| Age | Commit message (Collapse) | Author |
|---|
|
git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/suspend-2.6: (26 commits)
PM / Wakeup: Show wakeup sources statistics in debugfs
PM: Introduce library for device-specific OPPs (v7)
PM: Add sysfs attr for rechecking dev hash from PM trace
PM: Lock PM device list mutex in show_dev_hash()
PM / Runtime: Remove idle notification after failing suspend
PM / Hibernate: Modify signature used to mark swap
PM / Runtime: Reduce code duplication in core helper functions
PM: Allow wakeup events to abort freezing of tasks
PM: runtime: add missed pm_request_autosuspend
PM / Hibernate: Make some boot messages look less scary
PM / Runtime: Implement autosuspend support
PM / Runtime: Add no_callbacks flag
PM / Runtime: Combine runtime PM entry points
PM / Runtime: Merge synchronous and async runtime routines
PM / Runtime: Replace boolean arguments with bitflags
PM / Runtime: Move code in drivers/base/power/runtime.c
sysfs: Add sysfs_merge_group() and sysfs_unmerge_group()
PM: Fix potential issue with failing asynchronous suspend
PM / Wakeup: Introduce wakeup source objects and event statistics (v3)
PM: Fix signed/unsigned warning in dpm_show_time()
...
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (96 commits)
apic, x86: Use BIOS settings for IBS and MCE threshold interrupt LVT offsets
apic, x86: Check if EILVT APIC registers are available (AMD only)
x86: ioapic: Call free_irte only if interrupt remapping enabled
arm: Use ARCH_IRQ_INIT_FLAGS
genirq, ARM: Fix boot on ARM platforms
genirq: Fix CONFIG_GENIRQ_NO_DEPRECATED=y build
x86: Switch sparse_irq allocations to GFP_KERNEL
genirq: Switch sparse_irq allocator to GFP_KERNEL
genirq: Make sparse_lock a mutex
x86: lguest: Use new irq allocator
genirq: Remove the now unused sparse irq leftovers
genirq: Sanitize dynamic irq handling
genirq: Remove arch_init_chip_data()
x86: xen: Sanitise sparse_irq handling
x86: Use sane enumeration
x86: uv: Clean up the direct access to irq_desc
x86: Make io_apic.c local functions static
genirq: Remove irq_2_iommu
x86: Speed up the irq_remapped check in hot pathes
intr_remap: Simplify the code further
...
Fix up trivial conflicts in arch/x86/Kconfig
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'timers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
ntp: Clamp PLL update interval
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'futexes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
futex: Fix kernel-doc notation & typos
futex: Add lock context annotations
futex: Mark restart_block.futex.uaddr[2] __user
futex: Change 3rd arg of fetch_robust_entry() to unsigned int*
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
futex: Fix errors in nested key ref-counting
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (29 commits)
sched: Export account_system_vtime()
sched: Call tick_check_idle before __irq_enter
sched: Remove irq time from available CPU power
sched: Do not account irq time to current task
x86: Add IRQ_TIME_ACCOUNTING
sched: Add IRQ_TIME_ACCOUNTING, finer accounting of irq time
sched: Add a PF flag for ksoftirqd identification
sched: Consolidate account_system_vtime extern declaration
sched: Fix softirq time accounting
sched: Drop group_capacity to 1 only if local group has extra capacity
sched: Force balancing on newidle balance if local group has capacity
sched: Set group_imb only a task can be pulled from the busiest cpu
sched: Do not consider SCHED_IDLE tasks to be cache hot
sched: Drop all load weight manipulation for RT tasks
sched: Create special class for stop/migrate work
sched: Unindent labels
sched: Comment updates: fix default latency and granularity numbers
tracing/sched: Add sched_pi_setprio tracepoint
sched: Give CPU bound RT tasks preference
sched: Try not to migrate higher priority RT tasks
...
