Trace the initiator and target name for debugging purpose.
Change-Id: I89230484072a7f12a58b4234abd1026a228f302a
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/403690
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Return NULL on resource failure (calloc) instead of
abort()'ing in static nbd function and check result
returning an errno, in that case, further up the call
chain.
Change-Id: If95f8db745fa77c76c415a1aa54c5338c270628f
Signed-off-by: Lance Hartmann <lance.hartmann@oracle.com>
Reviewed-on: https://review.gerrithub.io/403588
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This will be used to track time used in pollers - each poller can now
indicate if it found any work to do or not.
For cases where it was obvious and the infrastructure was already in
place, existing pollers have been modified to return 0 or a positive
value to indicate whether work was done. Other pollers have been
modified to return -1 by default, indicating that the poller isn't
indicating anything about whether work was performed. This will allow
us to find un-annotated pollers easily in the future and fix them
incrementally.
Change-Id: Ifebfa56604a38434fac5c76ba7263267574ff199
Signed-off-by: Roman Sudarikov <roman.sudarikov@intel.com>
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/391042
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
There are two separate function pointer types declared in io_channel.h:
spdk_thread_fn for cross-thread messages, and spdk_poller_fn for
pollers. They currently have the same signature, but this will be
changing in an upcoming patch, so we need to fix the poller-related
functions to use the correct type (a few were using spdk_thread_fn by
mistake).
Change-Id: I0f0d8f1eea9905395125fc91e0355a49e65be99e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/403598
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
This is a leftover from moving nvmf to a subsystem.
Change-Id: I6ad07d3c60dff29e34b92c9cf18ac451cfd00918
Fixes: 2491021f64 ("nvmf: convert nvmf_tgt into an event subsystem")
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/403374
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This better matches the style in the rest of SPDK.
No functional change - this is a pure find/replace of
spdk_bdev_module_if to spdk_bdev_module. Instances of this struct will
be renamed in another patch.
Change-Id: I3f6933c8a366e625fc3a1b6401aee26ee03ba69c
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/403368
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Modifies behavior of spdk_trace_init() such that it returns
on failure instead of terminating with exit().
Change-Id: I0ba321cddd233008a4b19bc592728230d89a11b2
Signed-off-by: Lance Hartmann <lance.hartmann@oracle.com>
Reviewed-on: https://review.gerrithub.io/403357
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Return NULL on resource failure (spdk_mem_get) instead of
abort()'ing in static bdev function.
Change-Id: I0ee2ce4b7e81cf80546119e3db27c987fa912749
Signed-off-by: Lance Hartmann <lance.hartmann@oracle.com>
Reviewed-on: https://review.gerrithub.io/403578
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
BlobFS shutdown path needs to be investigated more with these
changes.
This reverts commit a137b9afd0.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8b04b24e178945d62db20668b9e500f278ae955b
Reviewed-on: https://review.gerrithub.io/403600
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
For any given blob, if an spdk_blob_sync_md() operation
is already in progress, queue additional spdk_blob_sync_md()
operations until the previous one completes.
This ensures proper ordering of writing metadata to
disk.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I2051e8cb5b8d1a033ec1238cb4811232110aa0f4
Reviewed-on: https://review.gerrithub.io/401257
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
If we are not in ffp phase, we do not need to update last_nopin
Change-Id: I289beec8437d7117b6261483c333bf5db5fbd11f
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/403166
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
In the upcoming JSON config file, CHAP parameters for discovery will
be specified simply by the value of them.
This is as same as JSON-RPC for target node but different from .INI
config file.
If CHAP parameters are specified by the value of them, the combination
of them must be checked before applied to iSCSI globals.
Change-Id: Idf663796f97581366da945abb8dc351f3975ceae
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403235
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Currently CHAP parameters for discovery are handled as bool but
they are defined as int. Hence change their type from int to bool
as done for target node previously.
Change-Id: I1e815946d4bdececcdd7cc873a725afbbcb98e50
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403234
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Portal, portal group, initiator group, and target node don't use fixed size
array anymore. To use the same naming rule in iSCSI subsystem and in SPDK
is helpful to understand and maintain. Current naming rule is not bad but
to use unified and compact name is prioritized at this time.
This patch changes function names as follows:
- spdk_iscsi_init_tgt_nodes() -> spdk_iscsi_parse_tgt_nodes()
- spdk_cf_add_iscsi_tgt_node() -> spdk_iscsi_parse_tgt_node()
- spdk_iscsi_portal_grp_array_create() -> spdk_iscsi_parse_portal_grps()
- spdk_iscsi_portal_grp_create_from_configfile() -> spdk_iscsi_parse_portal_grp()
- spdk_iscsi_portal_create_from_configline() -> spdk_iscsi_parse_portal()
- spdk_iscsi_portal_grp_array_destroy() -> spdk_iscsi_portal_grps_destroy()
- spdk_iscsi_init_grp_array_create() -> spdk_iscsi_parse_init_grps()
- spdk_iscsi_init_grp_create_from_configfile() -> spdk_iscsi_parse_init_grp()
- spdk_iscsi_init_grp_array_destroy() -> spdk_iscsi_init_grps_destroy()
For example "parse" is already used to explain the operation in portal_grp.c.
