00
Ben Walker
085ade57fc event: Add additional checking around valid reactors
Try to catch mistakes when using invalid cores.

Change-Id: I3caef9d3898ab76f80a45799cb4305601fb02f2a
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465990
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: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-08-22 14:55:42 +00:00
Ben Walker
e30e1596b2 event: Remove rusage_poller
This was unused. The rusage polling is done in another way.

Change-Id: I478ddb2d664647e922f3049a64199fdc61f25ce1
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465989
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: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-08-22 14:55:42 +00:00
Tomasz Zawadzki
c8dfae7b8f lib/event: expose spdk_app_json_config_load() in internal header
Expose spdk_app_json_config_load() in internal to SPDK header.
In future patches it will be possible to use this function
without depending on rest of event framework (such as app.c).

Applications that do not use SPDK reactors (have their own threading
model) or no need to initialize using spdk_app_start(), will be
able to utilize subsystems and their json configuration loading.

Change-Id: I093181977d121e39ddbf212f8dff3182a4102fd6
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464178
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-22 14:53:28 +00:00
Ben Walker
f8d687bdb6 iscsi: Properly unregister iscsi_tgt io_device
Fixes #923

Change-Id: I5c1e02a7d6e2e22db9c0a1345c03a351e07a15d4
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465976
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-22 14:50:45 +00:00
paul luse
7e1f967c13 bdev/compress: support host buffers that cross a 2MB boundary
Only affects QAT where only partial data transfers would occur
when a host buffer crossed a 2MB boundary.

fixes issue #897

Change-Id: Ib20bfb3557c11a6da996f4b209e9bb7c634f8f49
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464719
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: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-08-22 04:34:18 +00:00
paul luse
68e7da44ec bdev/compress: add RPC to list orphaned comp bdevs
The previous patch in this series introduced the notion of an
orphan comp bdev which is available only for deletion due to
a missing PMEM file.  This RPC allows applications to list
orphaned comp bdevs as they will not show up with get_bdevs
because they are not registered bdevs.

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I431f9cdebd4e5ae6068308639cb41d6c52f7309b
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465812
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>
2019-08-22 04:31:46 +00:00
paul luse
09824fa0e7 bdev/compress: enable deletion of a vol w/o a pmem file
When a vol load fails because of a missing pmem file, instead of
doing nothing we now claim the underlying bdev and make an entry
in our global list for a comp bdev so that the regular delete
RPC can be used to delete the comp bdev.

fixes issue #890

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Icd5357060648e722f94e8f6b9038c8dad032feb3
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465807
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-22 04:31:46 +00:00
paul luse
fd646a28dc bdev/compress: move function
So it can be called from an earlier one in the next patch.

Change-Id: I1e79669d33d84e54c27305e38076cbdafea627e3
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465986
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: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-08-22 04:31:46 +00:00
paul luse
804ce73296 bdev/compress: factor out setting the comp bdev name
Will be re-used in an upcoming patch.

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I676beb7f61c100043189c56484a41c209cd2942d
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465829
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: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-08-22 04:31:46 +00:00
paul luse
a480b18eda bdev/compress: update internal delete function to delete by name
Needed in upcoming patches.

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I0db6f2e4aa99e9c1e3b1080dc63e50291a6f5938
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465825
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-22 04:31:46 +00:00
paul luse
ffc17e6e94 lib/reduce: enable deletion of a vol w/o a pmem file
First is a patch series that enables an application to delete
a compression vbdev when the volume is missing it's pmem file.

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ida639d2c231833f23131926d442ad430ec903e03
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465805
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-22 04:31:46 +00:00
Wojciech Malikowski
a4881cf82f lib/ftl: Check if write buffer is empty during shutdown
Added assertion to check is there is no any
acquired write buffer entries during shutdown.

Change-Id: I92be8ff07b2bf338acb65a0e37d0cc6ad6962d81
Signed-off-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462934
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: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
2019-08-21 23:14:25 +00:00
Wojciech Malikowski
b08337c216 lib/ftl: Fix padding size calculation
Padding size calculation should take into account
already acquired write buffer entries in case
number of blocks left for closing band is less than
write buffer size.

Change-Id: I0f9c9bc94eb5a4736eede30ec424c81103e1256f
Signed-off-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463525
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@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>
2019-08-21 23:14:25 +00:00
Maciej Szwed
7a260a5e99 bdev: Create generic _spdk_bdev_open function
This is a part of a change that will introduce
new spdk_bdev_open_ext function. This will make
possible to pass callback function while opening
bdev which will be called when some bdev events
occur.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I3e552edd5c90dacd39885e75e9114e48dddf50ea

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463157
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>
2019-08-21 22:39:07 +00:00
Maciej Szwed
c141bd94a1 bdev: Don't open bdev if it is being removed
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I7ddff2d1186ff3c03de9b48c79297b03957002c4

Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463156
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>
2019-08-21 22:39:07 +00:00
Seth Howell
f8433aad23 rpc/nvmf: add tgt_name options to relevant RPCs.
All of the RPCs in lib/nvmf/nvmf_rpc.c rely on knowing which nvmf_tgt
they should work with. They have historically relied on the assumption
that there will only be a single target in a given application. This is
true for the example application in the spdk repo, but it is not
necessarily true generally,

By adding an option tgt_name parameter to the RPCs we enable them for
multi-target NVMe-oF applications. We also further reduce the coupling
between the library and the example application.

Change-Id: I03b6695da05a42af3024842ed87d2ce2c296f33f
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465442
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2019-08-21 17:20:28 +00:00
Seth Howell
a54a6a266c lib/nvmf: extract RPCs from the subsystem directory
There are one or two RPCs that deal with application specific
configuration. We can leave these there for now.

Change-Id: I9c40aa3403d32d3e2214c8c904fb1c414ad99967
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465365
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-21 17:20:28 +00:00
Seth Howell
c795aa70cf nvmf_rpc: remove references to g_spdk_nvmf_tgt
The global nvmf target is really an example application specific
feature. This should be separated from the generic RPC functions as much
as possible.

Change-Id: I7671aa88c20a39129aa13d1a7100b537bf34b00d
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465364
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>
2019-08-21 17:20:28 +00:00
Seth Howell
79d876716c nvmf: add spdk_nvmf_get_tgt function
This function will allow applications (and RPCs)
to obtain an spdk_nvmf_tgt pointer by name.

Change-Id: I82792e06a819e06d9fddb5429830008653d92cd1
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465349
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-21 17:20:28 +00:00
Maciej Wawryk
40c959cbcc RPC: rename RPC crypto_bdev series
RPC: rename RPC delete_crypto_bdev to bdev_crypto_delete
RPC: rename RPC construct_crypto_bdev to bdev_crypto_create

Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: Ib93714504ee7a97cbbe36457f7826f0af69b1fe5
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465057
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-08-20 22:44:58 +00:00
Maciej Wawryk
9a91a45c99 RPC: rename RPC compress_bdev series
RPC: rename RPC construct_compress_bdev to bdev_compress_create
RPC: rename RPC delete_compress_bdev to bdev_compress_delete

Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Change-Id: I768825269967e6af079e87094a4b3ce0b11444ab
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465051
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-08-20 22:44:42 +00:00
Maciej Wawryk
acaa079b20 RPC: rename RPC aio_bdev series
RPC: rename RPC construct_aio_bdev to bdev_aio_create
RPC: rename RPC delete_aio_bdev to bdev_aio_delete

Change-Id: I09ffc3cc0d2117f7210be7920bffddb9d7c7f30c
Signed-off-by: Maciej Wawryk <maciejx.wawryk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465035
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-08-20 22:44:20 +00:00
Chunyang Hui
0fae4f64c4 Opal: Add support for erase locking range
Change-Id: Ie40ea642bc266f84ad5a3dbad8012b9eac178360
Signed-off-by: Chunyang Hui <chunyang.hui@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465244
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-08-20 20:38:54 +00:00
Seth Howell
f46b63e3e0 bdev/delay: fix latency reporting.
The arithmetic was backwards when computing the latency values to
report back to rpc calls like get_bdev. This caused reasonably sized
latency values to report back 0.

Change-Id: I85e22c9c8aa202a2ac1db7e7081f397800b151b8
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465168
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-08-20 20:35:59 +00:00
Seth Howell
8d6d26bd29 nvmf: add a name entry to the spdk_nvmf_tgt struct
This will provide a unique identifier which can be used to provide get
and set methods within the RPCs.

Change-Id: Idd144e99e49b8d26530f60530d2e908b18fa251b
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465330
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>
2019-08-20 19:15:04 +00:00
Seth Howell
7d6d95db3c nvmf: change the function signature of spdk_nvmf_tgt_create
This is necessary to allow the spdk_nvmf_tgt structure to evolve over
time without having to further change the target API.

Change-Id: Ib0f0f9b1f190913feff0229c96df4e84b1bf35f7
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465363
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.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>
2019-08-20 19:15:04 +00:00
Seth Howell
0ac5050624 lib/nvmf: add a global list of targets
As part of moving the nvmf rpc code to the library, we will need to make
it more inclusive of use cases outside of the example spdk nvmf_tgt
application. That application only supports a single nvmf target
structure. As such, many of the RPCs have this assumption built into
them.
In order to enable the multi-target use case, we need to configure a way
to translate between user supplied RPCs and actual target objects in the
library.

Change-Id: I5d3745afe9c2ca1c33f6e1a1bcc2b8bb3196ccd6
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465329
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>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
2019-08-20 19:15:04 +00:00
Seth Howell
ff69b368b8 lib: combine event/iscsi_rpc with lib/iscsi/iscsi_rpc.c
Part of a larger series simplifying the library directory.

Change-Id: Ib9c9dc9a0c92ac35a9f0260451f97fc126d10031
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465212
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>
2019-08-19 06:10:30 +00:00
Seth Howell
edc8c91a90 lib: move bdev_rpc under lib/bdev
Part of a larger series unifying and simplifying the library directory
structure.

Change-Id: I2782165aabbea9a31cc466fc7e3bb2b9263142dc
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465211
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>
2019-08-19 06:10:30 +00:00
Seth Howell
bc83adc2db lib: move trace_rpc into lib/trace
Combinining these two libraries removes some directory complexity. It
also helps us to align on a common practice for including the rpc code
with a given module. This is how all of our bdev modules already do it.
The nbd, net, and scsi modules also follow this pattern.

Change-Id: I5e4c99d7f0facacc6dfe30b2274b60e0d151f8d8
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465210
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>
2019-08-19 06:10:30 +00:00
Seth Howell
ef6108a7eb lib: move notify_rpc under lib/notify
This is part of a larger series aimed at simplifying/flattening the
directory structure of the SPDK lib directory. The ultimate goal of this
series is to properly create dynamic linker dependencies between all
spdk shared objects.

Change-Id: I6beb7103404ae2c24a3d25dd93a1061680c7176c
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465209
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>
2019-08-19 06:10:30 +00:00
paul luse
3966e0bf2e bdev/crypto: assert that a QAT DMA never crosses a 2MB boundary
Because required alignment is already set to block size and by design
the crypto module does one crypto operation per block (it uses the
LBA as the initialization vector) it should not be possible to get
a physical address that spans however adding an assert just in case.