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (163 commits)
tracing: Fix compile issue for trace_sched_wakeup.c
[S390] hardirq: remove pointless header file includes
[IA64] Move local_softirq_pending() definition
perf, powerpc: Fix power_pmu_event_init to not use event->ctx
ftrace: Remove recursion between recordmcount and scripts/mod/empty
jump_label: Add COND_STMT(), reducer wrappery
perf: Optimize sw events
perf: Use jump_labels to optimize the scheduler hooks
jump_label: Add atomic_t interface
jump_label: Use more consistent naming
perf, hw_breakpoint: Fix crash in hw_breakpoint creation
perf: Find task before event alloc
perf: Fix task refcount bugs
perf: Fix group moving
irq_work: Add generic hardirq context callbacks
perf_events: Fix transaction recovery in group_sched_in()
perf_events: Fix bogus AMD64 generic TLB events
perf_events: Fix bogus context time tracking
tracing: Remove parent recording in latency tracer graph options
tracing: Use one prologue for the preempt irqs off tracer function tracers
...
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (52 commits)
sched: fix RCU lockdep splat from task_group()
rcu: using ACCESS_ONCE() to observe the jiffies_stall/rnp->qsmask value
sched: suppress RCU lockdep splat in task_fork_fair
net: suppress RCU lockdep false positive in sock_update_classid
rcu: move check from rcu_dereference_bh to rcu_read_lock_bh_held
rcu: Add advice to PROVE_RCU_REPEATEDLY kernel config parameter
rcu: Add tracing data to support queueing models
rcu: fix sparse errors in rcutorture.c
rcu: only one evaluation of arg in rcu_dereference_check() unless sparse
kernel: Remove undead ifdef CONFIG_DEBUG_LOCK_ALLOC
rcu: fix _oddness handling of verbose stall warnings
rcu: performance fixes to TINY_PREEMPT_RCU callback checking
rcu: upgrade stallwarn.txt documentation for CPU-bound RT processes
vhost: add __rcu annotations
rcu: add comment stating that list_empty() applies to RCU-protected lists
rcu: apply TINY_PREEMPT_RCU read-side speedup to TREE_PREEMPT_RCU
rcu: combine duplicate code, courtesy of CONFIG_PREEMPT_RCU
rcu: Upgrade srcu_read_lock() docbook about SRCU grace periods
rcu: document ways of stalling updates in low-memory situations
rcu: repair code-duplication FIXMEs
...
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
lockdep: Check the depth of subclass
lockdep: Add improved subclass caching
affs: Use sema_init instead of init_MUTEX
hfs: Convert tree_lock to mutex
arm: Bcmring: semaphore cleanup
printk: Make console_sem a semaphore not a pseudo mutex
drivers/macintosh/adb: Do not claim that the semaphore is a mutex
parport: Semaphore cleanup
irda: Semaphore cleanup
net: Wan/cosa.c: Convert "mutex" to semaphore
net: Ppp_async: semaphore cleanup
hamradio: Mkiss: semaphore cleanup
hamradio: 6pack: semaphore cleanup
net: 3c527: semaphore cleanup
input: Serio/hp_sdc: semaphore cleanup
input: Serio/hil_mlc: semaphore cleanup
input: Misc/hp_sdc_rtc: semaphore cleanup
lockup_detector: Make callback function static
lockup detector: Fix grammar by adding a missing "to" in the comments
lockdep: Remove __debug_show_held_locks
|
|
With the addition of trace_softirq_raise() the softirq tracepoint got
even more convoluted. Why the tracepoints take two pointers to assign
an integer is beyond my comprehension.
But adding an extra case which treats the first pointer as an unsigned
long when the second pointer is NULL including the back and forth
type casting is just horrible.
Convert the softirq tracepoints to take a single unsigned int argument
for the softirq vector number and fix the call sites.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <alpine.LFD.2.00.1010191428560.6815@localhost6.localdomain6>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: mathieu.desnoyers@efficios.com
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
|
|
The tracing per_cpu buffers were limited to 999 CPUs for a mear
savings in stack space of a char array. Up the array to 30 characters
which is more than enough to hold a 64 bit number.
Reported-by: Robin Holt <holt@sgi.com>
Suggested-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
|
|
All security modules shouldn't change sched_param parameter of
security_task_setscheduler(). This is not only meaningless, but also
make a harmful result if caller pass a static variable.
