Commit Graph

248 Commits

Author SHA1 Message Date
Jim Harris
2ecab7bd6a net: remove ability to override default net_framework
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>
2018-02-21 12:40:30 -05:00
Daniel Verkamp
1023ca7b46 nvmf: allow configuration of ns NGUID and EUI64
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>
2018-02-20 12:01:47 -05:00
Daniel Verkamp
119ccada0a nvmf: add namespaces individually in construct
This will allow us to specify individual namespace options in upcoming
patches.

Change-Id: Id3301a2313a1d7cbafac1f8a5bcd8d73eae4cd47
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/399522
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>
2018-02-16 13:06:11 -05:00
Daniel Verkamp
250d342bc1 nvmf: pass an options struct for ns creation
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>
2018-02-16 13:06:11 -05:00
Jim Harris
bb24ce82a6 build: add @: to remaining 'all' targets
It is not ideal to have to add this in a bunch of
different Makefiles, but further consolidation of
Makefiles is going to be a more arduous process.

With this change, rebuilding SPDK after no changes
will result in no output - all of the "Nothing to
be done for 'all'" messages have been removed.  Note
that DPDK build output still remains - this can be
suppressed by either using an out-of-tree DPDK, or
using SKIP_DPDK_BUILD=1 when using the in-tree DPDK
submodule.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ib1d45432f2baaa1d9c1b9509906ee1e77966d3ca

Reviewed-on: https://review.gerrithub.io/399918
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2018-02-14 17:38:25 -05:00
Ziye Yang
ff3d53f74e nvmf_tgt: optimize the value assignment of g_num_poll_groups
We do not need the for loop.

Change-Id: Icd4cd768f8c7d8a8b996b19e4d9369e76ed1dcdb
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/399790
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>
2018-02-14 15:07:43 -05:00
Daniel Verkamp
9f04ca414c nvmf_tgt: remove unused shutdown function
nvmf_tgt_shutdown_subsystem_by_nqn() used to be part of the
delete_nvmf_subsystem RPC method, but that now uses the public
spdk_nvmf_subsystem_stop() API instead.

nvmf_tgt_shutdown_subsystem_by_nqn() isn't used anywhere else, so just
remove it.

Change-Id: Ic4908d5c911915da6794c3e096e027e4c9b06a52
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/399511
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>
2018-02-13 08:40:32 -05:00
Ben Walker
47b17299a4 nvmf: Add an rpc to add a namespace to a subsystem
Change-Id: I351c7bda1b32dc161c49d47fb2887595099e4be6
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/396696
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>
2018-02-07 23:22:57 -05:00
Daniel Verkamp
9f5970550c nvmf: use "nqn" rather than "subnqn" in RPC param
This fixes the new nvmf_subsystem_add_listener RPC method to use "nqn"
as the parameter name to be consistent with the other NVMe-oF target RPC
methods.

Since this method is brand new, no provision for compatibility with the
old name is provided.

Fixes: 6336217e16 ("nvmf: Add rpc to add listeners to subsystems")
Change-Id: I86263fb1c53ed6ab48fe70917686d78a4a7ce28d
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/398870
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>
2018-02-07 23:22:57 -05:00
Daniel Verkamp
039592e1fb nvmf: factor RPC trid parsing into a function
This will be reused in an upcoming patch to remove listen addresses.

Change-Id: Ia168ae1741f998fc7085ae05fb08406856aff6aa
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/398689
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>
2018-02-07 12:47:27 -05:00
Dariusz Stojaczyk
3fb4bc717b vhost: move app fini to the vhost subsystem
We already have a vhost subsystem and have to do
its fini anyway, so let's remove application fini.
Technically, any SPDK app can use vhost library
and create vhost devices, so we need to delete them
on shutdown in all cases - in module fini.

Change-Id: I013b45b4e73fd19288b9c10bc995dc24894ecf35
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/396573
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
2018-02-06 11:05:01 -05:00
Ben Walker
6336217e16 nvmf: Add rpc to add listeners to subsystems
The construct_nvmf_subsystem method's "listen_addresses" parameter is
now optional, and new listen addresses may be configured at runtime
using the "nvmf_subsystem_add_listener" method.

Change-Id: Ie0217c5d112e278cc0491a561753f50ed877d842
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/395556
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>
2018-02-06 10:29:42 -05:00
Daniel Verkamp
1dab20c225 nvmf: remove unused constants from conf.c
Change-Id: I2f7e0f4e634d8ed83d93a8670b2c72ada24cd537
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/398125
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2018-02-02 12:45:42 -05:00
Daniel Verkamp
c7b8b414d1 nvmf_tgt: add IPv6 listen address support
Change-Id: Ia165c3f033658adc86c8993a2a32783921ab1832
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/396494
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-01-29 12:41:57 -05:00
Daniel Verkamp
543cb17248 build: remove $(ENV_CFLAGS) where not necessary
Only Makefiles for libraries that directly depend on DPDK (rather than
the SPDK env abstraction) should add $(ENV_CFLAGS).

