* Qemu-kvm is leaking my memory ??? @ 2008-03-14 22:14 Zdenek Kabelac 2008-03-16 13:46 ` Avi Kivity 0 siblings, 1 reply; 13+ messages in thread From: Zdenek Kabelac @ 2008-03-14 22:14 UTC (permalink / raw) To: kvm-devel Hello Recently I'm using qemu-kvm on fedora-rawhide box with my own kernels (with many debug options) I've noticed that over the time my memory seems to disappear somewhere. Here is my memory trace after boot and some time of work - thus memory should be populated. MemTotal: 2007460 kB MemFree: 618772 kB Buffers: 46044 kB Cached: 733156 kB SwapCached: 0 kB Active: 613384 kB Inactive: 541844 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 148 kB Writeback: 0 kB AnonPages: 376152 kB Mapped: 67184 kB Slab: 80340 kB SReclaimable: 50284 kB SUnreclaim: 30056 kB PageTables: 27976 kB NFS_Unstable: 0 kB Bounce: 0 kB CommitLimit: 1003728 kB Committed_AS: 810968 kB VmallocTotal: 34359738367 kB VmallocUsed: 71244 kB VmallocChunk: 34359666419 kB 618772 + 46044 + 733156 + 148 + 376152 + 67184 + 80340 + 50284 + 30056 + 27976 = 2030112 2GB (though could be wrong - I could be wrong and adding something improperly) And this memory listing is when I work during the day with qemu-kvm do something like 30-50 qemu restarts. Then before I rebooted the machine I've killed nearly all running task (i.e no Xserver, most of services turned of) MemTotal: 2007416 kB MemFree: 652412 kB Buffers: 70000 kB Cached: 607144 kB SwapCached: 0 kB Active: 571464 kB Inactive: 709796 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 0 kB Writeback: 0 kB AnonPages: 6408 kB Mapped: 4844 kB Slab: 52620 kB SReclaimable: 32752 kB SUnreclaim: 19868 kB PageTables: 1468 kB NFS_Unstable: 0 kB Bounce: 0 kB CommitLimit: 1003708 kB Committed_AS: 33988 kB VmallocTotal: 34359738367 kB VmallocUsed: 68152 kB VmallocChunk: 34359668731 kB I've have expected much more free memory here and I definitely do not see how this could combine 2GB of my memory: 652412 + 70000 + 607144 + 6408 + 4844 + 52620 + 32752 + 19868 + 1468 = 1447516 1.4GB so where is my 600MB piece of memory hiding ? Zdenek ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-14 22:14 Qemu-kvm is leaking my memory ??? Zdenek Kabelac @ 2008-03-16 13:46 ` Avi Kivity 2008-03-19 15:05 ` Zdenek Kabelac 0 siblings, 1 reply; 13+ messages in thread From: Avi Kivity @ 2008-03-16 13:46 UTC (permalink / raw) To: Zdenek Kabelac; +Cc: kvm-devel Zdenek Kabelac wrote: > Hello > > Recently I'm using qemu-kvm on fedora-rawhide box with my own kernels > (with many debug options) I've noticed that over the time my memory > seems to disappear somewhere. > > Here is my memory trace after boot and some time of work - thus memory > should be populated. > No idea how these should add up. What does 'free' say? -- error compiling committee.c: too many arguments to function ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-16 13:46 ` Avi Kivity @ 2008-03-19 15:05 ` Zdenek Kabelac 2008-03-19 15:56 ` Avi Kivity 0 siblings, 1 reply; 13+ messages in thread From: Zdenek Kabelac @ 2008-03-19 15:05 UTC (permalink / raw) To: Avi Kivity; +Cc: kvm-devel 2008/3/16, Avi Kivity <avi@qumranet.com>: > Zdenek Kabelac wrote: > > Hello > > > > Recently I'm using qemu-kvm on fedora-rawhide box with my own kernels > > (with many debug options) I've noticed that over the time my memory > > seems to disappear somewhere. > > > > Here is my memory trace after boot and some time of work - thus memory > > should be populated. > > > > > No idea how these should add up. What does 'free' say? Ok - here goes my free log (I'm loggin free prior each start of my qemu-kvm so here is the log for this afternoon: (I'm running same apps all the time - except during kernel compilation I'm reading some www pages - and working with gnome-terminal - so some slightly more memory could have been eaten by them - but not in the range of hundreds of MB) Wed Mar 19 12:54:38 CET 2008 total used free shared buffers cached Mem: 2007460 1525240 482220 0 18060 469812 -/+ buffers/cache: 1037368 970092 Swap: 0 0 0 Wed Mar 19 13:27:51 CET 2008 total used free shared buffers cached Mem: 2007460 1491672 515788 0 13024 404220 -/+ buffers/cache: 1074428 933032 Swap: 0 0 0 Wed Mar 19 13:51:38 CET 2008 total used free shared buffers cached Mem: 2007460 1513000 494460 0 12676 366708 -/+ buffers/cache: 1133616 873844 Swap: 0 0 0 Wed Mar 19 14:05:30 CET 2008 total used free shared buffers cached Mem: 2007460 1976592 30868 0 12220 785672 -/+ buffers/cache: 1178700 828760 Swap: 0 0 0 Wed Mar 19 14:13:52 CET 2008 total used free shared buffers cached Mem: 2007460 1865500 141960 0 14592 633136 -/+ buffers/cache: 1217772 789688 Swap: 0 0 0 Wed Mar 19 14:16:04 CET 2008 total used free shared buffers cached Mem: 2007460 1533432 474028 0 5852 304736 -/+ buffers/cache: 1222844 784616 Swap: 0 0 0 Wed Mar 19 15:05:33 CET 2008 total used free shared buffers cached Mem: 2007460 1545796 461664 0 4100 276756 -/+ buffers/cache: 1264940 742520 Swap: 0 0 0 Wed Mar 19 15:14:07 CET 2008 total used free shared buffers cached Mem: 2007460 1748680 258780 0 8324 427172 -/+ buffers/cache: 1313184 694276 Swap: 0 0 0 -now it's: total used free shared buffers cached Mem: 2007460 1784952 222508 0 20644 335360 -/+ buffers/cache: 1428948 578512 Swap: 0 0 0 and top-twenty memory list of currently running processes: top - 15:52:29 up 19:07, 12 users, load average: 0.33, 0.30, 0.60 Tasks: 298 total, 1 running, 296 sleeping, 1 stopped, 0 zombie Cpu(s): 1.6%us, 3.3%sy, 0.0%ni, 95.1%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st Mem: 2007460k total, 1770748k used, 236712k free, 20304k buffers Swap: 0k total, 0k used, 0k free, 335036k cached PID PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND 15974 20 0 655m 207m 28m S 0.0 10.6 3:31.31 firefox 3980 20 0 378m 63m 10m S 1.3 3.2 1:00.53 gnome-terminal 2657 20 0 481m 58m 9928 S 2.3 3.0 19:16.03 Xorg 12492 20 0 494m 34m 17m S 0.0 1.8 1:20.52 pidgin 3535 20 0 336m 22m 12m S 0.0 1.2 0:15.41 gnome-panel 3571 20 0 265m 16m 10m S 0.0 0.9 0:06.25 nm-applet 3638 20 0 298m 16m 9296 S 0.0 0.8 0:36.79 wnck-applet 3546 20 0 458m 16m 10m S 0.0 0.8 1:21.65 gnome-power-man 3579 20 0 261m 16m 8252 S 0.0 0.8 0:02.65 python 3532 20 0 200m 15m 8144 S 0.3 0.8 1:14.34 metacity 3754 20 0 325m 14m 9856 S 0.0 0.7 0:00.42 mixer_applet2 3909 20 0 243m 14m 7988 S 0.0 0.7 0:06.13 notification-da 3706 20 0 330m 14m 9764 S 0.0 0.7 0:01.40 clock-applet 3534 20 0 449m 13m 9884 S 0.0 0.7 0:00.92 nautilus 3540 20 0 250m 12m 8616 S 0.3 0.6 0:07.30 pk-update-icon 3708 20 0 300m 12m 7940 S 0.0 0.6 0:03.15 gnome-keyboard- 3752 20 0 290m 11m 8028 S 0.0 0.6 0:00.27 gnome-brightnes 3553 20 0 286m 11m 8144 S 0.0 0.6 0:04.29 krb5-auth-dialo 3761 20 0 270m 11m 7968 S 0.0 0.6 0:23.02 cpufreq-applet 2898 20 0 328m 10m 8240 S 0.0 0.5 0:07.95 gnome-settings- 3702 20 0 282m 9436 7460 S 0.0 0.5 0:00.25 drivemount_appl 3749 20 0 288m 8848 6924 S 0.0 0.4 0:00.11 gnome-inhibit-a 3756 20 0 274m 8704 6604 S 0.7 0.4 4:32.99 multiload-apple 3759 20 0 273m 7964 6416 S 0.0 0.4 0:00.33 notification-ar 2827 20 0 267m 6608 5304 S 0.0 0.3 0:00.18 gnome-session 31581 20 0 108m 5764 2000 S 0.0 0.3 0:00.82 gconfd-2 7934 20 0 110m 4960 2372 S 0.0 0.2 0:13.31 fte 3742 20 0 173m 4896 4004 S 0.0 0.2 0:00.40 pam-panel-icon 3531 