On Mon 05-06-23 14:35:56, Marcelo Tosatti wrote: > On Mon, Jun 05, 2023 at 05:55:49PM +0200, Michal Hocko wrote: > > > The example above shows an additional 7us for the > > > > > > oslat -> kworker -> oslat > > > > > > switches. In the case of a virtualized CPU, and the vmstat_update > > > interruption in the host (of a qemu-kvm vcpu), the latency penalty > > > observed in the guest is higher than 50us, violating the acceptable > > > latency threshold. > > > > > > The isolated vCPU can perform operations that modify per-CPU page counters, > > > for example to complete I/O operations: > > > > > > CPU 11/KVM-9540 [001] dNh1. 2314.248584: mod_zone_page_state <-__folio_end_writeback > > > CPU 11/KVM-9540 [001] dNh1. 2314.248585: <stack trace> > > > => 0xffffffffc042b083 > > > => mod_zone_page_state > > > => __folio_end_writeback > > > => folio_end_writeback > > > => iomap_finish_ioend > > > => blk_mq_end_request_batch > > > => nvme_irq > > > => __handle_irq_event_percpu > > > => handle_irq_event > > > => handle_edge_irq > > > => __common_interrupt > > > => common_interrupt > > > => asm_common_interrupt > > > => vmx_do_interrupt_nmi_irqoff > > > => vmx_handle_exit_irqoff > > > => vcpu_enter_guest > > > => vcpu_run > > > => kvm_arch_vcpu_ioctl_run > > > => kvm_vcpu_ioctl > > > => __x64_sys_ioctl > > > => do_syscall_64 > > > => entry_SYSCALL_64_after_hwframe > > > > OK, this is really useful. It is just not really clear whether the IO > > triggered here is from the guest or it a host activity. > > Guest initiated I/O, since the host CPU is isolated. Make it explicit in the changelog. I am just wondering how you can achieve your strict deadlines when IO is involved but that is another story I guess. -- Michal Hocko SUSE Labs
