When perf tool parses CLI arguments, it saves
each argument to a global value. Later these
values are checked for non-zero and copied to
spdk_env_opts structure. It can be simplified
by saving parsed arguments directly to env_opts
structure. It is applicable to env options only,
options specific for perf are still copied to
global variables.
Change-Id: I298392348df959d8165ea72333764c6505373fc2
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7371
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Some earlier NVMe drives don't implement Deallocate
Logical Block Feature(dlfeat) read value field, but
it can return zeroes in deallocated ranges, that's
the quirk NVME_QUIRK_READ_ZERO_AFTER_DEALLOCATE, so
here we use the API to cover earlier NVMe drives.
Change-Id: I6867618c60dd5488a5d4820d663da7f074af229c
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7525
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
When submit_io cb returns bad status, current
task is dropped and allocated memory is not cleaned.
Change-Id: Ibc33e76e6800644c29eaeb826a3401ad5d5fd582
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7376
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Function cleanup_ns_worker_ctx is only called for
ns_ctx which have outstanding IO, so when draining
phase is started and some context doesn't have
outstanding IO, it won't be cleaned properly.
To fix this problem, call cleanup_ns_worker_ctx for
every context when drining is finished.
Fixes issue #1880
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I3ce4716ed6ac1369b6f72b03cbcfd7d407f7de55
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7282
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Check if qpair has a poll group during the connect process,
use poll group's statistics or allocate own structure per
qpair. That is done due to not all applications use poll
groups and we want to avoid "if (qpair->group)"
conditions in data path.
Admin qpair always allocates its own statistics
structure but the statistics are not reported
since this qpair is not attached to a poll group.
Statistics are reported by spdk_nvme_perf tool
if --transport-stats and in bdev_nvme_transport_statistics
RPC method.
Change-Id: I58765be161491fe394968ea65ea22db1478b219a
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6304
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Statistics are dumped in the end of perf tool work,
enabled using long option --transport-stats
Change-Id: Ice3755ba82ebcdacfa72ceb9b3d5a1caee911811
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6302
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: <dongx.yi@intel.com>
I was trying to find a free character to add
statistics reporting and didn't fine a suitable
one. Since perf provides a lot of short options,
let's change it to also use long options.
Change-Id: I2a7fd5619e996a40b2d432017992d5f888abb656
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6301
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: <dongx.yi@intel.com>
This option may have been valid at one point, but is
not any longer. So remove it from the usage text.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I83747968085a77fb52d735026294bf5f82517ffc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7276
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Optargs are missed about -G and -T
which are used to trace and debug.
Signed-off-by: yidong0635 <dongx.yi@intel.com>
Change-Id: I3624b80f52c1b603acf1bc96126b73d1042f1b34
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7109
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Community-CI: Mellanox Build Bot
spdk_nvme_zns_report_zones() is implemented using
nvme_allocate_request_user_copy(), which under the hood will do
a spdk_zmalloc() with the SPDK_MALLOC_DMA flag set, and will copy
over the result to our buffer.
Therefore, it is redundant for us to use spdk_dma_zmalloc(),
because it will cause us to allocate twice the amount of memory
from the precious DMA pool than needed.
Changing this zone report buffer allocation to a calloc also
has the benefit of making the code uniform with all other
spdk_nvme_zns_report_zones() call sites in the SPDK codebase.
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Change-Id: Ia354fa51c66ae07a38a9a57b07c15d145dd609f0
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7005
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
When support for printing the zone report was added,
the zone report buffer was allocated using calloc().
This was intentionally changed to a malloc in commit
5ef79a17ec ("examples/nvme/identify: add an option to dump
the full zns zone report").
While we shouldn't need to zero the buffer, since the drive
should write the "Number of Zones" field in zone report header,
and we should never read zone descriptors beyond this value,
the ZNS spec also states that reading beyond the last zone
descriptor has undefined results.
Considering that "Number of Zones" field in the zone report
header will only represent the number of zone descriptors
in the buffer when the partial bit was set to true,
always use calloc(), to avoid the chance that someone might
copy this code and call spdk_nvme_zns_report_zones() with the
partial bit set to false.
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Change-Id: Ia39c5235aa5c62a4ec42285f53f4bc80f7ec370f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7004
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
If PRACT is enabled, and metadata size is 8 bytes, for extended
LBA format, the controller will insert/strip the metadata, so
we don't need to pass the metadata buffer, so we should exclude
this metadata buffer from host buffer.
So here add a function to calculate host buffer size.
