Commit Graph

655 Commits

Author SHA1 Message Date
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
Ed Rodriguez
85c146ef6e log: Create a separate implementation file for common log flag operations.
Change-Id: I2524b7881885a0784492a8189bf22a0b8c92d470
Signed-off-by: Ed rodriguez <edwinr@netapp.com>
Reviewed-on: https://review.gerrithub.io/386169
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-11-14 15:53:37 -05:00
Yanbo Zhou
a6fea52116 include/bdev.h:add new comments and fix errors in original.
Change-Id: I0f0e75228561105c1d717e8b879373231bf3cdcd
Signed-off-by: Yanbo Zhou <yanbo.zhou@intel.com>
Reviewed-on: https://review.gerrithub.io/383850
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-11-14 14:50:08 -05:00
Jim Harris
6bef902ca5 rpc: add default UNIX domain socket listen address
RPC is a default feature required for almost all usages,
so enable RPC by default, but with a UNIX domain socket
for security reasons.

-r can now be used from the command line to specify
an alternative RPC listen address from the default
/var/tmp/spdk.sock.

Remove the Enable parameter from the Rpc config section
but still allow specifying an alternative listen address
using the Listen parameter as an alternative to the
command line option.  This keeps backward compatibility
for this release for anyone using the configuration file
still.

Remove the Rpc sections from all configuration files
that were using them, except for those that specified
alternate TCP ports for multi-process test cases.  We
can fix these later to use an alternate UNIX domain
socket and to use the command line instead.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ife0d03fcab638c67b659f1eb85348ddc2b55c4c4
Reviewed-on: https://review.gerrithub.io/386561
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>
2017-11-13 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
Barry Spinney
dcfbafeb77 barrier: add proper barrier instructions for ARM 64
Add code to implement the write memory barrier and read/write memory
barrier for ARM 64 platforms.

Change-Id: I8b63db25ba1f70a729874ca143db13501d976676
Signed-off-by: Barry Spinney <spinney@mellanox.com>
Reviewed-on: https://review.gerrithub.io/386534
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
2017-11-10 17:25:32 -05:00
Maciej Szwed
0c06e1ea89 lvol: show total accessible clusters in lvol store
Show total accessible clusters when listing lvol stores
instead of total blocks. This is more readable for user.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I22a14f626816769cf2f494ae30cfd8ee63897771
Reviewed-on: https://review.gerrithub.io/385634
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>
2017-11-10 17:24:31 -05:00
Tomasz Zawadzki
5eb52b951c blobstore: store usable number of clusters in blobstore structure
At the moment there was no way to a user of blobstore api to know,
how many clusters are availible to him. Total_clusters describes
number of clusters for metadata and user data.

New field added total_data_clusters, keeping number of clusters
that can be used to create blobs - meaning just user data.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I60555217644557410844f74628375a6b46fd2ac7
Reviewed-on: https://review.gerrithub.io/385633
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>
2017-11-10 17:24:31 -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
Cunyin Chang
d62e92823f nvme_spec: add NVMe 1.3 Virtualization structures.
This patch add the data structures related with virtualization of
nvme 1.3 spec.

Change-Id: I8bc2ca7ce22517317b559f2445a8a5a1e30cf156
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/386357
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>
2017-11-10 12:49:18 -05:00
Daniel Verkamp
0e00414344 env: add an opaque pointer for implementation use
This is a request from an implementer of an alternate (non-DPDK) env
implementation; it will only have meaning for the specific env
implementaiton, but it can be used for passing env-specific arguments
through the generic spdk_env_init() call.

Change-Id: I37f70dd3b961f08c3bc2f25f3d12cc02bd3d6699
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382055
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>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-11-09 12:51:50 -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
ccf8cb1834 barrier: explicitly check for x86 architecture
Prepare for the addition of more architectures by replacing the #else
case with an explicit x86 check, and add a final #else to trigger a
compile-time error if the architecture is not supported.