Change-Id: Ifdf44d3ef8c42bbf7f20edd524b330d00658235b
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/392818
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2018-01-03 12:05:59 -05:00
Ben Walker
95ac75aabe nvmf: Add synchronization primitives for subsystems
This allows the user to pause a subsystem, make some
modifications, and then resume it.

Change-Id: Ia18371023d8fc66e1797fda293a01b68c0a61c96
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/392422
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>
2018-01-03 11:58:11 -05:00
Ziye Yang
7e8a611568 nvmf/tgt: Fix issues for ctrlr+ c handling.
When receving ctrlr+c event, NVMe-oF target
could in any state. So we cannot guarantee
g_acceptor_poller is initialized or not. If
we do not handle such case, ctrlr+c will
trigger unexpected coredump issue. To
solve this issue, following methods are used.

Currently, our code in event module (lib/event/app.c)
can only receive ctrlr + c command once, so
when we receive the ctrlr+c, we should complete
the shutdown process.

The idea is to use spdk_event_call, we will only
enter shutdown process if tgt is in NVMF_TGT_RUNNING
status.

After several patch tries, I think that this solution
is much simple. Though we would like to kill after
entering the running state, it may wait some time
if users kill the application in early state, but those
operations will not be quite often in real case.

Change-Id: Id89a96b5d39f8a528e72dea8c0eb6524bdaf7ee4
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/389433
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-12-26 14:49:42 -05:00
Dariusz Stojaczyk
1c54773979 vhost: link with Linux-only libraries by default
vhost supports only Linux, so there's no
need to check OS inside vhost Makefiles.

Change-Id: Ia7129200ee4cb8db898552a8a990f6fab84f8711
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/392671
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-12-21 13:32:09 -05:00
Ben Walker
7b397f6281 nvmf: No longer tie subsystems to CPU cores
The "Core" parameter in the configuration file has been removed. New
connections are handed out to available cores using round-robin.

Change-Id: I24527fa22a0b2738ebbf5fb030e3bb373ead5da2
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/388295
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>
2017-12-15 16:26:33 -05:00
Ben Walker
8b79ef3372 nvmf: Remove poll group from controller
Now rely entirely on the user to create and poll
the poll groups.

Change-Id: I66baaa2d0f493390a055a32e6c902f5e2f574534
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/385954
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: Jim Harris <james.r.harris@intel.com>
2017-12-12 15:01:17 -05:00
Daniel Verkamp
2302dc6cdc nbd: add NBD subsystem to apps
Enable the NBD subsystem and RPC methods in the iSCSI target, NVMe-oF
target, vhost target, and bdev_svc test app.

Change-Id: I1c2e53a4c031ae6d4dc0a8e698bbfa085db33154
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/391014
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-12-12 13:36:22 -05:00
Daniel Verkamp
59970a89be astyle: enforce braces around single-line statements
Require braces around all conditional statements, e.g.:

    if (cond)
        statement();

becomes:

    if (cond) {
        statement();
    }

This is the style used through most of the SPDK code, but several
exceptions crept in over time.  Add the astyle option to make sure we
are consistent.

Change-Id: I5a71980147fe8dfb471ff42e8bc06db2124a1a7f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/390914
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-12-11 11:19:32 -05:00
Ben Walker
e26e0e2689 nvmf: Look up bdev channel from poll group instead of namespace
Change-Id: I9afa07b5dae99955ba87d7c8130b2ce6f04e7941
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/389641
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>
2017-12-04 16:02:16 -05:00
Ben Walker
7b57e9f973 nvmf: Stop subsystems from the thread they were started on
This correctly puts all of the I/O channels on the right
thread during shutdown.

Change-Id: I432c8cb981a68b40639f8876dae42597a9e6a85f
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/389637
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>
2017-12-01 16:41:57 -05:00
Ben Walker
3aba1a5690 nvmf: Use spdk_for_each_thread to simplify init
This simplifies both setting up and tearing down
the poll groups.

Change-Id: I719a544a6683e120cc6751f88a3c0944fe863c30
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/388042
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>
2017-11-28 15:29:35 -05:00
Ben Walker
eaaddf3d48 nvmf: Poll groups now automatically register pollers
This simplifies the public API and requirements for
user applications.

Change-Id: Ibb0d25a7838a0fa683f39e79cb4fef78adf6aee8
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/388040
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>
2017-11-28 15:29:35 -05:00
Ben Walker
9c35e39c54 event: Move spdk_poller_register to io_channel
Make this generic and not directly dependent on
the event framework. That way our libraries can
register pollers without adding a dependency.

