Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Iadb29a8ce8dcebfea68d4feeb5f3de1bb3124f16
Reviewed-on: https://review.gerrithub.io/392286
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: Ib3470fbac49e92308ed14e20ccde6655354f2580
Reviewed-on: https://review.gerrithub.io/389577
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>
bdev hotremove event is send directly to hotremove callback given
during spdk_scsi_dev_construct() call. So any bdev hotremove might be
promoted to whole SCSI device removal (like in vhost) wich will trigger
LUN removal. But after returning from hotremove callback LUN and device
might be still referenced (eg to register poller or by outstanding IO).
Even worse: spdk_scsi_dev object is not dynamicaly allocated but
returned from static array which mean there is no way to detect
use-after-free error on spdk_scsi_dev by any tool. This might lead to
using SCSI device that is freed or assigned to different device.
To fix this:
- always delete LUN using hotremove path
- defer spdk_scsi_dev delete/removal after all LUNS are really
deleted.
Change-Id: I65598bf42cd507f620095dff5d32509a0424d060
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-on: https://review.gerrithub.io/393674
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: Ben Walker <benjamin.walker@intel.com>
In current bdev_virtio_scsi PCI enumerate callback
implementation we rely on a global variable - a global
list of virtio devices. We do not need any opaque
context data inside this callback just yet. It will
be required to add virtio devices in runtime. See the
next patch for details.
Change-Id: I116cbd3bd633f56922eedcc7c07b8c0310e51d49
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/394444
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
`rpc.py remove_virtio_scsi_bdev <name>`
The RPC will remove entire Virtio SCSI device together
with all underlying bdevs.
Change-Id: I87f349b0e7543955d54a34406cf73c4a91d1495f
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/394170
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Consider the following scenario:
* user deletes a Virtio-SCSI bdev (spdk_bdev_unregister)
* user deletes entire Virtio-SCSI controller (virtio_scsi_dev_remove)
If there were any descriptors open with asynchronous
remove callback specified, the first bdev unregister
won't delete the bdev and won't notify the Virtio-SCSI
controller in any way. Subsequent Virtio-SCSI controller
deletion might result in unregistering the same bdev
again. This patch makes Virtio-SCSI controller open a
dummy descriptor on each of its bdevs, so that it's
notified of any started bdev_unregister
Change-Id: I9a8c841d08393ef1940c4cebc9dfcb58e9b0ac4a
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/394169
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Previous nbd implementation only processes one I/O at a time.
This patch increases spdk_nbd_disk io queue-depth.
lists are added to accommodate and coordinate overplapped nbd_io.
Change-Id: I3bda2c957a561b884ebfe9550b7cb6f3c991aef8
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/392609
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>
Apply a state for nbd io instead of using flag
bits like payload_in_progress and resp_in_progress.
Change-Id: I331567f7c4d7a6a886a145390a8b1e4db0f6040c
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/392175
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 avoids having to dereference the spdk_bdev_io's
channel in the spdk_bdev_free_io() path.
Cleaning up after hotplug events should ensure that
all associated bdev_ios have been freed (not just
completed) before the bdev channels have been freed,
but this patch gives us some more wiggle room in this
area.
Results in a small (1-2%) performance degradation on
a bdevperf microbenchmark, but should result in no
noticeable difference on any real world workload.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Id8b88300fc53e8c0b83309a738a4c3bd2aeaff52
Reviewed-on: https://review.gerrithub.io/394399
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
There is no need to keep a lun name anymore - we always
use the bdev name as the lun name so it is not providing any
additional value. This also keeps us from associating
the same bdev with different LUNs on different iSCSI target
nodes or vhost-scsi controllers.
Side effect of this change is:
1) Use "bdev_name" across the APIs to make it more clear
what these names refer to.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Change-Id: I3d42fde22087352ce1d5dc80178bd8c5cac8cb7c
Reviewed-on: https://review.gerrithub.io/390843
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
If the file have cache data and not flushed, the file length will be
not correct.
Change-Id: Idde23e158c1d010e67579b5d6a8d87d3cfbfed2d
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/393784
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
This patch provides logic for returning errors instead of
assert when size is larger than blobstore size.