This patch remove policy and sched_param parameter from
security_task_setscheduler() becuase none of security module is
using it.
Cc: James Morris <jmorris@namei.org>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: James Morris <jmorris@namei.org>
|
|
With the binding of time extends to events we no longer need to use
the macro RB_TIMESTAMPS_PER_PAGE. Remove it.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
|
|
By using inline and noinline, we are able to make the fast path of
recording an event 4% faster.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
|
|
There's a condition to check if we should add a time extend or
not in the fast path. But this condition is racey (in the sense
that we can add a unnecessary time extend, but nothing that
can break anything). We later check if the time or event time
delta should be zero or have real data in it (not racey), making
this first check redundant.
This check may help save space once in a while, but really is
not worth the hassle to try to save some space that happens at
most 134 ms at a time.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
|
|
When the time between two timestamps is greater than
2^27 nanosecs (~134 ms) a time extend event is added that extends
the time difference to 59 bits (~18 years). This is due to
events only having a 27 bit field to store time.
Currently this time extend is a separate event. We add it just before
the event data that is being written to the buffer. But before
the event data is committed, the event data can also be discarded (as
with the case of filters). But because the time extend has already been
committed, it will stay in the buffer.
If lots of events are being filtered and no event is being
written, then every 134ms a time extend can be added to the buffer
without any data attached. To keep from filling the entire buffer
with time extends, a time extend will never be the first event
in a page because the page timestamp can be used. Time extends can
only fill the rest of a page with some data at the beginning.
This patch binds the time extend with the data. The difference here
is that the time extend is not committed before the data is added.
Instead, when a time extend is needed, the space reserved on
the ring buffer is the time extend + the data event size. The
time extend is added to the first part of the reserved block and
the data is added to the second. The time extend event is passed
back to the reserver, but since the reserver also uses a function
to find the data portion of the reserved block, no changes to the
ring buffer interface need to be made.
When a commit is discarded, we now remove both the time extend and
the event. With this approach no more than one time extend can
be in the buffer in a row. Data must always follow a time extend.
Thanks to Mathieu Desnoyers for suggesting this idea.
Suggested-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
|
|
The delta between events is passed to the timestamp code by reference
and the timestamp code will reset the value. But it can be reset
from the caller. No need to pass it in by reference.
By changing the call to pass by value, lets gcc optimize the code
a bit more where it can store the delta in a register and not
worry about updating the reference.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
|
|
The original code for the ring buffer had locations that modified
the timestamp and that change was used by the callers. Now,
the timestamp is not reused by the callers and there is no reason
to pass it by reference.
By changing the call to pass by value, lets gcc optimize the code
a bit more where it can store the timestamp in a register and not
worry about updating the reference.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
|
|
Merge reason: update to almost-final-.36
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
|
|
git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/core
|
|
Gcc inlines the slow path of the ring buffer write which can
hurt performance. This patch simply forces the slow path function
rb_move_tail() to always be a function.
The ring_buffer_benchmark module with reader_disabled=1 shows that
this patch changes the time to record an event from 135 ns to
132 ns. (3 ns or 2.22% improvement)
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
|
|
The function start_func_tracer() was incorrectly added in the
#ifdef CONFIG_FUNCTION_TRACER condition, but is still used even
when function tracing is not enabled.
The calls to register_ftrace_function() and register_ftrace_graph()
become nops (and their arguments are even ignored), thus there is
no reason to hide start_func_tracer() when function tracing is
not enabled.
Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
|
|
futex_wait() is leaking key references due to futex_wait_setup()
acquiring an additional reference via the queue_lock() routine. The
nested key ref-counting has been masking bugs and complicating code
analysis. queue_lock() is only called with a previously ref-counted
key, so remove the additional ref-counting from the queue_(un)lock()
functions.
Also futex_wait_requeue_pi() drops one key reference too many in
unqueue_me_pi(). Remove the key reference handling from
unqueue_me_pi(). This was paired with a queue_lock() in
futex_lock_pi(), so the count remains unchanged.
Document remaining nested key ref-counting sites.
