| Message ID | 20241122095806.4034415-1-bk@alpico.io (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | KVM: make uevents configurable | expand |
On Fri, 22 Nov 2024 09:58:02 +0000, Bernhard Kauer <bk@alpico.io> wrote: > > Handling of uevents in userlevel is a bottleneck for tiny VMs. > > Running 10_000 VMs keeps one and a half cores busy for 5.4 seconds to let > systemd-udevd handle all messages. That is roughly 27x longer than > the 0.2 seconds needed for running the VMs without them. > > We choose a read-only module parameter here due to its simplicity and > ease of maintenance. > > Signed-off-by: Bernhard Kauer <bk@alpico.io> > --- > virt/kvm/kvm_main.c | 5 ++++- > 1 file changed, 4 insertions(+), 1 deletion(-) > > diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c > index 609e0bd68e8e..6139cd67a96a 100644 > --- a/virt/kvm/kvm_main.c > +++ b/virt/kvm/kvm_main.c > @@ -97,6 +97,9 @@ EXPORT_SYMBOL_GPL(halt_poll_ns_shrink); > bool debugfs_per_vm = true; > module_param(debugfs_per_vm, bool, 0644); > > +bool disable_uevent_notify; > +module_param(disable_uevent_notify, bool, 0444); > + > /* > * Ordering of locks: > * > @@ -6276,7 +6279,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) > struct kobj_uevent_env *env; > unsigned long long created, active; > > - if (!kvm_dev.this_device || !kvm) > + if (!kvm_dev.this_device || !kvm || disable_uevent_notify) > return; > > mutex_lock(&kvm_lock); Thanks for this. It was on my list of things to investigate, as this is a bottleneck when running a lot of concurrent syzkaller tests which create and destroy VMs repeatedly. I'm not overly keen on the command-line flag though, as this is the sort of things you'd like to be able to control more finely. Or at least without having to trigger a reboot. How about something such as a sysctl? with the kvm namespace? Thanks, M.
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 609e0bd68e8e..6139cd67a96a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -97,6 +97,9 @@ EXPORT_SYMBOL_GPL(halt_poll_ns_shrink); bool debugfs_per_vm = true; module_param(debugfs_per_vm, bool, 0644); +bool disable_uevent_notify; +module_param(disable_uevent_notify, bool, 0444); + /* * Ordering of locks: * @@ -6276,7 +6279,7 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) struct kobj_uevent_env *env; unsigned long long created, active; - if (!kvm_dev.this_device || !kvm) + if (!kvm_dev.this_device || !kvm || disable_uevent_notify) return; mutex_lock(&kvm_lock);
Handling of uevents in userlevel is a bottleneck for tiny VMs. Running 10_000 VMs keeps one and a half cores busy for 5.4 seconds to let systemd-udevd handle all messages. That is roughly 27x longer than the 0.2 seconds needed for running the VMs without them. We choose a read-only module parameter here due to its simplicity and ease of maintenance. Signed-off-by: Bernhard Kauer <bk@alpico.io> --- virt/kvm/kvm_main.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)