Change-Id: I42d8d9cbfbf7ba2bc4bf64d65260c6cfe9bd4cb1
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6789
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Niklas Cassel <niklas.cassel@wdc.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Purpose: To setup an accelerated function callback
for created spdk_nvme_poll_group. In this patch,
we just create the interface. The real usage of this
call back will be provided in the other patch.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: I0d936aa4eba4dbfcc0137942156b9f2919eb5b78
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6758
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
For each active namespace, print the command set identifier.
This will work on namespaces that do not support or report a namespace
type, as spdk_nvme_ns_get_csi() will return SPDK_NVME_CSI_NVM for such
cases.
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Change-Id: I05fa7fd6bb3d9ea32dac236c98baef90347094ca
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6905
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
If the test run is aborted early (i.e. Ctrl-C), we
should use the elapsed time as the divisor instead
of the originally specified time.
Fixes issue #1800.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I3312cc83f3422ec46ad584e3ee2b40f3ad9ec6f5
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6474
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: <dongx.yi@intel.com>
This is a workaround for issue #1799 that would require
a fix from Google Cloud Platform. GCP NVMe SSDs do
not support overlapped GET_FEATURE commands - the
cdw0 value on completions get mixed up.
On GCP the result is that identify app reports only
1 SQ/CQ supported when in fact it supports 16.
We can easily workaround this in the identify app by
submitting one GET_FEATURE and then polling for its
completion before submitting the next one.
We may consider reverting this in the future should GCP
provide a fix, but there is really no harm in keeping
this patch long term since this isn't an I/O path issue.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I536033677a8364c955d562226e3feba4dbad0e07
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6454
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Mellanox Build Bot
print_qid_mappings=1 will now add logging messages
showing the {filename,qid} tuples associated with
each job.
Note that for the nvme plugin, the filename is
essentially the transport ID. We just print that
filename for simplicity rather than reconstructing
a transport ID string from the ctrlr object.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I9b714ac009fd16b96ed87c2c056be251009815b8
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6396
Reviewed-by: Niklas Cassel <niklas.cassel@wdc.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Now when we have support for spdk_nvme_zns_zone_append() and
spdk_nvme_zns_zone_appendv(), hook them up in the nvme fio plugin.
Note that fio itself does not have support for zone append,
since unlike SPDK, there is no user facing zone append API in
Linux. Therefore, this new option simply replaces writes with
zone appends in the SPDK fio backend.
This is however still useful for the following reasons:
-Provides a way to test zone append in SPDK.
-By using zone append, we can test with iodepth > 1.
With regular writes, the user can only specify iodepth=1.
This is because for zone namespaces, writes have to target
the write pointer. Having more than one write in flight, per
zone, will lead to I/O errors.
In Linux, it is possible to use fio with iodepth > 1
on zoned namespaces, simply because of the mq-deadline
scheduler, which throttles writes such that there is only
one write in flight, per zone, even if user space has
queued up more.
Since a user might not want to use zone append unconditionally,
even on a namespace that supports it, make this an option
rather than enabling it unconditionally.
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Change-Id: I028b79f6445bc63b68c97d1370c6f8139779666d
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6330
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Use the new function spdk_nvme_zns_ns_get_zone_size_sectors() where
it is appropriate (in comparison to the existing
spdk_nvme_zns_ns_get_zone_size() variant).
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Change-Id: Ic929ffbc5a1f4a16ba6719a985c05ae625caed46
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6417
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Add an optional limit, -z N, to the zone report dump option -z.
The variable g_zone_report_limit replaces the MAX_ZONE_DESC_ENTRIES such
that the maximum-number of zone-descriptors is overwritable. It also
replaces g_zone_report_full as it is represented by the limit-value 0,
e.g. "no limit" dump the full report.
The print of the section-header now includes the total amount of zones
and the limit. With this information, the header's width varies. A
helper-function, print_uline(), for printing an "underline" using a
given marker, is also added.
Signed-off-by: Simon A. F. Lund <simon.lund@samsung.com>
Change-Id: Ic8abead693ed83bb8612eef1f35605098ccade84
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6036
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Despite spdk_nvme_transport_id_parse() checking optarg for NULL, then
the Jenkins CI doing code-analysis fails with the error message:
"Null pointer passed as an argument to a 'nonnull' parameter"
This adds an assertion to satisfy the code-analysis.
Signed-off-by: Simon A. F. Lund <simon.lund@samsung.com>
Change-Id: I35f7ee659624c1d5a2abda91bccac9fb58393063
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6068
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Community-CI: Mellanox Build Bot
Identify application prints the PMR details if it is supported
Signed-off-by: Krishna Kanth Reddy <krish.reddy@samsung.com>
Change-Id: Iaba4c15e18e1402035b11a34b2defe8078855751
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6209
Community-CI: Broadcom CI
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
The original value of bs is 4096, we can rewrite it in another script.