Signed-off-by: Darren Hart <dvhart@linux.intel.com>
Reported-and-tested-by: Matthieu Fertré<matthieu.fertre@kerlabs.com>
Reported-by: Louis Rilling<louis.rilling@kerlabs.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
LKML-Reference: <4CBB17A8.70401@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@kernel.org
|
|
According to Jens, this code does not need the BKL at all,
it is sufficiently serialized by bd_mutex.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Jens Axboe <jaxboe@fusionio.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
|
|
The big kernel lock is going away, so make sure
that if it is disabled by Kconfig, we do not
try to validate it, which would result in
compile errors.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
|
|
Commit a25909a4 (lockdep: Add an in_workqueue_context() lockdep-based
test function) added in_workqueue_context() but there hasn't been any
in-kernel user and the lockdep annotation in workqueue is scheduled to
change. Remove the unused function.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
|
|
The documentation for schedule_on_each_cpu() states that it calls a
function on each online CPU from keventd. This can easily be
interpreted as an asyncronous call because the description does not
mention that flush_work is called. Clarify that it is synchronous.
tj: rephrased a bit
Signed-off-by: Mel Gorman <mel@csn.ul.ie>
Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
|
|
'st-ux' and 'unwind' into devel
|
|
KVM uses it for example:
ERROR: "account_system_vtime" [arch/x86/kvm/kvm.ko] undefined!
Cc: Venkatesh Pallipadi <venki@google.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-3-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
When CPU is idle and on first interrupt, irq_enter calls tick_check_idle()
to notify interruption from idle. But, there is a problem if this call
is done after __irq_enter, as all routines in __irq_enter may find
stale time due to yet to be done tick_check_idle.
Specifically, trace calls in __irq_enter when they use global clock and also
account_system_vtime change in this patch as it wants to use sched_clock_cpu()
to do proper irq timing.
But, tick_check_idle was moved after __irq_enter intentionally to
prevent problem of unneeded ksoftirqd wakeups by the commit ee5f80a:
irq: call __irq_enter() before calling the tick_idle_check
Impact: avoid spurious ksoftirqd wakeups
Moving tick_check_idle() before __irq_enter and wrapping it with
local_bh_enable/disable would solve both the problems.
Fixed-by: Yong Zhang <yong.zhang0@gmail.com>
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-9-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
The idea was suggested by Peter Zijlstra here:
http://marc.info/?l=linux-kernel&m=127476934517534&w=2
irq time is technically not available to the tasks running on the CPU.
This patch removes irq time from CPU power piggybacking on
sched_rt_avg_update().
Tested this by keeping CPU X busy with a network intensive task having 75%
oa a single CPU irq processing (hard+soft) on a 4-way system. And start seven
cycle soakers on the system. Without this change, there will be two tasks on
each CPU. With this change, there is a single task on irq busy CPU X and
remaining 7 tasks are spread around among other 3 CPUs.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-8-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
Scheduler accounts both softirq and interrupt processing times to the
currently running task. This means, if the interrupt processing was
for some other task in the system, then the current task ends up being
penalized as it gets shorter runtime than otherwise.
Change sched task accounting to acoount only actual task time from
currently running task. Now update_curr(), modifies the delta_exec to
depend on rq->clock_task.
Note that this change only handles CONFIG_IRQ_TIME_ACCOUNTING case. We can
extend this to CONFIG_VIRT_CPU_ACCOUNTING with minimal effort. But, thats
for later.
This change will impact scheduling behavior in interrupt heavy conditions.
Tested on a 4-way system with eth0 handled by CPU 2 and a network heavy
task (nc) running on CPU 3 (and no RSS/RFS). With that I have CPU 2
spending 75%+ of its time in irq processing. CPU 3 spending around 35%
time running nc task.
Now, if I run another CPU intensive task on CPU 2, without this change
/proc/<pid>/schedstat shows 100% of time accounted to this task. With this
change, it rightly shows less than 25% accounted to this task as remaining
time is actually spent on irq processing.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-7-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
s390/powerpc/ia64 have support for CONFIG_VIRT_CPU_ACCOUNTING which does
the fine granularity accounting of user, system, hardirq, softirq times.
Adding that option on archs like x86 will be challenging however, given the
state of TSC reliability on various platforms and also the overhead it will
add in syscall entry exit.