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I16d12338e2b682c39bd33d507d57ea126501a0d7
Reviewed-on: https://review.gerrithub.io/392749
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>
when test hotplug case with large write command which need r2t, after the
device hot removed, the outstanding r2t commands are waitting for data out PDU,
and the primary commands probably already return with error, then the lun
could be deleted, later the related data out PDU will received and try to send
other r2t, this patch make sure the r2t command sent smoothly even the device
hot removed.
Change-Id: I49061d1258e65cb0964526f755d870ebe7095920
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/394321
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>
Recovery code did not claim clusters taken by metadata.
Signed-off-by: Maciej Szwed <maciej.szwed@intel.com>
Change-Id: If6726eddd22f4e1a3f9814b2348243155fb0fdb9
Reviewed-on: https://review.gerrithub.io/394173
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
This `len` field describes the amount of bytes
*written* by the device. It is used to prevent
the driver from reading buffer memory that wasn't
really written to - it could contain either
leftover values from previous requests or even
be completely unitialized.
In a couple of invalid-request error conditions
we still write the VIRTIO_BLK_S_UNSUPP response while
returning used_len == 0, but that's fine. A properly
written driver will likely handle both of these cases
the same way.
Change-Id: I8e9f3a8051561096e2ee755122d534b4ffd94db1
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/393963
Reviewed-by: Pawel Kaminski <pawelx.kaminski@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This `len` field describes the amount of bytes
*written* by the device. It is used to prevent
the driver from reading buffer memory that wasn't
really written to - it could contain either
leftover values from previous requests or even
be completely unitialized.
Change-Id: I67aee5c8b9455fc86cdeb600ea3a051a7737c66f
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/393962
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Removed task `pending` queue. All tasks were
temporarily put in this queue just to be moved
out of it yet within the same reactor cycle.
Change-Id: I32d402f7abd3cfa21c263f41149425abdc71992f
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/393911
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The thread variable defined in the struct spdk_nvmf_rdma_qpair is
not used. Just remove it.
Change-Id: I5f406ff276733cc9474a997b3c18d23c7420cac8
Signed-off-by: GangCao <gang.cao@intel.com>
Reviewed-on: https://review.gerrithub.io/394152
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>
Change-Id: I343d2f1a8f3327ad030a786633bbe9e8c66c14fc
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/394138
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
The NVMe spec states that nqn names are to be encoded in utf-8. The
prefixes of all nqn's are already required to be ascii by virtue of
their structure so they are already valid utf-8, but the user specified
strings should be checked for valid utf-8 strings.
Change-Id: I20090d366e93e98af4932eaa120d4edb6e512206
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/394118
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>
Modifies spdk_env_init() and spdk_mem_map_init() such that
they return on failure instead of terminating with exit()
or abort().
Change-Id: I054c1d9b2e46516ff53d845328ab9547f54bdbc4
Signed-off-by: Lance Hartmann <lance.hartmann@oracle.com>
Reviewed-on: https://review.gerrithub.io/393987
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>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
When trying to create a scsi dev with inexistent
lun (bdev name), the scsi_dev_construct would
just return a NULL without printing any error.
We should probably return an error code of some
kind, but for now let's just print an extra
message.
Change-Id: I28823c2cb83204c11207d3e7011fecbf725a691c
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/393918
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This is more efficient and buf_link users don't
need the extra flexibility that TAILQ provides.
link could also be changed to an STAILQ, but its usage
is not in the performance path so not touching that
as part of this commit.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I7df2cc24a3784add8370db859003783e92cbfc21
Reviewed-on: https://review.gerrithub.io/393834
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Purpose: If the qp creates in a failure state,
we should set cm_id = NULL, then we do not need to
destroy the qp which is not created.
Also this patch add return value check while calling
spdk_nvmf_rdma_qpair_initialize.
Change-Id: I084c186738fcf6079cb36666f68e10b906e77145
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/394016
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>
This only adds the option and metadata flags.
Actual functionality will be added in an upcoming commit
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I66015f48f34d4c7c64fce1831ebaed134098407c
Reviewed-on: https://review.gerrithub.io/390196
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
This patch fixes issue when blobstore doesn't serialize flags
when there is also at least one extent or xattr.
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: I85d5031dc45df510cebe1acf4694ab62bca2e720
Reviewed-on: https://review.gerrithub.io/393770
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
The same check is done inside
spdk_vhost_vring_desc_to_iov.
