The current load balancing scheme isn't good enough for precise
group fairness.
For example: on a 8-cpu system, I created 3 groups as under:
a = 8 tasks (cpu.shares = 1024)
b = 4 tasks (cpu.shares = 1024)
c = 3 tasks (cpu.shares = 1024)
a, b and c are task groups that have equal weight. We would expect each
of the groups to receive 33.33% of cpu bandwidth under a fair scheduler.
This is what I get with the latest scheduler git tree:
Signed-off-by: Ingo Molnar <mingo@elte.hu>
--------------------------------------------------------------------------------
Col1 | Col2 | Col3 | Col4
------|---------|-------|-------------------------------------------------------
a | 277.676 | 57.8% | 54.1% 54.1% 54.1% 54.2% 56.7% 62.2% 62.8% 64.5%
b | 116.108 | 24.2% | 47.4% 48.1% 48.7% 49.3%
c | 86.326 | 18.0% | 47.5% 47.9% 48.5%
--------------------------------------------------------------------------------
Explanation of o/p:
Col1 -> Group name
Col2 -> Cumulative execution time (in seconds) received by all tasks of that
group in a 60sec window across 8 cpus
Col3 -> CPU bandwidth received by the group in the 60sec window, expressed in
percentage. Col3 data is derived as:
Col3 = 100 * Col2 / (NR_CPUS * 60)
Col4 -> CPU bandwidth received by each individual task of the group.
Col4 = 100 * cpu_time_recd_by_task / 60
[I can share the test case that produces a similar o/p if reqd]
The deviation from desired group fairness is as below:
a = +24.47%
b = -9.13%
c = -15.33%
which is quite high.
After the patch below is applied, here are the results:
--------------------------------------------------------------------------------
Col1 | Col2 | Col3 | Col4
------|---------|-------|-------------------------------------------------------
a | 163.112 | 34.0% | 33.2% 33.4% 33.5% 33.5% 33.7% 34.4% 34.8% 35.3%
b | 156.220 | 32.5% | 63.3% 64.5% 66.1% 66.5%
c | 160.653 | 33.5% | 85.8% 90.6% 91.4%
--------------------------------------------------------------------------------
Deviation from desired group fairness is as below:
a = +0.67%
b = -0.83%
c = +0.17%
which is far better IMO. Most of other runs have yielded a deviation within
+-2% at the most, which is good.
Why do we see bad (group) fairness with current scheuler?
=========================================================
Currently cpu's weight is just the summation of individual task weights.
This can yield incorrect results. For ex: consider three groups as below
on a 2-cpu system:
CPU0 CPU1
---------------------------
A (10) B(5)
C(5)
---------------------------
Group A has 10 tasks, all on CPU0, Group B and C have 5 tasks each all
of which are on CPU1. Each task has the same weight (NICE_0_LOAD =
1024).
The current scheme would yield a cpu weight of 10240 (10*1024) for each cpu and
the load balancer will think both CPUs are perfectly balanced and won't
move around any tasks. This, however, would yield this bandwidth:
A = 50%
B = 25%
C = 25%
which is not the desired result.
What's changing in the patch?
=============================
- How cpu weights are calculated when CONFIF_FAIR_GROUP_SCHED is
defined (see below)
- API Change
- Two tunables introduced in sysfs (under SCHED_DEBUG) to
control the frequency at which the load balance monitor
thread runs.
The basic change made in this patch is how cpu weight (rq->load.weight) is
calculated. Its now calculated as the summation of group weights on a cpu,
rather than summation of task weights. Weight exerted by a group on a
cpu is dependent on the shares allocated to it and also the number of
tasks the group has on that cpu compared to the total number of
(runnable) tasks the group has in the system.
Let,
W(K,i) = Weight of group K on cpu i
T(K,i) = Task load present in group K's cfs_rq on cpu i
T(K) = Total task load of group K across various cpus
S(K) = Shares allocated to group K
NRCPUS = Number of online cpus in the scheduler domain to
which group K is assigned.