20 0 215m 4824 3484 S 0.3 0.2 0:24.68 gnome-screensav 2421 20 0 34012 4628 3620 S 0.3 0.2 0:23.85 hald 29575 20 0 109m 4156 2272 S 0.0 0.2 0:00.21 fte 2904 9 -11 186m 3800 2964 S 0.3 0.2 1:37.88 pulseaudio 2752 20 0 176m 3688 2716 S 0.0 0.2 0:00.04 gdm-session-wor 3720 20 0 162m 3552 2932 S 0.0 0.2 0:00.13 gnome-vfs-daemo 2134 20 0 110m 3528 992 S 0.0 0.2 0:00.51 rsyslogd $ cat /proc/meminfo MemTotal: 2007460 kB MemFree: 222332 kB Buffers: 20780 kB Cached: 335400 kB SwapCached: 0 kB Active: 981836 kB Inactive: 532248 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 156 kB Writeback: 0 kB AnonPages: 493208 kB Mapped: 73264 kB Slab: 98552 kB SReclaimable: 57796 kB SUnreclaim: 40756 kB PageTables: 43180 kB NFS_Unstable: 0 kB Bounce: 0 kB CommitLimit: 1003728 kB Committed_AS: 2054396 kB VmallocTotal: 34359738367 kB VmallocUsed: 68536 kB VmallocChunk: 34359668731 kB $ cat /proc/vmstat nr_free_pages 55583 nr_inactive 133077 nr_active 245476 nr_anon_pages 123307 nr_mapped 18318 nr_file_pages 89063 nr_dirty 39 nr_writeback 0 nr_slab_reclaimable 14452 nr_slab_unreclaimable 10190 nr_page_table_pages 10785 nr_unstable 0 nr_bounce 0 nr_vmscan_write 57271 pgpgin 26968249 pgpgout 40773242 pswpin 0 pswpout 0 pgalloc_dma 307982 pgalloc_dma32 46469184 pgalloc_normal 0 pgalloc_movable 0 pgfree 46832935 pgactivate 6847846 pgdeactivate 6616407 pgfault 37817316 pgmajfault 27426 pgrefill_dma 212390 pgrefill_dma32 18516702 pgrefill_normal 0 pgrefill_movable 0 pgsteal_dma 192152 pgsteal_dma32 13101346 pgsteal_normal 0 pgsteal_movable 0 pgscan_kswapd_dma 217294 pgscan_kswapd_dma32 17699659 pgscan_kswapd_normal 0 pgscan_kswapd_movable 0 pgscan_direct_dma 544 pgscan_direct_dma32 52677 pgscan_direct_normal 0 pgscan_direct_movable 0 pginodesteal 282 slabs_scanned 1252864 kswapd_steal 13267510 kswapd_inodesteal 341476 pageoutrun 211214 allocstall 359 pgrotated 14866 $ slabtop -sc Active / Total Objects (% used) : 163039 / 210169 (77.6%) Active / Total Slabs (% used) : 17172 / 17172 (100.0%) Active / Total Caches (% used) : 102 / 124 (82.3%) Active / Total Size (% used) : 82070.16K / 90868.73K (90.3%) Minimum / Average / Maximum Object : 0.08K / 0.43K / 9.66K OBJS ACTIVE USE OBJ SIZE SLABS OBJ/SLAB CACHE SIZE NAME 21810 21809 99% 1.51K 4362 5 34896K ext3_inode_cache 68310 24144 35% 0.17K 2970 23 11880K buffer_head 14298 14267 99% 0.61K 2383 6 9532K radix_tree_node 24804 24791 99% 0.32K 2067 12 8268K dentry 391 391 100% 9.66K 391 1 6256K task_struct 24106 23844 98% 0.23K 1418 17 5672K vm_area_struct 5750 5277 91% 0.38K 575 10 2300K filp 13494 13478 99% 0.15K 519 26 2076K sysfs_dir_cache 406 349 85% 4.07K 58 7 1856K kmalloc-4096 1125 1120 99% 1.37K 225 5 1800K shmem_inode_cache 780 733 93% 2.07K 52 15 1664K kmalloc-2048 990 983 99% 1.15K 165 6 1320K proc_inode_cache 129 129 100% 4.12K 129 1 1032K names_cache I would have save I'm already missing quite a few hundred megabytes... What else would be interesting to see ? Zdenek ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-19 15:05 ` Zdenek Kabelac @ 2008-03-19 15:56 ` Avi Kivity 2008-03-19 17:31 ` Zdenek Kabelac 0 siblings, 1 reply; 13+ messages in thread From: Avi Kivity @ 2008-03-19 15:56 UTC (permalink / raw) To: Zdenek Kabelac; +Cc: kvm-devel Zdenek Kabelac wrote: > 2008/3/16, Avi Kivity <avi@qumranet.com>: > >> Zdenek Kabelac wrote: >> > Hello >> > >> > Recently I'm using qemu-kvm on fedora-rawhide box with my own kernels >> > (with many debug options) I've noticed that over the time my memory >> > seems to disappear somewhere. >> > >> > Here is my memory trace after boot and some time of work - thus memory >> > should be populated. >> > >> >> >> No idea how these should add up. What does 'free' say? >> > > Ok - here goes my free log (I'm loggin free prior each start of my qemu-kvm > so here is the log for this afternoon: > (I'm running same apps all the time - except during kernel compilation > I'm reading some www pages - and working with gnome-terminal - so some > slightly more memory could have been eaten by them - but not in the > range of hundreds of MB) > > Can you make sure that it isn't other processes? Go to runlevel 3 and start the VM using vnc or X-over-network? What host kernel and kvm version are you using? -- error compiling committee.c: too many arguments to function ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-19 15:56 ` Avi Kivity @ 2008-03-19 17:31 ` Zdenek Kabelac 2008-03-19 17:40 ` Avi Kivity 0 siblings, 1 reply; 13+ messages in thread From: Zdenek Kabelac @ 2008-03-19 17:31 UTC (permalink / raw) To: Avi Kivity; +Cc: kvm-devel 2008/3/19, Avi Kivity <avi@qumranet.com>: > Zdenek Kabelac wrote: > > 2008/3/16, Avi Kivity <avi@qumranet.com>: > > > >> Zdenek Kabelac wrote: > >> > Hello > >> > > >> > Recently I'm using qemu-kvm on fedora-rawhide box with my own kernels > >> > (with many debug options) I've noticed that over the time my memory > >> > seems to disappear somewhere. > >> > > >> > Here is my memory trace after boot and some time of work - thus memory > >> > should be populated. > >> > > >> > >> > >> No idea how these should add up. What does 'free' say? > >> > > > > Ok - here goes my free log (I'm loggin free prior each start of my qemu-kvm > > so here is the log for this afternoon: > > (I'm running same apps all the time - except during kernel compilation > > I'm reading some www pages - and working with gnome-terminal - so some > > slightly more memory could have been eaten by them - but not in the > > range of hundreds of MB) > > > > > > > Can you make sure that it isn't other processes? Go to runlevel 3 and > start the VM using vnc or X-over-network? Hmmm not really sure what do you mean by external VNC - I could grab this info once I'll finish some work today and kill all the apps running in the system - so most of the memory should be released - will go to single mode for this - is this what do you want ? > > What host kernel and kvm version are you using? Usually running quite up-to-date Linus git tree kernel - Both host/guest are running 2.6.25-rc6 kernels For compiling using gcc-4.3 kvm itself is fedora rawhide package: kvm-63-2.fc9.x86_64 (somehow I've troubles to compile the kvm-userspace git tree as libkvm mismatches my kernel version - which probably means I would have to use kvm linux kernel to use kvm-userspace ??) (actually why the gcc-3.x is preferred when this compiler is IMHO far more broken then 4.3 ?) I think I've already posted my configuration already several times if it's needed I'll repost again - I've many debugging features enabled for my kernels (yet having no idea how to use them to detect my lost memory :)) Zdenek ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-19 17:31 ` Zdenek Kabelac @ 2008-03-19 17:40 ` Avi Kivity 2008-03-23 9:26 ` Zdenek Kabelac 0 siblings, 1 reply; 13+ messages in thread From: Avi Kivity @ 2008-03-19 17:40 UTC (permalink / raw) To: Zdenek Kabelac; +Cc: kvm-devel Zdenek Kabelac wrote: > 2008/3/19, Avi Kivity <avi@qumranet.com>: > >> Zdenek Kabelac wrote: >> > 2008/3/16, Avi Kivity <avi@qumranet.com>: >> > >> >> Zdenek Kabelac wrote: >> >> > Hello >> >> > >> >> > Recently I'm using qemu-kvm on fedora-rawhide box with my own kernels >> >> > (with many debug options) I've noticed that over the time my