I have two xen hosts - host1 is 32bit, quad xeons, 16Gb RAM, running 12.1+updates, kernel 3.1.9-1.4-xen. (I'm pretty certain I've built xen from source on this one). host2 is 64bit, quad xeons, 32Gb RAM, also 12.1+updates, kernel 3.3.0-2-xen. (from factory) I've noticed that the virtual footprints of a few processes are _significantly_ different from host1 to host2: Host2: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 2769 root 20 0 705m 20m 1508 S 0 4.1 0:02.94 xend 2768 root 20 0 123m 12m 784 S 0 2.5 0:00.00 xend 2770 root 20 0 181m 7224 7052 S 0 1.4 0:00.31 blktapctrl 1 root 20 0 37180 4160 1916 S 0 0.8 0:00.89 systemd 2471 root 20 0 4094m 3848 2788 S 0 0.8 0:00.11 console-kit-dae 2543 root 20 0 184m 3052 2516 S 0 0.6 0:00.08 polkitd 882 root 20 0 315m 1456 1032 S 0 0.3 0:00.13 rsyslogd Host1: PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 5023 root 20 0 71260 10m 1644 S 0 4.1 0:00.90 xend 5022 root 20 0 13952 7788 836 S 0 2.9 0:00.00 xend 2066 root 20 0 90160 3292 2644 S 0 1.2 0:00.06 console-kit-dae 2133 root 20 0 24304 2716 2328 S 0 1.0 0:00.60 polkitd 1 root 20 0 5148 2548 1856 S 0 0.9 0:00.62 systemd 735 root 20 0 40116 1260 948 S 0 0.5 0:00.10 rsyslogd For instance, xend on host2 appears to have a virtual footprint of more than 10 times that of xend on host1. Look at rsyslogd too. Is this is really just due to 32 vs 64bit architecture? -- Per Jessen, Zürich (21.8°C) -- To unsubscribe, e-mail: opensuse-factory+unsubscribe@opensuse.org To contact the owner, e-mail: opensuse-factory+owner@opensuse.org