Change-Id: Id93a05848ed69b8dd048ac490df2432b4252c6e0
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/394088
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>
This makes spdk_file_write consistent with _file_sync.
The lock should not be held across calls to send_request.
Change-Id: I2a2987bbfe2688b520901267aa5a197bd55565a8
Signed-off-by: Cunyin Chang <cunyin.chang@intel.com>
Reviewed-on: https://review.gerrithub.io/393599
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>
Added tighter regulations to the NVMe-oF nqn checking to conform with
the nvme 1.3 spec. including, adding checks for valid nqn's in the case
of a generic uuid based nqn and checking for reverse domain name and
colon prefixed strings in a user specific nqn. Unit tests included.
Change-Id: I3ee4b269d0655ac9968699617e43e3297695c7ed
Signed-off-by: Seth Howell <seth.howell@intel.com>
Reviewed-on: https://review.gerrithub.io/393265
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>
spdk_scsi_lun_complete_mgmt_task can't be called with
lun == NULL, as it deliberately dereferences it.
Change-Id: Idf9b100b66cdc7fdfe2011fb7f9b2477651f1e8c
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/393912
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>
This requires exposing struct spdk_io_channel in the
public header - mark it as internal with Doxygen
comments to make it extra clear that applications
should not use the data structure directly.
This is a very hot function in the main I/O path,
so making this function inline has a significant
performance benefit. A bdevperf microbenchmark
using null bdevs shows a 11% improvement.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I70e30e184000705704bb004e8da1c7476a6aceeb
Reviewed-on: https://review.gerrithub.io/393824
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Purpose: Make the max_channel_ops initialization
in the single place, and we only need to call
spdk_lvol_bs_opts_init instead of spdk_bs_opts_init
Change-Id: If1dd0b30e982a26ab2801a0dd99dd82633e02c74
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/393722
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>
Retrieve LUN data directly from struct spdk_scsi_lun rather than copying
them into struct spdk_scsi_task, and access the LUN via the task->lun
pointer.
Change-Id: Id8745f116bc559fb2f9e58811c2b9781c8cbdae8
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393709
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
For a given hardware queue size, only allow a quarter of the queue size
to be returned as completions in a single call to
spdk_nvme_qpair_process_completions(), and adjust num_trackers to match
so that num_trackers + max_completions_cap doesn't exceed the hardware
completion queue size. This ensures that there is room in the
completion queue if new I/O is issued in response to completions before
we ring the completion queue doorbell.
The choice of 1/4 queue size is arbitrary; this seems to be a good
compromise between completion batch size and number of trackers.
Change-Id: I2c5aad7b98bfc8b33e53242240b2c9254fa05b4e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393529
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Most relevant fields get initialized after the structure
is returned to the caller, so this memset is just
wasting CPU cycles.
buf still needs to be set to NULL, so just set that
field explicitly.
bdevperf with null backend shows a 10% improvement
with this patch.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I92ef0ea887f1307abdcd4b80bc08b45ccefe27d9
Reviewed-on: https://review.gerrithub.io/393714
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
bdev_ch->io_outstanding - NOMEM_THRESHOLD_COUNT
can be negative, so change the type, then
we can make the comparision correct.
Change-Id: I823ceb3dd053f71c1902ee66cf4caba719a7ae7d
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/393437
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>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
The normal execution path for read/write commands is that none of the
checks fail; annotate all of the checks in spdk_bdev_scsi_readwrite()
with spdk_unlikely to encourage the compiler to generate the happy path
as straight-line code and move the error handling out of line.
Change-Id: Id0e606c78f0b99662e5c27e3bfa32535de20aa13
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393700
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
spdk_bdev_scsi_read_write_lba_check() was only called from one spot, and
moving its code directly into the caller makes the code simpler to read
and more consistent, since now all of the sense code setup is directly
in spdk_bdev_scsi_readwrite() rather than being split across two
functions.
No functional change.
Change-Id: Ic6ee21b06c721a949579817f0339a4b047ffb2cc
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393699
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Only two comparisons are necessary to ensure the I/O is in range.
Change-Id: I66e93abbf9b25949b3c783a47d26918362f00b93
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393698
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
The SCSI layer no longer needs to know about the parent/subtask
relationship maintained by iSCSI.