memory >> >> > seems to disappear somewhere. >> >> > >> >> > Here is my memory trace after boot and some time of work - thus memory >> >> > should be populated. >> >> > >> >> >> >> >> >> No idea how these should add up. What does 'free' say? >> >> >> > >> > Ok - here goes my free log (I'm loggin free prior each start of my qemu-kvm >> > so here is the log for this afternoon: >> > (I'm running same apps all the time - except during kernel compilation >> > I'm reading some www pages - and working with gnome-terminal - so some >> > slightly more memory could have been eaten by them - but not in the >> > range of hundreds of MB) >> > >> > >> >> >> Can you make sure that it isn't other processes? Go to runlevel 3 and >> start the VM using vnc or X-over-network? >> > > Hmmm not really sure what do you mean by external VNC - I could grab > this info once I'll finish some work today and kill all the apps > running in the system - so most of the memory should be released - > will go to single mode for this - is this what do you want ? > > The -vnc switch, so there's no local X server. A remote X server should be fine as well. Use runlevel 3, which means network but no local X server. >> What host kernel and kvm version are you using? >> > > Usually running quite up-to-date Linus git tree kernel - > Both host/guest are running 2.6.25-rc6 kernels > For compiling using gcc-4.3 > > kvm itself is fedora rawhide package: > kvm-63-2.fc9.x86_64 > > (somehow I've troubles to compile the kvm-userspace git tree as libkvm > mismatches my kernel version - which probably means I would have to > use kvm linux kernel to use kvm-userspace ??) > If running kvm.git, do ./configure --with-patched-kernel. Please report kvm compiler errors. > (actually why the gcc-3.x is preferred when this compiler is IMHO far > more broken then 4.3 ?) > > qemu requires gcc 3. The kernel may be compiled with any gcc that it supports. -- error compiling committee.c: too many arguments to function ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-19 17:40 ` Avi Kivity @ 2008-03-23 9:26 ` Zdenek Kabelac 2008-03-23 10:22 ` Avi Kivity 0 siblings, 1 reply; 13+ messages in thread From: Zdenek Kabelac @ 2008-03-23 9:26 UTC (permalink / raw) To: Avi Kivity; +Cc: kvm-devel [-- Attachment #1: Type: text/plain, Size: 1363 bytes --] 2008/3/19, Avi Kivity <avi@qumranet.com>: > Zdenek Kabelac wrote: > > 2008/3/19, Avi Kivity <avi@qumranet.com>: > > > >> Zdenek Kabelac wrote: > >> > 2008/3/16, Avi Kivity <avi@qumranet.com>: > > The -vnc switch, so there's no local X server. A remote X server should > be fine as well. Use runlevel 3, which means network but no local X server. Ok I've finaly got some time to make a comparable measurements about memory - I'm attaching empty trace log which is from the level where most of processes were killed (as you can see in the 'ps' trace) Then there are attachments after using qemu 7 times (log of free before execution is also attached) Both logs are after 3>/proc/sys/vm/drop_cache So how else I could help with tracking my problem. (I should also probably mention my 'busy loop' with dm_setup - which seems to be caused by some problematic page_fault routine - and I've been testing this issue during this qemu run - from gdb it looks like the code loop in the page_fault call) > > If running kvm.git, do ./configure --with-patched-kernel. Please report > kvm compiler errors. I'll check > > (actually why the gcc-3.x is preferred when this compiler is IMHO far > > more broken then 4.3 ?) > > qemu requires gcc 3. The kernel may be compiled with any gcc that it > supports. Though I only have gcc-4.3 on my system Zdenek [-- Attachment #2: empty --] [-- Type: application/octet-stream, Size: 29217 bytes --] USER PID %CPU %MEM VSZ RSS TTY STAT START TIME COMMAND root 1 0.0 0.0 4076 844 ? Ss 11:58 0:00 /sbin/init root 2 0.0 0.0 0 0 ? S< 11:58 0:00 [kthreadd] root 3 0.0 0.0 0 0 ? S< 11:58 0:00 [migration/0] root 4 0.0 0.0 0 0 ? S< 11:58 0:00 [ksoftirqd/0] root 5 0.0 0.0 0 0 ? S< 11:58 0:00 [watchdog/0] root 6 0.0 0.0 0 0 ? S< 11:58 0:00 [migration/1] root 7 0.0 0.0 0 0 ? S< 11:58 0:00 [ksoftirqd/1] root 8 0.0 0.0 0 0 ? S< 11:58 0:00 [watchdog/1] root 9 0.0 0.0 0 0 ? S< 11:58 0:00 [events/0] root 10 0.0 0.0 0 0 ? S< 11:58 0:00 [events/1] root 11 0.0 0.0 0 0 ? S< 11:58 0:00 [khelper] root 56 0.0 0.0 0 0 ? S< 11:58 0:00 [kblockd/0] root 57 0.0 0.0 0 0 ? S< 11:58 0:00 [kblockd/1] root 59 0.0 0.0 0 0 ? S< 11:58 0:00 [kacpid] root 60 0.0 0.0 0 0 ? S< 11:58 0:00 [kacpi_notify] root 156 0.0 0.0 0 0 ? S< 11:58 0:00 [ata/0] root 157 0.0 0.0 0 0 ? S< 11:58 0:00 [ata/1] root 158 0.0 0.0 0 0 ? S< 11:58 0:00 [ata_aux] root 160 0.0 0.0 0 0 ? S< 11:58 0:00 [kseriod] root 180 0.0 0.0 0 0 ? S< 11:58 0:00 [kondemand/0] root 181 0.0 0.0 0 0 ? S< 11:58 0:00 [kondemand/1] root 207 0.0 0.0 0 0 ? S 11:58 0:00 [pdflush] root 208 0.0 0.0 0 0 ? S 11:58 0:00 [pdflush] root 209 0.0 0.0 0 0 ? S< 11:58 0:00 [kswapd0] root 293 0.0 0.0 0 0 ? S< 11:58 0:00 [aio/0] root 294 0.0 0.0 0 0 ? S< 11:58 0:00 [aio/1] root 444 0.0 0.0 0 0 ? S< 11:58 0:00 [scsi_eh_0] root 446 0.0 0.0 0 0 ? S< 11:58 0:00 [scsi_eh_1] root 448 0.0 0.0 0 0 ? S< 11:58 0:00 [scsi_eh_2] root 464 0.0 0.0 0 0 ? S< 11:58 0:01 [scsi_eh_3] root 466 0.0 0.0 0 0 ? S< 11:58 0:00 [scsi_eh_4] root 523 0.0 0.0 0 0 ? S< 11:58 0:00 [ksuspend_usbd] root 524 0.0 0.0 0 0 ? S< 11:58 0:00 [khubd] root 533 0.0 0.0 0 0 ? S< 11:58 0:00 [kjournald] root 572 0.0 0.0 12900 960 ? S<s 11:58 0:00 /sbin/udevd -d root 1140 0.0 0.0 0 0 ? S< 11:58 0:00 [kauditd] root 1274 0.0 0.0 0 0 ? S< 11:58 0:00 [iwl3945/0] root 1275 0.0 0.0 0 0 ? S< 11:58 0:00 [iwl3945/1] root 1276 0.0 0.0 0 0 ? S< 11:58 0:00 [iwl3945] root 1287 0.0 0.0 0 0 ? S< 11:58 0:00 [kmmcd] root 1331 0.0 0.0 0 0 ? S< 11:58 0:00 [kpsmoused] root 1410 0.0 0.0 0 0 ? S< 11:58 0:00 [mmcqd] root 1489 0.0 0.0 0 0 ? S< 11:58 0:00 [kstriped] root 1505 0.0 0.0 0 0 ? S< 11:58 0:00 [kmpathd/0] root 1506 0.0 0.0 0 0 ? S< 11:58 0:00 [kmpathd/1] root 1535 0.0 0.0 0 0 ? S< 11:59 0:00 [kdmflush] root 1554 0.0 0.0 0 0 ? S< 11:59 0:00 [kdmflush] root 1589 0.0 0.0 0 0 ? S< 11:59 0:00 [kjournald] root 1590 0.0 0.0 0 0 ? S< 11:59 0:00 [kjournald] rpc 2087 0.0 0.0 18804 768 ? Ss 11:59 0:00 rpcbind rpcuser 2107 0.0 0.0 10280 816 ? Ss 11:59 0:00 rpc.statd root 2131 0.0 0.0 0 0 ? S< 11:59 0:00 [rpciod/0] root 2134 0.0 0.0 0 0 ? S< 11:59 0:00 [rpciod/1] root 2141 0.0 0.0 53192 800 ? Ss 11:59 0:00 rpc.idmapd root 2170 0.0 0.1 111188 3380 ? Sl 11:59 0:00 rsyslogd -c 3 root 2235 0.0 0.0 19484 900 ? Ss 11:59 0:00 xinetd -stayalive -pidfile /var/run/xinetd.pid root 2284 0.0 0.0 86452 268 ? Ss 11:59 0:00 rpc.rquotad root 2287 0.0 0.0 0 0 ? S 11:59 0:00 [lockd] root 2288 0.0 0.0 0 0 ? S< 11:59 0:00 [nfsd4] root 2289 0.0 0.0 0 0 ? S 11:59 0:00 [nfsd] root 2290 0.0 0.0 0 0 ? S 11:59 0:00 [nfsd] root 2291 0.0 0.0 0 0 ? S 11:59 0:00 [nfsd] root 2292 0.0 0.0 0 0 ? S 11:59 0:00 [nfsd] root 2293 0.0 0.0 0 0 ? S 11:59 0:00 [nfsd] root 2294 0.0 0.0 0 0 ? S 11:59 0:00 [nfsd] root 2295 0.0 0.0 0 0 ? S 11:59 0:00 [nfsd] root 2296 0.0 0.0 0 0 ? S 11:59 0:00 [nfsd] root 2299 0.0 0.0 23148 376 ? Ss 11:59 0:00 rpc.mountd root 2316 0.0 0.0 93660 1140 ? Ss 11:59 0:00 crond root 2322 0.0 0.0 16540 328 ? Ss 11:59 0:00 /usr/sbin/atd root 2594 0.0 0.0 3916 