linux/kernel/sched_fair.c

2103 lines
50 KiB
C
Raw Normal View History

/*
* Completely Fair Scheduling (CFS) Class (SCHED_NORMAL/SCHED_BATCH)
*
* Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
*
* Interactivity improvements by Mike Galbraith
* (C) 2007 Mike Galbraith <efault@gmx.de>
*
* Various enhancements by Dmitry Adamushko.
* (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
*
* Group scheduling enhancements by Srivatsa Vaddagiri
* Copyright IBM Corporation, 2007
* Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
*
* Scaled math optimizations by Thomas Gleixner
* Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
*
* Adaptive scheduling granularity, math enhancements by Peter Zijlstra
* Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
*/
#include <linux/latencytop.h>
#include <linux/sched.h>
/*
* Targeted preemption latency for CPU-bound tasks:
* (default: 5ms * (1 + ilog(ncpus)), units: nanoseconds)
*
* NOTE: this latency value is not the same as the concept of
* 'timeslice length' - timeslices in CFS are of variable length
* and have no persistent notion like in traditional, time-slice
* based scheduling concepts.
*
* (to see the precise effective timeslice length of your workload,
* run vmstat and monitor the context-switches (cs) field)
*/
unsigned int sysctl_sched_latency = 5000000ULL;
unsigned int normalized_sysctl_sched_latency = 5000000ULL;
/*
* The initial- and re-scaling of tunables is configurable
* (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus))
*
* Options are:
* SCHED_TUNABLESCALING_NONE - unscaled, always *1
* SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus)
* SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus
*/
enum sched_tunable_scaling sysctl_sched_tunable_scaling
= SCHED_TUNABLESCALING_LOG;
/*
* Minimal preemption granularity for CPU-bound tasks:
* (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
unsigned int sysctl_sched_min_granularity = 1000000ULL;
unsigned int normalized_sysctl_sched_min_granularity = 1000000ULL;
/*
* is kept at sysctl_sched_latency / sysctl_sched_min_granularity
*/
static unsigned int sched_nr_latency = 5;
/*
* After fork, child runs first. If set to 0 (default) then
* parent will (try to) run first.
*/
unsigned int sysctl_sched_child_runs_first __read_mostly;
/*
* sys_sched_yield() compat mode
*
* This option switches the agressive yield implementation of the
* old scheduler back on.
*/
unsigned int __read_mostly sysctl_sched_compat_yield;
/*
* SCHED_OTHER wake-up granularity.
* (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds)
*
* This option delays the preemption effects of decoupled workloads
* and reduces their over-scheduling. Synchronous workloads will still
* have immediate wakeup/sleep latencies.
*/
unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
static const struct sched_class fair_sched_class;
/**************************************************************
* CFS operations on generic schedulable entities:
*/
#ifdef CONFIG_FAIR_GROUP_SCHED
/* cpu runqueue to which this cfs_rq is attached */
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
return cfs_rq->rq;
}
/* An entity is a task if it doesn't "own" a runqueue */
#define entity_is_task(se) (!se->my_q)
static inline struct task_struct *task_of(struct sched_entity *se)
{
#ifdef CONFIG_SCHED_DEBUG
WARN_ON_ONCE(!entity_is_task(se));
#endif
return container_of(se, struct task_struct, se);
}
/* Walk up scheduling entities hierarchy */
#define for_each_sched_entity(se) \
for (; se; se = se->parent)
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
return p->se.cfs_rq;
}
/* runqueue on which this entity is (to be) queued */
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
return se->cfs_rq;
}
/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
return grp->my_q;
}
/* Given a group's cfs_rq on one cpu, return its corresponding cfs_rq on
* another cpu ('this_cpu')
*/
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
return cfs_rq->tg->cfs_rq[this_cpu];
}
/* Iterate thr' all leaf cfs_rq's on a runqueue */
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
/* Do the two (enqueued) entities belong to the same group ? */
static inline int
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
if (se->cfs_rq == pse->cfs_rq)
return 1;
return 0;
}
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
return se->parent;
}
/* return depth at which a sched entity is present in the hierarchy */
static inline int depth_se(struct sched_entity *se)
{
int depth = 0;
for_each_sched_entity(se)
depth++;
return depth;
}
static void
find_matching_se(struct sched_entity **se, struct sched_entity **pse)
{
int se_depth, pse_depth;
/*
* preemption test can be made between sibling entities who are in the
* same cfs_rq i.e who have a common parent. Walk up the hierarchy of
* both tasks until we find their ancestors who are siblings of common
* parent.
