Hide Forgot
Created attachment 510031 [details] call trace Description of problem: guest get call trace and can not login during iofuzz testing. Version-Release number of selected component (if applicable): How reproducible: 2/5 Steps to Reproduce: 1. cmd qemu-kvm -drive file=/home/images/RHEL-Server-5.7-64-virtio.qcow2,index=0,if=virtio,media=disk,cache=none,boot=on,format=qcow2 -net nic,vlan=0,model=virtio,macaddr=9a:b5:fb:de:2a:5e -net tap,vlan=0,script=/home/scripts/qemu-ifup-switch,downscript=no -m 2048 -smp 4,cores=1,threads=1,sockets=4 -cpu qemu64,+sse2 -soundhw ac97 -vnc :0 -rtc-td-hack -M rhel5.6.0 -boot c -usbdevice tablet -no-kvm-pit-reinjectionmu-kvm 1).Enumerate all IO port ranges through /proc/ioports 2). On each port of the range: * Read it * Write 0 to it * Write a random value to a random port on a random order 2. 3. Actual results: Expected results: Additional info: 1. host 2.6.18-269.el5 processor : 3 vendor_id : GenuineIntel cpu family : 6 model : 23 model name : Intel(R) Core(TM)2 Quad CPU Q9400 @ 2.66GHz stepping : 10 cpu MHz : 2000.000 cache size : 3072 KB physical id : 0 siblings : 4 core id : 3 cpu cores : 4 apicid : 3 fpu : yes fpu_exception : yes cpuid level : 13 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm syscall nx lm constant_tsc pni monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr sse4_1 lahf_lm bogomips : 5319.97 clflush size : 64 cache_alignment : 64 address sizes : 36 bits physical, 48 bits virtual 2. guest 2.6.18-269.el5 3. can ping guest, but can not login guest (no response after input username) 4. top PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ WCHAN COMMAND 3805 root 15 0 2303m 869m 2540 R 1.3 22.7 28:45.32 - qemu 5. kvm_stat: kvm statistics efer_reload 113 0 exits 367961448 10623 fpu_reload 11993124 2 halt_exits 59720811 4074 halt_wakeup 2712038 70 host_state_reload 90911248 4524 hypercalls 0 0 insn_emulation 116760131 5075 insn_emulation_fail 0 0 invlpg 11174879 0 io_exits 28587282 448 irq_exits 6339311 0 irq_injections 77928813 5076 irq_window 16409017 1001 kvm_request_irq 0 0 largepages 0 0 mmio_exits 1459691 0 mmu_cache_miss 5009774 2 mmu_flooded 1952738 0 mmu_pde_zapped 7146203 0 mmu_pte_updated 111 0 mmu_pte_write 10183742 0 mmu_recycled 0 0 mmu_shadow_zapped 5015989 2 mmu_unsync 230 0 mmu_unsync_global 0 0 nmi_injections 6 0 nmi_window 0 0 pf_fixed 82395999 6 pf_guest 46704357 2 remote_tlb_flush 9181414 1 request_nmi 0 0 signal_exits 42 0 tlb_flush 28970768 11 6. call trace
Suqin, Can you please check it with a raw file? writing to a fresh qcow2 is known to be extremely slow on RHEL5. Thanks.
can not reproduce with raw, but always failed with "Guest moved used index from 5698 to 65535‘
Kevin, See Comment 1. I believe that you can close it as WONTFIX. Thanks, Ronen.
Well, what are you expecting if you write randomly to I/O ports? For me, it's expected behaviour if the hardware starts behaving strangely and makes the guest kernel fail (if anything it's a bug in the guest kernel's error handling). As long as qemu itself lives, I can't see a bug in qemu.