Change-Id: Ia6f7c5367c5b656bd7521ed1abb6d0f713a0500b
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393697
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Simplify the logic in spdk_bdev_scsi_read_write_lba_check() to do the
LBA bounds check for both parent tasks and subtasks.
This will allow the parent/subtask relationship to be fully moved to
iSCSI in a follow-up patch.
Change-Id: Ic66466f7d77270c303c94b7002196398a34e4814
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393696
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>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
In the patch 393582, by analyzing the code,
accumulation of write completion to bdev was duplicated by
data_transferred and bytes_completed.
Hence accumulation of data_transferred for write was intended
to be removed.
However by mistake accumulation of data_transferred for read
was removed.
In this patch restore accumulation of data_transferred for
read and remove accumlation of data_transferred for write.
Test code to catch this degradation will be added by another
patch soon.
Change-Id: Iea9883e8ef1bfb0bdf00e291712e6faf2fad281f
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/393713
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
it appears that scsi name string designator
format in SPDK is not correct. The name strings
are not null terminated (which causees garbage
to appear in scsi_inq -p 0x83). Further, they
are not padded correctly.
SCSI port name and device name strings must be null
terminated. Further, the length must be a multiple
of 4 bytes, and must be padded with 0s.
See SPC-5 Section 7.7.6.11.
Change-Id: Id7c4ad27e5c3a17ad68e5e466142801c0d03b1f2
Signed-off-by: Karandeep Chahal <devilsgrotto@gmail.com>
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/393027
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 will follow the change 393212 by Daniel.
For read command:
- primary's scsi.bytes_completed is for read completion from bdev.
- primary's scsi.data_transferred si for send completion to initiator.
Two variables have its own meaning, respectively.
However for write command:
- both primary's scsi.bytes_completed and scsi.data_transferred are
for write completion to bdev.
Hence for write we should use only either one and it looks that
bytes_completed will be appropriate.
Change-Id: I991c00170ad3651fe926173657e8a49a9a38d02a
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/393582
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>
If spdk_nbd_stop is called because of socket error,
ioctl of NBD_CLEAR_QUE and NBD_CLEAR_SOCK may be blocked
which will cause deadlock.
close(kernel_sp_fd/spdk_sp_fd) first, then nbd kernel
module will not block them .
Change-Id: I9527d74986cbd2b6188b9a91154de8b0b85d2836
Signed-off-by: Xiaodong Liu <xiaodong.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/393581
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>
Each SCSI task should only report its data_transferred; the
parent/subtask relationship should be handled in iSCSI.
Change-Id: Ibece110fd8cca4e94648942fe6b5e004a4fd8a80
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393212
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This patch remove need for additional buffer when translating error code
to string.
Change-Id: Iaa60088b5c450581d3cdddbb425119b17d55a44b
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/386114
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
We need to make the channel operations numbers configurable for blob.
Reason: for iSCSI tests, if there is one CPU core, there will be only
one channel, thus read stress tests would
fail since we need more operations for blob channel.
Select a value equal to the small buffer size(8192) for
bdev layer, thus we can solve the iSCSI read issue
correctly. Since for bdev read, we currently only
allow 8192 active bdev I/o requests, so this solution should
work.
PS: Current solution is still not perfect, I think the very
precise fix is that we need to restrict sending I/Os
to the blob, if there is no channel operations. Though
current code, we have retry I/O in bdev , but it still fails
the iSCSI high pressure test.
Change-Id: I211f7a89d144af2c96ad4cc1bd7ac8e94adc72e7
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/393115
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>
Also added vbdev_get_lvol_by_unique_id function.
Change-Id: I55a64df008c23c0fedb8a59ef67e2c356097e780
Signed-off-by: Sebastian Basierski <sebastianx.basierski@intel.com>
Reviewed-on: https://review.gerrithub.io/392658
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
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>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Change-Id: Ic0cdcf088ebd5053f2e69ad2e607ee825d96fcb6
Signed-off-by: Sebastian Basierski <sebastianx.basierski@intel.com>
Reviewed-on: https://review.gerrithub.io/390202
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: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Added aliases list to bdev struct.
Added 2 API calls to add and remove aliases.
Added test for adding and removing aliases.