500 tty4 Ss+ 11:59 0:00 /sbin/mingetty tty4 root 2595 0.0 0.0 3916 496 tty5 Ss+ 11:59 0:00 /sbin/mingetty tty5 root 2597 0.0 0.0 3916 496 tty2 Ss+ 11:59 0:00 /sbin/mingetty tty2 root 2598 0.0 0.0 3916 500 tty3 Ss+ 11:59 0:00 /sbin/mingetty tty3 root 2599 0.0 0.1 109440 2800 ? Ss 11:59 0:00 login -- root root 2600 0.0 0.0 3916 500 tty6 Ss+ 11:59 0:00 /sbin/mingetty tty6 root 3783 0.0 0.0 0 0 ? S< 12:00 0:00 [kjournald] root 3824 0.0 0.0 0 0 ? S< 12:00 0:00 [kjournald] root 9718 0.0 0.0 6084 556 ? SN 13:28 0:00 /usr/bin/inotifywait --quiet --monitor --event create,open,close --exclude (config-|initrd|System.map|Basenames|Conflictname|__db.001|__db.002|__db.003|Dirnames|Filemd5s|Group|Installtid|Name|Packages|Providename|Provideversion|Pubkeys|Requirename|Requireversion|Sha1header|Sigmd5|Triggername) /boot/ /var/lib/rpm/ /usr/src/akmods/ root 9719 0.0 0.0 87596 780 ? SN 13:28 0:00 /bin/bash - /usr/sbin/akmodsd --daemon root 9753 0.1 0.0 87516 1780 tty1 Ss 13:28 0:01 -bash root 10073 4.0 0.0 87208 1008 tty1 R+ 13:37 0:00 ps aux MemTotal: 2007448 kB MemFree: 1957080 kB Buffers: 692 kB Cached: 4748 kB SwapCached: 0 kB Active: 11984 kB Inactive: 1088 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 28 kB Writeback: 0 kB AnonPages: 7700 kB Mapped: 3780 kB Slab: 16908 kB SReclaimable: 2708 kB SUnreclaim: 14200 kB PageTables: 1244 kB NFS_Unstable: 0 kB Bounce: 0 kB CommitLimit: 1003724 kB Committed_AS: 53888 kB VmallocTotal: 34359738367 kB VmallocUsed: 67076 kB VmallocChunk: 34359670267 kB nr_free_pages 489270 nr_inactive 290 nr_active 2991 nr_anon_pages 1920 nr_mapped 945 nr_file_pages 1370 nr_dirty 7 nr_writeback 0 nr_slab_reclaimable 677 nr_slab_unreclaimable 3549 nr_page_table_pages 309 nr_unstable 0 nr_bounce 0 nr_vmscan_write 0 pgpgin 994743 pgpgout 394231 pswpin 0 pswpout 0 pgalloc_dma 4482 pgalloc_dma32 2819700 pgalloc_normal 0 pgalloc_movable 0 pgfree 3313696 pgactivate 116843 pgdeactivate 26646 pgfault 3984749 pgmajfault 4324 pgrefill_dma 699 pgrefill_dma32 51018 pgrefill_normal 0 pgrefill_movable 0 pgsteal_dma 769 pgsteal_dma32 43783 pgsteal_normal 0 pgsteal_movable 0 pgscan_kswapd_dma 769 pgscan_kswapd_dma32 52129 pgscan_kswapd_normal 0 pgscan_kswapd_movable 0 pgscan_direct_dma 0 pgscan_direct_dma32 0 pgscan_direct_normal 0 pgscan_direct_movable 0 pginodesteal 0 slabs_scanned 508160 kswapd_steal 44552 kswapd_inodesteal 0 pageoutrun 807 allocstall 0 pgrotated 0 slabinfo - version: 2.1 # name <active_objs> <num_objs> <objsize> <objperslab> <pagesperslab> : tunables <limit> <batchcount> <sharedfactor> : slabdata <active_slabs> <num_slabs> <sharedavail> fat_inode_cache 6 6 1272 6 2 : tunables 0 0 0 : slabdata 1 1 0 fat_cache 0 0 104 39 1 : tunables 0 0 0 : slabdata 0 0 0 nf_conntrack_expect 0 0 312 13 1 : tunables 0 0 0 : slabdata 0 0 0 nf_conntrack 22 22 368 11 1 : tunables 0 0 0 : slabdata 2 2 0 bridge_fdb_cache 0 0 192 21 1 : tunables 0 0 0 : slabdata 0 0 0 nfsd4_delegations 0 0 344 11 1 : tunables 0 0 0 : slabdata 0 0 0 nfsd4_stateids 0 0 200 20 1 : tunables 0 0 0 : slabdata 0 0 0 nfsd4_files 0 0 144 28 1 : tunables 0 0 0 : slabdata 0 0 0 nfsd4_stateowners 0 0 496 8 1 : tunables 0 0 0 : slabdata 0 0 0 rpc_buffers 9 9 2176 3 2 : tunables 0 0 0 : slabdata 3 3 0 rpc_tasks 17 18 448 9 1 : tunables 0 0 0 : slabdata 2 2 0 rpc_inode_cache 10 10 1472 5 2 : tunables 0 0 0 : slabdata 2 2 0 dm_mpath_io 0 0 112 36 1 : tunables 0 0 0 : slabdata 0 0 0 dm_uevent 0 0 2680 3 2 : tunables 0 0 0 : slabdata 0 0 0 dm_target_io 546 546 96 42 1 : tunables 0 0 0 : slabdata 13 13 0 dm_io 540 540 112 36 1 : tunables 0 0 0 : slabdata 15 15 0 kmalloc_dma-512 7 7 584 7 1 : tunables 0 0 0 : slabdata 1 1 0 uhci_urb_priv 64 64 128 32 1 : tunables 0 0 0 : slabdata 2 2 0 UNIX 20 35 1472 5 2 : tunables 0 0 0 : slabdata 7 7 0 flow_cache 0 0 168 24 1 : tunables 0 0 0 : slabdata 0 0 0 scsi_sense_cache 42 42 192 21 1 : tunables 0 0 0 : slabdata 2 2 0 scsi_cmd_cache 18 18 448 9 1 : tunables 0 0 0 : slabdata 2 2 0 cfq_io_context 49 108 224 18 1 : tunables 0 0 0 : slabdata 6 6 0 cfq_queue 49 95 208 19 1 : tunables 0 0 0 : slabdata 5 5 0 mqueue_inode_cache 5 5 1536 5 2 : tunables 0 0 0 : slabdata 1 1 0 ext2_inode_cache 0 0 1584 5 2 : tunables 0 0 0 : slabdata 0 0 0 ext2_xattr 0 0 160 25 1 : tunables 0 0 0 : slabdata 0 0 0 journal_handle 64 64 128 32 1 : tunables 0 0 0 : slabdata 2 2 0 journal_head 68 144 168 24 1 : tunables 0 0 0 : slabdata 6 6 0 revoke_table 92 92 88 46 1 : tunables 0 0 0 : slabdata 2 2 0 revoke_record 64 64 128 32 1 : tunables 0 0 0 : slabdata 2 2 0 ext3_inode_cache 199 420 1544 5 2 : tunables 0 0 0 : slabdata 84 84 0 ext3_xattr 50 50 160 25 1 : tunables 0 0 0 : slabdata 2 2 0 dnotify_cache 36 36 112 36 1 : tunables 0 0 0 : slabdata 1 1 0 inotify_event_cache 72 72 112 36 1 : tunables 0 0 0 : slabdata 2 2 0 inotify_watch_cache 59 112 144 28 1 : tunables 0 0 0 : slabdata 4 4 0 kioctx 0 0 640 6 1 : tunables 0 0 0 : slabdata 0 0 0 kiocb 0 0 320 12 1 : tunables 0 0 0 : slabdata 0 0 0 fasync_cache 84 84 96 42 1 : tunables 0 0 0 : slabdata 2 2 0 shmem_inode_cache 1039 1050 1400 5 2 : tunables 0 0 0 : slabdata 210 210 0 nsproxy 0 0 128 32 1 : tunables 0 0 0 : slabdata 0 0 0 posix_timers_cache 0 0 320 12 1 : tunables 0 0 0 : slabdata 0 0 0 uid_cache 24 24 320 12 1 : tunables 0 0 0 : slabdata 2 2 0 ip_mrt_cache 0 0 192 21 1 : tunables 0 0 0 : slabdata 0 0 0 UDP-Lite 0 0 1344 6 2 : tunables 0 0 0 : slabdata 0 0 0 tcp_bind_bucket 70 128 128 32 1 : tunables 0 0 0 : slabdata 4 4 0 inet_peer_cache 0 0 192 21 1 : tunables 0 0 0 : slabdata 0 0 0 secpath_cache 0 0 128 32 1 : tunables 0 0 0 : slabdata 0 0 0 xfrm_dst_cache 0 0 448 9 1 : tunables 0 0 0 : slabdata 0 0 0 ip_fib_alias 0 0 104 39 1 : tunables 0 0 0 : slabdata 0 0 0 ip_fib_hash 56 56 144 28 1 : tunables 0 0 0 : slabdata 2 2 0 ip_dst_cache 20 20 384 10 1 : tunables 0 0 0 : slabdata 2 2 0 arp_cache 18 18 448 9 1 : tunables 0 0 0 : slabdata 2 2 0 RAW 12 12 1280 6 2 : tunables 0 0 0 : slabdata 2 2 0 UDP 20 30 1344 6 2 : tunables 0 0 0 : slabdata 5 5 0 tw_sock_TCP 32 32 256 16 1 : tunables 0 0 0 : slabdata 2 2 0 request_sock_TCP 21 21 192 21 1 : tunables 0 0 0 : slabdata 1 1 0 TCP 12 15 2304 3 2 : tunables 0 0 0 : slabdata 5 5 0 eventpoll_pwq 56 56 144 28 1 : tunables 0 0 0 : slabdata 2 2 0 eventpoll_epi 32 32 256 16 1 : tunables 0 0 0 : slabdata 2 2 0 sgpool-128 4 4 5248 1 2 : tunables 0 0 0 : slabdata 4 4 0 sgpool-64 8 9 2688 3 2 : tunables 0 0 0 : slabdata 3 3 0 sgpool-32 10 10 1408 5 2 : tunables 0 0 0 : slabdata 2 2 0 sgpool-16 10 10 768 5 1 : tunables 0 0 0 : slabdata 2 2 0 sgpool-8 18 18 448 9 1 : tunables 0 0 0 : slabdata 2 2 0 scsi_bidi_sdb 0 0 96 42 1 : tunables 0 0 0 : slabdata 0 0 0 scsi_io_context 0 0 184 22 1 : tunables 0 0 0 : slabdata 0 0 0 blkdev_queue 21 21 2256 3 2 : tunables 0 0 0 : slabdata 7 7 0 blkdev_requests 30 33 368 11 1 : tunables 0 0 0 : slabdata 3 3 0 blkdev_ioc 52 120 200 20 1 : tunables 0 0 0 : slabdata 6 6 0 biovec-256 34 34 4224 1 2 : tunables 0 0 0 : slabdata 34 34 0 biovec-128 36 36 2176 3 2 : tunables 0 0 0 : slabdata 12 12 0 biovec-64 48 49 1152 7 2 : tunables 0 0 0 : slabdata 7 7 0 biovec-16 52 60 384 10 1 : tunables 0 0 0 : slabdata 6 6 0 biovec-4 74 84 192 21 1 : tunables 0 0 0 : slabdata 4 4 0 biovec-1 118 126 96 42 1 : tunables 0 0 0 : slabdata 3 3 0 bio 74 84 192 