Then,
W(K,i) = S(K) * NRCPUS * T(K,i) / T(K)
A load balance monitor thread is created at bootup, which periodically
runs and adjusts group's weight on each cpu. To avoid its overhead, two
min/max tunables are introduced (under SCHED_DEBUG) to control the rate
at which it runs.
Fixes from: Peter Zijlstra <a.p.zijlstra@chello.nl>
- don't start the load_balance_monitor when there is only a single cpu.
- rename the kthread because its currently longer than TASK_COMM_LEN
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Clean up the use of ksets and kobjects. Kobjects are instances of
objects (like struct user_info), ksets are collections of objects of a
similar type (like the uids directory containing the user_info directories).
So, use kobjects for the user_info directories, and a kset for the "uids"
directory.
On object cleanup, the final kobject_put() was missing.
Cc: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Kay Sievers <kay.sievers@vrfy.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
task_ppid_nr_ns is called in three places. One of these should never
have called it. In the other two, using it broke the existing
semantics. This was presumably accidental. If the function had not
been there, it would have been much more obvious to the eye that those
patches were changing the behavior. We don't need this function.
In task_state, the pid of the ptracer is not the ppid of the ptracer.
In do_task_stat, ppid is the tgid of the real_parent, not its pid.
I also moved the call outside of lock_task_sighand, since it doesn't
need it.
In sys_getppid, ppid is the tgid of the real_parent, not its pid.
Signed-off-by: Roland McGrath <roland@redhat.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch adds a proper prototype for migration_init() in
include/linux/sched.h
Since there's no point in always returning 0 to a caller that doesn't check
the return value it also changes the function to return void.
Signed-off-by: Adrian Bunk <bunk@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
SMP balancing is done with IRQs disabled and can iterate the full rq.
When rqs are large this can cause large irq-latencies. Limit the nr of
iterations on each run.
This fixes a scheduling latency regression reported by the -rt folks.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Tested-by: Gregory Haskins <ghaskins@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove PREEMPT_RESTRICT. (this is a separate commit so that any
regression related to the removal itself is bisectable)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Since powerpc started using CONFIG_GENERIC_CLOCKEVENTS, the
deterministic CPU accounting (CONFIG_VIRT_CPU_ACCOUNTING) has been
broken on powerpc, because we end up counting user time twice: once in
timer_interrupt() and once in update_process_times().
This fixes the problem by pulling the code in update_process_times
that updates utime and stime into a separate function called
account_process_tick. If CONFIG_VIRT_CPU_ACCOUNTING is not defined,
there is a version of account_process_tick in kernel/timer.c that
simply accounts a whole tick to either utime or stime as before. If
CONFIG_VIRT_CPU_ACCOUNTING is defined, then arch code gets to
implement account_process_tick.
This also lets us simplify the s390 code a bit; it means that the s390
timer interrupt can now call update_process_times even when
CONFIG_VIRT_CPU_ACCOUNTING is turned on, and can just implement a
suitable account_process_tick().
account_process_tick() now takes the task_struct * as an argument.
Tested both with and without CONFIG_VIRT_CPU_ACCOUNTING.
Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
we lost the sched_min_granularity tunable to a clever optimization
that uses the sched_latency/min_granularity ratio - but the ratio
is quite unintuitive to users and can also crash the kernel if the
ratio is set to 0. So reintroduce the min_granularity tunable,
while keeping the ratio maintained internally.
no functionality changed.
[ mingo@elte.hu: some fixlets. ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
keep utime/stime monotonic.
cpustats use utime/stime as a ratio against sum_exec_runtime, as a
consequence it can happen - when the ratio changes faster than time
accumulates - that either can be appear to go backwards.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
[PATCH] De-constify sched.h
This reverts commit a8972ccf00 ("sched:
constify sched.h")
1) Patch doesn't change any code here, so gcc is already smart enough
to "feel" constness in such simple functions.