Change-Id: I1815aec8c02cfa398b2d1de41577197315665fdc
Signed-off-by: Sebastian Basierski <sebastianx.basierski@intel.com>
Reviewed-on: https://review.gerrithub.io/390200
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>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Existing implementation worked, but results in a lot of
unnecessary error messages.
Found while debugging nightly iSCSI tests, which generate
a config file from the existing configuration and calls
spdk_trace_get_tpoint_group_mask() to do it.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I36df9ca30c7dd2d0039da2377173edb11b1f47dc
Reviewed-on: https://review.gerrithub.io/393680
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>
When LUN with no io_channels is being hotremoved,
the hotremove poller was being started on the core
pointed by lun->lcore. However, this field is only
valid when there are io_channels open. For example,
when user tries to delete a bdev that's attached to
an unused vhost controller (no io_channels ever opened)
the scsi layer could start a hotremove poller on
lun->lcore == 0. If SPDK runs on a different cpuset -
not containing CPU0 - SPDK could even segfault.
Change-Id: I31a363352875d944f220b0296d5cfe570319023d
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/371863
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>
Distinguish between "not enough descriptors available"
and "iovcnt > queue depth".
This patch brings back I/O re-queueing for virtio bdev
module. It was temporarily disabled by 451de7e1 [1].
[1] 451de7e1: "virtio: switch to the new virtqueue API"
Change-Id: I4c4f6a6d9d91373ee647ea7cafd53ad999aa6aa2
Signed-off-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/393447
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>
This gives user an information of which
device caused an error.
Change-Id: I47eb1c1b6c9adc36a9c26b4c36b6f6bc1e467ca7
Suggested-by: Daniel Verkamp <daniel.verkamp@intel.com>
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388195
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>
Handle the possibility of the system strerror_r() returning an error
internally within spdk_strerror_r() so that callers don't need to check
the return value.
Change-Id: I0571c3f5999873575562d08a04d714716a7881ff
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393105
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
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>
Change-Id: I7df72b21f78ab7f0fe0389b478072330bbbd4215
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/393015
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>
SPDK drops the connection when it observes any sequence error of
Data-out PDU when ERL = 0. This is too severe and change dropping
the connection to Reject response.
This issue was detected by libiscsi test suite.
Change-Id: Ic8f50ce55c4e73c8517f726e8cf0e4ff8a0953df
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/391158
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>
LUN hotremove callback can be triggered when
it's vhost-scsi controller is not started
yet. In such case it is not necessary to check
against HOTPLUG flag (if the controller doesn't
have any driver connected yet, there might be
no negotiated flags whatsoever).
Change-Id: Ic7c78e3bdf45fa4d5628cd19c4c5ad723699e45f
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/371864
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@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>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
The error vbdev was missing a remove_cb, so unregistering its base bdev
would cause issues later since the error vbdev would not get torn down.
Change-Id: I6d94f67ce0d4f20a7a63c902b11d965115481df7
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393264
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>
This is not used in the generic SCSI layer.
Fixes: 8eba104b73 ("iscsi: Fix the bug for hotplug when read IO is
running.")
Change-Id: Ie0715ea0ee5084eaf1321ba2f65f7bfa674c663a
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393211
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>
The SCSI task transfer_len field is only distinct from length in iSCSI;
vhost should always have length == transfer_len.
Change-Id: I37faec26f0f49c27019a965c1f1f48903ca54b58
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393203
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
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>
Netmasks with 0 bits of prefix do not make sense. For example,
192.168.1.2/0 would allow hosts from any address, but this is
indicated with a special "ANY" value rather than a normal netmask.
Netmask prefixes of the full address size (e.g. 32 for IPv4 and 128 for
IPv6) are still allowed, since this represents a valid configuration
that matches a single specific address.
This also allows the IPv4 netmask math to be done entirely in uint32_t
instead of promoting to unsigned long long to avoid undefined behavior
when bits == 0 (shift count would have been 32 in that case).
Change-Id: I021b718e6a46f628c96a358edae816de81cd8929
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/392969
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: Ibffb43e39b44e5f443d3dfbfa5b5d7dcac3243ef
Reviewed-on: https://review.gerrithub.io/391182
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>
Signed-off-by: Piotr Pelplinski <piotr.pelplinski@intel.com>
Change-Id: Ic2c23d16360b26359c2a32920b89f2f3a21a2a9a
Reviewed-on: https://review.gerrithub.io/391191
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>
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>
Make them usable for other Virtio drivers
(not just SCSI).