Instead, add a lighter variant that only does finer accounting of
hardirq and softirq times, providing precise irq times (instead of timer tick
based samples). This accounting is added with a new config option
CONFIG_IRQ_TIME_ACCOUNTING so that there won't be any overhead for users not
interested in paying the perf penalty.
This accounting is based on sched_clock, with the code being generic.
So, other archs may find it useful as well.
This patch just adds the core logic and does not enable this logic yet.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-5-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
To account softirq time cleanly in scheduler, we need to identify whether
softirq is invoked in ksoftirqd context or softirq at hardirq tail context.
Add PF_KSOFTIRQD for that purpose.
As all PF flag bits are currently taken, create space by moving one of the
infrequently used bits (PF_THREAD_BOUND) down in task_struct to be along
with some other state fields.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-4-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
Peter Zijlstra found a bug in the way softirq time is accounted in
VIRT_CPU_ACCOUNTING on this thread:
http://lkml.indiana.edu/hypermail//linux/kernel/1009.2/01366.html
The problem is, softirq processing uses local_bh_disable internally. There
is no way, later in the flow, to differentiate between whether softirq is
being processed or is it just that bh has been disabled. So, a hardirq when bh
is disabled results in time being wrongly accounted as softirq.
Looking at the code a bit more, the problem exists in !VIRT_CPU_ACCOUNTING
as well. As account_system_time() in normal tick based accouting also uses
softirq_count, which will be set even when not in softirq with bh disabled.
Peter also suggested solution of using 2*SOFTIRQ_OFFSET as irq count
for local_bh_{disable,enable} and using just SOFTIRQ_OFFSET while softirq
processing. The patch below does that and adds API in_serving_softirq() which
returns whether we are currently processing softirq or not.
Also changes one of the usages of softirq_count in net/sched/cls_cgroup.c
to in_serving_softirq.
Looks like many usages of in_softirq really want in_serving_softirq. Those
changes can be made individually on a case by case basis.
Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-2-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
When SD_PREFER_SIBLING is set on a sched domain, drop group_capacity to 1
only if the local group has extra capacity. The extra check prevents the case
where you always pull from the heaviest group when it is already under-utilized
(possible with a large weight task outweighs the tasks on the system).
For example, consider a 16-cpu quad-core quad-socket machine with MC and NUMA
scheduling domains. Let's say we spawn 15 nice0 tasks and one nice-15 task,
and each task is running on one core. In this case, we observe the following
events when balancing at the NUMA domain:
- find_busiest_group() will always pick the sched group containing the niced
task to be the busiest group.
- find_busiest_queue() will then always pick one of the cpus running the
nice0 task (never picks the cpu with the nice -15 task since
weighted_cpuload > imbalance).
- The load balancer fails to migrate the task since it is the running task
and increments sd->nr_balance_failed.
- It repeats the above steps a few more times until sd->nr_balance_failed > 5,
at which point it kicks off the active load balancer, wakes up the migration
thread and kicks the nice 0 task off the cpu.
The load balancer doesn't stop until we kick out all nice 0 tasks from
the sched group, leaving you with 3 idle cpus and one cpu running the
nice -15 task.
When balancing at the NUMA domain, we drop sgs.group_capacity to 1 if the child
domain (in this case MC) has SD_PREFER_SIBLING set. Subsequent load checks are
not relevant because the niced task has a very large weight.
In this patch, we add an extra condition to the "if(prefer_sibling)" check in
update_sd_lb_stats(). We drop the capacity of a group only if the local group
has extra capacity, ie. nr_running < group_capacity. This patch preserves the
original intent of the prefer_siblings check (to spread tasks across the system
in low utilization scenarios) and fixes the case above.
It helps in the following ways:
- In low utilization cases (where nr_tasks << nr_cpus), we still drop
group_capacity down to 1 if we prefer siblings.
- On very busy systems (where nr_tasks >> nr_cpus), sgs.nr_running will most
likely be > sgs.group_capacity.
- When balancing large weight tasks, if the local group does not have extra
capacity, we do not pick the group with the niced task as the busiest group.