Hence using "parse" is familiar and not strange in iSCSI.
Change-Id: Ieff952069d39bd96b7afa1586bfff927968accc2
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403149
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Some variables of struct spdk_iscsi_globals are initialized by using
.INI config file but others are initialized without using .INI config
file.
This patch aggregates all initialization operations into a function
spdk_iscsi_initialize_iscsi_globals().
Next patch move the code to read .INI config file from
spdk_iscsi_initialize_iscsi_globals() to spdk_iscsi_parse_iscsi_globals()
to make implementation cleaner.
The purpose of the patch series is
- to separate iSCSI subsystem initialization and iSCSI subsystem
configuration, and
- to develop a new JSON-RPC by reusing the separated iSCSI subsystem
initialization.
Change-Id: I0bda0de1d8bf1ba5e4b4e5157949fd300ec9ff9d
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403148
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Upcoming JSON config file will support iSCSI global params initialization.
This patch is an effort for JSON config file to reuse the current code as
much as possible.
SPDK's other libraries use options structure effectively, and hence
iSCSI library also utilizes it.
The purpose of the patch series is
- to separate iSCSI subsystem initialization and iSCSI subsystem
configuration, and
- to develop a new JSON-RPC by reusing the separated iSCSI subsystem
initialization.
Change-Id: I9936a4cac4048adaa5d69233f156887376d7cde1
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403147
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This patch is to add the basic support of QoS on bdev.
Including two major functionalities:
1. The QoS rate limiting algorithm:
a. New IO will be always queued first also under
the no memory condition
b. Start the QoS IO operation based on the limit
c. A poller started in each millisecond to reset
the rate limit and send new IOs down
d. The rate limit is based on the millisecond and
converted from user configurable IOsPerSecond
2. The Master Thread management:
a. Add a per bdev channel_count
b. Whenever QoS is enabled on bdev, if QoS bdev
channel is not created, create the QoS bdev
channel and assign the QoS thread
c. When new IOs coming from different channels
(threads), pass the IOs to the QoS bdev channel
through the thread event
d. When the IOs are completed from the QoS bdev
channel, pass the IOs back to its orignal
channel(thread)
e. Destroy the QoS bdev channel when it is the
last bdev channel for this bdev. Defer the
destruction if current thread is not QoS thread
Change-Id: Ie4444551d7c3c7de52f6513c9db926628796adb4
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/393136
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I94bbf1f035aca463530450811200f1f1800d6485
Fixes: 4294719ed7 ("subsystem: make subsystem declaration ...")
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/403355
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Change-Id: If5e16c2ac148fd4818c942e8f57b02671e76ed62
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/403153
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Currently SPDK_BDEV_MODULE_REGISTER() take many parameters. Extending it
(eg for incoming JSON configuration dump/load) is quite challenging and
error prone. As we are already here in next patches, rework this macro
to take one parameter - the pointer to struct spdk_bdev_module_if.
This patch also remove following macros:
SPDK_GET_BDEV_MODULE - this is not really needed, to find module outside
module translation unit use spdk_bdev_module_list_find()
SPDK_BDEV_MODULE_ASYNC_INIT and SPDK_BDEV_MODULE_ASYNC_FINI - replaced
by bool fields in spdk_bdev_module_if struct.
Change-Id: Ief88e023fbbaee7d5402c838dbecbdffd4dfb259
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/402883
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Don't do anything under the scene as adding/removing fields in struct
spdk_subsystem will require both macro change and C file changes.
Change-Id: I11bc0d5758edd7e0e0bd3f93e251d868cd9b1d2b
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/401850
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
This allows vhost initialization to be fully handled in the event
framework subsystem.
Change-Id: Ic0ff11f3765cc553b7ca183027209fb6dd131364
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/403226
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This lets us drop the basename parameter from spdk_vhost_startup(),
which is a step toward making vhost initialization happen as part of the
event subsystem instead of in the spdk_app_start() callback.
Change-Id: I4fe18c4c3f12b706e73ae74500be58f1582110fd
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/403225
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This is required as part of our effort to build a single target app that
can run e.g. NVMe-oF and iSCSI targets in the same process.
Change-Id: Ic8426df08899070d709e3675a57f47f64c23c5eb
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/403218
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This can be used to force specific UUIDs for testing.
Change-Id: I40c403fd00c142552d632dd5f0fbe1ea9a6c9962
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/403221
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
This patch extracts iSCSI subsystem initialization by .INI config file
into a function spdk_iscsi_parse_iscsi_globals().
Naming rule was adopted from NVMf-tgt.
By these two patches,
iSCSI subsystem init is done in spdk_iscsi_parse_iscsi_globals().
iscsi subsystem config is done in spdk_iscsi_parse_iscsi_configuration().
The purpose of the patch series is
- to separate iSCSI subsystem initialization and iSCSI subsystem
configuration, and
- to develop a new JSON-RPC by reusing the separated iSCSI subsystem
initialization.
Change-Id: Ibafb0b62cbb0aa23dd6dd6007dad0345293e65b8
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403146
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
iSCSI poll_group initialization must be completed before starting JSON-RPC.