When spdk_nvme_ns_supports_extended_lba(ns) is 1, we need to
test with an integer multiple value of extended_sector_size, such as 4160.
Change-Id: I8257bee4f741f62597bb2bb645ee9c59cf57bf33
Signed-off-by: wanghailiangx <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6018
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
NVMe namespace ID (i.e., ns) is a key of Transport ID, which is
supported by perf, but it's missed in the help. In addtion, a
note is added to specify multiple '-r' parameters can be used
to test multiple disks/targets.
Signed-off-by: Allen Zhu <allenz@mellanox.com>
Change-Id: Icf55e6213a63d97396bdc7022e4c0d09c67aab9a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6141
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
It may be an interesting test case to send I/O to hot
removed namespaces, but for a perf tool it seems better
to stop sending them once we get an INVALID_NAMESPACE
status code.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ie458fa63b12114cf05d5a3f1702e37f91d8a00f6
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6091
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
The nvme perf tool can be useful to generate I/O for
stress conditions. But if we use it for situations
where we expect a high rate of failures, the excessive
spew can significantly clutter the log.
So add a new -Q option (meaning "quiet") which will
rate limit these error messages.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ia8ab2e1ea1cfab9f43d87bcabe8f3f7589b77cda
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6077
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Next patch will add rate limiting on some of the
error messages. Separating the read error message
from the write error message will allow us to
rate limit them independently.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Id49b64aa1ee545874d7230399a5127c47f217836
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/6076
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: sunshihao <sunshihao@huawei.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
We konw bs should be extended_sector_size(ns) * num_blocks.
In other words, bs should be an integral multiple of extended_sector_size.
num_blocks cannot be got here, so we used integral multiple.
Change-Id: Ie521db194cdad6f2d2247fd2704cab92c36ddb82
Signed-off-by: wanghailiangx <hailiangx.e.wang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5881
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
When NVMf target linked with vfio-user library, we can use
vfio-user client library to connect to the target.
Here is the three examples that can work with target:
identify -r 'trtype:VFIOUSER traddr:/var/run/muser/domain/muser0/8' -g
perf -r 'trtype:VFIOUSER traddr:/var/run/muser/domain/muser0/8' -g -q 1 -o 4096 -w read -t 10
reconnect -r 'trtype:VFIOUSER traddr:/var/run/muser/domain/muser0/8' -g -q 32 -o 4096 -w randrw \
-M 50 -t 10 -c 0xE
You can run the following test script test/nvmf/target/nvmf_vfio_user.sh to have a quick test,
currently enabled with NVMe Identify,Perf,Reconnect tools.
Change-Id: Ieb9842b2f372184fffbf7f23e4aad26feb47c350
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3839
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
There was some confusion from a user on whether thread=1
means only one thread is supported. So add some extra
documentation around this section to clarify this a bit
more, since the option is a bit confusing.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ibcccd1759180e2e6c47e736d94ffbeafc405f7bb
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5995
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: <dongx.yi@intel.com>
Community-CI: Mellanox Build Bot
Perf tool doesn't have handlers for SIGINT and SIGTERM
signals, so when the tool is killed with e.g. ctrl-c
all SPDK and transport resources are destroyed
ungracefully. In the case of RDMA we may have
IO requests inflight and if the request is processed
by the driver when the corresponding MR is destroyed by
the kernel, it may cause an error on the target side.
Such errors are not harmful but it is better to
have a graceful shutdown procedure.
Fixes issue #1549
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Change-Id: I7818a4705d2b5cf4a5f3ca4745c62392312d22d2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5869
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: <dongx.yi@intel.com>
Reviewed-by: Michael Haeuptle <michaelhaeuptle@gmail.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Fixes: 5ef79a17ec (add an option to dump the full zns zone report)
max_zones_per_buf was only used in an assert. Per-patch
testing doesn't do a release build, so this wasn't found
until running nightly tests.
So rework the code a bit to print error message and exit
instead of this unexpected condition occurs.
While here, change another error message to use stderr
instead of stdout.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I2c2893089cc82f76d7dd6b569952dd4a9f907ebc
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5949
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Add a new option, -z, to dump the full zone report for
NVMe Zoned Namepaces.
Rather than allocating a buffer that can exactly hold the number
of zones we request, allocate a fixed size buffer of size MDTS.
That way, the controller will copy as many zones as it can,
while not exceeding the buffer. The nr_zones field in the
received report indicates the number of zones that were
successfully copied to the buffer.
The full zns zone report can be larger than MDTS, therefore
we now need to put the spdk_nvme_zns_report_zones() call
inside a loop.