2) There is no such thing as const task_struct. Anyone who think
otherwise deserves compiler warning.
Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
At the moment, a lot of load balancing code that is irrelevant to non
SMP systems gets included during non SMP builds.
This patch addresses this issue and reduces the binary size on non
SMP systems:
text data bss dec hex filename
10983 28 1192 12203 2fab sched.o.before
10739 28 1192 11959 2eb7 sched.o.after
Signed-off-by: Peter Williams <pwil3058@bigpond.net.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
At the moment, balance_tasks() provides low level functionality for both
move_tasks() and move_one_task() (indirectly) via the load_balance()
function (in the sched_class interface) which also provides dual
functionality. This dual functionality complicates the interfaces and
internal mechanisms and makes the run time overhead of operations that
are called with two run queue locks held.
This patch addresses this issue and reduces the overhead of these
operations.
Signed-off-by: Peter Williams <pwil3058@bigpond.net.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The pgrp field is not used widely around the kernel so it is now marked as
deprecated with appropriate comment.
The initialization of INIT_SIGNALS is trimmed because
a) they are set to 0 automatically;
b) gcc cannot properly initialize two anonymous (the second one
is the one with the session) unions. In this particular case
to make it compile we'd have to add some field initialized
right before the .pgrp.
This is the same patch as the 1ec320afdc one
(from Cedric), but for the pgrp field.
Some progress report:
We have to deprecate the pid, tgid, session and pgrp fields on struct
task_struct and struct signal_struct. The session and pgrp are already
deprecated. The tgid value is close to being such - the worst known usage
in in fs/locks.c and audit code. The pid field deprecation is mainly
blocked by numerous printk-s around the kernel that print the tsk->pid to
log.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Add a new per-cpuset flag called 'sched_load_balance'.
When enabled in a cpuset (the default value) it tells the kernel scheduler
that the scheduler should provide the normal load balancing on the CPUs in
that cpuset, sometimes moving tasks from one CPU to a second CPU if the
second CPU is less loaded and if that task is allowed to run there.
When disabled (write "0" to the file) then it tells the kernel scheduler
that load balancing is not required for the CPUs in that cpuset.
Now even if this flag is disabled for some cpuset, the kernel may still
have to load balance some or all the CPUs in that cpuset, if some
overlapping cpuset has its sched_load_balance flag enabled.
If there are some CPUs that are not in any cpuset whose sched_load_balance
flag is enabled, the kernel scheduler will not load balance tasks to those
CPUs.
Moreover the kernel will partition the 'sched domains' (non-overlapping
sets of CPUs over which load balancing is attempted) into the finest
granularity partition that it can find, while still keeping any two CPUs
that are in the same shed_load_balance enabled cpuset in the same element
of the partition.
This serves two purposes:
1) It provides a mechanism for real time isolation of some CPUs, and
2) it can be used to improve performance on systems with many CPUs
by supporting configurations in which load balancing is not done
across all CPUs at once, but rather only done in several smaller
disjoint sets of CPUs.
This mechanism replaces the earlier overloading of the per-cpuset
flag 'cpu_exclusive', which overloading was removed in an earlier
patch: cpuset-remove-sched-domain-hooks-from-cpusets
See further the Documentation and comments in the code itself.
[akpm@linux-foundation.org: don't be weird]
Signed-off-by: Paul Jackson <pj@sgi.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Since these are expanded into call to pid_nr_ns() anyway, it's OK to move
the whole routine out-of-line. This is a cheap way to save ~100 bytes from
vmlinux. Together with the previous two patches, it saves half-a-kilo from
the vmlinux.
Un-inline other (currently inlined) functions must be done with additional
performance testing.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
With pid namespaces this field is now dangerous to use explicitly, so hide
it behind the helpers.
Also the pid and pgrp fields o task_struct and signal_struct are to be
deprecated. Unfortunately this patch cannot be sent right now as this
leads to tons of warnings, so start isolating them, and deprecate later.