Change-Id: I1dc844d0a32395f9ed4869429368f60b919703a4
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465107
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>
2019-08-15 21:18:02 +00:00
Seth Howell
9d1e4260cb mk: move log_rpc from inside log
The log_rpc library has several dependencies which depend upon the log
library. This creates a circular dependency chain that makes single
threaded make unwieldy and makes multi-threaded make impossible.

Change-Id: I35e6532afcabce0f25974ed97444a56975654904
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465192
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>
2019-08-15 20:32:28 +00:00
Pawel Kaminski
7964f1df90 scripts/rpc: Change rpc construct_malloc_bdev to bdev_malloc_create
This is patch that implements changes according to proposal
submitted in https://review.gerrithub.io/c/spdk/spdk/+/453036

Change-Id: I5423cd34cb5fc111b34cab2b7f7c6c5f11898af8
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464677
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-14 22:15:08 +00:00
Pawel Kaminski
6fdd36e100 nbd/rpc: Add logs with more information about rpc error.
Now if rpc fails ambiguous logs are printed.
Use more descriptive errors.

Change-Id: I7bd3a9e9d94d42fd1effb74f48c5de331b419440
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462627
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-14 22:11:40 +00:00
Changpeng Liu
6ddbcc0301 blobfs: use __wake_caller() to wake up the caller
__fs_create_file_done() is just used to wake up the caller
in synchronous API.

Change-Id: I08611eab74ab353021d5e9d7a33fe825f4c5a8c2
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464362
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>
2019-08-14 21:41:36 +00:00
Ben Walker
1e82ec0640 nvmf: Delay sending AER until subsystem resumes
Change-Id: Id5152a793c6b530cb1419c559ac3ed71ee042037
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464614
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-14 21:24:27 +00:00
Jim Harris
0aa72ffb74 nvme: fix WRITE_TO_RO_RANGE status code
WRITE_TO_RO_PAGE was incorrect and misleading.  This
0x82 NVMe status code indicates a write to a read-only
range of LBAs.  So modify the constant name and
associated usages to use WRITE_TO_RO_RANGE instead.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I993dbebb5acc2e685a0e99aa14084942ef79d659
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/465083
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-08-14 02:19:49 +00:00
Changpeng Liu
2226750a7c nvme: add an option 'no_shn_notification' to driver
spdk_nvme_detach() will do the normal shutdown notification for
most cases, and it will take some time e.g. 2 seconds to finish
the process for PCIe based controllers.  If users' environment
has several drives, each drive will call spdk_nvme_detach() one
by one, and the shutdown process may take very long time.

Since users know exactly what they would like to do for the next
step, so here we provide an option to users, users can enable it
to skip the shutdown notification process so that they can have
very quick shutdown process, and when starting next time, the
controller can be enabled again.

Change-Id: Ie7f87115d57776729fab4cdac489cae6dc13511b
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463949
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-13 22:50:03 +00:00
Changpeng Liu
5adac19ad0 blobfs: return error to caller when loading a bs which isn't blobfs
Also release the IO channels with filesystem data structure.

Change-Id: I75a5d427fe4837ad7d85444d09ded9ab41e0ca8e
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464851
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>
2019-08-13 17:12:02 +00:00
Changpeng Liu
62202dda32 blobfs: use macro instead of hardcoded BLOBFS string
We used "BLOBFS" as the signature when loading from blobstore, so define
a macro here.

Change-Id: Iff504a36686c2bc08c90c49b8a505b5533b62508
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464850
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>
2019-08-13 17:12:02 +00:00
Seth Howell
d2424824a1 bdev/delay: make latencies reconfigurable.
This will allow us to do interesting things in tests like configure a
bdev with a really long delay, and allow I/O to build up on a target to
see what happens, then decrease the latency to allow traffic to flow
through normally without ever having to delete and reconfigure the bdev.

Change-Id: Ibcb1101f8eed9fe3094ba239110cb4e49ace6554
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464454
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-13 16:56:01 +00:00
Shuhei Matsumoto
7877ddc86e iscsi: Use cached host and port name of connection widely
portal_host and portal_name were added to struct spdk_iscsi_conn long
ago but had not been used yet. Portal group and its portals can be
removed dynamically even if there is any binded connection. Using
cached pg_tag will avoid potential errors.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I56d02664a3e8b2398bbb9162b1c85856e991b5b4
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463879
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-13 15:46:17 +00:00
Shuhei Matsumoto
f338b43a86 iscsi: Use cached portal group tag of connection widely
pg_tag was added to struct spdk_iscsi_conn long ago but had not
been used yet. Portal group and its portals can be removed
dynamically even if there is any binded connection. Using cached
pg_tag will avoid potential errors.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ic7a96ef97c3cab7e5a58aa7f439364b53694a1e4
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463874
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-13 15:46:17 +00:00
Shuhei Matsumoto
23eb38f1ac iscsi: Use fixed size string for host and port name of connection
This will reduce the potential malloc failure.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Ibcd631bf318ef6ece4ac337219652323ca5fd8f1
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464136
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>
2019-08-13 15:46:17 +00:00
paul luse
2c35c8fbea bdev/compress: re-type and re-name misleading variable name
Becomes important in next patch

Change-Id: Ida19f0b59c4b841d6f5120f9130e24b57ae91560
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464717
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-12 21:37:21 +00:00
Mateusz Kozlowski
0cb8a3319c lib/ftl: Update initialization of io channel
Changed initialization of io channels to be made in the core/read
thread themselves. This fixes potential hangs when using the ftl lib
directly, without bdev and initializing an ftl device from a different
thread than will be used for IO.

Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Change-Id: I7089cc46cc6de5e9008e7c22cc01d2b4103ebb14
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464891
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-12 21:37:13 +00:00
Shuhei Matsumoto
ff9d333171 iscsi: Move macros to define max port name from portal_grp.h to iscsi.h
This is a preparation to the next patch which will change portal_host
and portal_port from malloc to fixed size.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I0f95d969edfd88efde41a43eaf0426fcd4b98987
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464135
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-12 21:31:44 +00:00
Shuhei Matsumoto
1738ec7a9e iscsi: Simplify duplicated target pointers in iscsi_op_login_phase_none
conn->target is initialized to NULL in iscsi_op_login_phase_none
and then configured in iscsi_op_login_session_normal. Hence
subsequent references to target node can be done by conn->target and
related local variables can be removed.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I68b94cb8e136522ef1e0ed74c0035ec2b666bb9e
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463700
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-12 21:31:44 +00:00
Seth Howell
8f71ab3a2b mk: use the env shared lib when linking apps
Previously, aplications were always being linked against the
spdk_env_dpdk.a file even during the shared object build. Change this to
be consistent with our linking.

Also, the old behavior causes issues with resolving symbols in FreeBSD.

Change-Id: I96e2e6044c16e7579cff35ad46e3688ce6fa2b5a
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464733
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>
2019-08-12 21:12:16 +00:00
Seth Howell
e29c6fe133 mk: force --no-as-needed for spdk libs.
When building shared libs, we specifically don't set the --as-needed
flag so that we still link against libraries that have constructor
functions. LD reports on its man page that the default behavior is
equivalent to --no-as-needed.

For RHEL based distros like fedora and centos this works fine. While
the LD man page shipped with ubuntu distributions also states that
--no-as-needed is the default, they don't respect that behavior and do
--as-needed linking unless you force them with --no-as-needed.

Change-Id: I914ab849323de198af5c5e53fffb1f57fcaff5fe
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464621
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>
2019-08-12 21:12:16 +00:00
Shuhei Matsumoto
b3cf508f56 iscsi: Make get_iscsi_connections RPC asynchronous
iSCSI poll groups are bind to SPDK thread through IO channel now.

This patch changes get_iscsi_connections RPC from synchronous to
asynchronous by using spdk_for_each_channel.

Core ID was removed from the output of the RPC but thread name
is added to the output of the RPC in this patch.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I20fdb7f11434acf838a89435ba5052b19869181c
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463569
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>
2019-08-12 20:49:36 +00:00
Shuhei Matsumoto
9a17b539f9 iscsi: Factor out JSON information of connection
Factor out writing connection information to JSON context into
a helper function spdk_iscsi_conn_info_json.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I3e92bcb4f21cc7a36af182f850c944b8c5dd559f
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463568
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: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-08-12 20:49:36 +00:00
Ben Walker
fb641c4b54 iscsi: Assign connections to poll groups instead of lcores.
This patch binds poll groups to SPDK thread through IO channel and
assigns connections to poll groups instead of cores.

iSCSI subsystem registers iSCSI global object as an IO device, and create
poll groups as context of IO channels of the IO device.

Each portal get and hold portal group on which the corresponding acceptor is
running.

When a connection is constructed, iSCSI subsystem assigns a poll group
to the connection by getting it from the corresponding portal.

When a connection enters full-feature phase, iSCSI subsystem schedules
the connection to a poll group by round-robin.

Then, each connection can know its running SPDK thread directly and can
use SPDK message passing infrastructure instead of SPDK event framework.

By this change, iSCSI connections are binded to SPDK thread, and not
binded to processor core anymore.

Some other changes in this patch are
- core ID is removed from the output of get_iscsi_connections RPC. The
  upcoming patches will change the RPC to use spdk_for_each_channel and can
  access SPDK thread safely, and add SPDK thread ID instead.
- utilize UT multithread framework added by the last patch to test
  iSCSI poll groups by UT.

Change-Id: Iec73c778aa413bcabdb63141cc41d4160911ea0e
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463359
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-12 20:49:36 +00:00
Evgeniy Kochetov
42dec8ffa2 bdev/null: Pack constructor parameters into a structure
Null bdev constructor parameters are packed into a single structure to
simplify future extensions.

Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I2c542c159d21703147c3a5b910fcc853bb5db890
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464776
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.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>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-12 20:41:31 +00:00
Evgeniy Kochetov
e06e34be1d bdev/null: Fix infinite loop in configuration parsing
Invalid configuration file parameter in Null bdev section results in
infinite loop.

Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I79a1a53e0f4d76a8724e7a624cabda7250b511c5
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464775
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.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>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-12 20:41:31 +00:00
Shuhei Matsumoto
e5f28d5d39 bdev/raid: Unify data type of number of base bdevs to uint8_t
Data type of number of base bdevs are corrupted. uint8_t is enough
and unify almost all related variables into uint8_t.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I323aaa229a76c3d5b5361d7643c3a9591ccad340
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464357
Reviewed-by: yidong0635 <dongx.yi@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>
2019-08-12 04:20:15 +00:00
Shuhei Matsumoto
441ecc09ae bdev/raid: Check if required params are specified when parsing .INI config file
Checking if required parameters strip_size, num_base_bdevs, and
raid_level had been done in raid_bdev_config_add(). However, this
required us to use integer type.

If we do the check in raid_bdev_parse_raid(), we will be able to
use the same type between function parameters and variables of
struct, and hence do in this patch.