This prevents failed balances, active migration and the under-utilization
described above.
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1287173550-30365-5-git-send-email-ncrao@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
This patch forces a load balance on a newly idle cpu when the local group has
extra capacity and the busiest group does not have any. It improves system
utilization when balancing tasks with a large weight differential.
Under certain situations, such as a niced down task (i.e. nice = -15) in the
presence of nr_cpus NICE0 tasks, the niced task lands on a sched group and
kicks away other tasks because of its large weight. This leads to sub-optimal
utilization of the machine. Even though the sched group has capacity, it does
not pull tasks because sds.this_load >> sds.max_load, and f_b_g() returns NULL.
With this patch, if the local group has extra capacity, we shortcut the checks
in f_b_g() and try to pull a task over. A sched group has extra capacity if the
group capacity is greater than the number of running tasks in that group.
Thanks to Mike Galbraith for discussions leading to this patch and for the
insight to reuse SD_NEWIDLE_BALANCE.
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1287173550-30365-4-git-send-email-ncrao@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
When cycling through sched groups to determine the busiest group, set
group_imb only if the busiest cpu has more than 1 runnable task. This patch
fixes the case where two cpus in a group have one runnable task each, but there
is a large weight differential between these two tasks. The load balancer is
unable to migrate any task from this group, and hence do not consider this
group to be imbalanced.
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286996978-7007-3-git-send-email-ncrao@google.com>
[ small code readability edits ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
This patch adds a check in task_hot to return if the task has SCHED_IDLE
policy. SCHED_IDLE tasks have very low weight, and when run with regular
workloads, are typically scheduled many milliseconds apart. There is no
need to consider these tasks hot for load balancing.
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1287173550-30365-2-git-send-email-ncrao@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
Trades a call + conditional + ret for an unconditional jmp.
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20101014203625.501657727@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
Now that there's still only a few users around, rename things to make
them more consistent.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20101014203625.448565169@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
hw_breakpoint creation needs to account stuff per-task to ensure there
is always sufficient hardware resources to back these things due to
ptrace.
With the perf per pmu context changes the event initialization no
longer has access to the event context, for the simple reason that we
need to first find the pmu (result of initialization) before we can
find the context.
This makes hw_breakpoints unhappy, because it can no longer do per
task accounting, cure this by frobbing a task pointer in the event::hw
bits for now...
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20101014203625.391543667@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
So that we can pass the task pointer to the event allocation, so that
we can use task associated data during event initialization.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20101014203625.340789919@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
Currently it looks like find_lively_task_by_vpid() takes a task ref
and relies on find_get_context() to drop it.
The problem is that perf_event_create_kernel_counter() shouldn't be
dropping task refs.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Acked-by: Matt Helsley <matthltc@us.ibm.com>
LKML-Reference: <20101014203625.278436085@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
Matt found we trigger the WARN_ON_ONCE() in perf_group_attach() when we take
the move_group path in perf_event_open().
Since we cannot de-construct the group (we rely on it to move the events), we
have to simply ignore the double attach. The group state is context invariant
and doesn't need changing.
Reported-by: Matt Fleming <matt@console-pimps.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1287135757.29097.1368.camel@twins>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
Provide a mechanism that allows running code in IRQ context. It is
most useful for NMI code that needs to interact with the rest of the
system -- like wakeup a task to drain buffers.
Perf currently has such a mechanism, so extract that and provide it as
a generic feature, independent of perf so that others may also
benefit.
The IRQ context callback is generated through self-IPIs where
possible, or on architectures like powerpc the decrementer (the
built-in timer facility) is set to generate an interrupt immediately.
Architectures that don't have anything like this get to do with a
callback from the timer tick. These architectures can call
irq_work_run() at the tail of any IRQ handlers that might enqueue such
work (like the perf IRQ handler) to avoid undue latencies in
processing the work.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Kyle McMartin <kyle@mcmartin.ca>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[ various fixes ]
Signed-off-by: Huang Ying <ying.huang@intel.com>
LKML-Reference: <1287036094.7768.291.camel@yhuang-dev>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
The group_sched_in() function uses a transactional approach to schedule
a group of events. In a group, either all events can be scheduled or
none are. To schedule each event in, the function calls event_sched_in().