*/
/* First walk up until both entities are at same depth */
se_depth = depth_se(*se);
pse_depth = depth_se(*pse);
while (se_depth > pse_depth) {
se_depth--;
*se = parent_entity(*se);
}
while (pse_depth > se_depth) {
pse_depth--;
*pse = parent_entity(*pse);
}
while (!is_same_group(*se, *pse)) {
*se = parent_entity(*se);
*pse = parent_entity(*pse);
}
}
#else /* !CONFIG_FAIR_GROUP_SCHED */
static inline struct task_struct *task_of(struct sched_entity *se)
{
return container_of(se, struct task_struct, se);
}
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
{
return container_of(cfs_rq, struct rq, cfs);
}
#define entity_is_task(se) 1
#define for_each_sched_entity(se) \
for (; se; se = NULL)
static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
{
return &task_rq(p)->cfs;
}
static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
{
struct task_struct *p = task_of(se);
struct rq *rq = task_rq(p);
return &rq->cfs;
}
/* runqueue "owned" by this group */
static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
{
return NULL;
}
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
return &cpu_rq(this_cpu)->cfs;
}
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
static inline int
is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
return 1;
}
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
return NULL;
}
static inline void
find_matching_se(struct sched_entity **se, struct sched_entity **pse)
{
}
#endif /* CONFIG_FAIR_GROUP_SCHED */
/**************************************************************
* Scheduling class tree data structure manipulation methods:
*/
static inline u64 max_vruntime(u64 min_vruntime, u64 vruntime)
{
s64 delta = (s64)(vruntime - min_vruntime);
if (delta > 0)
min_vruntime = vruntime;
return min_vruntime;
}
static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
{
s64 delta = (s64)(vruntime - min_vruntime);
if (delta < 0)
min_vruntime = vruntime;
return min_vruntime;
}
static inline int entity_before(struct sched_entity *a,
struct sched_entity *b)
{
return (s64)(a->vruntime - b->vruntime) < 0;
}
static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
return se->vruntime - cfs_rq->min_vruntime;
}
static void update_min_vruntime(struct cfs_rq *cfs_rq)
{
u64 vruntime = cfs_rq->min_vruntime;
if (cfs_rq->curr)
vruntime = cfs_rq->curr->vruntime;
if (cfs_rq->rb_leftmost) {
struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost,
struct sched_entity,
run_node);
if (!cfs_rq->curr)
vruntime = se->vruntime;
else
vruntime = min_vruntime(vruntime, se->vruntime);
}
cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
}
/*
* Enqueue an entity into the rb-tree:
*/
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
struct rb_node *parent = NULL;
struct sched_entity *entry;
s64 key = entity_key(cfs_rq, se);
int leftmost = 1;
/*
* Find the right place in the rbtree:
*/
while (*link) {
parent = *link;
entry = rb_entry(parent, struct sched_entity, run_node);
/*
* We dont care about collisions. Nodes with
* the same key stay together.
*/
if (key < entity_key(cfs_rq, entry)) {
link = &parent->rb_left;
} else {
link = &parent->rb_right;
leftmost = 0;
}
}
/*
* Maintain a cache of leftmost tree entries (it is frequently
* used):
*/
if (leftmost)
cfs_rq->rb_leftmost = &se->run_node;
rb_link_node(&se->run_node, parent, link);
rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
}
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
if (cfs_rq->rb_leftmost == &se->run_node) {
struct rb_node *next_node;
next_node = rb_next(&se->run_node);
cfs_rq->rb_leftmost = next_node;
}
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
}
static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *left = cfs_rq->rb_leftmost;
if (!left)
return NULL;
return rb_entry(left, struct sched_entity, run_node);
}
static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
if (!last)
return NULL;
return rb_entry(last, struct sched_entity, run_node);
}
/**************************************************************
* Scheduling class statistics methods:
*/
#ifdef CONFIG_SCHED_DEBUG
int sched_proc_update_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
int factor = get_update_sysctl_factor();
if (ret || !write)
return ret;
sched_nr_latency = DIV_ROUND_UP(sysctl_sched_latency,
sysctl_sched_min_granularity);
#define WRT_SYSCTL(name) \
(normalized_sysctl_##name = sysctl_##name / (factor))
WRT_SYSCTL(sched_min_granularity);
WRT_SYSCTL(sched_latency);
WRT_SYSCTL(sched_wakeup_granularity);
WRT_SYSCTL(sched_shares_ratelimit);
#undef WRT_SYSCTL
return 0;
}
#endif
/*
* delta /= w
*/
static inline unsigned long
calc_delta_fair(unsigned long delta, struct sched_entity *se)
{
if (unlikely(se->load.weight != NICE_0_LOAD))
delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
return delta;
}
/*
* The idea is to set a period in which each task runs once.
*
* When there are too many tasks (sysctl_sched_nr_latency) we have to stretch
* this period because otherwise the slices get too small.
*
* p = (nr <= nl) ? l : l*nr/nl
*/
static u64 __sched_period(unsigned long nr_running)
{
u64 period = sysctl_sched_latency;
unsigned long nr_latency = sched_nr_latency;
if (unlikely(nr_running > nr_latency)) {
period = sysctl_sched_min_granularity;
period *= nr_running;
}
return period;
}
/*
* We calculate the wall-time slice from the period by taking a part
* proportional to the weight.