21 1 : tunables 0 0 0 : slabdata 4 4 0 sock_inode_cache 45 60 1280 6 2 : tunables 0 0 0 : slabdata 10 10 0 skbuff_fclone_cache 14 14 576 7 1 : tunables 0 0 0 : slabdata 2 2 0 skbuff_head_cache 333 516 320 12 1 : tunables 0 0 0 : slabdata 43 43 0 file_lock_cache 26 26 304 13 1 : tunables 0 0 0 : slabdata 2 2 0 Acpi-Operand 3142 3180 136 30 1 : tunables 0 0 0 : slabdata 106 106 0 Acpi-ParseExt 60 60 136 30 1 : tunables 0 0 0 : slabdata 2 2 0 Acpi-Parse 72 72 112 36 1 : tunables 0 0 0 : slabdata 2 2 0 Acpi-State 52 52 152 26 1 : tunables 0 0 0 : slabdata 2 2 0 Acpi-Namespace 1950 1950 104 39 1 : tunables 0 0 0 : slabdata 50 50 0 proc_inode_cache 440 444 1176 6 2 : tunables 0 0 0 : slabdata 74 74 0 sigqueue 34 34 232 17 1 : tunables 0 0 0 : slabdata 2 2 0 radix_tree_node 473 816 624 6 1 : tunables 0 0 0 : slabdata 136 136 0 bdev_cache 35 35 1536 5 2 : tunables 0 0 0 : slabdata 7 7 0 sysfs_dir_cache 12799 12870 152 26 1 : tunables 0 0 0 : slabdata 495 495 0 mnt_cache 48 48 320 12 1 : tunables 0 0 0 : slabdata 4 4 0 inode_cache 94 154 1144 7 2 : tunables 0 0 0 : slabdata 22 22 0 dentry 1784 2904 328 12 1 : tunables 0 0 0 : slabdata 242 242 0 filp 281 550 384 10 1 : tunables 0 0 0 : slabdata 55 55 0 names_cache 2 2 4224 1 2 : tunables 0 0 0 : slabdata 2 2 0 idr_layer_cache 249 258 600 6 1 : tunables 0 0 0 : slabdata 43 43 0 buffer_head 242 483 176 23 1 : tunables 0 0 0 : slabdata 21 21 0 mm_struct 31 72 1280 6 2 : tunables 0 0 0 : slabdata 12 12 0 vm_area_struct 825 1360 240 17 1 : tunables 0 0 0 : slabdata 80 80 0 fs_cache 67 126 192 21 1 : tunables 0 0 0 : slabdata 6 6 0 files_cache 28 44 896 4 1 : tunables 0 0 0 : slabdata 11 11 0 signal_cache 90 116 960 4 1 : tunables 0 0 0 : slabdata 29 29 0 sighand_cache 88 105 2304 3 2 : tunables 0 0 0 : slabdata 35 35 0 task_struct 86 86 9888 1 4 : tunables 0 0 0 : slabdata 86 86 0 anon_vma 364 812 144 28 1 : tunables 0 0 0 : slabdata 29 29 0 pid 126 231 192 21 1 : tunables 0 0 0 : slabdata 11 11 0 kmalloc-4096 382 392 4168 7 8 : tunables 0 0 0 : slabdata 56 56 0 kmalloc-2048 381 510 2120 15 8 : tunables 0 0 0 : slabdata 34 34 0 kmalloc-1024 380 435 1096 29 8 : tunables 0 0 0 : slabdata 15 15 0 kmalloc-512 420 455 584 7 1 : tunables 0 0 0 : slabdata 65 65 0 kmalloc-256 545 588 328 12 1 : tunables 0 0 0 : slabdata 49 49 0 kmalloc-128 355 380 200 20 1 : tunables 0 0 0 : slabdata 19 19 0 kmalloc-64 1788 2340 136 30 1 : tunables 0 0 0 : slabdata 78 78 0 kmalloc-32 683 780 104 39 1 : tunables 0 0 0 : slabdata 20 20 0 kmalloc-16 2471 2530 88 46 1 : tunables 0 0 0 : slabdata 55 55 0 kmalloc-8 3125 3213 80 51 1 : tunables 0 0 0 : slabdata 63 63 0 kmalloc-192 257 300 264 15 1 : tunables 0 0 0 : slabdata 20 20 0 kmalloc-96 1710 1824 168 24 1 : tunables 0 0 0 : slabdata 76 76 0 Name Objects Objsize Space Slabs/Part/Cpu O/S O %Fr %Ef Flg Acpi-Namespace 1950 32 204.8K 50/0/0 39 0 0 30 PZFU Acpi-Operand 3142 64 434.1K 106/10/0 30 0 9 46 PZFU Acpi-Parse 72 40 8.1K 2/0/0 36 0 0 35 PZFU Acpi-ParseExt 60 64 8.1K 2/0/0 30 0 0 46 PZFU Acpi-State 52 80 8.1K 2/0/0 26 0 0 50 PZFU anon_vma 364 72 118.7K 29/25/0 28 0 86 22 PZFU arp_cache 18 348 8.1K 2/0/0 9 0 0 76 APZFU bdev_cache 35 1432 57.3K 7/0/0 5 1 0 87 APaZFU bio 74 104 16.3K 4/1/0 21 0 25 46 APZFU biovec-1 118 16 12.2K 3/1/0 42 0 33 15 APZFU biovec-128 36 2048 98.3K 12/0/0 3 1 0 75 APZFU biovec-16 52 256 24.5K 6/1/0 10 0 16 54 APZFU biovec-256 34 4096 278.5K 34/0/0 1 1 0 50 APZFU biovec-4 74 64 16.3K 4/1/0 21 0 25 28 APZFU biovec-64 48 1024 57.3K 7/1/0 7 1 14 85 APZFU blkdev_ioc 52 128 24.5K 6/4/0 20 0 66 27 PZFU blkdev_queue 21 2184 57.3K 7/0/0 3 1 0 79 PZFU blkdev_requests 30 296 12.2K 3/1/0 11 0 33 72 PZFU buffer_head 257 104 86.0K 21/12/0 23 0 57 31 PaZFU cfq_io_context 49 152 24.5K 6/4/0 18 0 66 30 PZFU cfq_queue 49 136 20.4K 5/3/0 19 0 60 32 PZFU dentry 6228 256 2.1M 519/0/0 12 0 0 75 PaZFU dm_io 540 40 61.4K 15/0/0 36 0 0 35 PZFU dm_target_io 546 24 53.2K 13/0/0 42 0 0 24 PZFU dnotify_cache 36 40 4.0K 1/0/0 36 0 0 35 PZFU eventpoll_epi 32 128 8.1K 2/0/0 16 0 0 50 APZFU eventpoll_pwq 56 72 8.1K 2/0/0 28 0 0 49 PZFU ext3_inode_cache 203 1472 688.1K 84/66/0 5 1 78 43 PaZFU ext3_xattr 50 88 8.1K 2/0/0 25 0 0 53 PaZFU fasync_cache 84 24 8.1K 2/0/0 42 0 0 24 PZFU fat_inode_cache 6 1200 8.1K 1/0/0 6 1 0 87 PaZFU file_lock_cache 26 232 8.1K 2/0/0 13 0 0 73 PZFU files_cache 28 768 45.0K 11/7/0 4 0 63 47 APZFU filp 620 288 258.0K 63/0/0 10 0 0 69 APZFU fs_cache 67 120 24.5K 6/4/0 21 0 66 32 APZFU idr_layer_cache 249 528 176.1K 43/5/0 6 0 11 74 PZFU inode_cache 4494 1072 5.2M 642/0/0 7 1 0 91 PaZFU inotify_event_cache 72 40 8.1K 2/0/0 36 0 0 35 PZFU inotify_watch_cache 59 72 16.3K 4/2/0 28 0 50 25 PZFU ip_dst_cache 20 312 8.1K 2/0/0 10 0 0 76 APZFU ip_fib_hash 56 72 8.1K 2/0/0 28 0 0 49 PZFU journal_handle 64 56 8.1K 2/0/0 32 0 0 43 PaZFU journal_head 68 96 24.5K 6/4/0 24 0 66 26 PaZFU kmalloc-1024 380 1024 491.5K 15/8/0 29 3 53 79 PZFU kmalloc-128 355 128 77.8K 19/5/0 20 0 26 58 PZFU kmalloc-16 2471 16 225.2K 55/5/0 46 0 9 17 PZFU kmalloc-192 257 192 81.9K 20/5/0 15 0 25 60 PZFU kmalloc-2048 381 2048 1.1M 34/13/0 15 3 38 70 PZFU kmalloc-256 545 256 200.7K 49/7/0 12 0 14 69 PZFU kmalloc-32 683 32 81.9K 20/6/0 39 0 30 26 PZFU kmalloc-4096 382 4096 1.8M 56/3/0 7 3 5 85 PZFU kmalloc-512 420 512 266.2K 65/12/0 7 0 18 80 PZFU kmalloc-64 1788 64 319.4K 78/30/0 30 0 38 35 PZFU kmalloc-8 3125 8 258.0K 63/8/0 51 0 12 9 PZFU kmalloc-96 1722 96 311.2K 76/9/0 24 0 11 53 PZFU kmalloc_dma-512 7 512 4.0K 1/0/0 7 0 0 87 dPZFU mm_struct 31 1176 98.3K 12/10/0 6 1 83 37 APZFU mnt_cache 48 208 16.3K 4/0/0 12 0 0 60 APZFU mqueue_inode_cache 5 1456 8.1K 1/0/0 5 1 0 88 APZFU names_cache 2 4096 16.3K 2/0/0 1 1 0 50 APZFU nf_conntrack 22 296 8.1K 2/0/0 11 0 0 79 PZFU pid 126 88 45.0K 11/9/0 21 0 81 24 APZFU proc_inode_cache 462 1104 630.7K 77/0/0 6 1 0 80 PaZFU radix_tree_node 483 552 557.0K 136/96/0 6 0 70 47 PZFU RAW 12 1200 16.3K 2/0/0 6 1 0 87 APZFU request_sock_TCP 21 88 4.0K 1/0/0 21 0 0 45 APZFU revoke_record 64 32 8.1K 2/0/0 32 0 0 25 APaZFU revoke_table 92 16 8.1K 2/0/0 46 0 0 17 PaZFU rpc_buffers 9 2048 24.5K 3/0/0 3 1 0 75 APZFU rpc_inode_cache 10 1376 16.3K 2/0/0 5 1 0 83 APaZFU rpc_tasks 17 352 8.1K 2/1/0 9 0 50 73 APZFU scsi_cmd_cache 18 320 8.1K 2/0/0 9 0 0 70 APZFU scsi_sense_cache 42 96 8.1K 2/0/0 21 0 0 49 APZFU sgpool-128 4 5120 32.7K 4/0/0 1 1 0 62 APZFU sgpool-16 10 640 8.1K 2/0/0 5 0 0 78 APZFU sgpool-32 10 1280 16.3K 2/0/0 5 1 0 78 APZFU sgpool-64 8 2560 24.5K 3/1/0 3 1 33 83 APZFU sgpool-8 18 320 8.1K 2/0/0 9 0 0 70 APZFU shmem_inode_cache 1039 1328 1.7M 210/4/0 5 1 1 80 PZFU sighand_cache 88 2184 286.7K 35/11/0 3 1 31 67 APZFU signal_cache 90 880 118.7K 29/15/0 4 0 51 66 APZFU sigqueue 34 160 8.1K 2/0/0 17 0 0 66 PZFU skbuff_fclone_cache 14 452 8.1K 2/0/0 7 0 0 77 APZFU skbuff_head_cache 333 224 176.1K 43/41/0 12 0 95 42 APZFU sock_inode_cache 45 1200 81.9K 10/6/0 6 1 60 65 APaZFU sysfs_dir_cache 12799 80 2.0M 495/11/0 26 0 2 50 PZFU task_struct 86 9808 1.4M 86/0/0 1 2 0 59 PZFU TCP 12 2200 40.9K 5/2/0 3 1 40 64 APZFU tcp_bind_bucket 70 40 16.3K 4/2/0 32 0 50 17 APZFU tw_sock_TCP 32 144 8.1K 2/0/0 16 0 0 56 APZFU UDP 20 1224 40.9K 5/3/0 6 1 60 59 APZFU uhci_urb_priv 64 56 8.1K 2/0/0 32 0 0 43 PZFU uid_cache 24 208 8.1K 2/0/0 12 0 0 60 APZFU UNIX 20 1376 57.3K 7/4/0 