Actually the p->tgid == pid has to be changed to has_group_leader_pid(),
but Oleg pointed out that in case of posix cpu timers this is the same, and
thread_group_leader() is more preferable.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Acked-by: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The find_task_by_something is a set of macros are used to find task by pid
depending on what kind of pid is proposed - global or virtual one. All of
them are wrappers above the most generic one - find_task_by_pid_type_ns() -
and just substitute some args for it.
It turned out, that dereferencing the current->nsproxy->pid_ns construction
and pushing one more argument on the stack inline cause kernel text size to
grow.
This patch moves all this stuff out-of-line into kernel/pid.c. Together
with the next patch it saves a bit less than 400 bytes from the .text
section.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When clone() is invoked with CLONE_NEWPID, create a new pid namespace and then
create a new struct pid for the new process. Allocate pid_t's for the new
process in the new pid namespace and all ancestor pid namespaces. Make the
newly cloned process the session and process group leader.
Since the active pid namespace is special and expected to be the first entry
in pid->upid_list, preserve the order of pid namespaces.
The size of 'struct pid' is dependent on the the number of pid namespaces the
process exists in, so we use multiple pid-caches'. Only one pid cache is
created during system startup and this used by processes that exist only in
init_pid_ns.
When a process clones its pid namespace, we create additional pid caches as
necessary and use the pid cache to allocate 'struct pids' for that depth.
Note, that with this patch the newly created namespace won't work, since the
rest of the kernel still uses global pids, but this is to be fixed soon. Init
pid namespace still works.
[oleg@tv-sign.ru: merge fix]
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When searching the task by numerical id on may need to find it using global
pid (as it is done now in kernel) or by its virtual id, e.g. when sending a
signal to a task from one namespace the sender will specify the task's virtual
id and we should find the task by this value.
[akpm@linux-foundation.org: fix gfs2 linkage]
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When showing pid to user or getting the pid numerical id for in-kernel use the
value of this id may differ depending on the namespace.
This set of helpers is used to get the global pid nr, the virtual (i.e. seen
by task in its namespace) nr and the nr as it is seen from the specified
namespace.
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
Cc: Oleg Nesterov <oleg@tv-sign.ru>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
is_init() is an ambiguous name for the pid==1 check. Split it into
is_global_init() and is_container_init().
A cgroup init has it's tsk->pid == 1.
A global init also has it's tsk->pid == 1 and it's active pid namespace
is the init_pid_ns. But rather than check the active pid namespace,
compare the task structure with 'init_pid_ns.child_reaper', which is
initialized during boot to the /sbin/init process and never changes.
Changelog:
2.6.22-rc4-mm2-pidns1:
- Use 'init_pid_ns.child_reaper' to determine if a given task is the
global init (/sbin/init) process. This would improve performance
and remove dependence on the task_pid().
2.6.21-mm2-pidns2:
- [Sukadev Bhattiprolu] Changed is_container_init() calls in {powerpc,
ppc,avr32}/traps.c for the _exception() call to is_global_init().
This way, we kill only the cgroup if the cgroup's init has a
bug rather than force a kernel panic.
[akpm@linux-foundation.org: fix comment]
[sukadev@us.ibm.com: Use is_global_init() in arch/m32r/mm/fault.c]
[bunk@stusta.de: kernel/pid.c: remove unused exports]
[sukadev@us.ibm.com: Fix capability.c to work with threaded init]
Signed-off-by: Serge E. Hallyn <serue@us.ibm.com>
Signed-off-by: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Acked-by: Pavel Emelianov <xemul@openvz.org>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Herbert Poetzel <herbert@13thfloor.at>
Cc: Kirill Korotaev <dev@sw.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The set of functions process_session, task_session, process_group and
task_pgrp is confusing, as the names can be mixed with each other when looking
at the code for a long time.
The proposals are to
* equip the functions that return the integer with _nr suffix to
represent that fact,
* and to make all functions work with task (not process) by making
the common prefix of the same name.