This adds a empty #defines of spdk_wmb() and spdk_mb() in the #else
error case so that they still show up in the generated Doxygen output.

Change-Id: Ia9e9de1648694013de1cd8a2e3edfa9b1166401c
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/386345
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: Jim Harris <james.r.harris@intel.com>
2017-11-09 12:38:05 -05:00
PepperJo
1a2dc66189 barrier: ppc64 memory barriers
Introduce memory barriers for ppc64.

Change-Id: Ie51f959dd8d677f5af3ce6843e5304dd5e24a1e9
Signed-off-by: Jonas Pfefferle <jpf@zurich.ibm.com>
Reviewed-on: https://review.gerrithub.io/383726
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-11-08 18:21:45 -05:00
Jim Harris
3178ad6476 env: return fd from spdk_pci_device_claim()
This allows users of this interface to then close the fd
when they want to release the claim.

This prepares for calling spdk_pci_device_claim() in the
nvme driver to cover not just the bdev_nvme driver but all
of our nvme example and test applications as well.  We'll
want the fd returned so that we can properly close it during
detach (including hotplug) use cases.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I8b149cc4e778ba31c0e7045b858c8a1561b6b7af

Reviewed-on: https://review.gerrithub.io/385523
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@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>
2017-11-03 18:48:33 -04:00
Daniel Verkamp
eec7e868b3 version: v18.01-pre
Change-Id: Id3ccec9f5d77d4125b9ef70e286caac83a0ac2fe
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/385159
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-10-31 18:28:21 -04:00
Daniel Verkamp
8ccfe74abc SPDK 17.10
Change-Id: I3842b654167345326979177ffdf3d10a33fae70c
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/385145
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-10-31 17:14:58 -04:00
Piotr Pelplinski
511adde02f lvol: add lvs name in rpc calls
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: Ic6770371d9d62cbdd40ae0612eb4f7dceccd507f
Reviewed-on: https://review.gerrithub.io/383771
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@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>
2017-10-27 13:10:21 -04:00
Tomasz Zawadzki
fde584034d lvol: give EEXIST error code on lvs name conflict
Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I1df83cbd6414a1bb8f54328c735950b9476e323b
Reviewed-on: https://review.gerrithub.io/384105
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Piotr Pelpliński <piotr.pelplinski@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-27 13:07:09 -04:00
Pawel Wodkowski
ff1863f428 vhost: interrupts coalescing
Virtio spec say that any IRQ requests are only hints. So try to limit
number of interrupts generated by vhost by defining minimum interval
between sending IRQ. Coalescing is disabled by default. Can be enabled
using RPC command 'set_vhost_controller_coalescing'.

Change-Id: I9b96014d004ea0ea022b4498c6b47d30d867091a
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/378130
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>
2017-10-27 13:06:40 -04:00
Tomasz Zawadzki
6c54c13cd4 event/subsystem/bdev: asynchronous SPDK finish
First this change moves spdk_subsystem_fini() to trigger on
spdk_app_stop(). This ensures that spdk_subsystem_fini() is called
before reactors are stopped in spdk_reactors_stop().

Finish paths for subsystems, bdevs and copy engine is now
asynchronous.
Each of those three mentioned have to make sure they are
asynchronous as well.

Only bdev that currently has requirement for asynchronous finish
are logical volume.
Thus the change in vbdev_lvol.c making it move to next bdev module
only after all lvol stores were unloaded.

Fio_plugin finish of bdev and copy_engine was removed for now.
Next patch in series adds it back with async support.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I80ee2d084f3d82c50bf1329e08996604ae61b1b3
Reviewed-on: https://review.gerrithub.io/381536
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>
2017-10-27 13:03:55 -04:00
Tomasz Zawadzki
ebf0312eef lvol: Add vbdev_lvs_destruct() and change unload behaviour [3/3]
This patch adds new API to remove logical volume store
from device it is on. It is only used from RPC, when
user explicitly requests. It allows to use the device to
use as any other bdev.

vbdev_lvs_unload() is now only called from hotremove and
during application shutdown. Which makes it possible to
load it again during application start up.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: If6452ecc3fff99237d1704ff7cd8de4d7133221d
Reviewed-on: https://review.gerrithub.io/382021
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>
2017-10-26 17:23:58 -04:00
Maciej Szwed
e68e2e749b lvol: do not unload/destroy lvs when operation on lvol is pending
There is a scenario where we can try do unload or remove
lvol store while lvol present on that lvol store is being
closed or destroyed.

