Add an new option to let users choose PRP or SGL for I/O commands,
for SGL, users can append `-enable_sgl=1` when starting fio tests.
PRP is used by default.
Change-Id: Ic28c85c95fdd92d4bbe8a02616686b57e91e7271
Signed-off-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-on: https://review.gerrithub.io/407251
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>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Automatically detect more whitespace errors.
All existing cases are fixed; only whitespace change (verify with
diff -w) except for one comment style fixup in include/spdk/nvme.h.
Change-Id: If750e54b9c8e3421ea6feda5f20184a31431631e
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/402360
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Change-Id: Id259261d387998f332dee11dca740ecaba311de4
Signed-off-by: Pan Liu <liupan1111@gmail.com>
Reviewed-on: https://review.gerrithub.io/399274
Reviewed-by: GangCao <gang.cao@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
A previous commit updated the fio version for the bdev fio plugin, but
the NVMe fio plugin should also be updated.
Change-Id: I32fab18563b6b723a3e9b71589e3a3904196d07f
Fixes: 21ec62533d ("CHANGELOG: add fio 3.3 support")
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/395788
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>
Add some options to reduce the number of calls to
get time.
Change-Id: Iceea12b1ad82cba96d1a4bd687af3e9743d5f58a
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/393686
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>
The test already writes to the entire device twice, so
the trim step does not actually accomplish anything.
Change-Id: Ie761389511196d659358f18f557feb80087628cc
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/393832
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
If it cannot be allocated, we should return error.
Change-Id: I48aa50a8842c35ee112fe7185128b1bc1930176e
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/386369
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Describe the phenoemon for peformance difference
between fio + spdk plugin and spdk nvme perf
on multiple NVMe SSDs while both using single
cpu core.
Change-Id: I80c2cfd51cd1d8ec28a11a1a8653469cfc3335eb
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/379573
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
The reason is that we create duplicated qpair on same subsystem many times,
thus the performance is influenced. And this patch can fix this issue.
Change-Id: I075b028b15e0d34857a89510710642f2d9520235
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-on: https://review.gerrithub.io/375782
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>
With this change, the polling qpairs can be in round-robin manner.
Change-Id: I1926468dc596de2a43f42451525650356f44fbbd
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/375707
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
This will cause the NVMe driver to use the default qpair size
as opposed to setting it up for the first job in what may end
being a series of jobs in the same fio config file. If we
don't do this and subsequent jobs are specifying a higher queue
depth than earlier jobs, the NVMe qpairs will be too small and
performance results can be way off.
Future fix logged on Trello to correctly size q pairs even when
multiple jobs are specified in a single file but this is a small
optimization.
Change-Id: I73a7b83b10418dd22b663a50ea8e33a6c3d7ecf7
Signed-off-by: Paul Luse <paul.e.luse@intel.com>
Reviewed-on: https://review.gerrithub.io/371240
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>
Add a new struct spdk_nvme_io_qpair_opts to allow the user to override
controller options on a per-I/O qpair basis.
Existing callers with qprio == 0 can be updated to:
... = spdk_nvme_ctrlr_alloc_io_qpair(ctrlr, NULL, 0);
Callers that need to specify a non-default qprio should be updated to:
struct spdk_nvme_io_qpair_opts opts;
spdk_nvme_ctrlr_get_default_io_qpair_opts(ctrlr, &opts, sizeof(opts));
opts.qprio = SPDK_NVME_QPRIO_...;
... = spdk_nvme_ctrlr_alloc_io_qpair(ctrlr, &opts, sizeof(opts));
Change-Id: I8ac3ea369535cfde759abbe75e1d974b6450a800
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/369676
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
FIO backends are supposed to return a negative value on error.
Add special handling for -ENOMEM (out of requests) case to return
FIO_Q_BUSY, indicating that FIO should resubmit the request later.
This is part of the fix for issue #169, which is related to high queue
depths with large I/Os causing the NVMe library to run out of request
objects.
Change-Id: I4fa4001b078b07c42fcd4d1357434575b2c84023
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/369664
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>
Documentation update - the plugin just works with 2.21 with no
changes.
Change-Id: If1fb2367a00065bfb5627d0d2af9683e5c909dc1
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/367734
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>
Checked the code and found that our nvme perf example
added 1 io_queue_depth. Since if you set queue_depth=n,
the real entry is n - 1.
Change-Id: Ie204fc061b98e853e9b810eff21f79565c2ad8d0
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/367931
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>
Any transport that is not PCIe is a NVMe over Fabrics transport and
requires a subsystem NQN.
Change-Id: I68bfe49086f7f633fea8589ac15069327c4a4aa9
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/367290
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>
While here, change the recently added mem_size_mb to
also use the automatic option parsing for integer values
provided by fio.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I889073b3b3b01c7003b21d8ace61e71b672ff2df
Reviewed-on: https://review.gerrithub.io/367284
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>
We do not need quotes around the filename.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I31685409eb5d956cdfb2fc30896e9e43312b61a3
Reviewed-on: https://review.gerrithub.io/367280
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>
While doing performance testing for the SPDK NVMe driver using fio with
our fio_plugin, I saw the error (transport->ctrlr_create_io_qpair() failed)
when running 18 jobs on my system. The error was happening when trying
to allocate memory for the trackers at line 890 in the lib/nvme/nvme_pcie.c.