For monotony the routines signal_session() and set_signal_session() are
replaced with task_session_nr() and set_task_session(), especially since they
are only used with the explicit task->signal dereference.
Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Acked-by: Serge E. Hallyn <serue@us.ibm.com>
Cc: Kirill Korotaev <dev@openvz.org>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Remove the filesystem support logic from the cpusets system and makes cpusets
a cgroup subsystem
The "cpuset" filesystem becomes a dummy filesystem; attempts to mount it get
passed through to the cgroup filesystem with the appropriate options to
emulate the old cpuset filesystem behaviour.
Signed-off-by: Paul Menage <menage@google.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Paul Jackson <pj@sgi.com>
Cc: Kirill Korotaev <dev@openvz.org>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Replace the struct css_set embedded in task_struct with a pointer; all tasks
that have the same set of memberships across all hierarchies will share a
css_set object, and will be linked via their css_sets field to the "tasks"
list_head in the css_set.
Assuming that many tasks share the same cgroup assignments, this reduces
overall space usage and keeps the size of the task_struct down (three pointers
added to task_struct compared to a non-cgroups kernel, no matter how many
subsystems are registered).
[akpm@linux-foundation.org: fix a printk]
[akpm@linux-foundation.org: build fix]
Signed-off-by: Paul Menage <menage@google.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Paul Jackson <pj@sgi.com>
Cc: Kirill Korotaev <dev@openvz.org>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Paul Jackson <pj@sgi.com>
Cc: Kirill Korotaev <dev@openvz.org>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Generic Process Control Groups
--------------------------
There have recently been various proposals floating around for
resource management/accounting and other task grouping subsystems in
the kernel, including ResGroups, User BeanCounters, NSProxy
cgroups, and others. These all need the basic abstraction of being
able to group together multiple processes in an aggregate, in order to
track/limit the resources permitted to those processes, or control
other behaviour of the processes, and all implement this grouping in
different ways.
This patchset provides a framework for tracking and grouping processes
into arbitrary "cgroups" and assigning arbitrary state to those
groupings, in order to control the behaviour of the cgroup as an
aggregate.
The intention is that the various resource management and
virtualization/cgroup efforts can also become task cgroup
clients, with the result that:
- the userspace APIs are (somewhat) normalised
- it's easier to test e.g. the ResGroups CPU controller in
conjunction with the BeanCounters memory controller, or use either of
them as the resource-control portion of a virtual server system.
- the additional kernel footprint of any of the competing resource
management systems is substantially reduced, since it doesn't need
to provide process grouping/containment, hence improving their
chances of getting into the kernel
This patch:
Add the main task cgroups framework - the cgroup filesystem, and the
basic structures for tracking membership and associating subsystem state
objects to tasks.
Signed-off-by: Paul Menage <menage@google.com>
Cc: Serge E. Hallyn <serue@us.ibm.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Paul Jackson <pj@sgi.com>
Cc: Kirill Korotaev <dev@openvz.org>
Cc: Herbert Poetzl <herbert@13thfloor.at>
Cc: Srivatsa Vaddagiri <vatsa@in.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This adds items to the taststats struct to account for user and system
time based on scaling the CPU frequency and instruction issue rates.
Adds account_(user|system)_time_scaled callbacks which architectures
can use to account for time using this mechanism.
Signed-off-by: Michael Neuling <mikey@neuling.org>
Cc: Balbir Singh <balbir@in.ibm.com>
Cc: Jay Lan <jlan@engr.sgi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Hell knows what happened in commit 63b05203af57e7de4f3bb63b8b81d43bc196d32b
during 2.6.9 development. Commit introduced io_wait field which remained
write-only than and still remains write-only.
Also garbage collect macros which "use" io_wait.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
schedstat is useful in investigating CPU scheduler behavior. Ideally,
I think it is beneficial to have it on all the time. However, the
cost of turning it on in production system is quite high, largely due
to number of events it collects and also due to its large memory
footprint.
