Currently the irq vector spread algorithm is restricted to online CPUs,
which ties the IRQ mapping to the currently online devices and doesn't deal
nicely with the fact that CPUs could come and go rapidly due to e.g. power
management.
Instead assign vectors to all present CPUs to avoid this churn.
Build a map of all possible CPUs for a given node, as the architectures
only provide a map of all onlines CPUs. Do this dynamically on each call
for the vector assingments, which is a bit suboptimal and could be
optimized in the future by provinding a mapping from the arch code.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: Sagi Grimberg <sagi@grimberg.me>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: linux-nvme@lists.infradead.org
Cc: Keith Busch <keith.busch@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20170603140403.27379-5-hch@lst.de
The vectors_per_node is calculated from the remaining available vectors.
The current vector starts after pre_vectors, so we need to subtract that
from the current to properly account for the number of remaining vectors
to assign.
Fixes: 3412386b53 ("irq/affinity: Fix extra vecs calculation")
Reported-by: Andrei Vagin <avagin@virtuozzo.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Link: http://lkml.kernel.org/r/1492645870-13019-1-git-send-email-keith.busch@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This fixes a math error calculating the extra_vecs. The error assumed
only 1 cpu per vector, but the value needs to account for the actual
number of cpus per vector in order to get the correct remainder for
extra CPU assignment.
Fixes: 7bf8222b9b ("irq/affinity: Fix CPU spread for unbalanced nodes")
Reported-by: Xiaolong Ye <xiaolong.ye@intel.com>
Signed-off-by: Keith Busch <keith.busch@intel.com>
Link: http://lkml.kernel.org/r/1492104492-19943-1-git-send-email-keith.busch@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The irq_create_affinity_masks routine is responsible for assigning a
number of interrupt vectors to CPUs. The optimal assignemnet will spread
requested vectors to all CPUs, with the fewest CPUs sharing a vector.
The algorithm may fail to assign some vectors to any CPUs if a node's
CPU count is lower than the average number of vectors per node. These
vectors are unusable and create an un-optimal spread.
Recalculate the number of vectors to assign at each node iteration by using
the remaining number of vectors and nodes to be assigned, not exceeding the
number of CPUs in that node. This will guarantee that every CPU is assigned
at least one vector.
Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: linux-nvme@lists.infradead.org
Link: http://lkml.kernel.org/r/1491247553-7603-1-git-send-email-keith.busch@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Commit 34c3d9819f ("genirq/affinity: Provide smarter irq spreading
infrastructure") introduced a better IRQ spreading mechanism, taking
account of the available NUMA nodes in the machine.
Problem is that the algorithm of retrieving the nodemask iterates
"linearly" based on the number of online nodes - some architectures
present non-linear node distribution among the nodemask, like PowerPC.
If this is the case, the algorithm lead to a wrong node count number
and therefore to a bad/incomplete IRQ affinity distribution.
For example, this problem were found in a machine with 128 CPUs and two
nodes, namely nodes 0 and 8 (instead of 0 and 1, if it was linearly
distributed). This led to a wrong affinity distribution which then led to
a bad mq allocation for nvme driver.
Finally, we take the opportunity to fix a comment regarding the affinity
distribution when we have _more_ nodes than vectors.
Fixes: 34c3d9819f ("genirq/affinity: Provide smarter irq spreading infrastructure")
Reported-by: Gabriel Krisman Bertazi <gabriel@krisman.be>
Signed-off-by: Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Gabriel Krisman Bertazi <gabriel@krisman.be>
Reviewed-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Cc: linux-pci@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: hch@lst.de
Link: http://lkml.kernel.org/r/1481738472-2671-1-git-send-email-gpiccoli@linux.vnet.ibm.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The reserved vectors at the beginning and the end of the vector space get
cpu_possible_mask assigned as their affinity mask.
All other non-auto affine interrupts get the default irq affinity mask
assigned. Using cpu_possible_mask breaks that rule.
Treat them like any other interrupt and use irq_default_affinity as target
mask.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Christoph Hellwig <hch@lst.de>
The recent addition of reserved vectors at the beginning or the end of the
vector space did not take the reserved vectors at the beginning into
account for the various loop exit conditions. As a consequence the last
vectors of the spread area are not included into the spread algorithm and
are treated like the reserved vectors at the end of the vector space and
get the default affinity mask assigned.
Sum up the affinity vectors and the reserved vectors at the beginning and
use the sum as exit condition.
[ tglx: Fixed all conditions instead of only one and massaged changelog ]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/1479201178-29604-2-git-send-email-hch@lst.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Only calculate the affinity for the main I/O vectors, and skip the
pre or post vectors specified by struct irq_affinity.
Also remove the irq_affinity cpumask argument that has never been used.
If we ever need it in the future we can pass it through struct
irq_affinity.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: linux-pci@vger.kernel.org
Link: http://lkml.kernel.org/r/1478654107-7384-4-git-send-email-hch@lst.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Only calculate the affinity for the main I/O vectors, and skip the pre or
post vectors specified by struct irq_affinity.
Also remove the irq_affinity cpumask argument that has never been used. If
we ever need it in the future we can pass it through struct irq_affinity.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Acked-by: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Cc: linux-pci@vger.kernel.org
Link: http://lkml.kernel.org/r/1478654107-7384-3-git-send-email-hch@lst.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The current irq spreading infrastructure is just looking at a cpumask and
tries to spread the interrupts over the mask. Thats suboptimal as it does
not take numa nodes into account.
Change the logic so the interrupts are spread across numa nodes and inside
the nodes. If there are more cpus than vectors per node, then we set the
affinity to several cpus. If HT siblings are available we take that into
account and try to set all siblings to a single vector.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: axboe@fb.com
Cc: keith.busch@intel.com
Cc: agordeev@redhat.com
Cc: linux-block@vger.kernel.org
Link: http://lkml.kernel.org/r/1473862739-15032-3-git-send-email-hch@lst.de
Without locking out CPU mask operations we might end up with an inconsistent
view of the cpumask in the function.
Fixes: 5e385a6ef31f: "genirq: Add a helper to spread an affinity mask for MSI/MSI-X vectors"
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: http://lkml.kernel.org/r/1470924405-25728-1-git-send-email-hch@lst.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Christoph Hellwig