This bug has been copied from bug #575585 and has been proposed to be backported to 5.5 z-stream (EUS).
Summary: PASS. Reproduced in kvm-83-164.el5_5.2 and verified in kvm-83-164.el5_5.6 Host environment: processor : 0 vendor_id : AuthenticAMD cpu family : 16 model : 2 model name : AMD Phenom(tm) 9600B Quad-Core Processor stepping : 3 cpu MHz : 1200.000 cache size : 512 KB physical id : 0 siblings : 4 core id : 0 cpu cores : 4 apicid : 0 fpu : yes fpu_exception : yes cpuid level : 5 wp : yes flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm 3dnowext 3dnow constant_tsc nonstop_tsc pni cx16 popcnt lahf_lm cmp_legacy svm extapic cr8_legacy altmovcr8 abm sse4a misalignsse 3dnowprefetch osvw ... Mem: 8G CLI: /usr/libexec/qemu-kvm -m 8G -smp 1 -drive file=/mnt/win2008-64.qcow2,if=ide,cache=off -net nic,model=e1000,vlan=1,macaddr=02:00:40:3F:20:10 -net tap,vlan=1,script=/etc/qemu-ifup -boot c -uuid 17544ecc-d3a1-4d3c-a386-12daf50015f1 -usbdevice tablet -no-hpet -rtc-td-hack -no-kvm-pit-reinjection -monitor stdio -notify all -cpu qemu64,+sse2 -balloon none -startdate now -vnc :11 -name 175-test1 -M rhel5.5.0 Setup: Prepare two 64bit Windows guests (In case host has large memory, 64bit guest can support memory size above 4G). Steps: 1. reboot host to provide a clean environment (SwapCached: 0 kB) 2. start ksm scanner (e.g. pages_to_scan 5000, sleep_time 5000) # ksmctl 5000 5000 3. start two Windows guests in parallel, each with large memory (e.g. equal to the physical memory size of the host ). # /usr/libexec/qemu-kvm -m 8G -smp 1 -drive file=/mnt/win2008-64.qcow2 ... # /usr/libexec/qemu-kvm -m 8G -smp 1 -drive file=/mnt/win2008-64.qcow2.2 ... 4. wait till pages shared by two guests become relatively stable (RES, SHR columns) # top ... PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 1830 root 20 -5 0 0 0 R 79.4 0.0 6:16.39 kksmd 4357 root 15 0 8426m 4.5g 4.3g S 2.0 59.5 2:45.67 qemu-kvm 4372 root 15 0 8426m 2.6g 2.4g S 0.7 34.9 3:40.03 qemu-kvm 5. check host Swap Cache # grep Swap /proc/meminfo 6. shut down both Windows guests. 7. check host Swap Cache again. Results after step 7: 1. kvm-83-164.el5_5.2 free -m total used free shared buffers cached Mem: 7718 1879 5839 0 2 16 -/+ buffers/cache: 1860 5858 Swap: 9727 1835 7892 # grep Swap /proc/meminfo SwapCached: 1829152 kB SwapTotal: 9961464 kB SwapFree: 8082072 kB 2. kvm-83-164.el5_5.6 # free -m total used free shared buffers cached Mem: 7718 916 6802 0 25 798 -/+ buffers/cache: 92 7626 Swap: 9727 79 9648 [root@dhcp-91-175 ~]# grep Swap /proc/meminfo SwapCached: 6152 kB SwapTotal: 9961464 kB SwapFree: 9879556 kB
An advisory has been issued which should help the problem described in this bug report. This report is therefore being closed with a resolution of ERRATA. For more information on therefore solution and/or where to find the updated files, please follow the link below. You may reopen this bug report if the solution does not work for you. http://rhn.redhat.com/errata/RHBA-2010-0419.html