Purpose: This patch is used to prepare to add the kernel
idxd support later.
Signed-off-by: Ziye Yang <ziye.yang@intel.com>
Change-Id: If89665f95d622c7342ab75050664158ec6fc615a
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/7330
Community-CI: Broadcom CI
Community-CI: Mellanox Build Bot
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Changpeng Liu <changpeng.liu@intel.com>
Reviewed-by: Paul Luse <paul.e.luse@intel.com>
For flow control reasons we have to resize the bit arrays we
use to manage flow as channels come and go. However since
channels are assigned to devices, until the channel count
reaches the device count there's no sharing so no resize of
the array is needed. So, when we use a device for the first
time there's no need to run through the rest of the channels
and re-balance.
Same thing is done on destruction. The code to free idxd
specific resources was moved from the rebalance function to
the idxd put channel function which is a much more logical
place for it as well.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ib4df163286906f413dd6429dc6833af7b68e208c
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5846
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>
Config #1 remains what is shown as an example in the spec. Change
config #0 to just have 1 work group and 1 work queue all backed
by 4 engines. As the majority of initial use cases will not be
implementing separate priorities and/or different back end
targets (mem, pmem, etc) having just 1 group and work queue makes
the most sense as it allows the silicon to decide which engine to
use.
Also, having multiple work queues spreads out the available
entires such that if we're not using all of the work queues then
we're not using all of the resources. As channels are created
they are assigned the next available device. As a channel is
assigned a device that is already in use it will round robin
work queues. If then, for example, we have 16 devices then only
the first work queue will ever be used for the first 16 threads
which seems and if there are even just 2 work queues per device
it would take 32 threads to use all of the resources at the
device.
By haing just one work queue per device we always have the max
number of work queue entries available regardless of how many threads
are being used.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ie15ff6bdea12525fe3bfc769613084ddd2de50bf
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5845
Tested-by: SPDK CI Jenkins <sys_sgci@intel.com>
Community-CI: Mellanox Build Bot
Reviewed-by: Ziye Yang <ziye.yang@intel.com>
Reviewed-by: Shuhei Matsumoto <shuhei.matsumoto.xt@hitachi.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
With some build environments (e.g. clang, see #1613) linking fails with
unresolved references. This is caused by the inclusion of 'unused code'
which is usually discarded by the linker. The 'unused code' contains
references to functions that have not been 'stubbed' out. The failure
can be seen by removing 'LDFLAGS += -Wl,--gc-sections' in
spdk.unittest.mk
Resolved by adding stubs for missing references. These are never called
so return an arbtrary default value.
Move include of idxd/idxd.c after definition of movdir64b so that mock
function is used.
Part of a set of independent changes which
Fixes#1613
Signed-off-by: Nick Connolly <nick.connolly@mayadata.io>
Change-Id: I760755122a1d3ca96f12b00b0040ae15471beafa
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/5110
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: Aleksey Marchuk <alexeymar@mellanox.com>
And to eliminate an artificial constraint on # of user descriptors.
The main idea here was to move from a single ring that covered all
user descriptors to a pre-allocated ring per pre-allocated batch.
In addition, the other major change here is in how we poll for
completions. We used to poll the batch rings then the main ring.
Now when commands are prepared their completion address is added to
a per channel list and the poller simply runs through that list
not caring which ring the completion address belongs too. This
simplifies the completion logic considerably and will avoid
polling locations that can't potentially have a completion.
Some minor rework was included as well, mainly getting rid of the
ring_ctrl struct as it didn't serve much of a purpose anyway and
with how things are setup now its easier to read with all the
elements in the channel struct.
Also, a change that came in while this was WIP needed a few fixes
to function correctly. Addressed those and moved them to a
helper function so we have one point of control for xlations.
Added support for NOP in cases where a batch is submitted with
only 1 descriptor.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: Ie201b28118823100e908e0d1b08e7c10bb8fa9e7
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/3654
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: Ben Walker <benjamin.walker@intel.com>
More tests will follow in later patches.
Signed-off-by: paul luse <paul.e.luse@intel.com>
Change-Id: I6c45b94cc17219acfae863c774fc7dbc33625c85
Reviewed-on: https://review.spdk.io/gerrit/c/spdk/spdk/+/1782
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: Ben Walker <benjamin.walker@intel.com>
Reviewed-by: Jim Harris <james.r.harris@intel.com>