Root cause was the fio_plugin.c initializes the environment with only
512 MB of hugepage RAM. I changed opts.mem_size to 1024 and rebuild
the plugin the issue was resolved.
This patch enables setting the mem_size in the fio config file using
parameter named mem_size_mb. E.g. mem_size_mb=1024
Change-Id: I3541b2029a6b36c26f814101313f49c2dd98c9bc
Signed-off-by: John Kariuki <John.K.Kariuki@intel.com>
Reviewed-on: https://review.gerrithub.io/365735
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 can be used by threads within SPDK to undo the
affinitization done either by DPDK (for DPDK lcores)
or by inheriting the parent's thread when using
pthread_create().
This will be used by the stub app to unaffinitize
the reactor core to allow the scheduler to flexibly
move it to an idle core.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I7e550953cd9dcd7fd9d98bfbb70660994f2eefcd
Reviewed-on: https://review.gerrithub.io/366680
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 dpdk_ prefix in spdk_app_opts and spdk_env_opts
Change-Id: I6f231f67072b808e84945d41b1fe31a180beb350
Signed-off-by: Ziye Yang <optimistyzy@gmail.com>
Reviewed-on: https://review.gerrithub.io/365787
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>
fio has a race between reap_threads() and free_ioengine(). free_ioengine()
will call the ioengine's cleanup routine and then dlclose it if it
is dynamically linked (like the spdk fio plugin). free_ioengine() does
not set td->io_ops = NULL though until after dlclose() is complete. If
reap_threads() tries to dereference td->io_ops after our plugin has been
closed but before io_ops was set to NULL, it will segfault.
Solution (until an upstream fio fix is available) is to use LD_PRELOAD
instead.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: Ide4eb3cb92a636513289107fc211fdf1f98b616f
Reviewed-on: https://review.gerrithub.io/365272
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: Ziye Yang <optimistyzy@gmail.com>
- rename spdk_malloc_socket to spdk_dma_malloc_socket
- rename spdk_malloc to spdk_dma_malloc
- rename spdk_zmalloc to spdk_dma_zmalloc
- rename spdk_realloc to spdk_dma_realloc
- rename spdk_free to spdk_dma_free
Change-Id: I52a11b7a4243281f9c56f503e826fd7c4a1fd883
Signed-off-by: John Meneghini <johnm@netapp.com>
Reviewed-on: https://review.gerrithub.io/362604
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>
Also update the example fio file
Change-Id: I2a9074d524072e95340cc0e87041e87e3bb7d4f8
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-on: https://review.gerrithub.io/362069
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I9ee1c2ab49691f7e31bbec83a057faa718177c90
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
Reviewed-on: https://review.gerrithub.io/362260
Tested-by: SPDK Automated Test System <sys_sgsw@intel.com>
Reviewed-by: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: GangCao <gang.cao@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
These variables are not needed outside of this file.
Change-Id: I577db5140fb4156100e72e6219c8121304a9b137
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
This patch is causing intermittent errors in the automated tests, so
reverting for now until this can be resolved.
This reverts commit 1d9891989c.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I237e31b1b8a1a1e28262851ae0a21cd7345f0f1b
The reaon is that rte_eal_init called in spdk_env_init binds
the master thread on master core, we need to restore the
affinity.
Change-Id: I4eb2d36b74404c1af6d242c4fd5c403bd3d5036c
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
This patch will be prepare to support multi threads.
Change-Id: I2234ae1d564c9cf17b92c85fd0a414adaa639bf2
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Also adds the automation test case for using remote
NVMe devices exported by NVMe-oF target.
Change-Id: I2b839a4eeec33d5b0c30d654e6013ad8c7949e23
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
The SPDK fio plugin only supports jobs as threads, not separate
processes. So log an error and bail if --thread=1 is not
specified.
Signed-off-by: Jim Harris <james.r.harris@intel.com>
Change-Id: I318f924e0b7fbb76f11427a447dd7c5fc0ebc221
The previous implementation tried to maintain a ring buffer of completed
I/O retrieved from ->getevents() that had not yet been retrieved by
->event(), but this is not necessary. None of the other FIO engines
implement this sort of ring buffer, and the only code that calls
->getevents() will always retrieve the full number of events via
->event() afterwards.
Instead, just count how many I/Os have been completed within each
->getevents() call in iocq_count, and reset iocq_count on each new
->getevents().
Change-Id: I2776c3a5c89a0d2b24478328bc138ff7a9fb5bdd
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
They were very close to the same already, so finish the job.
Change-Id: Ifba9e3b2d11a3e70cbfbe46f57a67552db2757ed
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
The probe_info was reduced to just containing a
transport_id, so remove probe_info entirely.
Change-Id: Ica9a22d126cd14e282decd3eea1a0afe0460f099
Signed-off-by: Ben Walker <benjamin.walker@intel.com>
Make it easier to use SPDK libraries by putting them all in a single
directory that can be added with -L rather than scattered around the
source tree.
Change-Id: I5c0f5dd6e7058b5f92fa9bc41548190ffc064761
Signed-off-by: Daniel Verkamp <daniel.verkamp@intel.com>