This will align with the next patch.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I10fd75f25ed9a5d40eb189b05c2a20c276fa3ad6
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464365
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: yidong0635 <dongx.yi@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-12 04:20:15 +00:00
Shuhei Matsumoto
284aca9e36 bdev/raid: Fix race issue among multiple threads to free RAID bdev
The following issue was observed.

The first thread returned the last IO channel and the second thread
then removed the first base device, but raid_bdev_cleanup() was
called before raid_bdev_destroy_cb() was called.

raid_bdev_destroy_cb() was accessed to the raid bdev already freed
by raid_bdev_cleanup() and caused segmentation fault.

The call sequence was as follows:

The first thread:
 spdk_put_io_channel() -> ch->destroy_cb -> raid_bdev_destroy_cb
-> access raid bdev

The second thread:
 raid_bdev_remove_base_devices() -> raid_bdev_deconfigure() ->
spdk_bdev_unregister() -> spdk_io_device_unregister() ->
spdk_bdev_destroy_cb() -> raid_bdev_destruct() -> raid_bdev_cleanup()
-> free raid bdev

The fix is to hold number of created channels in struct
raid_bdev_io_channel and use it in raid_bdev_destroy_cb().

Bdev layer, IO device/channel layer, and NVMe-oF layer  already
process this case correctly.

    Fixes #884.

Reported-by: yidong0635 <dongx.yi@intel.com>

Change-Id: Ie9d61bdddca479ce7f491ff9a08db45e71f16a8d
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463249
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-12 04:20:15 +00:00
Changpeng Liu
ea1132a926 blobfs: free sync request if got error with flush request allocation
Change-Id: I13bd02b1083816781980bcd7af7a6dd27235ed7d
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464360
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>
2019-08-12 02:59:24 +00:00
Darek Stojaczyk
3d23defba4 Remove remaining spdk_jsonrpc_begin_result() NULL checks
After recent changes, that function can not return
NULL anymore, so remove all redundant checks from
various SPDK libraries.

Change-Id: If80344b6fa81ad5f87a7086804dba221522cd7e2
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464175
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-09 16:35:00 +00:00
Darek Stojaczyk
4a713238b7 nvme: fix json response on failed construct_nvme_bdev RPCs
spdk_jsonrpc_send_error_response() is documented as a
shorthand for spdk_jsonrpc_begin_result() + end result,
but we used to call it already after doing
spdk_jsonrpc_begin_result(), which makes the response
completely invalid.

Fix it by deferring the initial spdk_jsonrpc_begin_result()
until after we did our error checking. While here, remove
the NULL checks from that function. After recent jsonrpc
changes it can never return NULL.

Change-Id: Ibb69803d4e6ce6516817673eec6626dcfc4f1abf
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464174
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-09 16:35:00 +00:00
Ziye Yang
1917d3b413 nvmf: move the assigment of pdu outside the switch
Purpose: To reduce the duplicated code.

And one minor fix: add an empty line between two functions

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I12c9ddba6526c094cd2bd945e14f9d8bf5209adf
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464504
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-09 07:37:12 +00:00
Changpeng Liu
3d12e6d4e6 bdev/nvme: deprecate ResetControllerOnTimeout configuration option
'ResetControllerOnTimeout' was renamed to 'ActionOnTimeout' for a
long time, so we deprecate the support for this old configuration
option.

Change-Id: Ia44035a8749ca046c1df16f82601389b5bafeb76
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464491
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-09 00:44:50 +00:00
Changpeng Liu
7cbe1ccd56 nvme: move SPDK_NVME_DEFAULT_RETRY_COUNT out from nvme.h
SPDK_NVME_DEFAULT_RETRY_COUNT is the default value for each controller, so
we can move it out from public header file, and change the value if users
provide a new one.

"NvmeRetryCount" was deprecated for a long time, so we removed the support
for this configuration option as well.

Change-Id: I187251cc1e5342abb4fce96727d06631b7c16a01
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464489
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-09 00:44:50 +00:00
Changpeng Liu
62bb65289d nvme: change retry count can be configured via bdev nvme driver
Also eliminate 'spdk_nvme_retry_count' finally.

Change-Id: I2f3e390e4b8a49208a11b54bb82c4891cf3e1845
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464473
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-09 00:44:50 +00:00
Changpeng Liu
936d856219 nvme: eliminate global configuration 'spdk_nvme_retry_count' option with PCIe transport
We have defined NVMe controller initialization 'transport_retry_count' option, so
global 'spdk_nvme_retry_count' can be removed, we will remove the variable with
PCIe transport first, and make the retry count can be configured via RPC.

Change-Id: I4d54f78c8da2180d536635587e7291f44a57c4fb
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464472
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>
2019-08-09 00:44:50 +00:00
Seth Howell
2cbe2acaef delay_bdev: move delay_type enum to header file.
Change-Id: Iaab3104b87e87d2fef4f4858e6e05d0773c5e453
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464453
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-08 22:57:59 +00:00
Jacek Kalwas
8a14af685b nvmf/rdma: fix missing destory qp
From rdma_cma.h "Users must destroy any QP associated with an
rdma_cm_id before destroying the ID."

Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: I5ed0c25221c5401cdde8b31a4e217b9d79e7caaa
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464290
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-08 20:07:11 +00:00
Chunyang Hui
a4516ad2ed opal: Fix get string for bigger length
Skip token header length which varies for short,
medium and long atom.

Fix Issue #898

Change-Id: I2351193e5a43608495f3d816ff4e5932399a6312
Signed-off-by: Chunyang Hui <chunyang.hui@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464502
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-08 20:06:40 +00:00
Shuhei Matsumoto
8cf1945432 iscsi: Hot remove callback closes LUN directly without using event call
This patch is in the patch series to migrate iSCSI connection management
from core based to SPDK thread based.

The callback to hot removal of LUN, iscsi_conn_remove_lun, is called
on the same core when the corresponding LUN is opened. Additionally,
all operations in iscsi_conn_remove_lun are completed synchronously.

Hence inline _iscsi_conn_remove_lun into iscsi_conn_remove_lun.
Add assert to check the function is called on the specified core.

This change is helpful to achieve the goal of the patch series
because spdk_event can have two parameters but spdk_msg can have
only a single variable, and hence we cannot convert simply and have
to introduce a context allocated dynamically otherwise.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: Iaebf18265dfe839f7361b09539527a1806aed1c4
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463551
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-08-08 05:35:01 +00:00
Ben Walker
39e850d17b iscsi: Remove cpumask from portals
Connections will soon be assigned to poll groups, which will be
dynamically moved between CPU cores based on load. It no longer makes
sense to restrict certain portal groups to specific cpu cores in this
model.

Change-Id: Iee983d75febc9797aa60021c5bc0680335e895cd
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463358
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-08 05:35:01 +00:00
Takeshi Yoshimura
553c16b27c lib/ftl: eliminate PAGE_SIZE
Commit 6708b7 ("lib/ftl: fix the unclear PAGE_SIZE") removed
PAGE_SIZE from lib/ftl, but one PAGE_SIZE remains. I follow
the commit to change the PAGE_SIZE to FTL_BLOCK_SIZE and 4096
for alignment.

This broke my ppc64le build, which PAGE_SIZE is not defined and
should be taken with sysconf.

Signed-off-by: Takeshi Yoshimura <tyos@jp.ibm.com>
Change-Id: I9cabb5ffc4d41e094eae62439ab701579c87d014
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464251
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-07 12:36:05 +00:00
Seth Howell
4640f32482 Make: conditionally build the event_vhost library
This library was being consistently built, even when the CONFIG_VHOST
directory was set to false. On the shared object build, this leads to a
few undefined references from the event_vhost.so library when trying to
link against an SPDK application.

This library should be built based on the same conditions as the vhost
library. This assumption is already baked into other aspects of the
build system. See for example the makefile under app/spdk_tgt.

Change-Id: I1c6e651b29785b48455a3a0ce7faaed4319148d9
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463941
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: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-08-07 12:28:48 +00:00
Ziye Yang
73d9cef8c5 nvmf/tcp: add nvme_tcp_pdu_cal_psh function.
Purpose:

1 Do not caculated the psh_len every time.
2 Small fix, for ch_valid_bypes, and psh_valid_bytes,
we do not need to use uin32_t.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I9b643da4b0ebabdfe50f30e9e0a738fe95beb159
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/464253
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-07 01:46:54 +00:00
Richael Zhuang
a7f7e8639f env_dpdk: upgrade to C11 atomics
Replace legacy __sync builtins with C11 __atomic ones to leverage fine
memory order controlling.

Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Change-Id: Ie799889dccba88551516b1c15452392ba5a5dae5
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463459
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Yibo Cai <yibo.cai@arm.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-05 23:56:32 +00:00
Darek Stojaczyk
bcb9d9361a scsi: fail invalid MODE_SELECT requests
For MODE_SELECT request we didn't verify the parameter
list length field from CDB and could complete an invalid
I/O without reporting any error. Fix it by adding an
additional check. Just to clarify: the I/O did not do
any harm, we just completed it with success while we
should have completed it with some error status.

Change-Id: I473e321da37259ee6318ca7dadab2726851d2b68
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463065
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-08-05 23:15:08 +00:00
Darek Stojaczyk
1aa34d2361 bdev/raid/rpc: try to break lines after 100 characters
The lines in this file are extremely long. astyle doesn't
really allow us to always go under 100, but we can at least
try to do our best.

Change-Id: I36f454b67460cadf92f99578512349d048d4861b
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462377
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-05 23:12:49 +00:00
Pawel Kaminski
0140c62b1e log/rpc: Add logs with more information about rpc error.
Now if rpc fails ambiguous logs are printed.
Use more descriptive errors.

Change-Id: I0c2abff2f0264ca110e3cd37e39aa710f29d973b
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462595
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-05 22:48:01 +00:00
Mateusz Kozlowski
b8919745c5 lib/ftl: ANM during write error handling
If an ANM event has come to a chunk/sector that has been marked as
high_prio (eg. after a write failure), there's no need to add any
sectors for relocation, as the whole band should be marked for a move
anyway.

Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Change-Id: I57824ba7e592540ea639f9f011149210fd688a5a
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463289
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-05 16:30:19 +00:00
Pawel Kaminski
3c8c4ce346 net/rpc: Add logs with more information about rpc error.
Now if rpc fails ambiguous logs are printed.
Use more descriptive errors.

Change-Id: Ia70cacd4699fb2e421334db177b9510626997378
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462773
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-08-05 06:14:58 +00:00
paul luse
2b483475d9 bdev: change error to warning
Ran into this while putting the compress tests in CI, an error
message will print following the completion of the app, checked
with Jim and it is actually not an error when lvols are involved
so change to warn now as this will show up in everyone's build
log for bdev testing.

Change-Id: Ib509b89acf5b6bfbeb349692ab59bbea4964557f
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463803
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-08-05 00:24:05 +00:00
Seth Howell
59a3afa0ff nvmf/rdma: pass iov_base to spdk_mem_map_translate
We should be checking directly against the base of the iov when doing
memory map translations. The current behavior is to check against the
starting address of the buffer which is a close address, but not exactly
the same.