Scenario:
1. send delete_bdev rpc command
2. command returns before lvol is actually closed/destroyed
   (does not wait for callback)
3. send destroy_lvol_store rpc command
4. lvs is destroyed before lvol is destroyed
5. lvol destroy callback is called on destroeyd lvol store

Aboive scenario can be reproduced using:
spdk/test/vhost/spdk_vhost.sh --integrity-lvol-scsi

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ie715279195bd4b1145cf05d4f5a8477b4fac87f7
Reviewed-on: https://review.gerrithub.io/383595
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>
2017-10-26 17:23:58 -04:00
Maciej Szwed
2baeea7dd4 bdev: add callback to spdk bdev unregister and bdev destruct
Currently deleting bdev does not support asynchronous delete
operations. Because of that results are returned before device
is actually deleted and some operation can be peformed on that
device after removal of this device started.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I305c302d8abd5d7c2c0f947fca70c58396872132
Reviewed-on: https://review.gerrithub.io/383732
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>
2017-10-26 17:23:58 -04:00
Piotr Pelplinski
d17345183e lvol: updated documentation.
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I566a4d277ac1595fa7b4d630df52301a9abeec49
Reviewed-on: https://review.gerrithub.io/381629
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-26 15:04:27 -04:00
Jim Harris
e6d053e78a lvol: add lvol unique name
Add a name to each lvol which is persisted as a blob
xattr.  lvol names must be unique within its
lvolstore.

While here, fix a few lvol_ut issues that were caught
as part of testing the lvol unique names.  Also fix
a couple of tests that registered the wrong string
name with CUnit.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I6d24d241e8f52158d14886f928d41823bbc93fa9

Reviewed-on: https://review.gerrithub.io/383567
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-25 12:10:38 -04:00
Jim Harris
c6f1d12930 lvol: move name to old_name
There are some upcoming changes which will deprecate
the old lvsuuid_blobid name in favor of an
lvs_name/lvol_name name where these names are
user-specified.

In preparation for this change, rename the previous
lvol->name to lvol->old_name.  This will allow us
to add a new lvol->name but keep the original
old_name during the transition.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I10deb219097fa8726c146ab2427ee7373933b97d

Reviewed-on: https://review.gerrithub.io/383534
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-25 12:10:38 -04:00
Jim Harris
08ac0074ce lvol: add unique lvolstore name
Each lvolstore now has a unique name which is persisted to
metadata.  Eventually this will provide a friendlier
way to reference logical volumes, in the form
lvolstore_name/lvol_name.

This patch only covers the unique lvolstore name.  An
lvolstore may not be created nor loaded if its name
conflicts with an already loaded blobstore.

Currently there is no way to rename an lvolstore to
resolve a conflict.  This will be coming in the future.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I842f13b79776e5b8f81e56de10778c35328e8cd3
Reviewed-on: https://review.gerrithub.io/383533
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Maciej Szwed <maciej.szwed@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-25 12:10:38 -04:00
Jim Harris
1efd9cfa2f lvol: delete super blob in spdk_lvs_destroy
If we don't delete the super blob, this blob structure
will leak.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I56d0ca4884846aee0c7865f9c600d6c43811373c

Reviewed-on: https://review.gerrithub.io/383311
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>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
2017-10-24 13:36:51 -04:00
Jim Harris
7d8fe2ca2c lvol: keep list of open lvolstores
This will be used in a future patch to ensure we do not
allow creating or loading an lvolstore with a names that
matches an already opened lvolstore.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I37e8786f91cd578dd36fbec99ca23609419fc8f8