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Change-Id: If3ff84876289a491d0482e74c58c5a11de7e19df
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5896
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Exit after showing the help text.
If the user specifies -H, it is confusing that
the regular execution of the program continues,
which might mislead the user to think that the
option they specified is not taking effect.
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Change-Id: I52d8e0f6c720c7ce1d66bddb99181babb12cef1f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5895
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
A new option -O is added to indicate the IO unit size.
Multiple IOVs are created according to the IO unit size.
We are able to test multiple-SGL SGL requests in NVMEoF
RDMA with this patch.
Signed-off-by: Allen Zhu <allenz@mellanox.com>
Signed-off-by: Alexey Marchuk <alexeymar@mellanox.com>
Signed-off-by: Evgeniy Kochetov <evgeniik@mellanox.com>
Change-Id: I7624966b585bf0a9d2bbbb6263fa06fbcdb65820
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4377
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: John Kariuki <John.K.Kariuki@intel.com>
Reviewed-by: sunshihao <sunshihao@huawei.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Add one optional parameter to enable single memory segment, which
can be tested with libvfio-user NVMeoF target.
Change-Id: I6d77b0c33f13500e24266ca190d2ee797708a65e
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5593
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
According to the SPDK nvme fio plugin documentation:
"Blocksize should be set as the sum of data and metadata.
For example, if data blocksize is 512 Byte, host generated
PI metadata is 8 Byte, then blocksize in fio configure file
should be 520 Byte."
Error out if this requirement is not satisfied.
This requirement does not apply for the separate metadata case.
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Change-Id: I730a83beb6a85695c8a4b80995340b4064375d5a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5557
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
All of our Makefiles duplicate huge lists of libraries
in SPDK_LIB_LIST. We have a very precise and accurate
accounting of the library dependencies in
mk/spdk.lib_deps.mk which can be used to generate
the full list if the app specifies the modules and
subsystem libraries it wishes to link.
I did a first pass through all of the existing
Makefiles to take advantage of this new functionality.
There may be more optimizations we can make later but
don't want to hold up this patch for all of them.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Icdaf6f749a6908df2c2ce2db22631a4af4ff3a9e
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5553
Community-CI: Broadcom CI
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Currently, NVMe perf worker starts IO and measurements as soon as all
its QPs were connected. But other workers may still be connecting and
not started their measurements yet. With large number of QPs when
connections take a long time this can cause inaccurate performance
reporting.
This patch adds synchronization point for workers after all QPs were
connected and before start of IO and measurements.
Signed-off-by: Evgeniy Kochetov <evgeniik@nvidia.com>
Change-Id: If0c9be8dd41c8e851aae6b3e71afa3efe5314330
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5126
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
While here, replace use of "slave workers" in some
comments with "secondary workers".
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I2169c108da18d449a66a29daa77a3f9c3145d4b2
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5352
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
This helps us remove master/slave terminology from
SPDK and is aligned with similar changes made recently
in DPDK.
While updating nvme/identify to use the new member
name, also replace g_master_core there with g_main_core.
Other nvme utility usage of "master_core" will be updated
in a later patch.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I0ec4e3e9b644bec21b3729809bf5c4d35b10837f
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5351
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
The old pci_whitelist/pci_blacklist are now deprecated.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I9fddec0c90691dd385eb21d13be849247f144889
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5279
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
POSIX defines PRId64/PRIu64/PRIx64 for printing 64-bit values in a
portable way. Replace a few references to %ld to remove the assumption
about the size of a long.
Where the value being printed is an unsigned 64-bit value, use PRIu64
instead of %ld.
Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
Change-Id: Ifa558522437f4922b922abf17712173cb5ca1184
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5134
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Tomasz Zawadzki <tomasz.zawadzki@intel.com>
This patch is used to test the allowed pci list feature.
The reason we add in perf because NVMe Device is the typical
pci device. And we also want to make sure it works.
Change-Id: Ic98ddcfecb162ffb74c9bdf3bc9e702633ddd3e2
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3246
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
There is no need for an additional function to calculate the max transfer
size based on mdts.
nvme_ctrlr_identify_done() already initializes ctrlr->max_xfer_size
based on mdts, and spdk_nvme_ns_get_max_io_xfer_size() simply returns
ns->ctrlr->max_xfer_size.
Signed-off-by: Niklas Cassel <niklas.cassel@wdc.com>
Change-Id: I747ff8ac9767eababffc3c7e0b6846029a98b826
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/4985
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Simon A. F. Lund <simon.lund@samsung.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Aleksey Marchuk <alexeymar@mellanox.com>
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