5 1 57 47 APZFU vm_area_struct 814 168 327.6K 80/59/0 17 0 73 41 PZFU [-- Attachment #3: leaked.runlog --] [-- Type: application/octet-stream, Size: 1820 bytes --] Sat Mar 22 21:09:48 CET 2008 total used free shared buffers cached Mem: 2007448 1669756 337692 0 34028 988040 -/+ buffers/cache: 647688 1359760 Swap: 0 0 0 Sat Mar 22 22:12:34 CET 2008 total used free shared buffers cached Mem: 2007448 1483300 524148 0 25660 809800 -/+ buffers/cache: 647840 1359608 Swap: 0 0 0 Sat Mar 22 22:23:35 CET 2008 total used free shared buffers cached Mem: 2007448 1604092 403356 0 26472 906352 -/+ buffers/cache: 671268 1336180 Swap: 0 0 0 Sat Mar 22 23:30:09 CET 2008 total used free shared buffers cached Mem: 2007448 1676232 331216 0 27920 930184 -/+ buffers/cache: 718128 1289320 Swap: 0 0 0 Sat Mar 22 23:38:06 CET 2008 total used free shared buffers cached Mem: 2007448 1788520 218928 0 28380 1011280 -/+ buffers/cache: 748860 1258588 Swap: 0 0 0 Sat Mar 22 23:51:14 CET 2008 total used free shared buffers cached Mem: 2007448 1980800 26648 0 49824 1098728 -/+ buffers/cache: 832248 1175200 Swap: 0 0 0 Sun Mar 23 01:05:20 CET 2008 total used free shared buffers cached Mem: 2007448 1745896 261552 0 52804 804832 -/+ buffers/cache: 888260 1119188 Swap: 0 0 0 [-- Attachment #4: leaked.meminfo --] [-- Type: application/octet-stream, Size: 630 bytes --] MemTotal: 2007448 kB MemFree: 1552484 kB Buffers: 848 kB Cached: 7984 kB SwapCached: 0 kB Active: 130932 kB Inactive: 284432 kB SwapTotal: 0 kB SwapFree: 0 kB Dirty: 24 kB Writeback: 0 kB AnonPages: 8844 kB Mapped: 4708 kB Slab: 18656 kB SReclaimable: 3412 kB SUnreclaim: 15244 kB PageTables: 1480 kB NFS_Unstable: 0 kB Bounce: 0 kB CommitLimit: 1003724 kB Committed_AS: 55792 kB VmallocTotal: 34359738367 kB VmallocUsed: 68152 kB VmallocChunk: 34359668731 kB [-- Attachment #5: leaked.free --] [-- Type: application/octet-stream, Size: 230 bytes --] total used free shared buffers cached Mem: 2007448 454992 1552456 0 964 8020 -/+ buffers/cache: 446008 1561440 Swap: 0 0 0 [-- Attachment #6: leaked.slabinfo --] [-- Type: application/octet-stream, Size: 8607 bytes --] Name Objects Objsize Space Slabs/Part/Cpu O/S O %Fr %Ef Flg inode_cache 4676 1072 5.4M 668/0/0 7 1 0 91 PaZFU dentry 6696 256 2.2M 558/0/0 12 0 0 75 PaZFU sysfs_dir_cache 13180 80 2.0M 509/9/0 26 0 1 50 PZFU kmalloc-4096 389 4096 1.8M 57/4/0 7 3 7 85 PZFU shmem_inode_cache 1058 1328 1.7M 215/9/0 5 1 4 79 PZFU task_struct 90 9808 1.4M 90/0/0 1 2 0 59 PZFU radix_tree_node 729 552 1.0M 260/219/0 6 0 84 37 PZFU kmalloc-2048 390 2048 1.0M 31/12/0 15 3 38 78 PZFU ext3_inode_cache 306 1472 966.6K 118/88/0 5 1 74 46 PaZFU proc_inode_cache 551 1104 761.8K 93/2/0 6 1 2 79 PaZFU kmalloc-1024 387 1024 557.0K 17/7/0 29 3 41 71 PZFU Acpi-Operand 3194 64 438.2K 107/6/0 30 0 5 46 PZFU kmalloc-64 1942 64 421.8K 103/54/0 30 0 52 29 PZFU vm_area_struct 1009 168 397.3K 97/71/0 17 0 73 42 PZFU kmalloc-96 1733 96 315.3K 77/10/0 24 0 12 52 PZFU sighand_cache 90 2184 311.2K 38/17/0 3 1 44 63 APZFU filp 551 288 286.7K 70/28/0 10 0 40 55 APZFU kmalloc-512 435 512 278.5K 68/12/0 7 0 17 79 PZFU biovec-256 34 4096 278.5K 34/0/0 1 1 0 50 APZFU kmalloc-8 3304 8 270.3K 66/8/0 51 0 12 9 PZFU kmalloc-16 2493 16 225.2K 55/5/0 46 0 9 17 PZFU idr_layer_cache 275 528 208.8K 51/10/0 6 0 19 69 PZFU Acpi-Namespace 1950 32 204.8K 50/0/0 39 0 0 30 PZFU kmalloc-256 548 256 200.7K 49/7/0 12 0 14 69 PZFU buffer_head 371 104 139.2K 34/24/0 23 0 70 27 PaZFU skbuff_head_cache 336 224 131.0K 32/10/0 12 0 31 57 APZFU signal_cache 93 880 122.8K 30/13/0 4 0 43 66 APZFU anon_vma 434 72 110.5K 27/22/0 28 0 81 28 PZFU biovec-128 38 2048 106.4K 13/1/0 3 1 7 73 APZFU sock_inode_cache 53 1200 106.4K 13/7/0 6 1 53 59 APaZFU blkdev_queue 33 2184 90.1K 11/0/0 3 1 0 79 PZFU kmalloc-192 260 192 86.0K 21/7/0 15 0 33 58 PZFU kmalloc-32 716 32 81.9K 20/5/0 39 0 25 27 PZFU kmalloc-128 379 128 81.9K 20/4/0 20 0 20 59 PZFU mm_struct 34 1176 81.9K 10/8/0 6 1 80 48 APZFU UNIX 27 1376 65.5K 8/6/0 5 1 75 56 APZFU dm_io 540 40 61.4K 15/0/0 36 0 0 35 PZFU bdev_cache 35 1432 57.3K 7/0/0 5 1 0 87 APaZFU biovec-64 48 1024 57.3K 7/1/0 7 1 14 85 APZFU pid 134 88 53.2K 13/11/0 21 0 84 22 APZFU files_cache 31 768 53.2K 13/10/0 4 0 76 44 APZFU dm_target_io 546 24 53.2K 13/0/0 42 0 0 24 PZFU TCP 13 2200 40.9K 5/2/0 3 1 40 69 APZFU UDP 20 1224 32.7K 4/2/0 6 1 50 74 APZFU sgpool-128 4 5120 32.7K 4/0/0 1 1 0 62 APZFU cfq_io_context 59 152 32.7K 8/6/0 18 0 75 27 PZFU blkdev_ioc 62 128 28.6K 7/5/0 20 0 71 27 PZFU cfq_queue 58 136 28.6K 7/5/0 19 0 71 27 PZFU biovec-16 54 256 24.5K 6/1/0 10 0 16 56 APZFU sgpool-64 8 2560 24.5K 3/1/0 3 1 33 83 APZFU rpc_buffers 9 2048 24.5K 3/0/0 3 1 0 75 APZFU fs_cache 70 120 20.4K 5/3/0 21 0 60 41 APZFU journal_head 57 96 20.4K 5/3/0 24 0 60 26 PaZFU sgpool-32 10 1280 16.3K 2/0/0 5 1 0 78 APZFU inotify_watch_cache 60 72 16.3K 4/2/0 28 0 50 26 PZFU kvm_vcpu 2 5488 16.3K 2/0/0 1 1 0 66 PZFU names_cache 2 4096 16.3K 2/0/0 1 1 0 50 APZFU bio 76 104 16.3K 4/1/0 21 0 25 48 APZFU rpc_inode_cache 10 1376 16.3K 2/0/0 5 1 0 83 APaZFU RAW 12 1200 16.3K 2/0/0 6 1 0 87 APZFU nf_conntrack 24 296 16.3K 4/2/0 11 0 50 43 PZFU fat_inode_cache 7 1200 16.3K 2/1/0 6 1 50 51 PaZFU biovec-1 118 16 12.2K 3/1/0 42 0 33 15 APZFU mnt_cache 34 208 12.2K 3/1/0 12 0 33 57 APZFU blkdev_requests 30 296 12.2K 3/1/0 11 0 33 72 PZFU tcp_bind_bucket 69 40 12.2K 3/1/0 32 0 33 22 APZFU biovec-4 63 64 12.2K 3/0/0 21 0 0 32 APZFU file_lock_cache 28 232 12.2K 3/1/0 13 0 33 52 PZFU Acpi-State 52 80 8.1K 2/0/0 26 0 0 50 PZFU ip_fib_hash 56 72 8.1K 2/0/0 28 0 0 49 PZFU eventpoll_pwq 56 72 8.1K 2/0/0 28 0 0 49 PZFU fasync_cache 84 24 8.1K 2/0/0 42 0 0 24 PZFU sigqueue 34 160 8.1K 2/0/0 17 0 0 66 PZFU inotify_event_cache 72 40 8.1K 2/0/0 36 0 0 35 PZFU ext3_xattr 50 88 8.1K 2/0/0 25 0 0 53 PaZFU eventpoll_epi 32 128 8.1K 2/0/0 16 0 0 50 APZFU revoke_record 64 32 8.1K 2/0/0 32 0 0 25 APaZFU revoke_table 92 16 8.1K 2/0/0 46 0 0 17 PaZFU ip_dst_cache 20 312 8.1K 2/0/0 10 0 0 76 APZFU journal_handle 64 56 8.1K 2/0/0 32 0 0 43 PaZFU mqueue_inode_cache 5 1456 8.1K 1/0/0 5 1 0 88 APZFU arp_cache 18 348 8.1K 2/0/0 9 0 0 76 APZFU uid_cache 24 208 8.1K 2/0/0 12 0 0 60 APZFU scsi_cmd_cache 18 320 8.1K 2/0/0 9 0 0 70 APZFU scsi_sense_cache 42 96 8.1K 2/0/0 21 0 0 49 APZFU sgpool-16 10 640 8.1K 2/0/0 5 0 0 78 APZFU uhci_urb_priv 64 56 8.1K 2/0/0 32 0 0 43 PZFU kvm_pte_chain 64 56 8.1K 2/0/0 32 0 0 43 PZFU kvm_rmap_desc 72 40 8.1K 2/0/0 36 0 0 35 PZFU kvm_mmu_page_header 50 88 8.1K 2/0/0 25 0 0 53 PZFU sgpool-8 18 320 8.1K 2/0/0 9 0 0 70 APZFU skbuff_fclone_cache 14 452 8.1K 2/0/0 7 0 0 77 APZFU posix_timers_cache 24 248 8.1K 2/0/0 12 0 0 72 PZFU tw_sock_TCP 32 144 8.1K 2/0/0 16 0 0 56 APZFU rpc_tasks 17 352 8.1K 2/1/0 9 0 50 73 APZFU request_sock_TCP 42 88 8.1K 2/0/0 21 0 0 45 APZFU Acpi-ParseExt 60 64 8.1K 2/0/0 30 0 0 46 PZFU Acpi-Parse 72 40 8.1K 2/0/0 36 0 0 35 PZFU kmalloc_dma-512 7 512 4.0K 1/0/0 7 0 0 87 dPZFU ip_fib_alias 39 32 4.0K 1/0/0 39 0 0 30 PZFU dnotify_cache 36 40 4.0K 1/0/0 36 0 0 35 PZFU inet_peer_cache 21 64 4.0K 1/0/0 21 0 0 32 APZFU [-- Attachment #7: leaked.vmstat --] [-- Type: application/octet-stream, Size: 944 bytes --] nr_free_pages 388135 nr_inactive 71118 nr_active 32735 nr_anon_pages 2209 nr_mapped 1177 nr_file_pages 2220 nr_dirty 