Reviewed-on: https://review.gerrithub.io/383012
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-24 13:36:51 -04:00
Maciej Szwed
199e73908d lvol: Lvol store tasting
This patch introduces lvol store and lvols parameters saving
on persistent memories and loading it from saved data on app start.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ia63f0cf3d6365d59f31c5f0a1724636bfe73b5b8
Reviewed-on: https://review.gerrithub.io/375764
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>
2017-10-24 13:36:51 -04:00
Seth Howell
3f9cbe513b blob: add write_zeroes support
Unmap does not guarantee that erased blocks will return all zeroes.
using write_zeroes when unmapping metadata gives the
desired behavior for a blob.

Only metadata pages will be cleared with write_zeroes in this patch;
blob data clusters will still call unmap.  This behavior may be made
configurable in a later patch (to allow the user to request zeroing of
clusters rather than just unmapping).

Change-Id: I1b210abac110867ce703bcfdeb634eb45aa9d5c9
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/372004
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-23 11:50:16 -04:00
Seth Howell
3fd7f28dc9 bdev: add fallback from write_zeroes to writev
if write_zeroes is not supported by the block device, we can get the
same behavior by simply writing a buffer full of zeroes to the blocks
we want to erase. I also incorporate splitting into the bdev layer to
accomodate large i/o.

Change-Id: I8fa1bfaaf22d7bfc6e3afb6e89d22fa9f7767e55
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/373829
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-10-23 11:50:16 -04:00
Tomasz Zawadzki
f71f486d0b lvol: Add spdk_lvs_destroy() API [2/3]
This goes along with previous patch in series.
Adding functionality to remove logical volume store from
device.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I6338a35ed02838498a3cd9bb2dddd25803e65f79
Reviewed-on: https://review.gerrithub.io/382020
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>
2017-10-20 16:06:53 -04:00
Tomasz Zawadzki
2df9f03c47 blobstore: New API call to destroy blobstore [1/3]
Currently exposed API allows to load/unload and to
initialize blobstore on a device.

A spdk_bs_destroy() call is added in order to reach
functional parity with spdk_bs_init(). It was not
possible to remove blobstore from device from within
SPDK previously.

spdk_bs_destroy() takes blobstore pointer as argument
(instead of bs_dev), because blobstore has to be already
loaded to destroy it.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I2c493a4407868fcf08fd1766a19fc8463f634ef5
Reviewed-on: https://review.gerrithub.io/382019
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>
2017-10-20 16:06:53 -04:00
Maciej Szwed
63fce5595b lvol: add reference counter for open lvols
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I3a86f28056e67b3c237441fb1048ca6ccd081ae7

Reviewed-on: https://review.gerrithub.io/383252
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>
2017-10-20 16:06:53 -04:00
Maciej Szwed
94cf9837aa lvol: support callbacks in lvol close/destroy functions
Close and destroy lvol functions should support callback
functions so that they can be processed sequentially
and also give user result.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I9e87fb281916c65c17b2b7e54e91228844962048

Reviewed-on: https://review.gerrithub.io/383230
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>
2017-10-20 14:26:01 -04:00
Jim Harris
f97c8b3142 lvol: add spdk_lvs_opts_init()
Some future patches will require specifying an lvol_store
name when calling spdk_lvs_init().  This means that passing
NULL for spdk_lvs_opts will no longer be an option.  So
add an spdk_lvs_opts_init() (similar to spdk_bs_opts_init)
which will initialize a default value for the cluster size.

While here, prepend an underscore to spdk_setup_lvs_opts, since
this function is not part of the public SPDK API.

Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I155bcfd0c396017304bb3d58b7511ada71dade17

Reviewed-on: https://review.gerrithub.io/383030
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-19 13:23:58 -04:00
Daniel Verkamp
8eef5183d3 bdev: remove spdk_bdev_poller_start() lcore option
Always start bdev pollers on the calling core.