Most of the fields probably don't need to be full 64-bit on 64-bit
arch. Rolling over 4 billion events will most like take a long time
and user space tool can be made to accommodate that. I'm proposing
kernel to cut back most of variable width on 64-bit system. (note,
the following patch doesn't affect 32-bit system).
Signed-off-by: Ken Chen <kenchen@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
For those who don't care about CONFIG_SECURITY.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: "Serge E. Hallyn" <serge@hallyn.com>
Cc: Casey Schaufler <casey@schaufler-ca.com>
Cc: James Morris <jmorris@namei.org>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
There is nice 2 byte hole after struct task_struct::ioprio field
into which we can put two 1-byte fields: ->fpu_counter and ->oomkilladj.
Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru>
Acked-by: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
For those who deselect POSIX message queues.
Reduces SLAB size of user_struct from 64 to 32 bytes here, SLUB size -- from
40 bytes to 32 bytes.
[akpm@linux-foundation.org: fix build]
Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
robust_list, compat_robust_list, pi_state_list, pi_state_cache are
really used if futexes are on.
Signed-off-by: Alexey Dobriyan <adobriyan@sw.ru>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
oomkilladj is int, but values which can be assigned to it are -17, [-16,
15], thus fitting into s8.
While patch itself doesn't help in making task_struct smaller, because of
natural alignment of ->link_count, it will make picture clearer wrt futher
task_struct reduction patches. My plan is to move ->fpu_counter and
->oomkilladj after ->ioprio filling hole on i386 and x86_64. But that's
for later, because bloated distro configs need looking at as well.
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This adds the MMF_DUMP_ELF_HEADERS option to /proc/pid/coredump_filter.
This dumps the first page (only) of a private file mapping if it appears to
be a mapping of an ELF file. Including these pages in the core dump may
give sufficient identifying information to associate the original DSO and
executable file images and their debugging information with a core file in
a generic way just from its contents (e.g. when those binaries were built
with ld --build-id). I expect this to become the default behavior
eventually. Existing versions of gdb can be confused by the core dumps it
creates, so it won't enabled by default for some time to come. Soon many
people will have systems with a gdb that handle these dumps, so they can
arrange to set the bit at boot and have it inherited system-wide.
This also cleans up the checking of the MMF_DUMP_* flag bits, which did not
need to be using atomic macros.
Signed-off-by: Roland McGrath <roland@redhat.com>
Cc: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Control the trigger limit for softlockup warnings. This is useful for
debugging softlockups, by lowering the softlockup_thresh to identify
possible softlockups earlier.
This patch:
1. Adds a sysctl softlockup_thresh with valid values of 1-60s
(Higher value to disable false positives)
2. Changes the softlockup printk to print the cpu softlockup time
[akpm@linux-foundation.org: Fix various warnings and add definition of "two"]
Signed-off-by: Ravikiran Thirumalai <kiran@scalex86.org>
Signed-off-by: Shai Fultheim <shai@scalex86.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Based on ideas of Andrew:
http://marc.info/?l=linux-kernel&m=102912915020543&w=2
Scale the bdi dirty limit inversly with the tasks dirty rate.
This makes heavy writers have a lower dirty limit than the occasional writer.
Andrea proposed something similar:
http://lwn.net/Articles/152277/
The main disadvantage to his patch is that he uses an unrelated quantity to
measure time, which leaves him with a workload dependant tunable. Other than
that the two approaches appear quite similar.
[akpm@linux-foundation.org: fix warning]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When CONFIG_SYSFS is not set, CONFIG_FAIR_USER_SCHED fails to build
with
kernel/built-in.o: In function `uids_kobject_init':
(.init.text+0x1488): undefined reference to `kernel_subsys'
kernel/built-in.o: In function `uids_kobject_init':
(.init.text+0x1490): undefined reference to `kernel_subsys'
kernel/built-in.o: In function `uids_kobject_init':
(.init.text+0x1480): undefined reference to `kernel_subsys'
kernel/built-in.o: In function `uids_kobject_init':
(.init.text+0x1494): undefined reference to `kernel_subsys'
This patch fixes this build error.