Change-Id: I7f65224a6836a814708438f2866d84ae22882216
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463893
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: <jiandong.zheng@broadcom.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-02 07:15:36 +00:00
Jacek Kalwas
db0c7f6a4f nvmf/rdma: fix missing return statement
In case of failure during resource allocation within poll_group_create
there is a lack of return statement which could lead to NULL ptr
dereference.

Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: I84abe64a1843117d76b97e62656bdfc4fe2b35d8
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463195
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-02 03:55:32 +00:00
Shuhei Matsumoto
cf95d4a24f sock: Fix return value of spdk_sock_group_poll to return number of events
spdk_sock_group_poll() and spdk_sock_group_poll_count() had returned
0 on success. The implementation didn't match the specification
described in the header file, and couldn't be used to collect stats
correctly because 0 means idle.

This patch fixes the return value of spdk_sock_group_poll() and
spdk_sock_group_poll_count() to return number of events and
the callers not to overwrite the return value by 0.

Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I7e2a17187fc74ea44d3acf2f35d63f5e5a254eda
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463710
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-08-02 00:19:43 +00:00
Ziye Yang
a2dcdde2da sock: Add the code to free the entry
Checked code, we do not free the memory allocated
spdk_sock_placement_id_entry.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ie614dc17334b21b8904b16ee7e6e68a24e29d6a3
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463725
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-08-01 01:52:37 +00:00
paul luse
b64ff135c5 test/compress: add bdevio and bdevperf tests
Will execute short run per patch, longer nightly. This
path only covers the ISAL PMD as there are QAT upgrades
needed in CI. It does so by using the new 'perform_tests'
RPC in both bdevio and bdevperf.

Change-Id: I93afda336d7411b695b2ddd0332cce0050d075a4
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/455113
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Chunyang Hui <chunyang.hui@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-30 07:36:03 +00:00
Ziye Yang
a81bdcf380 sock: Fix the spdk_sock_remove_sock_group_from_map_table
We need to compare the group info, then delete the
related entry.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ie5ed7f3ce8611fd61448788f54a63f624c813c19
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463176
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-29 23:06:17 +00:00
Changpeng Liu
90520634bd bdev/nvme: configure the number of requests allocated for one NVMe I/O queue via RPC
A single I/O may allocate more than one request, since splitting may be
necessary to conform to the device's maximum transfer size, PRP list
compatibility requirements, or driver-assisted striping.  Very big
I/O request sent from application may get error due to limited resources
in NVMe driver layer, so here we add an optional parameter to make the
parameter can be configured by users.

Fix issue #745.

Change-Id: I7824232c54865b052dcd0ec6e91484c3837fc2c4
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461182
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: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-29 22:52:39 +00:00
Richael Zhuang
b2101c9a5c bdev: replace spdk_mb with spdk_smp_mb
For aarch64 spdk_mb is defined as "__asm volatile("dsb sy" ::: "memory")"
and spdk_smp_mb is defined as "__asm volatile("dmb ish" ::: "memory")".
"dsb sy" completes when all instructions before this instruction complete.
And "dmb ish" only keeps the order of memory access instructions before
and after it. It doesn't affect the ordering of any other instructions.
Here I think "dmb ish" is enough.

And replace spdk_mb with spdk_smp_mb here will not affect PPC64, X86_64
and i386.

Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Change-Id: Idd65f74567c594e5a6514a4ab0665b8f3606c883
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463455
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>
2019-07-29 20:54:27 +00:00
paul luse
562a93e45b bdev/compress: increase mbuf pool size
Was 1024 but w/the performance optimizations we can now use up
to 4 mbufs per outstanding IO so going to 8192 only uses 1MB of
mem and gives us better head room before we have to start queueing
compression operations to wait for mbufs. Note: the mbuf pool is
shared accross all virtual compression bdevs.

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I64d3973e7c7d31925b1ce5028ef960f90331c067
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463538
Reviewed-by: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.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>
2019-07-29 20:43:08 +00:00
Evgeniy Kochetov
c9c80e6932 nvmf/rpc: Fix io channel reference counting in NVMf statistics
NVMf statistics functions use spdk_get_io_channel function to get a
poll group. It increases reference counter in io channel and causes
problems on application exit. spdk_put_io_channel calls were added to
release the channel.

Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: I832d1eae346c3bc3858ed0ed063ff7a7a897a2f5
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463389
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-29 18:05:09 +00:00
paul luse
5de38f9543 bdev/compress: update some defines for QAT
There's a small drive-by in here also, use the max iovec define
from the reduce header instead of manually making sure its the same
here.

The change in the size of the MBUF pool is to accommodate the new
QAT driver being faster (?) than the old such that we could run out
of MBUFS with a fio test using 6 threads.  On the + side, when we did
the queueing code in the compression operation worked good.

Also related to QAT and experimenting with fio compression ratios, QAT
can fairly often return an error on compression that we were treating
as an error for printing, change it to a NOTCELOG instead of an error.

Change-Id: Id842064b7d659f7ad7f9d785ffffdc6b827f6989
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463369
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>
2019-07-29 04:36:59 +00:00
paul luse
34146a7a52 lib/reduce: change and move the max IOVEC define for reduce
Changed to 17 from 32 per conversation with Jim and moved to
header file so it can be shared with the vbdev module.

Change-Id: Ic516b6466bf21d21d8073e9180deaa9929c6b742
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463368
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: Broadcom SPDK FC-NVMe CI <spdk-ci.pdl@broadcom.com>
2019-07-29 04:36:59 +00:00
paul luse
9b639aa9a4 bdev/compress: function rename
Old name was misleading due to earlier changes

Change-Id: Ic04223db983e98c9703a43e6778b0094f99bc81d
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463341
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-29 03:46:31 +00:00
paul luse
faf9ad6a6d bdev/compress: fail get channel calback if we are out of qpairs
qpairs can be limited by the compression polled mode driver or
system resources and we need one per thread so if we run out we
have to fail the callback.

Change-Id: Ibd07d9c65880e7de321c439119aed479ef00746c
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463339
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: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-07-29 03:46:31 +00:00
paul luse
c2d441226a lib/reduce: close hole in compress optimization
If a write operation comes in and is not a read-modify-write but
we don't end up compressing the data (because of either error or
we decide the compression ratio isn't good enough) then we not
only need to copy the data to the host buffers but we need to
zero any offset and/or remainder in the decomp scratch buffer.

Change-Id: Ifb2235507826f9ef1110dd9dbaf88045d8979e7c
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463337
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: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-07-29 03:33:40 +00:00
Jeffry Molanus
bc315deae3 bdev_iscsi: fix crash when connecting to a non existing iqn
When connecting to an iscsi url that effectively does not exist we free
the data structures of the very context we are processing. This results in a
use after free and subsequently in a crash.

Signed-off-by: Jeffry Molanus <jeffry.molanus@gmail.com>
Change-Id: I67cab1efb161bfa23fa1022e150661080d90b556
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462614
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Jeffry Molanus <Jeffry.molanus@gmail.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-29 03:18:33 +00:00
Anil Veerabhadrappa
ed56a3d482 NVMe-oF Target: Add FC transport.
- New files and updates to existing SPDK files to add the NVMf-FC transport.
  - Depends on an existing low level driver library. This driver is not part of SPDK repository.
  - Makefile updates to build FC transport (using CONFIG_FC)
  - Update configure script for FC build.
  - New FC unit test for FC-LS commands.
  - Update unittest.sh to run FC unit test (when built).

Signed-off-by: John Barnard <john.barnard@broadcom.com>
Signed-off-by: Anil Veerabhadrappa <anil.veerabhadrappa@broadcom.com>
Change-Id: If31d4d25feab76c2dbe90a7faf71d465c2c3a354
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/450077
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>
2019-07-26 22:17:17 +00:00
Ziye Yang
6d4f580e79 nvmf/tcp: Remove spdk_nvmf_tcp_qpair_process_pending
Phenomenon:
Test case:  Using the following command to test
./test/nvmf/target/shutdown.sh --iso --transport=tcp
without this patch, it will cause coredump.
The error is that the NVMe/TCP request in data buffer
waiting list has "FREE" state.

We do not need call this function in
spdk_nvmf_tcp_qpair_flush_pdus_internal, it causes the
bug during shutdown test since it will call the function
recursively, and it does not work for the shutdown path.

There are two possible recursive calls:

(1)spdk_nvmf_tcp_qpair_flush_pdus_internal ->
spdk_nvmf_tcp_qpair_process_pending ->
spdk_nvmf_tcp_qpair_flush_pdus_internal ->
>..
(2) spdk_nvmf_tcp_qpair_flush_pdus_internal->
pdu completion (pdu->cb)
->..
-> spdk_nvmf_tcp_qpair_flush_pdus_internal.

And we need to move the processing for NVMe/TCP requests
which are waiting buffer in another function to handle
in order to avoid the complicated possbile recursive
function calls. (Previously, we found the simliar
issue in spdk_nvmf_tcp_qpair_flush_pdus_internal for
pdu sending handling)

But we cannot remove this feature,
otherwise, the initiator will hang for waiting the
I/O. So we add the same functionality in spdk_nvmf_tcp_poll_group_poll
function.

Purpose: To fix the NVMe/TCP shutdown issue.
And this patch also reables the test for shutdown and bdevio.

Change-Id: Ifa193faa3f685429dcba7557df5b311bd566e297
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462658
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-26 21:16:23 +00:00
Evgeniy Kochetov
fbe8f8040c nvmf/rdma: Add request latency statistics
This patch adds measurement of time request spends from the moment it
was polled till completion.

Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: I1fcda68735f2210c5365dd06f26c10162e4ddf33
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/445291
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-26 20:30:00 +00:00
Evgeniy Kochetov
251db8144f nvmf/rdma: Add NVMf RDMA transport pending statistics
This patch adds statistics for pending state in NVMf RDMA subsytem
which may help to detect lack of resources and adjust configuration
correctly.

Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: I9560d931c0dfb469659be42e13b8302c52912420
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452300
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-26 20:30:00 +00:00
Evgeniy Kochetov
38ab383a8f nvmf/rdma: Add RDMA polling statistics
RDMA polling statistics: number of polls and number of completion
entries returned.

Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: Iabcf2cb6f6a35f595b89b58cdfcd177a637dda13
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/445289
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-26 20:30:00 +00:00
Evgeniy Kochetov
43bb4e6b1f rpc: Add NVMf transport statistics to nvmf_get_stats RPC method
This patch adds transport part to nvmf_get_stats RPC method and basic
infrastructure to report NVMf transport specific statistics.

Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: Ie83b34f4ed932dd5f6d6e37897cf45228114bd88
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/452299
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-07-26 20:30:00 +00:00
paul luse
ca1a3bf18e bdev/compress: use base bdev alias as base for comp_bdev name
If available, if not use the bdev unique name. This results in
a much friendlier comp_bdev naem for the user.  For example,
now it would look something like this: COMP_lvs0/lvs as opposed
to like this COMP_0b149b31-b66b-4cf7-ab39-a55b50788cd1

Change-Id: I319a141221ed8880edcec930ca5be9f256b105e0
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463246
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>
2019-07-26 19:47:33 +00:00
paul luse
e9211cbf45 bdev/compress: fix qpair assignment code
Was previously creating the number of qp based on the # of cores
reported via DPDK function.  Also was assigning one qp per comp_bdev.
After testing w/multiple threads in fio 2 things needed to change:

* remove use of rte core related functions as fio threads are not EAL
threads.  This required choosing an upper limit for the number of
threads that the bdev module will support
* changing the qp assignment code such that comp_bdevs share the
same device_qp if on the same thread

Fixes issue #879

Change-Id: Ib968ee04bef63013616546341974a4431d8f266a
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463107
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>
2019-07-26 19:47:33 +00:00
Jan Kryl
59339feac3 jsonrpc: tolerate null json value for parameters in json-rpc call
Rust lang has notion of empty value `()` which is translated to json null
value using serialization library like serde. Thus it means that jsonrpc
methods having no parameters translate to parameters with null value (as
opposed to a request without parameter member as it is done now in spdk).
This change handles null parameter gracefully instead of returning an
error - improving interoperability with such clients.

Signed-off-by: Jan Kryl <jan.kryl@mayadata.io>
Change-Id: I8c3cc5613582aebb10ac6eaee3ac4e6538aaa0b1
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463171
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>
2019-07-26 19:30:57 +00:00
Wojciech Malikowski
825ae66bd0 event/subsystem/vmd: RPC support
Added enable_vmd RPC call.

Change-Id: Ib0bea12f097a46a8be537a1db8aace6cb3b9b699
Signed-off-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459949
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-26 18:27:40 +00:00
paul luse
f9cae9d20f lib/reduce: minor cleanup for consistency in recent changes
Had used a few different means to determine if there's space
remaining in a chunk after accounting for offset and host data,
just making them all consistent. Nothing functionally changes.

Change-Id: Iffd3b0b6d8ab1253f5b1bebda88d6f63d5061e19
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463023
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>
2019-07-26 17:44:18 +00:00
Darek Stojaczyk
f89166c089 scsi: remove bdev_scsi_mode_select_page()
The function didn't do anything.

Change-Id: Id44a7d0c129ab60751eda382911935d677730ec9
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463066
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: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-07-26 04:14:59 +00:00
Konrad Sztyber
fb15434659 lib/ftl: store non-volatile cache's current write address
Remember current write position within the cache when shutting down.  It
allows for faster recovery after clean shutdown (no need to scan the
device) as well as grants a quick way to distinguish between clean and
dirty shutdowns.

Change-Id: I79c22caa0b1ca4373951ac43f747b085d331cdd0
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460796
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: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
2019-07-25 22:36:31 +00:00
Konrad Sztyber
3e911e17c7 lib/ftl: non-volatile cache's header validation function
Moved metadata header verification to a separate function, since the
metadata read callback got pretty large.

Change-Id: I0c8b2eb493631a6495ce2ef7d9586d2c7cb7772f
Signed-off-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460795
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>
2019-07-25 22:36:31 +00:00
Changpeng Liu
28439890e4 nvmf: always update discovery log page if the offset is zero
Global tgt->discovery_log_page may contain old hostnqn log
page, so we will update the discovery log page if the offset
is zero.

Change-Id: Iba24409b16626d157d2782c6813fe5a0c27f1082
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463123
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: <shahar.salzman@kaminario.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-07-25 18:05:13 +00:00
Hailiang Wang
563b98223b lib/compress: fix a compilation error for low GCC version
Some low GCC(such as v4.8.5) can't recognize this style:
static struct rte_comp_xform g_comp_xform = (struct rte_comp_xform)
Fix issue #877.

Change-Id: I021c62b7b1437d67ce87cc2e13d1b90ea6a18140
Signed-off-by: Hailiang Wang <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/463126
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-07-25 15:49:24 +00:00
Tomasz Kulasek
9307ff5a54 net/vpp: move to VPP 19.04
This patch updates net/vpp implementation from version VPP 19.01 to
VPP 19.04.

1. Some binary APIs are deprecated in 19.04 and message queue is used
   to handle control events:

   - vl_api_bind_sock_reply_t_handler by SESSION_CTRL_EVT_BOUND,
   - vl_api_unbind_sock_reply_t_handler by SESSION_CTRL_EVT_UNLISTEN_REPLY,
   - vl_api_accept_session_t_handler by SESSION_CTRL_EVT_ACCEPTED,
   - vl_api_connect_session_reply_t_handler by SESSION_CTRL_EVT_CONNECTED,
   - vl_api_disconnect_session_t_handler by SESSION_CTRL_EVT_DISCONNECTED,
   - vl_api_reset_session_t_handler by SESSION_CTRL_EVT_RESET

2. Fixes for Fedora 29/30:

   - added "-Wno-address-of-packed-member" (DPDK 19.02 fails to compile
     with gcc9.1),
   - force "-maes" compile flag for gcc9.1 to compile crypto_ia32 and
     crypto_ipsecmb plugins (gcc9.1 doesn't do that for -march=silvermont)
   - some minor fixes

3. Default path for VPP instalation is changed for test scripts from
   /usr/local/src/vpp to /usr/local/src/vpp-19.04 to avoid VPP version
   conflict.

Change-Id: I1d20ad7f138f5086ba7fab41d77d86f8139d038e
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459113
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-25 14:51:21 +00:00
Tomasz Kulasek
bee1130c03 net/vpp: prepare vpp 19.01 to move to 19.04
No functional changes done, just reordering for next patch in series.

Change-Id: I32022fddffbc7b00eeecb29a2fcbaa85fbf2e99f
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462473
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-25 14:51:21 +00:00
Wojciech Malikowski
093bc3390a lib/ftl: Wait for IO retry queue drain during shutdown
In case shutdown occurs during band relocation
we can have situation that on retry queue are
some internal IOs and we need to wait to drain
this queue before we start shutdown sequence.

Change-Id: Ie5b33732568aeda0586f4de384b22dcf463bf31e
Signed-off-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460421
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: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-07-25 14:50:58 +00:00
Mateusz Kozlowski
4d9faf7c6b lib/ftl: Add check if device is halted during reloc
It's possible there's a delay between spdk_ftl_dev_free setting
dev->halt and sending message to core thread which would set
reloc->halt. This patch should bridge this gap and prevent potential
additional/unneeded relocations from happening.

Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Change-Id: I3d69fe86900c9233fadd8e3795accb36b1c01791
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461598
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-25 14:50:58 +00:00
paul luse
7384ca015b lib/reduce: for compress path, copy data from host buffers if needed
If the data was not compressed for whatever reason, it needs to be
copied from the host buffers much in the same way as the patch before
this did.

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I5c92db16afbce3ca573c556ee78a51ba6511c564
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462895
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>
2019-07-25 14:50:25 +00:00
paul luse
907ec7268d lib/reduce: conditionally memcpy data to host follow decompression
If the decompression code path runs into a chunk that wasn't
compressed, the data needs to be copied to the host as the
compression engine was not engaged.

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ibabd6d6bd2bc5db79953a0a55d7f49d556c08af7
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462892
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>
2019-07-25 14:50:25 +00:00
paul luse
0242a80793 lib/reduce: fix problem with size of chunk map area in PMEM
This fixes a segfault found by using a very small logical volume.
The PMEM file chunk map area wasn't including the chunk map struct
itself.  In PMEM, a single entry as returned by _reduce_vol_get_chunk_map()
is made up of a 'struct spdk_reduce_chunk_map' plus one uint64_t for
each backing IO unit for the volume (# depends on vol parms). So when
an app got close to the end of the chunk map indices it would run off
the end of PMEM and segfault.

With this fix that no longer happens however data integrity issues now
show up with fio. I believe this fix is valid though and am pursuing the data
integrity issue as something new.

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I69a223064c7bbd44bcd0a62d155cf409603970a3
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461316
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-25 14:50:25 +00:00
Karol Latecki
5f96e92c8c bdev/pmem: add more descriptive rpc error messages
Improve error messages where possible.
Also change return code values to negative in bdev_pmem.c so that
it follows the same pattern as other bdev modules.

Change-Id: I81b205a41104e15457154d1e31540210636ef9d3
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461548
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-24 18:28:46 +00:00
Karol Latecki
0fc5acea8c bdev/nvme: add more descriptive rpc error messages
Improve error messages where possible.

Change-Id: Ief04cf32f7a65ef94f3d994ca76da2637ba66ca1
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461875
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-24 18:27:44 +00:00
Mateusz Kozlowski
cd115ecfcd bdev/ftl: Add defrag parameters to construct_ftl_bdev rpc
Added parsing and saving of (optional) parameters which are responsible for
relocation in FTL. Changing the parameters may affect Write
Amplification Factor and overall performance, especially during random
write workloads. If parameters are not specified, default values will be used.

Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Change-Id: Ic0229e39109460f3541c31e1cbf2a485efe408c6
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460504
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
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>
2019-07-24 18:21:07 +00:00
Mateusz Kozlowski
7a867c4fdb lib/ftl: Pass ftl conf to write_config rpc function
Changed write_config to use the ftl configuration file instead of
allow_open_bands directly. This allows for easier expansion of saved
fields.

Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Change-Id: Ie1d480983636f26840dba9a3a6c93b2883903bdb
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460519
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
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>
2019-07-24 18:21:07 +00:00
Mateusz Kozlowski
a039d024ff lib/ftl: Remove anonymous defrag structure in config
Merged configuration fields for defrag into the main config structure.

Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Change-Id: I315c78e2843bd6a310b484af5b688aca424336b0
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460518
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
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>
2019-07-24 18:21:07 +00:00
Mateusz Kozlowski
5a16b8e671 lib/ftl: Segmentation fault fix after write error handling
Fixed touching NULL write pointer, which would happen after some other
I/O in the same band would receive error and issue its deletion. Any
subsequent write callbacks would then be unable to find and update the
information.

Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Change-Id: I07d9791f1b1b673a48356fae55b784c0bf6a6f7a
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462387
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2019-07-24 18:20:48 +00:00
paul luse
eb1ddcb664 lib/reduce: remove dead code clearing unused backing io units
At the start of time all of values of io_unit_index[] array in
the chunk maps are FF's.  When a partial chunk is written, only
some of the io_unit_index[] vals will be assigned values from the
allocated_backing_io_units bit array.  When that chunk is written
again, it is not done so in place and at that time in when
_write_write_done() is called, the io_unit_index[] values are
set to FF again and the bit array bits are cleared for the old
chunk so that it is fresh again for use by another write.

This change removes code from an early stage of the write process
where a 'fresh' chuck in allocated.  Because of points made earlier,
it is not possible for any of the io_unit_index[] values to be
assigned or have a corresponding bit set in the bit array.

The prev version of this patch cleared the bit array because the
io_unit_index[] array was being cleared however after further
investigation, and for the reasons stated earlier, the io_unit_index[]
did not have a valid value so clearing the bit array was simply wrong.

Removing this dead code clears things up and leaves it to one place
to clear the io_unit_index[], when a chunk is overwritten.  Well, 2
places including init time.

