[Devel] Re: + cgroups-add-functionality-to-read-write-lock-clone_thread-forking-pe r-threadgroup.patch added to -mm tree

2010-01-03 Thread Ben Blum
On Sat, Aug 22, 2009 at 03:09:52PM +0200, Oleg Nesterov wrote: OK, cgroups-add-ability-to-move-all-threads-in-a-process-to-a-new-cgroup-atomically.patch does threadgroup_sighand = threadgroup_fork_lock(leader); rcu_read_lock(); list_for_each_entry_rcu(tsk,

[Devel] [RFC] [PATCH 1/2] cgroups: read-write lock CLONE_THREAD forking per threadgroup

2010-01-03 Thread Ben Blum
Adds functionality to read/write lock CLONE_THREAD fork()ing per-threadgroup From: Ben Blum bb...@andrew.cmu.edu This patch adds an rwsem that lives in a threadgroup's sighand_struct (next to the sighand's atomic count, to piggyback on its cacheline), and two functions in kernel/cgroup.c (for

[Devel] [RFC] [PATCH 2/2] cgroups: make procs file writable

2010-01-03 Thread Ben Blum
Makes procs file writable to move all threads by tgid at once From: Ben Blum bb...@andrew.cmu.edu This patch adds functionality that enables users to move all threads in a threadgroup at once to a cgroup by writing the tgid to the 'cgroup.procs' file. This current implementation makes use of a

[Devel] Re: [PATCH v5 3/4] memcg: rework usage of stats by soft limit

2010-01-03 Thread KAMEZAWA Hiroyuki
On Wed, 30 Dec 2009 17:57:58 +0200 Kirill A. Shutemov kir...@shutemov.name wrote: Instead of incrementing counter on each page in/out and comparing it with constant, we set counter to constant, decrement counter on each page in/out and compare it with zero. We want to make comparing as fast

[Devel] Re: [PATCH v4 0/4] cgroup notifications API and memory thresholds

2010-01-03 Thread Balbir Singh
* Kirill A. Shutemov kir...@shutemov.name [2009-12-27 20:37:57]: On Sun, Dec 27, 2009 at 2:47 PM, Balbir Singh bal...@linux.vnet.ibm.com wrote: * Kirill A. Shutemov kir...@shutemov.name [2009-12-27 04:08:58]: This patchset introduces eventfd-based API for notifications in cgroups and

[Devel] Re: [PATCH v5 0/4] cgroup notifications API and memory thresholds

2010-01-03 Thread Balbir Singh
* Kirill A. Shutemov kir...@shutemov.name [2009-12-30 17:57:55]: This patchset introduces eventfd-based API for notifications in cgroups and implements memory notifications on top of it. It uses statistics in memory controler to track memory usage. Output of time(1) on building kernel on

[Devel] lxc-start: Device or resource busy - failed to remove previous cgroup

2010-01-03 Thread Dwight Schauer
I'm starting to get is quite regularly, but not every time: lxc-start: Device or resource busy - failed to remove previous cgroup '/cgroup/CONTAINER_NAME' lxc version: 0.6.3 Cgroup memory controller: disabled (everything else is enabled) Linux version 2.6.30-bpo.1-amd64 (Debian

[Devel] Re: lxc-start: Device or resource busy - failed to remove previous cgroup

2010-01-03 Thread Dwight Schauer
On Sun, Jan 3, 2010 at 7:22 PM, Balbir Singh bsinghar...@gmail.com wrote: Can you please paste the output of cat /proc/cgroups and cat /proc/mounts Sure. This should not really happen, /proc/cgroups will help us figure out what is going on. As an alternative, if you can compile the debug

[Devel] Re: lxc-start: Device or resource busy - failed to remove previous cgroup

2010-01-03 Thread Dwight Schauer
# strace lxc-start -n arch64-1 /root/boot-init.sh execve(/usr/bin/lxc-start, [lxc-start, -n, arch64-1, /root/boot-init.sh], [/* 21 vars */]) = 0 brk(0) = 0x1bf9000 mmap(NULL, 4096, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, -1, 0) = 0x7feca8223000