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Remove the cpuset hooks that defined sched domains depending on the setting
of the 'cpu_exclusive' flag.
The cpu_exclusive flag can only be set on a child if it is set on the
parent.
This made that flag painfully unsuitable for use as a flag defining a
partitioning of a system.
It was entirely unobvious to a cpuset user what partitioning of sched
domains they would be causing when they set that one cpu_exclusive bit on
one cpuset, because it depended on what CPUs were in the remainder of that
cpusets siblings and child cpusets, after subtracting out other
cpu_exclusive cpusets.
Furthermore, there was no way on production systems to query the
result.
Using the cpu_exclusive flag for this was simply wrong from the get go.
Fortunately, it was sufficiently borked that so far as I know, almost no
successful use has been made of this. One real time group did use it to
affectively isolate CPUs from any load balancing efforts. They are willing
to adapt to alternative mechanisms for this, such as someway to manipulate
the list of isolated CPUs on a running system. They can do without this
present cpu_exclusive based mechanism while we develop an alternative.
There is a real risk, to the best of my understanding, of users
accidentally setting up a partitioned scheduler domains, inhibiting desired
load balancing across all their CPUs, due to the nonobvious (from the
cpuset perspective) side affects of the cpu_exclusive flag.
Furthermore, since there was no way on a running system to see what one was
doing with sched domains, this change will be invisible to any using code.
Unless they have real insight to the scheduler load balancing choices, they
will be unable to detect that this change has been made in the kernel's
behaviour.
Initial discussion on lkml of this patch has generated much comment. My
(probably controversial) take on that discussion is that it has reached a
rough concensus that the current cpuset cpu_exclusive mechanism for
defining sched domains is borked. There is no concensus on the
replacement. But since we can remove this mechanism, and since its
continued presence risks causing unwanted partitioning of the schedulers
load balancing, we should remove it while we can, as we proceed to work the
replacement scheduler domain mechanisms.
Signed-off-by: Paul Jackson <pj@sgi.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Christoph Lameter <clameter@engr.sgi.com>
Cc: Dinakar Guniguntala <dino@in.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Move the definitions of struct mm_struct and struct vma_area_struct to
include/mm_types.h. This allows to define more function in asm/pgtable.h
and friends with inline assemblies instead of macros. Compile tested on
i386, powerpc, powerpc64, s390-32, s390-64 and x86_64.
[aurelien@aurel32.net: build fix]
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
modify account_system_time() to add cputime to cpustat->guest if we are
running a VCPU. We add this cputime to cpustat->user instead of
cpustat->system because this part of KVM code is in fact user code
although it is executed in the kernel. We duplicate VCPU time between
guest and user to allow an unmodified "top(1)" to display correct value.
A modified "top(1)" is able to display good cpu user time and cpu guest
time by subtracting cpu guest time from cpu user time. Update "gtime" in
task_struct accordingly.
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Acked-by: Avi Kivity <avi@qumranet.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
like for cpustat, introduce the "gtime" (guest time of the task) and
"cgtime" (guest time of the task children) fields for the
tasks. Modify signal_struct and task_struct.
Modify /proc/<pid>/stat to display these new fields.
Signed-off-by: Laurent Vivier <Laurent.Vivier@bull.net>
Acked-by: Avi Kivity <avi@qumranet.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
reintroduce a simplified version of cache-hot/cold scheduling
affinity. This improves performance with certain SMP workloads,
such as sysbench.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Prevent wakeup over-scheduling. Once a task has been preempted by a
task of the same or lower priority, it becomes ineligible for repeated
preemption by same until it has been ticked, or slept. Instead, the
task is marked for preemption at the next tick. Tasks of higher
priority still preempt immediately.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