This doesn't have any dependency to the other iSCSI subsystem
initialization and completes asynchronously. Hence thisis good to be placed
at the end of iSCSI subsystem initialization.
Besides, object creation of iSCSI configurable components started after
poll_group initialization by .INI config file is aggregated into a function
spdk_iscsi_parse_iscsi_configuration().
Naming rule was adopted from NVMf-tgt.
The purpose of the patch series is
- to separate iSCSI subsystem initialization and iSCSI subsystem
configuration, and
- to develop a new JSON-RPC by reusing the separated iSCSI subsystem
initialization.
Change-Id: I44421803268361f53840a7e47f07ce95c13d1139
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403145
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The next patch will move the location and change the callback of poll
group initialization. Besides it is probable for JSON config file to
change the callback of poll group initialization.
Passing callback as argument increases visibility and flexibility of
code.
Change-Id: Ie4bfd2c60a112bb7c697110ef0efc30a2c098dc8
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403144
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Pool of iSCSI connections and related variables are initialized in
initialize_iscsi_conns().
Currently initialize_iscsi_conns() is located after configuration of
target nodes by .INI config file.
Configuration of target nodes can be done by JSON-RPC but connection
initialization must be completed before starting JSON-RPC.
iSCSI connections don't belong to iSCSI global params directly and
hence move connection initialization right after initialization of
iSCSI global params.
The purpose of the patch series is
- to separate iSCSI subsystem initialization and iSCSI subsystem
configuration, and
- to develop a new JSON-RPC by reusing the separated iSCSI subsystem
initialization.
Change-Id: I183365b84aa205790b27adf7cc1f632b932195aa
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403143
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
iSCSI subsystem have a pool for PDU, session, and task, respectively.
They belong to the struct spdk_iscsi_globals and are initialized by
using the parameters of the struct spdk_iscsi_globals.
Hence their initialization should be located just behind the setup of
parameters of the struct spdk_iscsi_globals.
The purpose of the patch series is
- to separate iSCSI subsystem initialization and iSCSI subsystem
configuration, and
- to develop a new JSON-RPC by reusing the separated iSCSI subsystem
initialization.
Change-Id: Ie39f63ee24c547dcd31a1a06d72d915e8c272864
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403142
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Object creation of portal, portal group, and initiator group can be
done by JSON-RPC.
This patch moves object creation of portal, portal group, and initiator
group right before object creation of target node.
The purpose of the patch series is
- to separate iSCSI subsystem initialization and iSCSI subsystem
configuration, and
- to develop a new JSON-RPC by reusing the separated iSCSI subsystem
initialization.
Change-Id: If78beabb478923e7c920c09b16e42d6f8aa55775
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403141
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
There are four configurable components, portal, portal group, target node,
and initiator group in iSCSI.
They have a TAILQ to manage their objects, respectively.
Currently each TAILQ initialization is done together with its object
creation by .INI config file.
This patch separates TAILQ initialization from object creation for four
configurable components in iSCSI.
The purpose of the patch series is
- to separate iSCSI subsystem initialization and iSCSI subsystem
configuration, and
- to develop a new JSON-RPC by reusing the separated iSCSI subsystem
initialization.
Change-Id: Ia4ac3f06f15acef671e785904f4c687e5d189fbe
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/403140
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ie7a940efde885dbf0bb7c085fd17c3991dfa3341
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/403165
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Modifies behavior of spdk_app_start() and spdk_app_parse_args()
such that they return on failure instead of terminating with
exit().
Change-Id: I82566417f04e1ae2e3ca60a00c72e664db26c9e4
Signed-off-by: Lance Hartmann <lance.hartmann@oracle.com>
Reviewed-on: https://review.gerrithub.io/401243
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Change-Id: I738b4e28065797c9df7b0bc27ec0aee8c9f4f257
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/402381
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This patch adds possibility to set internal xattrs on blob
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I2d0f14558e4a1af7071ee1a4f59aaf9f14bea2d9
Reviewed-on: https://review.gerrithub.io/396418
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Unit tests implemented in following patches.
This is rebased patch from https://review.gerrithub.io/#/c/396648
merged as commit c1174e6895
and reverted in 0847f27b54.
Change-Id: I3d152bf7847c83bf75149edd61564c1f393927d8
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Reviewed-on: https://review.gerrithub.io/402529
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
For some xattrs we need to know its value even if blob is in loading
state, e.g. BLOB_SNAPSHOT xattr value when blob is loading.
Change-Id: I1cd7805cf33be64cf59792f85a270e9b536e23bd
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/403062
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Change-Id: Ief1f809308fbde2e696c60d3ce79c0720cb3e2ff
Signed-off-by: Sebastian Basierski <sebastianx.basierski@intel.com>
Reviewed-on: https://review.gerrithub.io/398934
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I22c11cdd5ab0ffdf72b27223c0c9cd7282537613
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/402667
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
In addition to the lvolstore uuid, add a per-lvol uuid for bdev
identification.
The lvol uuid is stored as an xattr for each lvol blob; if an lvol blob
without a uuid xattr is encountered, the lvol bdev will not report a
uuid for now (it will be set to all zeroes, which will be treated as
no uuid available by the generic bdev layer).