Change-Id: I5c4e5360c9c13817d2fa7d3c7d004b44537af7f4
Signed-off-by: paul luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/458520
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>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-24 18:12:05 +00:00
Tomasz Zawadzki
8df52a0f4a lib/nvme_tcp: assert tcp_req->req before it is dereferenced
The value of tcp_req->req was asserted after it was already
dereferenced. This patch fixes that.

Change-Id: I5eb01e88be09d41fb8e632c49d5a7ccf2315788f
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462508
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>
2019-07-24 18:09:33 +00:00
Tomasz Zawadzki
f75d1540e9 lib/ftl: check namespace for NULL during initialization
spdk_nvme_ctrlr_get_ns() can return NULL, which was
not verified, but dereferenced anyway.

Change-Id: Ib0554148cc47ea3ff2afa1862ac962f284fe6d43
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462486
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-24 18:09:29 +00:00
Tomasz Zawadzki
eb84a1133f lib/ftl: assert write pointer from band
This is just assert to assure the Klocwork
static analizer that wptr is not NULL.

Change-Id: I003620431afb8497a57c50af8480c34ec3fac6d6
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462489
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-24 18:09:25 +00:00
Changpeng Liu
3fe300609e nvmf: check HOSTNQN access right for discovery service
Initiator can use `nvme discover` command to display all
the subsystem's information, because we don't check
the allowed HOSTNQN for Discovery service, so here
adding this feature so that only return the log pages
to the allowed hosts.

Fix issue #576.

Change-Id: I51e6770bd67ea0b41caf9de3a8899923377e6255
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462440
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: yidong0635 <dongx.yi@intel.com>
2019-07-24 11:25:59 +00:00
Changpeng Liu
234eb48bf6 nvmf: save hostnqn to controller data structure
When creating a new controller in the NVMe-oF target, hostnqn is
a must parameter, so we save the hostnqn to controller data
structure, and it can be used to verify the access right of
Discovery service.

Change-Id: I86a6f50d3209d5bbb8ac85508288173d826ea216
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462439
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: yidong0635 <dongx.yi@intel.com>
2019-07-24 11:25:59 +00:00
Alexey Marchuk
f0b7a6e7d1 rdma: fix possible double free on qpair destruction
Update rqpair->last_wqe_reached in the context of thread that owns qpair's poll group to avoid possible double free
This patch fixes #858

Change-Id: If5422944b7928c2cc05af528fbcc4482aeef22df
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462012
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Lorne Li <lorneli@163.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-23 22:56:57 +00:00
Darek Stojaczyk
a7ff5ff558 env_dpdk/memory: silence scan-build errors
Scan-build complains that spdk_vtophys_notify() can segfault
on vaddr == 0. We know that and it's not a programming error.
In fact, SPDK with UIO pci driver can segfault upon registering
any non-mapped memory address. The user is just not supposed
to do that.

Assert vaddr != 0 to silence scan-build.

Change-Id: I9a14696361eca0aeea5ede9f9f2956fcbf59bdb5
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462869
Reviewed-by: yidong0635 <dongx.yi@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-23 22:56:23 +00:00
Darek Stojaczyk
bb63fe6fc3 blobstore: don't realloc any memory under scan-build
Scan-build has a real issue with reallocs. The original
error from latest version of scan-build is rather complicated,
but it can be greatly simplified with the following change:

> diff --git a/lib/blob/blobstore.c b/lib/blob/blobstore.c
> index 7580c9dd2..6a594edf3 100644
> --- a/lib/blob/blobstore.c
> +++ b/lib/blob/blobstore.c
> @@ -1147,8 +1147,9 @@
> _spdk_blob_persist_clear_clusters_cpl(spdk_bs_sequence_t *seq, void *cb_arg, int
>         } else if (blob->active.num_clusters != blob->active.cluster_array_size) {
>                 tmp = realloc(blob->active.clusters, sizeof(uint64_t) * blob->active.num_clusters);
>                 assert(tmp != NULL);
> -               blob->active.clusters = tmp;
> -               blob->active.cluster_array_size = blob->active.num_clusters;
> +               ctx->blob->active.clusters = tmp;
> +               assert(ctx->blob->active.clusters[0] != 14213);
> +               ctx->blob->active.cluster_array_size = ctx->blob->active.num_clusters;
>         }
>
>         _spdk_blob_persist_complete(seq, ctx, bserrno);
> ```

Scan-build will then complain:

blobstore.c:1151:10: warning: Use of memory after it is freed
                assert(ctx->blob->active.clusters[0] != 14213);

Asserting blob == ctx->blob, blob->active.clusters == ctx->...,
or even tmp != blob->active.clusters doesn't work, so use the
last resort scan-build weapon - #ifdef __clang_analyzer__.

The realloc in this case is just down-sizing a buffer to
save some memory. For scan-build, just don't do it. This
finally silences all scan-build false positives.

Change-Id: Ib88ea145370f5035eedd2412e98ee61f96ad1915
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462868
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-23 22:56:23 +00:00
Alexey Marchuk
5282edfd7b rdma: fix double free of qpair struct in case of failed initialization
qpair structure is freed and an error code is returned to the caller in the case of failed qpair initialization in function spdk_nvmf_rdma_qpair_initialize (e.g. bad return value of rdma_create_qp).
The return code is handled by nvmf_tgt_poll_group_add function which destroys the qpair for the second time.
This patch fixes #857

Change-Id: I0773652ecccbbd634ad272106e0a93c1e591d7d2
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462011
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Lorne Li <lorneli@163.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-23 22:55:43 +00:00
Tomasz Zawadzki
06c7ef7f6a lib/ftl: check for io not being NULL before dereferencing
ftl_io_free() handles NULL io being passed, but shouldn't
dereference it before returning.

Change-Id: Ia705d4ab9f8b3569e9704a1f97e70f7579084efb
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462487
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-23 19:55:30 +00:00
Tomasz Zawadzki
8500db5ee0 lib/vmd: check header_type after the vmd_adapter structure is verified
First check both vmd_pci_device for not being a NULL,
same as vmd_adapter structure being present.

Otherwise dev was dereferenced before checking for NULL.

Change-Id: I3719f33c1762f789b0eb63b0f2ddce8258843ded
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462509
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-23 19:55:04 +00:00
lorneli
ba323d44ca nvmf/rdma: log spdk_nvmf_rdma_destroy_defunct_qpair
Func spdk_nvmf_rdma_destroy_defunct_qpair is a "last chance option"
to destroy qp manually if some driver/hardware doesn't drain qp's
failed wr as expected.

There's a probability that ibv_poll_cq polls wr of the destoryed qp
after spdk_nvmf_rdma_destroy_defunct_qpair's execution. Although in
practice the risk of this situation is minimal(if not non-existent),
add a log here so that we could detect this situation easily.

Change-Id: Ifa9534397513bcea34c18fbb8168eef8f53599c1
Signed-off-by: lorneli <lorneli@163.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462441
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-23 19:35:16 +00:00
lorneli
b4d3066890 nvmf/rdma: defer qp destruction until nvmf layer closes qp
Currently rqpair will be destroyed directly in ibv_poll_cq path
if it has been drained, regardless of whether there are outstanding
I/Os issued to bdev layer. So after outstanding I/Os completing,
spdk_nvmf_rdma_close_qpair will be called from nvmf layer, accessing
a destroyed qp.

This path defers qp destruction in nvmf_rdma_destroy_drained_qpair
func until nvmf layer closes qp.

Fixes 851

Change-Id: I8bcce66f8053ddb105702ac603d5d73af54bdcfc
Signed-off-by: lorneli <lorneli@163.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461237
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Seth Howell <seth.howell@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-23 19:35:16 +00:00
Mateusz Kozlowski
a3c78e150b lib/ftl: Remove separate dma_buf allocation in band
Since 4k alignment is no longer required for I/O buffers, the
band doesn't need a separate lba map and dma buffer and can use the
same memory location.

Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Change-Id: Iea127e8c2f39e6de5d57258098b2dc6be56f439f
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462042
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-07-23 04:00:05 +00:00
Mateusz Kozlowski
a4b3481242 lib/ftl: Remove buffer alignment requirements
Ftl should no longer require 4k alignment for I/O buffers for either
internal or external requests. The 4k alignment was needed due
to a bug in QEMU when handling internal SGL buffers in LNVM commands.

Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Change-Id: Icafc14b7811c9c0ffa13789e341c453503cf2821
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460106
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
2019-07-23 04:00:05 +00:00
Mateusz Kozlowski
1897943987 env: define minimum alignment for dma-able memory
DPDK defines the minimum alignment as "suitable for any
kind of variable (in the same manner as malloc())", but
internally the alignment is always rounded up to the
cache line size, even if the requested alignment is 0.

We would like to start relying on this behavior in FTL,
where lba maps are allocated using DMA-able memory and
are constantly looked up or modified by different threads.
By having the lba maps unaligned, we risk having those
threads pollute each other's cache lines.

Rather than enforcing this memory alignment in FTL, we
do it in spdk_*malloc directly. In general it makes
sense to have DMA-able memory always cache-line-size
aligned for the same reason as above.

Change-Id: Ib6edda4a7bf3f4952eb1875a4e1753be96bed642
Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460329
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-23 04:00:05 +00:00
x00267701
a50246fb64 log: optimize spdk_log() when logging is disabled
If the log level of the output log is higher than
the process's log level, the system does not output
it, so we needn't generate the formatting logs.

Change-Id: I36be0e6807ed575fcbf1d0ae01f064a6ca2c4539
Signed-off-by: Huiming Xie <xiehuiming@huawei.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462790
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-23 00:42:24 +00:00
yidong0635
c0d4f7145e crypto: Fix scanbuild issue on Fedora30.
Issue reports:
vbdev_crypto.c:695:12: warning: The left operand of '+' is a garbage value
                iv_ptr = rte_crypto_op_ctod_offset(crypto_ops[crypto_index], uint8_t *,

Change-Id: I1a4f89111e94a13d8daf38070aa69306783a83c5
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462576
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>
2019-07-23 00:38:27 +00:00
yidong0635
425b89a4ed compress: Fix scanbuild error about dereference of null pointer.
Issue reports:
vbdev_compress.c:468:34: warning: Dereference of null pointer
                 src_mbufs[iov_index]->userdata = reduce_cb_arg;
                    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~
Add assert here is enough.

Change-Id: I8dccf107a89f7af46437a1f678adccf122beb4b2
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462592
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-23 00:17:25 +00:00
Wojciech Malikowski
4c5282bcf7 lib/vmd: Clear prefetch base and limit registers
During PCI bridge initialization not all
registers was cleaned properly.