In case of error, event_sched_out() is called on each event in the group.
The problem is that event_sched_out() does not completely cancel the
effects of event_sched_in(). Furthermore event_sched_out() changes the
state of the event as if it had run which is not true is this particular
case.
Those inconsistencies impact time tracking fields and may lead to events
in a group not all reporting the same time_enabled and time_running values.
This is demonstrated with the example below:
$ task -eunhalted_core_cycles,baclears,baclears -e unhalted_core_cycles,baclears,baclears sleep 5
1946101 unhalted_core_cycles (32.85% scaling, ena=829181, run=556827)
11423 baclears (32.85% scaling, ena=829181, run=556827)
7671 baclears (0.00% scaling, ena=556827, run=556827)
2250443 unhalted_core_cycles (57.83% scaling, ena=962822, run=405995)
11705 baclears (57.83% scaling, ena=962822, run=405995)
11705 baclears (57.83% scaling, ena=962822, run=405995)
Notice that in the first group, the last baclears event does not
report the same timings as its siblings.
This issue comes from the fact that tstamp_stopped is updated
by event_sched_out() as if the event had actually run.
To solve the issue, we must ensure that, in case of error, there is
no change in the event state whatsoever. That means timings must
remain as they were when entering group_sched_in().
To do this we defer updating tstamp_running until we know the
transaction succeeded. Therefore, we have split event_sched_in()
in two parts separating the update to tstamp_running.
Similarly, in case of error, we do not want to update tstamp_stopped.
Therefore, we have split event_sched_out() in two parts separating
the update to tstamp_stopped.
With this patch, we now get the following output:
$ task -eunhalted_core_cycles,baclears,baclears -e unhalted_core_cycles,baclears,baclears sleep 5
2492050 unhalted_core_cycles (71.75% scaling, ena=1093330, run=308841)
11243 baclears (71.75% scaling, ena=1093330, run=308841)
11243 baclears (71.75% scaling, ena=1093330, run=308841)
1852746 unhalted_core_cycles (0.00% scaling, ena=784489, run=784489)
9253 baclears (0.00% scaling, ena=784489, run=784489)
9253 baclears (0.00% scaling, ena=784489, run=784489)
Note that the uneven timing between groups is a side effect of
the process spending most of its time sleeping, i.e., not enough
event rotations (but that's a separate issue).
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <4cb86b4c.41e9d80a.44e9.3e19@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
|
You can only call update_context_time() when the context
is active, i.e., the thread it is attached to is still running.
However, perf_event_read() can be called even when the context
is inactive, e.g., user read() the counters. The call to
update_context_time() must be conditioned on the status of
the context, otherwise, bogus time_enabled, time_running may
be returned. Here is an example on AMD64. The task program
is an example from libpfm4. The -p prints deltas every 1s.
$ task -p -e cpu_clk_unhalted sleep 5
2,266,610 cpu_clk_unhalted (0.00% scaling, ena=2,158,982, run=2,158,982)
0 cpu_clk_unhalted (0.00% scaling, ena=2,158,982, run=2,158,982)
0 cpu_clk_unhalted (0.00% scaling, ena=2,158,982, run=2,158,982)
0 cpu_clk_unhalted (0.00% scaling, ena=2,158,982, run=2,158,982)
0 cpu_clk_unhalted (0.00% scaling, ena=2,158,982, run=2,158,982)
5,242,358,071 cpu_clk_unhalted (99.95% scaling, ena=5,000,359,984, run=2,319,270)
Whereas if you don't read deltas, e.g., no call to perf_event_read() until
the process terminates:
$ task -e cpu_clk_unhalted sleep 5
2,497,783 cpu_clk_unhalted (0.00% scaling, ena=2,376,899, run=2,376,899)
Notice that time_enable, time_running are bogus in the first example
causing bogus scaling.
This patch fixes the problem, by conditionally calling update_context_time()
in perf_event_read().
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: stable@kernel.org
LKML-Reference: <4cb856dc.51edd80a.5ae0.38fb@mx.google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
|