This removes the lcore concept from the bdev poller abstraction and
simplifies the job of spdk_bdev_initialize() callers providing their own
poller and event implementations.

All callers except the NVMe bdev hotplug poller already used the current
core as the parameter.  The NVMe HotplugPollCore option was undocumented
and unused in any of the tests or example configuration files, so it
should be safe to remove.

Change-Id: I93b466e1e58901b8785c40cbe296fa46c157850f
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382857
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-18 20:28:29 -04:00
Dariusz Stojaczyk
922aaac68b env/ring: add spdk_ring_count
Added a wrapper for rte_ring_count().

Change-Id: Ia12fde3f250604a0f801309ed1c4706a311e7896
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382919
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-18 13:08:45 -04:00
Daniel Verkamp
31521306a5 log: change spdk_trace_dump() to take a void *
Previously, spdk_trace_dump() took a const uint8_t * as the buffer, but
it is more flexible to allow any type to be passed (we are just going to
interpret it as an array of bytes anyway).

Change-Id: I1750316928cd330ed461bb513ff8af37e0170ef3
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382854
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
2017-10-17 16:26:02 -04:00
Dariusz Stojaczyk
13017493af bdev: added spdk_bdev_io_get_thread()
This is required for virtio-initiator,
where multiple io_channels have to
share the same virtio queue. A single
poller will receive responses from
a virtio queue and send the completions
to the thread that submitted bdev_io.

Change-Id: I951c7655aaa17d41a680d437661afff27d2c3077
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/382200
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>
2017-10-17 15:21:09 -04:00
Maciej Szwed
eb8b1e20a9 blobstore: add bstype to blobstore super block
Introducing bstype as a way to identify and verify
 blobstore type.

Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I50267b5408625be10fe0c146ae329016d5509b4a
Reviewed-on: https://review.gerrithub.io/380476
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-17 13:36:03 -04:00
Daniel Verkamp
fc5f527c21 scsi: split Inquiry peripheral type and qualifier
The SCSI spec defines two separate fields within the first byte of
the Inquiry data.  Define them as bitfields and add enum values for the
peripheral qualifier field.

Change-Id: Ibbb158338da199fc1b67b04c52ec91633577c571
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382713
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>
2017-10-17 11:32:45 -04:00
Tomasz Zawadzki
7aba48fe1e subsystem: move allocation of subsystem_init event to subsystem
Previously two spdk_events were allocated in spdk_app_start().

Now app allocated spdk_event for function to be called after
initialization is complete. Meanwhile subsystem allocates
its own spdk_event.

Signed-off-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Change-Id: I4822f76d30cc2f7b95a86a4ffbfc61b80c0a903e
Reviewed-on: https://review.gerrithub.io/382673
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 15:14:36 -04:00
Daniel Verkamp
15e978340d mmio: add functions for 1 and 2 byte I/O accesses
Change-Id: I7a325ddd8db3424207cf2e561c6d6e894f549989
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/382073
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: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
2017-10-13 10:46:00 -04:00
Maciej Szwed
ee732292d6 lvol: create super blob on lvolstore initialization
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: I68a56666d30a550de4a2dc5a66fb669dfbad12dd
Reviewed-on: https://review.gerrithub.io/379659
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>
2017-10-12 16:34:54 -04:00
Shuhei Matsumoto
0e5b81b3d7 scsi: remove port from scsi_dev dynamically
Current implementation supports only adding port to scsi_dev.
This change is required to support dynamic remapping of portals.

Change-Id: Idce49aeae43c8861ebe2807df853694f7bacf884
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/379931
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
2017-10-12 15:46:14 -04:00
Maciej Szwed
e46404f9cb bdev: remove bdev_opened field from spdk_bdev structure
bdev_opened field in spdk_bdev structure is no longer required.


Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ie4a368425b11b1c2e1a3a48b5858857b3935498b
Reviewed-on: https://review.gerrithub.io/381375
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>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
2017-10-11 12:13:38 -04:00