Change-Id: If00221383a12d62234fc085d56e257dd48053103
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/402973
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Add a generic way to get a UUID from a bdev.
For now, malloc and null bdevs generate random UUIDs, and no other bdev
types report a UUID.
Change-Id: Id9608c8c1b3ce3f1783e7f74bef96d44cd5d98a7
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/402177
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
This lets us have a common place to put definitions like the length of
the UUID string, as well as abstract away some of the API warts in
libuuid (non-const values, no size checking for uuid_unparse, etc.).
Change-Id: I80607fcd21ce57fdbb8729442fbb721bc71ccb98
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/402176
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Rather than explicitly asking for time-based UUIDs, let libuuid choose
the best available UUID source (high-quality random number based if
available, or time-based if not).
Change-Id: Ic2f538890f86d3158b64f5884708439b72c373f6
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/402963
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
We should add this state after free the io channel.
To make sure that we will not touch the wild pointer.
Change-Id: I570f649fe3ddffaea430125b40c6b6b020a05222
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/402999
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Before this patch super_blob id for blobstore was persisted
only during spdk_bs_unload. If power fail occurred after creating and
syncing blob, super_blob id was lost within blobstore.
Lvol store metadata would be lost, if proper shutdown
didn't occur in first SPDK instance run since creation of lvs.
This fix changes setting super blob to be instantly persisted
on disk in super block. Without affecting clean bit in super block.
Change-Id: I578f1fc8717e2d7968ad506fa4dead7507a5e0b4
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-on: https://review.gerrithub.io/398804
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
The variable ntargets in the struct spdk_iscsi_globals was needed
previously because iSCSI target node was managed by a fixed size
array.
Now iSCSI target node is managed by a linked list and ntargets
doesn't take any meaningful role now.
Change-Id: I1805d7a6a6ce40efa4d18f198fbb9104bee43b26
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/402976
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Even if the value specified by user through the config file is correct,
the default value is always set to DefaultTime2Retain.
Change-Id: Ifdf44e743419813b728a1423c441df59cc90c0a1
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/402635
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Change-Id: Ic3a612ceed65799d16dae111db355333a1915187
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/403002
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I5e636c4c9d930de0d9e6eadd453f0d17eadaf45e
Signed-off-by: Tomasz Kulasek <tomaszx.kulasek@intel.com>
Reviewed-on: https://review.gerrithub.io/402530
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
A bdev that is claimed is not a leaf, even if it has no vbdevs exposed
currently.
Change-Id: I3b790068128890a569f83b15071ea916c54bff9b
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/402935
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
As for NVMeoF controller, SPDK always set volatile write cache to
present, so OS may submit FLUSH command to backend block device,
while here, return success for those block devices which can't
support FLUSH command.
Change-Id: Ib764503f1986e7e0a38a1751a91d6c11e1b78865
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/402653
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Also remove the related login and full feature
function
Change-Id: Ia2d0a6617910134c889d1322b53830fe26b9e956
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/402486
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
This patch will also re-export spdk_iscsi_conn_destruct
Change-Id: I7d6cbba33294c84398a919d888c8b375e901e09e
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/402485
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
iSCSI's global mutex is used in spdk_iscsi_portal_grp_create()
before it is initialized by pthread_mutex_init().
A mutex filled with zero bytes has been accepted by now but
this should be fixed.
Change-Id: I2e197bec8da2f781c8c4f6e2a2caf9924b0a4369
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/402497
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Put it in the iscsi.c
Change-Id: Ifb2843fb7c78f9ca948eac60704547b8b0635bf0
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/402484
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Automatically detect more whitespace errors.
All existing cases are fixed; only whitespace change (verify with
diff -w) except for one comment style fixup in include/spdk/nvme.h.
Change-Id: If750e54b9c8e3421ea6feda5f20184a31431631e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/402360
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Currently if the application exits with some error (i.e., core
dump), the socket file is not removed. So that at next time the
RPC method can not enabled unless user manually removes the
socket file. The error of failing to start RPC is not that
obvious.
This patch introduces a lock for the reuse socket to properly
detect the only usage and handles the above error case particularly.
Refer to https://gavv.github.io/blog/unix-socket-reuse/ for the
details.
For the concern of the sockect file can be shared from different
applications, in the spdk_app_opts struct, it offers a parameter
to assign a specific socket file per application.
Change-Id: Ie2ef6af9207c468279cba5efd173fd06579ccdc7
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/396089
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I30675083dcb7dda47ac62eaf124614033ff9c587
Reviewed-on: https://review.gerrithub.io/401702
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This change wasn't correctly rebased and needs to be updated to compile
against the current blobstore.
This reverts commit c1174e6895.
Change-Id: I529608bee7323cb626d8c36dff15adc9ba24ad26
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/402352
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Unit tests implemented in following patches.
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: Ib18c9060f527bd22bfdbed74e96871a6e0551ead
Reviewed-on: https://review.gerrithub.io/396648
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Currently only thin_provisioned zeroes back_bs_dev is supported.
There was no unit tests for channel in this bs_dev, because it's never used.
However, unit tests in patch https://review.gerrithub.io/c/393935/ show that channel is wrong.
This patch passed proper spdk_io_channel to callback function.
