5504a81261
Zhiyi reported an infinite loop issue in VFIO use case. The cause of that
was a separate discussion, however during that I found a regression of
dirty sync slowness when profiling.
Each KVMMemoryListerner maintains an array of kvm memslots. Currently it's
statically allocated to be the max supported by the kernel. However after
Linux commit 4fc096a99e ("KVM: Raise the maximum number of user memslots"),
the max supported memslots reported now grows to some number large enough
so that it may not be wise to always statically allocate with the max
reported.
What's worse, QEMU kvm code still walks all the allocated memslots entries
to do any form of lookups. It can drastically slow down all memslot
operations because each of such loop can run over 32K times on the new
kernels.
Fix this issue by making the memslots to be allocated dynamically.
Here the initial size was set to 16 because it should cover the basic VM
usages, so that the hope is the majority VM use case may not even need to
grow at all (e.g. if one starts a VM with ./qemu-system-x86_64 by default
it'll consume 9 memslots), however not too large to waste memory.
There can also be even better way to address this, but so far this is the
simplest and should be already better even than before we grow the max
supported memslots. For example, in the case of above issue when VFIO was
attached on a 32GB system, there are only ~10 memslots used. So it could
be good enough as of now.
In the above VFIO context, measurement shows that the precopy dirty sync
shrinked from ~86ms to ~3ms after this patch applied. It should also apply
to any KVM enabled VM even without VFIO.
NOTE: we don't have a FIXES tag for this patch because there's no real
commit that regressed this in QEMU. Such behavior existed for a long time,
but only start to be a problem when the kernel reports very large
nr_slots_max value. However that's pretty common now (the kernel change
was merged in 2021) so we attached cc:stable because we'll want this change
to be backported to stable branches.
Cc: qemu-stable <qemu-stable@nongnu.org>
Reported-by: Zhiyi Guo <zhguo@redhat.com>
Tested-by: Zhiyi Guo <zhguo@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Fabiano Rosas <farosas@suse.de>
Link: https://lore.kernel.org/r/20240917163835.194664-2-peterx@redhat.com
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
40 lines
3.0 KiB
Plaintext
40 lines
3.0 KiB
Plaintext
# See docs/devel/tracing.rst for syntax documentation.
|
|
|
|
# kvm-all.c
|
|
kvm_ioctl(unsigned long type, void *arg) "type 0x%lx, arg %p"
|
|
kvm_vm_ioctl(unsigned long type, void *arg) "type 0x%lx, arg %p"
|
|
kvm_vcpu_ioctl(int cpu_index, unsigned long type, void *arg) "cpu_index %d, type 0x%lx, arg %p"
|
|
kvm_run_exit(int cpu_index, uint32_t reason) "cpu_index %d, reason %d"
|
|
kvm_device_ioctl(int fd, unsigned long type, void *arg) "dev fd %d, type 0x%lx, arg %p"
|
|
kvm_failed_reg_get(uint64_t id, const char *msg) "Warning: Unable to retrieve ONEREG %" PRIu64 " from KVM: %s"
|
|
kvm_failed_reg_set(uint64_t id, const char *msg) "Warning: Unable to set ONEREG %" PRIu64 " to KVM: %s"
|
|
kvm_init_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu"
|
|
kvm_create_vcpu(int cpu_index, unsigned long arch_cpu_id, int kvm_fd) "index: %d, id: %lu, kvm fd: %d"
|
|
kvm_destroy_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu"
|
|
kvm_park_vcpu(int cpu_index, unsigned long arch_cpu_id) "index: %d id: %lu"
|
|
kvm_unpark_vcpu(unsigned long arch_cpu_id, const char *msg) "id: %lu %s"
|
|
kvm_irqchip_commit_routes(void) ""
|
|
kvm_irqchip_add_msi_route(char *name, int vector, int virq) "dev %s vector %d virq %d"
|
|
kvm_irqchip_update_msi_route(int virq) "Updating MSI route virq=%d"
|
|
kvm_irqchip_release_virq(int virq) "virq %d"
|
|
kvm_set_ioeventfd_mmio(int fd, uint64_t addr, uint32_t val, bool assign, uint32_t size, bool datamatch) "fd: %d @0x%" PRIx64 " val=0x%x assign: %d size: %d match: %d"
|
|
kvm_set_ioeventfd_pio(int fd, uint16_t addr, uint32_t val, bool assign, uint32_t size, bool datamatch) "fd: %d @0x%x val=0x%x assign: %d size: %d match: %d"
|
|
kvm_set_user_memory(uint16_t as, uint16_t slot, uint32_t flags, uint64_t guest_phys_addr, uint64_t memory_size, uint64_t userspace_addr, uint32_t fd, uint64_t fd_offset, int ret) "AddrSpace#%d Slot#%d flags=0x%x gpa=0x%"PRIx64 " size=0x%"PRIx64 " ua=0x%"PRIx64 " guest_memfd=%d" " guest_memfd_offset=0x%" PRIx64 " ret=%d"
|
|
kvm_clear_dirty_log(uint32_t slot, uint64_t start, uint32_t size) "slot#%"PRId32" start 0x%"PRIx64" size 0x%"PRIx32
|
|
kvm_resample_fd_notify(int gsi) "gsi %d"
|
|
kvm_dirty_ring_full(int id) "vcpu %d"
|
|
kvm_dirty_ring_reap_vcpu(int id) "vcpu %d"
|
|
kvm_dirty_ring_page(int vcpu, uint32_t slot, uint64_t offset) "vcpu %d fetch %"PRIu32" offset 0x%"PRIx64
|
|
kvm_dirty_ring_reaper(const char *s) "%s"
|
|
kvm_dirty_ring_reap(uint64_t count, int64_t t) "reaped %"PRIu64" pages (took %"PRIi64" us)"
|
|
kvm_dirty_ring_reaper_kick(const char *reason) "%s"
|
|
kvm_dirty_ring_flush(int finished) "%d"
|
|
kvm_failed_get_vcpu_mmap_size(void) ""
|
|
kvm_cpu_exec(void) ""
|
|
kvm_interrupt_exit_request(void) ""
|
|
kvm_io_window_exit(void) ""
|
|
kvm_run_exit_system_event(int cpu_index, uint32_t event_type) "cpu_index %d, system_even_type %"PRIu32
|
|
kvm_convert_memory(uint64_t start, uint64_t size, const char *msg) "start 0x%" PRIx64 " size 0x%" PRIx64 " %s"
|
|
kvm_memory_fault(uint64_t start, uint64_t size, uint64_t flags) "start 0x%" PRIx64 " size 0x%" PRIx64 " flags 0x%" PRIx64
|
|
kvm_slots_grow(unsigned int old, unsigned int new) "%u -> %u"
|