8 nr_writeback 0 nr_slab_reclaimable 853 nr_slab_unreclaimable 3807 nr_page_table_pages 368 nr_unstable 0 nr_bounce 0 nr_vmscan_write 1546 pgpgin 4478462 pgpgout 5879067 pswpin 0 pswpout 0 pgalloc_dma 123316 pgalloc_dma32 70502689 pgalloc_normal 0 pgalloc_movable 0 pgfree 71014329 pgactivate 649329 pgdeactivate 504519 pgfault 95794801 pgmajfault 7341 pgrefill_dma 13592 pgrefill_dma32 1215553 pgrefill_normal 0 pgrefill_movable 0 pgsteal_dma 19534 pgsteal_dma32 1303074 pgsteal_normal 0 pgsteal_movable 0 pgscan_kswapd_dma 21066 pgscan_kswapd_dma32 1394109 pgscan_kswapd_normal 0 pgscan_kswapd_movable 0 pgscan_direct_dma 32 pgscan_direct_dma32 10244 pgscan_direct_normal 0 pgscan_direct_movable 0 pginodesteal 0 slabs_scanned 473856 kswapd_steal 1312332 kswapd_inodesteal 88626 pageoutrun 22494 allocstall 160 pgrotated 430 [-- Attachment #8: leaked.ps --] [-- Type: application/postscript, Size: 7026 bytes --] [-- Attachment #9: Type: text/plain, Size: 228 bytes --] ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ [-- Attachment #10: Type: text/plain, Size: 158 bytes --] _______________________________________________ kvm-devel mailing list kvm-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/kvm-devel ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-23 9:26 ` Zdenek Kabelac @ 2008-03-23 10:22 ` Avi Kivity 2008-03-23 12:20 ` Avi Kivity 0 siblings, 1 reply; 13+ messages in thread From: Avi Kivity @ 2008-03-23 10:22 UTC (permalink / raw) To: Zdenek Kabelac; +Cc: kvm-devel Zdenek Kabelac wrote: > 2008/3/19, Avi Kivity <avi@qumranet.com>: > >> Zdenek Kabelac wrote: >> > 2008/3/19, Avi Kivity <avi@qumranet.com>: >> > >> >> Zdenek Kabelac wrote: >> >> > 2008/3/16, Avi Kivity <avi@qumranet.com>: >> >> The -vnc switch, so there's no local X server. A remote X server should >> be fine as well. Use runlevel 3, which means network but no local X server. >> > > Ok I've finaly got some time to make a comparable measurements about memory - > > I'm attaching empty trace log which is from the level where most of > processes were killed (as you can see in the 'ps' trace) > > Then there are attachments after using qemu 7 times (log of free > before execution is also attached) > > Both logs are after 3>/proc/sys/vm/drop_cache > > I see the same issue too now, and am investigating. -- error compiling committee.c: too many arguments to function ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-23 10:22 ` Avi Kivity @ 2008-03-23 12:20 ` Avi Kivity 2008-03-23 23:06 ` Zdenek Kabelac 0 siblings, 1 reply; 13+ messages in thread From: Avi Kivity @ 2008-03-23 12:20 UTC (permalink / raw) To: Zdenek Kabelac; +Cc: kvm-devel [-- Attachment #1: Type: text/plain, Size: 276 bytes --] Avi Kivity wrote: > > I see the same issue too now, and am investigating. > The attached patch should fix the issue. It is present in 2.6.25-rc6 only, and not in kvm.git, which is why few people noticed it. -- error compiling committee.c: too many arguments to function [-- Attachment #2: fix-kvm-2.6.25-rc6-leak.patch --] [-- Type: text/x-patch, Size: 463 bytes --] diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 4ba85d9..e55af12 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -1412,7 +1412,7 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, up_read(¤t->mm->mmap_sem); vcpu->arch.update_pte.gfn = gfn; - vcpu->arch.update_pte.page = gfn_to_page(vcpu->kvm, gfn); + vcpu->arch.update_pte.page = page; } void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, [-- Attachment #3: Type: text/plain, Size: 228 bytes --] ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ [-- Attachment #4: Type: text/plain, Size: 158 bytes --] _______________________________________________ kvm-devel mailing list kvm-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/kvm-devel ^ permalink raw reply related [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-23 12:20 ` Avi Kivity @ 2008-03-23 23:06 ` Zdenek Kabelac 2008-03-24 10:09 ` Avi Kivity 0 siblings, 1 reply; 13+ messages in thread From: Zdenek Kabelac @ 2008-03-23 23:06 UTC (permalink / raw) To: Avi Kivity; +Cc: kvm-devel 2008/3/23, Avi Kivity <avi@qumranet.com>: > Avi Kivity wrote: > > > > I see the same issue too now, and am investigating. > > > > > The attached patch should fix the issue. It is present in 2.6.25-rc6 > only, and not in kvm.git, which is why few people noticed it. > Hi Tested - and actually seeing no difference in my case of memory leak. Still it looks like over 30M per execution of qemu is lost. (tested with fresh 2.6.25-rc6 with your patch) Also now I'd have said that before my dmsetup status loop test case was not causing big problems and it was just enough to run another dmsetup to unblock the loop - now it's usually leads to some wierd end of qemu itself - will explore more.... So it's probably fixing some bug - and exposing another. As I said before - in my debuger it was looping in page_fault hadler - i.e. memory should be paged_in - but as soon as the handler return to the code to continue memcopy - new page_fault is invoked and pointer & couters are not changed. Zdenek ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-23 23:06 ` Zdenek Kabelac @ 2008-03-24 10:09 ` Avi Kivity 2008-03-24 16:18 ` Avi Kivity 0 siblings, 1 reply; 13+ messages in thread From: Avi Kivity @ 2008-03-24 10:09 UTC (permalink / raw) To: Zdenek Kabelac; +Cc: kvm-devel Zdenek Kabelac wrote: > 2008/3/23, Avi Kivity <avi@qumranet.com>: > >> Avi Kivity wrote: >> > >> > I see the same issue too now, and am investigating. >> > >> >> >> The attached patch should fix the issue. It is present in 2.6.25-rc6 >> only, and not in kvm.git, which is why few people noticed it. >> >> > > Hi > > Tested - and actually seeing no difference in my case of memory leak. > Still it looks like over 30M per execution of qemu is lost. > (tested with fresh 2.6.25-rc6 with your patch) > > Can you double check? 2.6.25-rc6 definitely leaks without, and here it doesn't with the patch. > Also now I'd have said that before my dmsetup status loop test case > was not causing big problems and it was just enough to run another > dmsetup to unblock the loop - now it's usually leads to some wierd end > of qemu itself - will explore more.... > > So it's probably fixing some bug - and exposing another. > > As I said before - in my debuger it was looping in page_fault hadler - > i.e. memory should be paged_in - but as soon as the handler return to > the code to continue memcopy - new page_fault is invoked and pointer & > couters are not changed. I'll add some code to make it possible to enable the mmu tracer in runtime. -- Do not meddle in the internals of kernels, for they are subtle and quick to panic. ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ ^ permalink raw reply [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-24 10:09 ` Avi Kivity @ 2008-03-24 16:18 ` Avi Kivity 2008-03-24 21:42 ` Zdenek Kabelac 0 siblings, 1 reply; 13+ messages in thread From: Avi Kivity @ 2008-03-24 16:18 UTC (permalink / raw) To: Zdenek Kabelac; +Cc: kvm-devel [-- Attachment #1: Type: text/plain, Size: 523 bytes --] Avi Kivity wrote: >> >> >> Tested - and actually seeing no difference in my case of memory leak. >> Still it looks like over 30M per execution of qemu is lost. >> (tested with fresh 2.6.25-rc6 with your patch) >> >> > > Can you double check? 