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: Ia288ef6c35343ce533ea3f74603e73f823a18181
Reviewed-on: https://review.gerrithub.io/400955
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This patch adds the QoS parameters on the bdev channel.
Change-Id: I0cb9bf9e9cdbbe61c70c4a3df4eeb8be774793a0
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/393129
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Briefly tested with SPDK target via bdevio
through both vhost-user and QEMU's virtio-pci.
vhost-blk driver is not mentioned in any doc yet.
A virtio-blk bdev can be created as following:
`construct_virtio_user_blk_bdev /tmp/virtio.0 MyVirtioBlk0 --vq-count 16`
`construct_virtio_pci_blk_bdev 0000:01:00.0 MyVirtioBlk1`
or
```
[VirtioUser0]
Path /tmp/vhost.0
Type Blk
Queues 16
[VirtioPci]
Enable Yes
```
If `Type` field is not present, the VirtioUser
section will be parsed as a SCSI one, preserving
backward compatibility.
Change-Id: I3eae9f3b90570fbb0177df4951e5eed86fe07c66
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/393056
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
If this polling group is not initialized, we do not
need to destroy the polling group.
Change-Id: I5a94412d7f42b05d4a457c8652e2f465190fbe6e
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/401362
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Alters internal spdk_process_new_interface_msg() function
such that it returns a failure instead of exit()'ing.
Change-Id: I31c5dd9db43449f81dbb0f581258476a58aa8000
Signed-off-by: Lance Hartmann <lance.hartmann@oracle.com>
Reviewed-on: https://review.gerrithub.io/402165
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
There was a bug reported by Cunyin Chang with regards to how the
cmb_current_offset was calculated when the CMB offset into the CMB BAR
is non-zero. This patch fixes this issue and also fixes the problem
that the last valid offset into the BAR *may* differ if registration
is utilized or not (due to the 2MiB alignment and length requirements
for registered memory).
Change-Id: Id08d6a5a40b828338f6a66599171cc8dd59768a3
Signed-off-by: Stephen Bates <sbates@raithlin.com>
Reviewed-on: https://review.gerrithub.io/401832
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The better location is to put this function in
the end of process_read_task_completion which can match
the the same function call in spdk_iscsi_op_scsi_read.
Change-Id: I7dbfb23e2c469e0be22e148299643a99b93c8018
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/401985
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Since we have two pollers for each iSCSI polling group,
so it could be possible that the nop_poller to set
iSCSI connection in existed or existing state.
So add a check here, which means the incoming data
is too late.
Change-Id: I94e5090b005c35c9eb5d7eedbd7acdae67327f94
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/402039
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Purpose: To make the logic clear.
Change-Id: I6176f359a23816b316e92b63ee2e5d5175ae7e7b
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/401772
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This allows listening on the same port on IPv4 and IPv6 simultaneously;
otherwise, the second listen call would fail with an "address in use"
error.
Change-Id: I75010a2d1ec6559653e0bda40517dc13d8f5b9a5
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/401718
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
blobfs and lvol can now use this to automatically iterate
all existing blobs during spdk_bs_load. Changes to blobfs
and lvol will come in future patches.
This will also be used in some upcoming patches which need
to iterate through blobs during load to determine
snapshot/clone relationships.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ic7c5fac4535ceaa926217a105dda532517e3e251
Reviewed-on: https://review.gerrithub.io/400177
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Currently, this just reports the EUI64 and NGUID types, which are
already available in the Identify Namespace data, but this sets up the
framework for reporting a Namespace UUID (which doesn't have a
corresponding field in Identify Namespace) in the future.
Change-Id: I758e6d402ff874d65eca3f1db98d92c1a3f7a11f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/400893
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This patch is used to implement the sock fd event group
polling mechanism if there are incoming data from network
(read event in SPDK iSCSI target side) , thus we can awake
many connections one time, and it can reduce the system call
overhead.
Change-Id: I76c26a89ef9365d7e1ccec616985e7435253896b
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/399796
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This simplifies the code and eliminates the possibility of accidentally
inserting other items in between a key and its value.
Change-Id: Ic3bf7d0a85e9475171fe00cbcac6fe3ede731e69
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/401046
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Ctrlrs list maintanined by the subsystem structure should be operated
by the thread which creates the subsystem. And this will make the
operations correct.
Change-Id: I7f881a77b1846658b3acd4270b74f86816e87803
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/401541
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Purpose: To make the nvmf subsystem management correct
in next patch.
Change-Id: Ie5433f3a7d47f05c5949dfc723aba73465623f88
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/401540
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Finish the sequence first, before calling _spdk_bs_free().
Otherwise synchronous bs_devs (like we use in the unit
tests) cause the sequence memory to get freed via
_spdk_bs_free() and then we try to finish the sequence.
This eliminates the need for g_scheduler_delay and
_bs_flush_scheduler() in the blob unit tests. But don't
remove them - they will be useful in upcoming unit tests
for queued persist operations.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I09aac3ae4d3a56ff8e04a5b822fcd6746f13afc3
Reviewed-on: https://review.gerrithub.io/401267
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
No functional change - this just separates out the
code that creates the persist ctx from the code that
actually performs the persist operation.