Change-Id: Ie0752bb303ba06e2a21669908efd9f746f6b0039
Signed-off-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460197
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-22 20:02:54 +00:00
yidong0635
a1de2fe007 compress: Clear some simple scanbuild errors.
On Fedora30, GCC9+ reports errors:
Issues report:
vbdev_compress.c:482:17: warning: Assigned value is garbage or undefined
        comp_op->m_src = src_mbufs[0];
                       ^ ~~~~~~~~~~~~
vbdev_compress.c:502:17: warning: Assigned value is garbage or undefined
        comp_op->m_dst = dst_mbufs[0];
                       ^ ~~~~~~~~~~~~
vbdev_compress.c:491:3: warning: 1st function call argument is an uninitialized value
                rte_pktmbuf_attach_extbuf(dst_mbufs[iov_index],

compress_ut.c:826:2: warning: Attempt to free released memory
        free(g_mbuf_mp);
        ^~~~~~~~~~~~~~~
Should remove free(g_mbuf_mp), for pointer exchange.

Change-Id: I1a48b7c309a4e2aa0aa513f9be44ae3504d9e385
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462574
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>
2019-07-22 14:10:32 +00:00
Alexey Marchuk
0754417fa9 rdma: Use optimal ceiling integer division
This form of the celinig division allows to remove an extra condition

Change-Id: I8a2de792172ec9115563e7fb914745c476f16e8d
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Sasha Kotchubievsky <sashakot@mellanox.com>
Signed-off-by: Evgenii Kochetov <evgeniik@mellanox.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462198
Reviewed-by: Seth Howell <seth.howell@intel.com>
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>
2019-07-22 09:22:11 +00:00
Pawel Kaminski
de1d0f8fe9 jsonrpc: don't check returned value from spdk_jsonrpc_begin_result()
As spdk_jsonrpc_begin_result() is not allowed to return NULL we can
remove these checks. We didn't have any tests cases that goes this path
anyway.

Change-Id: I0894e76c0162591e550e70b172566b9060a6dd5f
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459199
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-22 05:13:30 +00:00
Tomasz Zawadzki
37acf6814b lib/ftl: assert that chunk is never NULL
Code on line 613 should never be reached for last
chunk on the band, since it is checked on line 606.

This assert verifies that, all chunks before last
are not NULL.

Change-Id: I78a9967f91c0873981b3308e888d85fa7c8d6641
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462488
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-22 04:53:05 +00:00
Tomasz Zawadzki
94bf29d268 lib/ftl: verify that iov is not NULL during read header completion
Moved the spdk_bdev_io_get_iovec() after the verification that io
succeeded.
Then added return path when iov could not be retrived from bdevio.

Change-Id: I2638e6657fd08a2dd85ab0906383cecef8fb4f4a
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462507
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>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-07-22 04:51:34 +00:00
Chunyang Hui
07f432641a opal: Fix memory leakage
Change-Id: I37f1468a41d568f7313143f0270f854f73bc4000
Signed-off-by: Chunyang Hui <chunyang.hui@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461560
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: yidong0635 <dongx.yi@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-22 04:32:59 +00:00
Chunyang Hui
8522624d03 opal: Add multiuser support
Admin can enable user and add user to locking range.
Then the user can lock/unlock his range.

Change-Id: Ifc5a8cf5c6b5febeb59c86333981f0cf5b938500
Signed-off-by: Chunyang Hui <chunyang.hui@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460891
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>
2019-07-22 04:32:59 +00:00
Changpeng Liu
e27421b344 nvme: fix req leaks
There are many req leaks when a controller failure
occurs during submitting IO. It must free all of
the children before freeing the parent req.

If a part of the child req has been sent to the back end
and a part of the child req fails, removes the failed req
from the parent req and the parent req must be retained,
freeing the parent req after all of the submitted reqs return.

Change-Id: Ieb5423fd19c9bb0420f154b3cfc17918c2b80748
Signed-off-by: Huiming Xie <xiehuiming@huawei.com>
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461734
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>
2019-07-22 04:15:34 +00:00
Changpeng Liu
c4f7c1bc2a nvme: put child I/O helper functions in nvme_internal.h
Existing children split functions defined in nvme_ns_cmd.c can
also be used in nvme_qpair.c to free children requests with error
paths.

Change-Id: I640b32884424709da67ee89ff780c2de45acc54c
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461372
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-22 04:15:13 +00:00
Ziye Yang
9375616ae2 nvmf/tcp: code cleanup
move the staement location of TCP request setting and remove
the duplicated code.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: Ia659756185547ff4f8aa26c5bc01f63defe6c113
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462589
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-07-22 02:40:35 +00:00
Pawel Kaminski
a15dcb0bf0 jsonrpc: always allocate response for request
We already have send buffer allocated. This will greatly improving code
as we guarantee by design that there is always JSON write context
object.

Change-Id: Id487c01448e1a65d9d4ef76d40a2a9f178b2f570
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459341
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>
2019-07-19 20:56:54 +00:00
Ziye Yang
6ad6a1131b nvmf/tcp: Add a feature to allow set the sock priority of the connection.
This priority is used to differentiate the sock priority on the TCP connections
between  NVMe-oF TCP target and other TCP based applications.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I6ee294e647420b56d1d91a07c2e37bf34ce24e03
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461801
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>
2019-07-19 06:30:19 +00:00
Tianyu Yang
96b759297f lib/bdev: fix coredump when bdev initialize failed.
If subsystem bdev module initialize failed, it will call
spdk_bdev_init_complete(-1) -> (subsystem bdev)->fini
_spdk_bdev_finish_unregister_bdevs_iter -> spdk_bdev_module_finish_iter

In abovt path, spdk_bdev_module_finish_iter will repeate to call
bdev_module->module_fini function. Some bdevs will call spdk_io_device_unregister
which never call spdk_io_device_register. It will coredump when assert false in
spdk_io_device_unregister dev is null.

To fix this, let's check whether g_bdev_mgr.module_init_complete is equals true
and then call the bdev_module->module_fini.

Change-Id: Ia9a13318720d954e40eb2d666574bcb86e5f49e3
Signed-off-by: Tianyu Yang <yangtianyu2@huawei.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462382
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-19 06:29:25 +00:00
Karol Latecki
ac8b488982 bdev/rbd: add more descriptive rpc error messages
Improve error messages where possible.
Modify spdk_bdev_rbd_create() to return instead instead
of pointer for better return code handling.

Change-Id: I5fcf90794f5fe44296422c654c5f8d404f3d5eef
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461884
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>
2019-07-19 02:21:53 +00:00
Mateusz Kozlowski
3500d9a98d lib/ftl: Add error log after IO failure
Adding some extra debug information for any failing IOs.

Signed-off-by: Mateusz Kozlowski <mateusz.kozlowski@intel.com>
Change-Id: If38de30bcb80d291778ad7325a33b7786d02390d
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461588
Reviewed-by: Wojciech Malikowski <wojciech.malikowski@intel.com>
Reviewed-by: Konrad Sztyber <konrad.sztyber@intel.com>
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>
2019-07-18 08:49:02 +00:00
Karol Latecki
89003d5ca7 bdev/rpc: add more descriptive rpc error messages
Improve error messages where possible.

Change-Id: I6e5a50a1422f55aff0b0bad53493edc80f345ccb
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461600
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-18 07:52:07 +00:00
Karol Latecki
6d442665fd bdev/rpc: remove if checks for obligatory rpc arguments
These arguments are obligatory and spdk_json_decode_object will
fail even before we reach the if block.

Change-Id: I3c17faf570aefc7d96d009a595cf3a76994977e7
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462043
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>
2019-07-18 07:52:07 +00:00
Karol Latecki
46ebf1b1e9 bdev/virtio: add more descriptive rpc error messages
Improve error messages where possible.

Change-Id: I68b48fd448636412a2b26241c787e7b7826c9a34
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461873
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-18 05:34:52 +00:00
Karol Latecki
2805cad12f bdev/compress: add more descriptive rpc error messages
Improve error messages where possible.
Modify parts of the code so that it follows the same pattern
as in previousle changed bdev modules.

Change-Id: I6672a14900326029c670bfca99a6d085093861c3
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461553
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-18 04:25:44 +00:00
Karol Latecki
695ecf48bf bdev/delay: update rpc error messages
Consolidate rpc error handling with previous bdev rpc
changes.

Change-Id: I3f0ac3b3a0f09869e8ad7edb4bd4c8fd1e42f6b6
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461557
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-18 04:25:40 +00:00
Karol Latecki
b8c84b1a39 bdev/error: add more descriptive rpc error messages
Improve error messages where possible.

Change-Id: Ieaae6f2477d4a9f636cc861afbe5d80b3c74a46c
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461562
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: Vitaliy Mysak <vitaliy.mysak@intel.com>
2019-07-18 04:25:27 +00:00
Karol Latecki
955518d6fc bdev/iscsi: add more descriptive rpc error messages
Improve error messages where possible.

Change-Id: If08bad9f4fc88b51403b89c3f5bfc8894ef4300a
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461567
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-18 04:25:09 +00:00
Karol Latecki
c6f2b30918 bdev/raid: add more descriptive rpc error messages
Improve error messages where possible.
Unify returned error codes and messages with previous
changes done in other bdev modules.

Change-Id: Id35b61e8157fab9940e5811b71289978a6f23b05
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461591
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-18 04:24:45 +00:00
Ziye Yang
ecb4ea90ce sock: Add the socket priority setting function.
Purpose: This API can be used to set the socket
with different priority.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I9df1122bf6ae640eba731e635a1784f4e9da4104
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461738
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-07-18 04:09:37 +00:00
Karol Latecki
fd4d7fcb15 bdev/passthru: add more descriptive rpc error messages
Improve error messages where possible.

Change-Id: I778b4b49c1e54c0da77f6da7906df91d8aa95f9b
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461587
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Vitaliy Mysak <vitaliy.mysak@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
2019-07-18 03:25:06 +00:00
Karol Latecki
c05355db23 bdev/lvol: add more descriptive rpc error messages
Improve error messages where possible.

Change-Id: I8f736fb6481d65b55e16e548fac0130cd152d3fa
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461575
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-18 03:24:26 +00:00
Karol Latecki
0965d63d3a bdev/lvol: remove optional flag for lvol_name in construct call
lvol_name is not an optional argument when creating a lvol bdev.
Also removing unnecessary if block.

Change-Id: I7d5790d648bce7f02bfed34bd714162d3ccb10ab
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461861
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-18 03:24:26 +00:00
Karol Latecki
75711828a9 bdev/lvol: remove if checks for obligatory rpc arguments
These arguments are obligatory and spdk_json_decode_object will
fail even before we reach the if block.

Change-Id: I295649629770ef062086308257da83a8bab44588
Signed-off-by: Karol Latecki <karol.latecki@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461860
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-18 03:24:26 +00:00
paul luse
a755fb5f14 lib/reduce: use global zero buffer instead of zeroing scratch buffer
Eliminates need for memset on parts of our scratch buffer

Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I00b7213d3c15562ceeda4d7a3ac2bb7cfd41bf66
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460010
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
2019-07-18 03:21:59 +00:00
Ziye Yang
4739f62365 nvmf: enable transport based scheduler decode in RPC.
Purpose: To eanble the transport based scheduler in RPC.
Previously, we only support it with configuration file.

Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I02ae9b1b316d4fec8b28b550e70dcdc78ce78722
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461645
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>
2019-07-17 15:01:20 +00:00
Darek Stojaczyk
96ec8bff78 nvmf/rdma: switch to spdk_*malloc()
spdk_dma_*malloc() is about to be deprecated.