Change-Id: I7ae2c43f311fefd40e447c8b5accaf824d0e23de
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/393121
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>
The only errno value that can usefully be returned from malloc(),
calloc(), realloc(), strdup(), etc. is ENOMEM, so there's no need to
translate the errno value to a string for the error message.
Change-Id: I8e8bd4f12ec4f3b99649760e397e1bc71cca7eff
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/392985
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
pthread_create() returns error codes via its return value, not errno.
Change-Id: Iac0f2380dd4daf15dc48829a3b9b0a75aedd87d1
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/392984
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Pawel Wodkowski <pawelx.wodkowski@intel.com>
Use spdk_bdev_unmap_blocks() in place of spdk_bdev_unmap(), since the
SCSI UNMAP descriptor already natively operates in blocks rather than
bytes.
Change-Id: I16a0c38d203cf5f60484229e7872783b11d8de6e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393202
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
Use spdk_bdev_flush_blocks() in place of spdk_bdev_flush(), since the
SCSI SYNCHRONIZE CACHE command already natively operates in blocks
rather than bytes.
Change-Id: I11810948fb8d0b6b911d48620e2a363f767cc7f7
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/393201
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: <shuhei.matsumoto.xt@hitachi.com>
If faced no memory status, we should set it to nomem,
thus, we can make this I/O resubmit it again.
Change-Id: Icb9a7eeab3278021fa95a5e33c7ff55b3cc62558
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/393122
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>
SPDK reactor is one per cpu and SPDK_MAX_REACTORS is used as the
maximum number of cpus locally in the file.
When the maximum number of cpus is changed, SPDK_MAX_REACTORS is likely
to fail to be changed.
Adopting two improvements for iSCSI by Ziye to the reactor will be safer
than now for the reactor.
- iscsi/conn: remove rte_config.h header
- env: export spdk_env_get_last_core function
Change-Id: I4941454ffdb704fa7799549e1f190c9bae3a4421
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/392911
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Adopt two improvements for iSCSI by Ziye to VHOST.
- iscsi/conn: remove rte_config.h header
- env: export spdk_env_get_last_core function
Change-Id: I8f067093d593c8d483c52587669f8b0b706f497f
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/392910
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
The latest patch for the iSCSI connection is applied to the vhost
too.
RTE_MAX_LCORE in the for loop is removed and the for loop is
replaced by SPDK_ENV_FOREACH_CORE().
When the cpumask is unexpectedly 0, not 0 but the first core is
returned.
Change-Id: I39cfc2219a3532eccc8c0ce59712102b947a76d7
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/392588
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Previously we used to manually set
vdev->max_queues and called virtio_dev_restart
to go through all virtio init states, negotiate
features and allocate virtqueues. This is,
however, insufficient for Virtio-Blk, where we
e.g. need to check against negotiated multiqueue
flag before deciding how many queues we can use
(reading num_queues field from device config is
forbidden unless VIRTIO_BLK_F_MQ is negotiated).
This patch refactors queue-num related code
and also removes various restrictions. If device
supports less queues than requested, a warning
will be printed during initialization, but
the device will now continue to init normally.
The queue-num negotiation for virtio-user should
be eventually moved to upper layers, but that is
not necessary for now.
Change-Id: I418b56fa62c17b547243422ea077f0d76555bd13
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/393087
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>
If the host fails to send some events,
the next event it succeeds to send
might have an EVENTS_MISSED flag set.
Once virtio receives such event, it will
schedule a full bus rescan to manually
detect any changes.
Change-Id: Ifa66536f8e2980ad31ee68769f042f08100da54e
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/392780
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>
Don't allow starting full device rescan
if such scan is already in progress.
This patch also makes it possible to
start a full scan while only particular
targets are being rescanned.
Change-Id: I8677f640a4e5d9d8c486dfe1e9a58331e941a461
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/392373
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>
Implemented eventq rescan message.
When the host hot-attaches a target
to the controller, it will now
automatically appear as a virtio bdev.