Change-Id: I7ad7a7ddc131596ca1791a7b0f43dabfda050f5f
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387690
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-11-28 12:30:37 -05:00
Ben Walker
00b02039c5 event: Pollers must now be unregistered from the thread they run on.
Change-Id: I8ea8c59a0c67176c0c0c39abf807afad61ff3828
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387689
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>
2017-11-17 11:11:23 -05:00
Ben Walker
fcb4776fe7 event: Pollers must now be registered from the thread they run on.
Change-Id: I864cd8a6c206dfbe62fcb3f72275c1ae51aa4ed7
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387688
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>
2017-11-17 11:11:23 -05:00
Ben Walker
9b63a93bab nvmf_tgt: Unregister pollers from the core they were polling on.
Change-Id: I129b278accb9f6e029abeba21701f633ecc775a5
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387684
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>
2017-11-17 11:11:23 -05:00
Ben Walker
bfd55056b0 nvmf_tgt: Remove AcceptorCore config parameter
Historically, polling for new connections was costly.
Now, it's very inexpensive and there isn't a reason
to change which core it occurs on. Simplify
initialization and configuration by removing it.

Change-Id: I1cc4c321bb5986289bd48860cb270b0b552e3baa
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387681
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: Daniel Verkamp <daniel.verkamp@intel.com>
2017-11-17 11:11:23 -05:00
Ben Walker
8cd7252f04 nvmf_tgt: Create pollers for poll groups on same core
Create the poller for a given poll group from the core
we intend to use it from.

Change-Id: I8bfb970f31f86b8b29f7fe89d82178b3f27da50b
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/387680
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-11-17 11:11:23 -05:00
Ed Rodriguez
63bf022b93 trace: Move trace flags to separate implementation file
Change-Id: Ibe31b961fec36644cf64716c512429d68e873e88
Signed-off-by: Ed rodriguez <edwinr@netapp.com>
Reviewed-on: https://review.gerrithub.io/386170
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-11-15 18:57:12 -05:00
Daniel Verkamp
52412ab10b build: include spdk.app.mk in all app Makefiles
This will be used to include common app-specific rules in upcoming
patches (it currently makes no difference).

Change-Id: Ia828ba01c94fc9f70e15db3fc1d9cafda387e912
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/387629
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2017-11-15 17:57:07 -05:00
Ben Walker
1f8b6f3752 nvmf_tgt: Destroy poll groups on their respective cores
Destroy the poll group from the core it was created
on.

Change-Id: I6960a356358e8c00ae234149aa3a12eff1a24e05
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/385953
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>
2017-11-15 17:54:13 -05:00
Ben Walker
07c639cdec nvmf: Create poll groups on their respective cores
Previously, all of the poll groups were created on the
core doing the configuration. However, creating poll groups
will eventually construct the I/O channels, and that must
be done on the core we plan to use the poll group on.

Change-Id: Iff57ac0e43bb722eb27cf01d7bf55f3946a165eb
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/385515
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>
2017-11-15 17:54:13 -05:00
Ben Walker
db3edeb341 nvmf_tgt: Rewrite initialization as a state machine
This is about to become a hot mess of asynchronous operations,
so introduce a state machine to make it easier to follow
the logic.

Change-Id: If67acfd61d4e70e30a95245d5f46112323943459
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/385482
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>
2017-11-15 17:54:13 -05:00
Jim Harris
d97476efdf iscsi: shutdown iscsi library as part of subsystem fini path
With the new asynchronous subsystem finish framework, we can
drive shutdown of existing connections as part of the subsystem
finish path instead of a separate spdk_iscsi_shutdown function
called as the shutdown function in response to SIGINT.

This is a step towards enabling a single target app that
supports multiple protocols (i.e. iSCSI + vhost + NVMe-oF).

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Id9f596a8091912a72ab7eb93cb45a46fdb130a48

Reviewed-on: https://review.gerrithub.io/386695
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-11-13 14:57:49 -05:00
Jim Harris
fbb9430ec4 app: add spdk_app_parse_args()
This is a helper function that eliminates a lot of
duplicated code in our target applications, specifically
around common command line argument parsing and usage
messages.  This patch only moves the iscsi, nvmf and
vhost targets to use this function, but there are other
test/example applications that could also take advantage
of it to reduce duplicated code and improve consistency.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I1903de3daed90ac6282b006a8283b9df07ce37e9

Reviewed-on: https://review.gerrithub.io/386542
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-11-13 14:57:49 -05:00
Jim Harris
246cdd08e1 iscsi, nvmf, vhost: break out common usage text to separate functions
This prepares for moving all of the common usage text into a library
that can be used by all applications using the app framework.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3dfc8beead6f40790eefc84b7767299f9d7b1bd4