Change-Id: I5bcac50baca785255eb068086e67c07d120b042f
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459432
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-17 01:28:57 +00:00
Darek Stojaczyk
36ccca2c08 nvmf/tcp: switch to spdk_*malloc()
spdk_dma_*malloc() is about to be deprecated.

Change-Id: Ic42db528bbae4b3ca2e91cb9ac46def99ecb5f28
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459431
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-07-17 01:28:57 +00:00
Darek Stojaczyk
e3e524306b nbd: switch to spdk_*malloc()
spdk_dma_*malloc() is about to be deprecated.

Change-Id: If0bcdf2be9756b343375f02837a414d3b86f2bca
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459430
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2019-07-17 01:28:57 +00:00
Jacek Kalwas
e95e4028c1 nvmf/rdma: exclude getaddrinfo from lock
No need to have it under lock. Additionally in case of failure
there was a lack of rdma_destroy_id(). This is addresed within this
change as well.

Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: Idbb36d51ad4ef7ef81051463f56efc87ef00c966
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462054
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-17 01:03:36 +00:00
Jacek Kalwas
0d4a5f7e69 nvmf/rdma: free list of devices
In case of failure during pd or map allocation freeing list of devices
was missing.

Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: If62f7b072f3894fd1a7e856c19b4ea51646dd20e
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/462079
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-17 00:59:34 +00:00
Darek Stojaczyk
27b920a2a4 configure: unset CONFIG_VHOST on BSD
Remove linux #ifdefs from the vhost code and just
implicitly disable CONFIG_VHOST for BSD systems.

This serves as cleanup.

Change-Id: I8b0e0e8f80478f50ca8586cc974f7afcee2566f0
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460562
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>
2019-07-16 11:06:03 +00:00
Darek Stojaczyk
efef26e234 Revert "bdev: temporarily allow bdev descriptors to be closed from any thread"
Now that vhost closes bdev descriptors on the same thread
that opened them, we can reintroduce thread asserts into
the bdev layer.

This reverts commit 283abcb9a2.

Change-Id: I1acc455df0674b808ecf2fa58dffd183db6cf3c2
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459168
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-16 10:57:46 +00:00
Darek Stojaczyk
feaf45d31a vhost: allocate just one ctx per foreach_session chain
We used to allocate a ctx whenever new event had to
be sent, but since all events in foreach_session are
always called in a chain, we could allocate one ctx
at the start and then re-initialize it before sending
each msg.

Change-Id: Ie5477b07242f0c6eb6dc2160055a829da8ba5d11
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459167
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>
2019-07-16 10:57:46 +00:00
Darek Stojaczyk
3fb1a9565e vhost: finish foreach_session chain always on the init thread
foreach_session() is used to e.g. close a bdev, where
for each session we close any io_channels and then,
on the final "finish" call, close the bdev descriptor.

The vhost init thread is the one that called
spdk_vhost_init() and also the same one that calls
all management APIs. One of those is for hotplugging
LUNs to vhost scsi targets, which practically results
in opening bdev descriptors.

By always scheduling that final foreach_session()
callback to the init thread, we end up with calling
spdk_bdev_close() always on the same thread which
called spdk_bdev_open(), which is actually a bdev
layer requirement.

Change-Id: I2338e15c63f93ef37dd4412dd677dee40d272ec2
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459166
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>
2019-07-16 10:57:46 +00:00
Darek Stojaczyk
4b60bd1b59 vhost: don't setup session coalescing on vdev init
We used to call potentially-asynchronous foreach_session()
in vdev initialization path and that was perfectly
fine because at that time there were no sessions created
and foreach_session() was always finishing synchronously.
We're about to refactor it to be always asynchronous, and
for this coalescing case it could complicate the init
error path. Once asynchronous thread msg is sent, we would
need to wait for it to complete and we just don't want to
do that. We want error handling to be simple.

Since we know there are no sessions at the time of vdev
creation, we just add a new function for setting coalescing
params just for vdev (and not for its sessions) and we
use that function in vdev init code.

Change-Id: I44d204d03b5040525e4871693678d4b4a0204e63
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459196
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>
2019-07-16 10:57:46 +00:00
Darek Stojaczyk
d476d10665 vhost: reorder foreach_sesion_continue
Put it next to other functions in this call chain.

Change-Id: Ic621855b028f9bd110cdcda86b3a182369ec5e90
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459165
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>
2019-07-16 10:57:46 +00:00
Darek Stojaczyk
74243e36b9 vhost: reorder spdk_vhost_session_send_event
Put it next to other functions in this call chain.

Change-Id: Ieafd91c6cfefec134594aec8671eb4efdac15dfe
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459164
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-16 10:57:46 +00:00
Darek Stojaczyk
5e63804146 vhost: remove spdk_ prefix from some static function
spdk_ prefix should be only used on public API functions.

Change-Id: I663b107bd6b1c92c2c6263f2ec7c763d9812e7fe
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459163
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>
2019-07-16 10:57:46 +00:00
Darek Stojaczyk
4de67bbf6d vhost: inline spdk_vhost_event_async_send_foreach_continue
Despite its name, this function is defined as static
and is only used in one place, so inline it.

Change-Id: I4e217b3baae9b735761f5497f06b681a118860e9
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459162
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-16 10:57:46 +00:00
Darek Stojaczyk
98af6aba4d vhost: remove vsession->ev_ctx
It's no longer used.

Change-Id: Iffa385e18ba7a979d7a384f420f546207774dea3
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/459161
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>
2019-07-16 10:57:46 +00:00
Darek Stojaczyk
f43a485299 env_dpdk/pci: make spdk_pci_device_detach() synchronous again
By making dpdk device detach asynchronous we have
actually broken some cases where devices are re-attached
immediately after and fail since they were not detached
yet, so now we're making device detach synchronous again.

For that we'll simply wait inside spdk_pci_device_detach()
for the background dpdk thread to perform all necessary
actions before we return. We'll also print an error msg
if DPDK failed the detach (probably because of some
internal error).

Change-Id: I7657ac1b169169eae3325de2d28c2cc311e7d901
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460286
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: <jacek.kalwas@intel.com>
2019-07-16 10:56:28 +00:00
Darek Stojaczyk
79b5618168 env_dpdk/pci: don't defer device detach while on the dpdk thread
By making dpdk device detach asynchronous we have
actually broken some cases where devices are re-attached
immediately after and fail since they were not detached
yet.

We'll need to make detach synchronous again, and for that
we'll wait for the background dpdk thread to perform all
necessary actions before we return from spdk_pci_device_detach().

However, device detach could be triggered from the very
same dpdk background thread as well. Waiting there would
cause a deadlock, so now we'll schedule asynchronous
device detach to the dpdk thread only if we're not on
that thread already.

This patch itself serves also as an optimization.

Change-Id: I86b7ac1b669169eee3325de2d28c2cc313e7d901
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460285
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>
2019-07-16 10:56:28 +00:00
Darek Stojaczyk
cf35beccf4 env_dpdk/memory: include rte_memory.h
Latest DPDK moved some definitions around and we don't
compile with it right now. Adding the missing include
fixes it.

Change-Id: I9b0a915632996acfedbcf3d0f03feed986889a2d
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460905
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-16 10:54:01 +00:00
Darek Stojaczyk
4617707d07 reduce: switch to spdk_*malloc()
spdk_dma_*malloc() is about to be deprecated.

Change-Id: I140e10b2fd07efb48e664cfa00e1d60f604abd21
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/449797
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>
2019-07-16 10:51:47 +00:00
Jacek Kalwas
114a067738 nvmf/rdma: pd null check
In case of pd allocation by nvmf hooks there is a lack of null
check as oposed to pd allocation by ibv_alloc_pd.

Signed-off-by: Jacek Kalwas <jacek.kalwas@intel.com>
Change-Id: Iead6e0332bdee3da4adb6e657af298215c4e2196
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461576
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2019-07-16 01:29:03 +00:00
Seth Howell
dc53a9de36 lib/ftl: remove local phase variable
Since the local is only used in the SPDK_DEBUGLOG call, it was causing
the build to fail when the configure options --disable-debug and
--enable-werror were supplied together. This can be seen in the most
recent nightly builds.

Change-Id: I32112cf832a705292783da4e841badaeed17dbb6
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461746
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-16 01:21:55 +00:00
Darek Stojaczyk
69642141bb blobstore: fix unused variable warning on non-debug builds
gcc complains:

blobstore.c: In function ‘_spdk_blob_load_cpl’:
blobstore.c:978:12: warning: unused variable ‘max_md_lba’ [-Wunused-variable]

Change-Id: If2875d2d83edce6d1b544d6a4f51e78fa760d752
Signed-off-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461750
Reviewed-by: Seth Howell <seth.howell5141@gmail.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-16 01:20:30 +00:00
James Bergsten
5acf617c6e nvme: add functions to pretty-print commands and completions
This change attempts to address the Trello request to decode I/O errors in
NVMe hello_world example.

See https://trello.com/c/MzJJw7hM/2-decode-io-errors-in-nvme-helloworld-example

As part of this change, spdk_nvme_cpl_get_status_string was declared
in nvme.h, and spdk_nvme_qpair_print_command and
spdk_nvme_qpair_print_completion were renamed and added to nvme.h,
allowing all three to used "externally."

To test the failing paths, two compile time defines were added to force a
write or read error (bad LBA) respectively.

As the example does a read after write, if the write fails, the example fails.

Signed-off-by: James Bergsten <jamesx.bergsten@intel.com>
Change-Id: Ib94b4a02495eb40966e3f49517a5bdf64485538a
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/457076
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-15 07:47:03 +00:00
Richael Zhuang
d4cbbf1751 nvme: use atomic builtins for g_signal_lock
The __sync builtin based implementation generates full memory
barriers on some non-x86 platforms. Replace it with C11 atomic
builtins can make:
·arm and ppc from full barrier to half barrier
·x86 code same as before

Signed-off-by: Richael Zhuang <richael.zhuang@arm.com>
Change-Id: Ib6624ef8e45af497b9eced6ecfa7710bcc88a733
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/461590
Reviewed-by: Darek Stojaczyk <dariusz.stojaczyk@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
2019-07-15 06:01:37 +00:00
Tomasz Zawadzki
672d42b284 lib/blob: fix check against lba during blob load
md_start and md_len are values in pages rather than lba.
Those should not be compared against lba of currently
loaded md page.

This patch changes assert to verify if the lba of current
page does not exceed max lba where md is expected to be.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Id445eb9871f82f7fe367bfc396f1b495591511c1
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460976
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>
2019-07-15 04:22:23 +00:00
Tomasz Zawadzki
6ced601526 lib/blob: only validate blobid of first page during bs_load
Blob id only is matched to the very first page of md for
that particular blob.

During loading blobstore, we shouldn't verify
further pages in chain against the blobid.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: Ifc7863ddcb403aedc264c14e6b4c3915bd30dc41
Reviewed-on: https://review.gerrithub.io/c/spdk/spdk/+/460607
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>
2019-07-15 04:22:23 +00:00