Change-Id: Ie81352b70808a0e078009f618cc1fcfed407d1ba
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/392374
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>
A public API to remove a virtio
controller is about to be published
soon. Hence, we need to cover all
possible corner-cases where calling
it could cause a segfault.
Change-Id: I804cc0bee4a60ab8fc159bb98b7712cc258117f3
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/392271
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>
The upcoming rescan implementation will
do scan I/O on existing I/O virtqueues.
To handle scan cleanly, we need to queue
scan I/O if virtqueues are full.
The heuristics for resending I/O should
be sufficient for all real case scenarios.
A scan I/O consists of either 2 or 3 iovs.
A raw I/O consists of at least 2
descriptors. Since most I/O requests
contain some additional payload, in 99%
of cases the scan I/O will be successfully
resent after polling a single I/O response.
To handle the remaining 1%, we try to
resend a scan I/O up to SCAN_REQUEST_RETRIES
(currently = 5) times.
Change-Id: I8c84ed1d109d9f403c9d7b8efabb904eb26183db
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/392174
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>
SCSI doesn't specify any payload associated
with TEST_UNIT_READY and START_STOP_UNIT
commands. Sending a payload didn't cause
any troubles so far, but still it's not SCSI
compliant and hence has been removed.
It is now assumed that iov_len of 0 means
that no payload should be sent.
Change-Id: Ibdfa7cd77af6049132278911d872cd52c10be6c7
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/391868
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>
scan_finish function will now unconditionally
finish the scan, while scan_next will continue
scanning on the next target.
Now that target scan be aborted from external
sources (device removal during re-scan). There
is simply a need for such scan_finish function.
Change-Id: I49e0dd6ea7abdddc24c23af362313d657fe1dc66
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/391866
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>
We used to defer registering bdevs when
a target scan was in progress, as bdev examine
(gpt) would do an I/O that could be polled by
the scan poller and parsed as a scan I/O response.
This limitation has been removed a long time
ago. Scan I/O can go alongside default I/O and
bdevs can now be registered at runtime.
Change-Id: I949c57acbfe23a7246de90e90ce58ea007be947e
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/391865
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Eventq is a special virtqueue. The driver
(e.g. SPDK virtio) enqueues some fixed
amount of write-only requests. The host
device completes them only when it has
something to tell us - like a device
hotremove. After we receive the response,
containing full event details, we schedule
proper action and re-enqueue the event to
be used later by the host as another event.
Change-Id: I0516b161d8d4a49490b909fa2a454c9c9fa517f2
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/390115
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Previous descriptor chain was being corrupted
by setting invalid vq->req_end (virtio.c:538).
Change-Id: I4b27db02dc990e6af011a1b614e30e3050379e9f
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/392774
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>
Remove unused macro constants of iSCSI.
MAX_PORTAL, MAX_INITIATOR, MAX_NETMASK are still used to determine
buffer size for JSON-RPC and iSCSI.conf and are not removed in
this patch yet.
Change-Id: I3036dc472eca09eff7fa3f6ea7e8e28b0978358f
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/392912
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>
A few previous changes replaced ALL by ANY for the initiator group
because ANY was normal for this case. ANY was tested enough for
the initiator name of the initiator group but not tested for
the netmask of the initiator group.
Hence the previous changes caused degradation.
This is the bug fix and UT code is added together.
Change-Id: Idf7642dd4c111a4788aca31a0105b3497631aecd
Signed-off-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-on: https://review.gerrithub.io/392923
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>
Exported lib/bdev/rte_virtio as a separate
library not dependent on bdev.
Virtio is now accessible via spdk_internal/virtio.h.
The header is marked `internal`, as it's
not meant to be used by end users. It's
not handy to handle all backend-specific
(e.g. Virtio-SCSI) logic in a user code.
For now the Virtio interface is publicly
exposed only via bdev_virtio module. We
might want to consider adding a separate,
public Virtio-SCSI library in the future.
Note: this patch doesn't do any changes
to the virtio code. Everything is
moved 1:1.
Change-Id: I805e5d12d265d82b0bc5784c89fbadb81abdb278
Signed-off-by: Dariusz Stojaczyk <dariuszx.stojaczyk@intel.com>
Reviewed-on: https://review.gerrithub.io/388166
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>