Part of series to enable queuing persist operations -
this will be useful for starting a previously queued
persist operation.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ie1966ff2a477f3075c36f90560010d036658f803
Reviewed-on: https://review.gerrithub.io/401255
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Iaef32731b05a53ac0707524d78086eedc89d6af6
Reviewed-on: https://review.gerrithub.io/401254
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I096fb24dd2fe2fc4dd97d80c957c328d960fb867
Reviewed-on: https://review.gerrithub.io/401073
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
spdk_blob_close() and spdk_blob_sync_md() currently do their
own CLEAN state. To consolidate the state checking code,
have both functions rely on the check in _spdk_blob_persist()
instead.
This will reduce code but more importantly is needed for
some upcoming changes for queuing persist operations.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I38118624b4fad6f18c4b7466d9ddfa0915c3fce0
Reviewed-on: https://review.gerrithub.io/401065
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
These are common functions that can be called from
any function that reads or modifies a blob's metadata to
perform necessary asserts.
This will also fix several places where blob metadata
functions were asserting the calling thread context,
but not the current state of the blob.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I9e16c082a27c439311f8ff214335adadfa715497
Reviewed-on: https://review.gerrithub.io/401053
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
All metadata operations are now done on the metadata
thread, so we no longer have to worry about one thread
updating in-memory metadata structures while another
thread is transferring the in-memory structures to
on-disk structures.
This does not protect against multiple sync operations
outstanding at once - that will be coming in an
upcoming path.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ibf33edf4d41d867c96a38df017737e9ceb87fa58
Reviewed-on: https://review.gerrithub.io/401056
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
The md (metadata) thread is always the thread that
initialize/loaded the blobstore. Metadata operations may
only be performed from this thread. This patch adds some
more asserts in metadata functions that were previously
missed.
While here, also update some of the blobstore documentation
related to this.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I5cafdb3ba402ceb6c3ccb6fdd9d36e7768f59f39
Reviewed-on: https://review.gerrithub.io/400885
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Unfortunatly not all bdevs produce its configuration in responce to
get_bdevs RPC call (eg nvme is producing tons of additional
informations). To not breake any existing scripts rename
'dump_config_json' to 'dump_info_json' instead of reworking those
callbacks. Next patches will introduce real 'dump_config_json' handlers
and API
Change-Id: If9c1a4ab864791b24a5f7d022e970cd65990ffc0
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/401216
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
The iSCSI connection does not have the poller anymore, so
change the name
Change-Id: I534f72998c6bcc73ad9caf5e8f700751acd95c99
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/401372
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ic2bae1c750d2c9b35bded8ed96c3b84832690ce2
Reviewed-on: https://review.gerrithub.io/401479
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Three new RPC methods are added to allow modification of the NVMe-oF
subsystem allowed host whitelist at runtime:
- nvmf_subsystem_add_host
- nvmf_subsystem_remove_host
- nvmf_subsystem_allow_any_host
Change-Id: I5c98658f949dad013165c04497cca49867022ba0
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/396063
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Implement a poor approximation of reset handling for the RBD bdev so it
can pass the bdevio tests.
This should be replaced with a solution similar to bdev_aio, which waits
for all outstanding I/O to return before completing the reset. However,
this should ideally be handled by the generic bdev layer rather than in
each individual module.
Change-Id: I1be2bf90875e23e05efdebb003e5412f3fc43793
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/401273
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Previously, the RBD bdev only supported a single iovec entry, which is
not sufficient for the bdev API.
Change-Id: Ic18257bae0363b9c01e091547e5b41bae0a21e9a
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/401259
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
During converting type of CHAP params of target from int to bool
for JSON, changed names of them to be consistent with others.
In this patch, adjust variable name of struct to of JSON.
Change-Id: I1ccbfa11d57479dc55680835eb80e111bd24d9a3
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/400928
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This is a TODO from long ago. Complete this while adjusting dump()
and construct() format of target.
Besides names of variables and parameters about CHAP are not unified
between JSON-RPC and SPDK internal. JSON-RPC's wording looks better
and adjust SPDK internal to JSON-RPC.
Change-Id: I89bcd1ce13a11f7d63a62d51ef094dd302186d37
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/400201
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This is a TODO from long ago. Complete this while adjusting dump()
and construct() format of target.
Change-Id: I44348ec404cae8882086a1a71a65914c9bafccc3
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/400202
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This patch adds a iSCSI poll group for each core,
thus we can poll a group of connections instead of one
by one on each core.
Change-Id: I9cd82c8c0f7f6e7b3ee34034339638199bfca5da
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/399565
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
These new names are much more clear and are aligned with other
functions such as spdk_blob_close.