2.6.25-rc6 definitely leaks without, and here it > doesn't with the patch. > btw, there's an additional patch I have queued up that might have an effect. please test the attached (which is my 2.6.25 queue). -- error compiling committee.c: too many arguments to function [-- Attachment #2: kvm-2.6.25-rollup.patch --] [-- Type: text/x-patch, Size: 2551 bytes --] diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index d8172aa..e55af12 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -222,8 +222,7 @@ static int is_io_pte(unsigned long pte) static int is_rmap_pte(u64 pte) { - return pte != shadow_trap_nonpresent_pte - && pte != shadow_notrap_nonpresent_pte; + return is_shadow_present_pte(pte); } static gfn_t pse36_gfn_delta(u32 gpte) @@ -893,14 +892,25 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte, int *ptwrite, gfn_t gfn, struct page *page) { u64 spte; - int was_rmapped = is_rmap_pte(*shadow_pte); + int was_rmapped = 0; int was_writeble = is_writeble_pte(*shadow_pte); + hfn_t host_pfn = (*shadow_pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT; pgprintk("%s: spte %llx access %x write_fault %d" " user_fault %d gfn %lx\n", __FUNCTION__, *shadow_pte, pt_access, write_fault, user_fault, gfn); + if (is_rmap_pte(*shadow_pte)) { + if (host_pfn != page_to_pfn(page)) { + pgprintk("hfn old %lx new %lx\n", + host_pfn, page_to_pfn(page)); + rmap_remove(vcpu->kvm, shadow_pte); + } + else + was_rmapped = 1; + } + /* * We don't set the accessed bit, since we sometimes want to see * whether the guest actually used the pte (in order to detect @@ -1402,7 +1412,7 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, up_read(¤t->mm->mmap_sem); vcpu->arch.update_pte.gfn = gfn; - vcpu->arch.update_pte.page = gfn_to_page(vcpu->kvm, gfn); + vcpu->arch.update_pte.page = page; } void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 94ea724..8e14628 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -349,8 +349,6 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu) static void reload_tss(void) { -#ifndef CONFIG_X86_64 - /* * VT restores TR but not its size. Useless. */ @@ -361,7 +359,6 @@ static void reload_tss(void) descs = (void *)gdt.base; descs[GDT_ENTRY_TSS].type = 9; /* available TSS */ load_TR_desc(); -#endif } static void load_transition_efer(struct vcpu_vmx *vmx) @@ -1436,7 +1433,7 @@ static int init_rmode_tss(struct kvm *kvm) int ret = 0; int r; - down_read(¤t->mm->mmap_sem); + down_read(&kvm->slots_lock); r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE); if (r < 0) goto out; @@ -1459,7 +1456,7 @@ static int init_rmode_tss(struct kvm *kvm) ret = 1; out: - up_read(¤t->mm->mmap_sem); + up_read(&kvm->slots_lock); return ret; } [-- Attachment #3: Type: text/plain, Size: 228 bytes --] ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ [-- Attachment #4: Type: text/plain, Size: 158 bytes --] _______________________________________________ kvm-devel mailing list kvm-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/kvm-devel ^ permalink raw reply related [flat|nested] 13+ messages in thread
* Re: Qemu-kvm is leaking my memory ??? 2008-03-24 16:18 ` Avi Kivity @ 2008-03-24 21:42 ` Zdenek Kabelac 0 siblings, 0 replies; 13+ messages in thread From: Zdenek Kabelac @ 2008-03-24 21:42 UTC (permalink / raw) To: Avi Kivity; +Cc: kvm-devel 2008/3/24, Avi Kivity <avi@qumranet.com>: > Avi Kivity wrote: > >> > >> > >> Tested - and actually seeing no difference in my case of memory leak. > >> Still it looks like over 30M per execution of qemu is lost. > >> (tested with fresh 2.6.25-rc6 with your patch) > >> > >> > > > > Can you double check? 2.6.25-rc6 definitely leaks without, and here it > > doesn't with the patch. > > > > > btw, there's an additional patch I have queued up that might have an > effect. please test the attached (which is my 2.6.25 queue). Yep - I've made a quick short test - and it looks promising - so far I can not see the leak with your additional patch. But I still have get my busy loop problem. Though now it's sometime stack-back-traced on the leaveq - maybe this instruction might cause some problems ?? Before this patch - I've always got the back-trace at the point of copy_user_generic_string - now its slightly different -- and still applies when I run the second dmsetup status - it unblocks the looped one) Call Trace: [<ffffffff8803558d>] :dm_mod:dm_compat_ctl_ioctl+0xd/0x20 [<ffffffff802bd352>] compat_sys_ioctl+0x182/0x3d0 [<ffffffff80283d20>] vfs_write+0x130/0x170 [<ffffffff80221192>] sysenter_do_call+0x1b/0x66 Call Trace: [<ffffffff88032100>] ? :dm_mod:table_status+0x0/0x90 [<ffffffff80436809>] ? error_exit+0x0/0x51 [<ffffffff88032100>] ? :dm_mod:table_status+0x0/0x90 [<ffffffff8032d157>] ? copy_user_generic_string+0x17/0x40 [<ffffffff880332d7>] ? :dm_mod:copy_params+0x87/0xb0 [<ffffffff80237b11>] ? __capable+0x11/0x30 [<ffffffff88033469>] ? :dm_mod:ctl_ioctl+0x169/0x260 [<ffffffff80340712>] ? tty_ldisc_deref+0x62/0x80 [<ffffffff8034320c>] ? tty_write+0x22c/0x260 [<ffffffff8803358d>] ? :dm_mod:dm_compat_ctl_ioctl+0xd/0x20 [<ffffffff802bd352>] ? compat_sys_ioctl+0x182/0x3d0 [<ffffffff80283d20>] ? vfs_write+0x130/0x170 [<ffffffff80221192>] ? sysenter_do_call+0x1b/0x66 Here is dissambled dm_compat_ctl_ioctl: 0000000000001fa0 <dm_compat_ctl_ioctl>: return (long)ctl_ioctl(command, (struct dm_ioctl __user *)u); } #ifdef CONFIG_COMPAT static long dm_compat_ctl_ioctl(struct file *file, uint command, ulong u) { 1fa0: 55 push %rbp 1fa1: 89 f7 mov %esi,%edi 1fa3: 48 89 e5 mov %rsp,%rbp return r; } static long dm_ctl_ioctl(struct file *file, uint command, ulong u) { return (long)ctl_ioctl(command, (struct dm_ioctl __user *)u); 1fa6: 89 d6 mov %edx,%esi 1fa8: e8 73 fd ff ff callq 1d20 <ctl_ioctl> #ifdef CONFIG_COMPAT static long dm_compat_ctl_ioctl(struct file *file, uint command, ulong u) { return (long)dm_ctl_ioctl(file, command, (ulong) compat_ptr(u)); } 1fad: c9 leaveq return r; } static long dm_ctl_ioctl(struct file *file, uint command, ulong u) { return (long)ctl_ioctl(command, (struct dm_ioctl __user *)u); 1fae: 48 98 cltq #ifdef CONFIG_COMPAT static long dm_compat_ctl_ioctl(struct file *file, uint command, ulong u) { return (long)dm_ctl_ioctl(file, command, (ulong) compat_ptr(u)); } 1fb0: c3 retq Zdenek ------------------------------------------------------------------------- This SF.net email is sponsored by: Microsoft Defy all challenges. Microsoft(R) Visual Studio 2008. http://clk.atdmt.com/MRT/go/vse0120000070mrt/direct/01/ ^ permalink raw reply [flat|nested] 13+ messages in thread
end of thread, other threads:[~2008-03-24 21:42 UTC | newest] Thread overview: 13+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2008-03-14 22:14 Qemu-kvm is leaking my memory ??? Zdenek Kabelac 2008-03-16 13:46 ` Avi Kivity 2008-03-19 15:05 ` Zdenek Kabelac 2008-03-19 15:56 ` Avi Kivity 2008-03-19 17:31 ` Zdenek Kabelac 2008-03-19 17:40 ` Avi Kivity 2008-03-23 9:26 ` Zdenek Kabelac 2008-03-23 10:22 ` Avi Kivity 2008-03-23 12:20 ` Avi Kivity 2008-03-23 23:06 ` Zdenek Kabelac 2008-03-24 10:09 ` Avi Kivity 2008-03-24 16:18 ` Avi Kivity 2008-03-24 21:42 ` Zdenek Kabelac
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox