Hello, FreeBSD. After upgrading VirtualBox (Windows host) to 4.3.x, FreeBSD guest starts to spent a lot of time in swi4:clock: PID USERNAME PRI NICE SIZE RES STATE C TIME WCPU COMMAND 11 root -60 - 0K 176K WAIT 0 29:13 18.99% intr{swi4: clock} Also, host becomes almost unusable, as half of keyboard presses are missed and other are multiplied and mouse is chaotic. It looks to be connected to complex/mixed workload (like "make -j4 buildworld buildkernel") as pure-CPU load (like xz-ipping /dev/zero to /dev/null) and pure-I/O load (like dd'ing from /dev/zero to virtual disk) doesn't cause this behavior. FreeBSD (exactly same VM configuration) doesn't have this problem on VirtualBox 4.2.x. VM is 2 CPU (out of 4 physical), 4Gb of RAM (out of 8 physical) ICH9, I/O APIC, virtual SATA controller (AHCI mode) with 3 virtual disks, that's all. Timers in system: kern.eventtimer.et.LAPIC.flags: 15 kern.eventtimer.et.LAPIC.frequency: 500014822 kern.eventtimer.et.LAPIC.quality: 400 kern.eventtimer.et.i8254.flags: 1 kern.eventtimer.et.i8254.frequency: 1193182 kern.eventtimer.et.i8254.quality: 100 kern.eventtimer.et.RTC.flags: 17 kern.eventtimer.et.RTC.frequency: 32768 kern.eventtimer.et.RTC.quality: 0 kern.eventtimer.choice: LAPIC(400) i8254(100) RTC(0) kern.eventtimer.singlemul: 4 kern.eventtimer.idletick: 0 kern.eventtimer.timer: LAPIC kern.eventtimer.periodic: 0 I think, it is new VBox version problem, but I want to be sure before reporting it to Oracle's bugtracking, as FreeBSD is not usual guest system and I don't want bug to be ignored :) -- // Black Lion AKA Lev Serebryakov <lev_at_FreeBSD.org>Received on Wed Jan 22 2014 - 09:37:40 UTC
This archive was generated by hypermail 2.4.0 : Wed May 19 2021 - 11:40:46 UTC