Keep the old names around for now but deprecate them. We will
remove them in next release.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Idc60fd0b19fa2a8b0247a1f5835774d342e721f9
Reviewed-on: https://review.gerrithub.io/400884
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This is needed for an upcoming change which will
prevent metadata functions from being called on
threads other than the metadata thread. Without
this change, there was no way for this function
to return an error if it was called from the wrong
thread.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I67e591140194ff6ad250878168f6b166a1ff2282
Reviewed-on: https://review.gerrithub.io/400883
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
There was some thinking that we would need to allocate
I/O channels on a per-blob basis to handle dynamic
resizing during I/O. Making spdk_blob an opaque handle,
with the existing spdk_blob structure renamed to
spdk_blob_data was a first step towards making that
happen. But more recent work on blobstore has
simplified the resizing approach, so this spdk_blob_data
is no longer needed. So revert it.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I22e07008faceb70649ee560176ebe5e014d5f1a3
Reviewed-on: https://review.gerrithub.io/400881
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This will let us e.g. read device blocksize in the
upcoming vhost-blk initiator. All the public API
was already there - we've been using it for
virtio-pci. Now we're making use of it for vhost-user
as well.
Change-Id: I39eab820bb9bbff59c8b8efa79cc97d2ec7806fd
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/398828
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I02ca8aed1bba1922a69a9b22bca22bce06e9c55f
Signed-off-by: Pan Liu <liupan1111@gmail.com>
Reviewed-on: https://review.gerrithub.io/399536
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The default method for building DPDK now is via the submodule, and users
that explicitly want to link a different DPDK need to specify its path
during configure. Therefore, nothing should be depending on these
hard-coded paths, and we can remove them.
Change-Id: Ic7d70ef10c46f9711691fb804f7dc854e05f7ed1
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/401075
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
With recent update to bdev.c for its io_device_register
handle for new bdevs, several modules can now just use
their respective structures defining each bdev rather
than picking a more complicated one.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ic8ea24c64a782e54d18b6241e36f56dbbbb5f1e7
Reviewed-on: https://review.gerrithub.io/400555
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Many bdev modules create their own bdev structure
with spdk_bdev as the first member. bdev.c currently
uses the spdk_bdev pointer as its io_device handle,
forcing bdev modules to pick something different.
Change this to use the spdk_bdev pointer + 1 bytes
as its io_device handle. The actual handle does not
really matter - it just needs to be unique. This will
simplify bdev module development.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8b6da3be9c16c87bc7a393c3a2221c6bae26e0a5
Reviewed-on: https://review.gerrithub.io/400554
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
This can be enabled with -t nvme in debug builds.
Change-Id: I4392d0a7decd65cc567fdf6fd56cac6db0424cd8
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/401052
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This function returns uint64_t, but the existing code was returning
the bool 'false' (which is also 0, so there is no functional change).
Change-Id: I546b15974c2d9e4107efe262950e3eb5613e0e9f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/401051
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Unify several similar functions checking for a buffer of all zero bytes
into the util library.
Change-Id: Idfbeffa22add34ac9ed1bd75ee27d6bd8b188940
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/400892
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Supporting sock_groups with multiple spdk_net_impls
is a bit tricky. We cannot just allocate space off
the end of spdk_sock_group for the implementation-specific
details - we need separate allocations for each
spdk_net_impl so that one spdk_sock_group can handle
spdk_socks from multiple spdk_net_impls.
Unit tests will come in upcoming patch.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I1570862a044192d30a79224f6029bf3d8157ce80
Reviewed-on: https://review.gerrithub.io/400528
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
JSON format of bdev_name_id_pair is different between
construct_target_node() and get_target_nodes().
construct_target_nodes() uses the following format:
"lun_ids": [
1
],
"bdev_names": [
"Malloc0"
]
get_target_nodes() uses the following format:
"luns": [
{
"lun_id": 0,
"bdev_name": "lvs_1/lbd_1"
},
]
The second format is better than the first format. Hence unify to
the second format.
Change-Id: If097e41ada0f2fe3754691cee0a0774db97c4ebb
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/399993
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
For the following JSON-RPC:
1) get_target_nodes
2) construct_target_node
3) add_pg_ig_maps
4) delete_pg_ig_maps
JSON format is not unified yet.
1) uses the following:
"pg_ig_maps": [
{
"ig_tag": 1,
"pg_tag": 1
}
2), 3), and 4) use the following:
"ig_tags": [
1
],
"pg_tags": [
1
],
the first format is better than the second format. Hence unify to
the first format.
Change-Id: I6cc19115001b9c9ba9db5c87db1def7c0b3bd80c
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/400203
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
The list of net impls doesn't need to be visible outside of sock.c.
Change-Id: I8def009acb82e5cd6f1e13e797079c1a94e3c7da
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/400864
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
The CFLAGS in these files add unneeded include directories.
Change-Id: I742a75b7ce5bff2f1dfd6f92d99ebc99a1936666
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/400862
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
spdk_sock_group_impl represents the implementation of
a sock group for a given spdk_net_impl (posix, vpp, etc.)
This extra abstraction is required for enabling
spdk_sock_groups with sockets associated with different
spdk_net_impls.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I7a380cc62c59bdac98996faf0387550c234165a0
Reviewed-on: https://review.gerrithub.io/400527
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Also convert the primary spdk_sock/spdk_sock_group
routines to use the spdk_net_impl abstraction
instead of calling the posix routines directly.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I6ae8f4aae619f326f28c40f28a387ada1b263e27
Reviewed-on: https://review.gerrithub.io/400335
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This is the framework for providing multiple implementations
of TCP sockets in a single application. This patch just
adds the framework - upcoming patches will convert the
existing POSIX implementation to use this framework.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I07951e71f344dfe7689c818a13d7e7113c826643
Reviewed-on: https://review.gerrithub.io/400334
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This moves the POSIX specific pieces (namely the
file descriptor) out of the common sock/sock_group
structures and into posix-specific structures.