Reviewed-on: https://review.gerrithub.io/385929
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-11-13 14:57:49 -05:00
Jim Harris
0489bcb137 iscsi, nvmf, vhost: break out arg parsing into separate functions
This prepares for moving all of the common app framework argument
parsing into a library that can be used by all app framework based
applications.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ibbfb08ac687acf3201c4a3e808edbe770213a6f0

Reviewed-on: https://review.gerrithub.io/385928
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-11-13 14:57:49 -05:00
Jim Harris
973a27d08c app: add print_level to opts structure
This allows us to remove some duplicated code from our
main target applications.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I15b517fd2b58ce682660b4f6ba0b8412beda053b

Reviewed-on: https://review.gerrithub.io/385714
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: Ben Walker <benjamin.walker@intel.com>
2017-11-10 17:00:58 -05:00
Jim Harris
4bcfef0021 rpc: remove rpc subsystem
RPC is core functionality for SPDK applications and should always
be initialized last (after all subsystems have been initialized).
So make RPC a first class citizen and integrate it with the
app framework directly instead of making it an "optional" subsystem.
Then we initializing it after all subsystems have completed
initialization, and tear it down before tearing down subsystems.

We can also do some other cleanup while here - for example, reactors
are already started when spdk_rpc_initialize() is called, so remove
the extra event that was added during initialization since this is no
longer needed.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I4cc63586a6d55be68786629a2176c61a88979267

Reviewed-on: https://review.gerrithub.io/385914
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2017-11-10 17:00:58 -05:00
Daniel Verkamp
7ea544b46a nvmf: move poll groups to public API
The end goal is to have the application create one poll group per core.
Then each poll group will have a single CQ per network device and an I/O
channel per back-end storage device to poll.

This is just the first step toward that, which is to wire up the
creation of the per-core poll groups in the application.

Note that the app poll groups don't do anything yet.  We'll need
additional library API changes to make the library use the existing poll
groups, rather than creating a new poll group per subsystem as we do
right now.

Change-Id: I2d4e2a5e5aa354d37714750f1d5b1d1e4ab9edce
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/381887
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-11-09 12:51:18 -05:00
Daniel Verkamp
6a0e6abcd3 vhost: use int to store getopt() return value
getopt() returns int, not char, so assigning the return value into a
char will truncate it.

Fixes a warning on platforms where char is unsigned:

  vhost.c:109:61: warning: comparison is always true due to limited
  range of data type [-Wtype-limits]

Change-Id: I3a290096346db241a473434952e0f5fd69e98c2f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/386347
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-11-09 12:42:45 -05:00
Jim Harris
df7cf89394 iscsi, vhost, nvmf: allow running without config file
If the default config file does not exist, keep the
app's config_file options field as NULL, so that the
app code will not fail when trying to open a non-existent
file.

Also leverage the recent iSCSI and NVMe-oF refactoring,
to just skip trying to read config file parameters if no
config file exists (or the requisite section in the config
file is not present).  vhost already handled this so it did
not need to be modified.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ic32f0a7a8ce85322a8effd537b62d14732d7b82e

Reviewed-on: https://review.gerrithub.io/385497
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-11-03 18:42:53 -04:00
Jim Harris
889a9c762a nvmf: break out config file reading into separate function
This prepares for skipping the config file if it doesn't
exist or there is no Nvmf section.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ib96c9c9e8bd462558240a2210150def1a950f1d1

Reviewed-on: https://review.gerrithub.io/385496
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-11-03 18:42:53 -04:00
Daniel Verkamp
901aafe675 nvmf_tgt/rpc: check trtype and adrfam for NULL
If the NVMe library trtype and adrfam translation functions are passed
an unknown value, they may return NULL.  This shouldn't normally happen,
since any supported transport type or address family in the NVMe-oF
target should always be supported in the string lookup functions, but
add a fallback anyway to satisfy the static analyzer.

Change-Id: Icadf991d6742a2a759b5793253b71b4eabc763ed
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/383313
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
2017-10-23 12:19:38 -04:00
Dariusz Stojaczyk
5b6e67886e vhost: added multi-process support
Added -i parameter to vhost that specifies DPDK shared memory id.

Fixes #171

Change-Id: I103eb57886eed2c1663137b5b8195a11039319fa
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/373692
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@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>
2017-10-16 15:29:58 -04:00
Tomasz Zawadzki
48b2eff97d app: spdk_app_fini no longer gives return code
spdk_app_fini() changed to void, as no operation within it
can fail with meaningful return code.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: If77cbf745a8e3fcba4ea24411aa1816f3910cde7
Reviewed-on: https://review.gerrithub.io/381537
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
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>
2017-10-10 10:56:34 -04:00