Note that the first member of these new structures
is the respective base structure - which allows for
simple casting between the generic and implementation-
specific structure types.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ie80800e66b792627fc9dc056cbdd1fd8991f0b22
Reviewed-on: https://review.gerrithub.io/400333
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Have the main spdk_sock_group_poll_count routine
just pass an array of sock pointers to the posix
implementation function. Then the posix implementation
can just fill out which spdk_socks have data and let
the caller do the callback routines.
This moves a fair bit of code from the posix implementation
to the common code, which will simplify the upcoming
VPP implementation.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I547821ce9875777448f433cae59e316a45c259f6
Reviewed-on: https://review.gerrithub.io/400332
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Parts of the close code (for both sock and sock_group)
is generic and will apply to every net implementation
(POSIX, VPP, etc.) - so move that generic code now.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I50b5b272b6af219a516c18c41eee5a2e00bf034d
Reviewed-on: https://review.gerrithub.io/400330
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This is a step towards abstracting the posix implementations
of these functions behind an upcoming net_implementation
abstraction. This will allow for use of multiple TCP
stacks in parallel.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I1ed7d8ae3f1a585ac7a503335c958ebb68fd057c
Reviewed-on: https://review.gerrithub.io/400329
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
In early days of SPDK, there was an experimental userspace
TCP stack called libuns. The SPDK iSCSI target supported
using either the default POSIX/kernel TCP stack or this
libuns TCP stack.
libuns is no longer in use, but work has started on
supporting the FD.io VPP TCP userspace stack. Abstractions
are being put in place to allow *both* the POSIX and VPP
stacks simultaneously.
So remove the concept of a "default" net_framework that is
defined with weak symbols that can be overridden by another
object file. While here, also remove the "clear_socket_association"
concept which was specific to libuns.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8a0385ca5ae113e34a637f835d8d69f8d510433e
Reviewed-on: https://review.gerrithub.io/400328
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
This avoids recursion in the case where the remove_cb
immediately closes its open descriptor, resulting in
a second call to spdk_bdev_unregister without unwinding
first.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I093786f13bb2953b8f08888a668a045581a9f81c
Reviewed-on: https://review.gerrithub.io/400305
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
spdk_vhost_dev_has_feature() is internal function so we can move it's
declaration to header file. This remove function call overhead.
Change-Id: I1704e8279cd6720177047a1ae8818f68982998db
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/400241
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
adding nvme_ctrlr_destruct_finish because nvme_transport_ctrlr_destruct may
use a destroyed mutex.
nvme_ctrlr_destruct() free "ctrlr_lock" and after that call
nvme_transport_ctrlr_destruct()->nvme_pcie_ctrlr_destruct()(with pci)->
nvme_ctrlr_proc_get_devhandle()->nvme_robust_mutex_lock(&ctrlr->ctrlr_lock);
Change-Id: I55714ea9097d2c9d844a00b5a88fa2d51a3f4469
Signed-off-by: Ehud Naim <ehudn@marvell.com>
Reviewed-on: https://review.gerrithub.io/399605
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Add optional parameters to namespace creation to let the user pick the
namespace globally unique identifier and EUI-64.
Change-Id: Ia3eebaf22f8a64733a00a83f90cafb4977c2d07a
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/399531
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Change-Id: Ice343afdc84c2a11cd9026d128a35f7a62aa7125
Signed-off-by: Sebastian Basierski <sebastianx.basierski@intel.com>
Reviewed-on: https://review.gerrithub.io/398933
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
This will allow more parameters to be added to
spdk_nvmf_subsystem_add_ns() without breaking API/ABI compatibility
later.
Change-Id: I6b2f58f1a2d5fcd4c754830cbd4713dc461a31fc
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/399519
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
The subsystem->ns array may be resized with realloc(), so old ns
pointers can become invalid.
To fix this, allocate each ns as a separate object, and change the
subsystem->ns[] array to point to the namespaces rather than containing
them.
Change-Id: I873502fa90cf840e4eaa9b1abd94a95afe0f737f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/399726
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
This reduces some code duplication and ensures all
successful load operations (whether or not it included
recovery after power fail) through the same function.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ia463ce6ebe976ab2420525d86962e8fe54ad04d7
Reviewed-on: https://review.gerrithub.io/400164
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
This patch is a preparation to match response of dump with request
of construct (load).
Change-Id: I08d0e860ecd842fabf2bbea0b888a60ffd51b055
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/399992
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
This patch is used to solve
https://github.com/spdk/spdk/issues/235
With multiple core bining for NVMe-oF target,
the qpairs which belonging to the same ctrlr may
be scheduled to different cores. Thus there is
resource contention to access the struct spdk_nvmf_ctrlr.
And we put the thread info in polling group. Morever,
we introduce an admin_qpair in ctrlr. Since admin_qpair will
always be created at first and freed at last, to reference
this pointer is safe.
Change-Id: I12ac26f9e65b4ed8e48687750046455af0e3be1d
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/398904
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