*
* s = p*P[w/rw]
*/
static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq);
for_each_sched_entity(se) {
struct load_weight *load;
struct load_weight lw;
cfs_rq = cfs_rq_of(se);
load = &cfs_rq->load;
if (unlikely(!se->on_rq)) {
lw = cfs_rq->load;
update_load_add(&lw, se->load.weight);
load = &lw;
}
slice = calc_delta_mine(slice, se->load.weight, load);
}
return slice;
}
/*
* We calculate the vruntime slice of a to be inserted task
*
* vs = s/w
*/
static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
return calc_delta_fair(sched_slice(cfs_rq, se), se);
}
/*
* Update the current task's runtime statistics. Skip current tasks that
* are not in our scheduling class.
*/
static inline void
__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
unsigned long delta_exec)
{
unsigned long delta_exec_weighted;
schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
curr->sum_exec_runtime += delta_exec;
schedstat_add(cfs_rq, exec_clock, delta_exec);
delta_exec_weighted = calc_delta_fair(delta_exec, curr);
curr->vruntime += delta_exec_weighted;
update_min_vruntime(cfs_rq);
}
static void update_curr(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr = cfs_rq->curr;
u64 now = rq_of(cfs_rq)->clock;
unsigned long delta_exec;
if (unlikely(!curr))
return;
/*
* Get the amount of time the current task was running
* since the last time we changed load (this cannot
* overflow on 32 bits):
*/
delta_exec = (unsigned long)(now - curr->exec_start);
if (!delta_exec)
return;
__update_curr(cfs_rq, curr, delta_exec);
curr->exec_start = now;
sched: cpu accounting controller (V2) Commit cfb5285660aad4931b2ebbfa902ea48a37dfffa1 removed a useful feature for us, which provided a cpu accounting resource controller. This feature would be useful if someone wants to group tasks only for accounting purpose and doesnt really want to exercise any control over their cpu consumption. The patch below reintroduces the feature. It is based on Paul Menage's original patch (Commit 62d0df64065e7c135d0002f069444fbdfc64768f), with these differences: - Removed load average information. I felt it needs more thought (esp to deal with SMP and virtualized platforms) and can be added for 2.6.25 after more discussions. - Convert group cpu usage to be nanosecond accurate (as rest of the cfs stats are) and invoke cpuacct_charge() from the respective scheduler classes - Make accounting scalable on SMP systems by splitting the usage counter to be per-cpu - Move the code from kernel/cpu_acct.c to kernel/sched.c (since the code is not big enough to warrant a new file and also this rightly needs to live inside the scheduler. Also things like accessing rq->lock while reading cpu usage becomes easier if the code lived in kernel/sched.c) The patch also modifies the cpu controller not to provide the same accounting information. Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com> Tested the patches on top of 2.6.24-rc3. The patches work fine. Ran some simple tests like cpuspin (spin on the cpu), ran several tasks in the same group and timed them. Compared their time stamps with cpuacct.usage. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-12-02 19:04:49 +00:00
if (entity_is_task(curr)) {
struct task_struct *curtask = task_of(curr);
trace_sched_stat_runtime(curtask, delta_exec, curr->vruntime);
sched: cpu accounting controller (V2) Commit cfb5285660aad4931b2ebbfa902ea48a37dfffa1 removed a useful feature for us, which provided a cpu accounting resource controller. This feature would be useful if someone wants to group tasks only for accounting purpose and doesnt really want to exercise any control over their cpu consumption. The patch below reintroduces the feature. It is based on Paul Menage's original patch (Commit 62d0df64065e7c135d0002f069444fbdfc64768f), with these differences: - Removed load average information. I felt it needs more thought (esp to deal with SMP and virtualized platforms) and can be added for 2.6.25 after more discussions. - Convert group cpu usage to be nanosecond accurate (as rest of the cfs stats are) and invoke cpuacct_charge() from the respective scheduler classes - Make accounting scalable on SMP systems by splitting the usage counter to be per-cpu - Move the code from kernel/cpu_acct.c to kernel/sched.c (since the code is not big enough to warrant a new file and also this rightly needs to live inside the scheduler. Also things like accessing rq->lock while reading cpu usage becomes easier if the code lived in kernel/sched.c) The patch also modifies the cpu controller not to provide the same accounting information. Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com> Tested the patches on top of 2.6.24-rc3. The patches work fine. Ran some simple tests like cpuspin (spin on the cpu), ran several tasks in the same group and timed them. Compared their time stamps with cpuacct.usage. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-12-02 19:04:49 +00:00
cpuacct_charge(curtask, delta_exec);
timers: fix itimer/many thread hang Overview This patch reworks the handling of POSIX CPU timers, including the ITIMER_PROF, ITIMER_VIRT timers and rlimit handling. It was put together with the help of Roland McGrath, the owner and original writer of this code. The problem we ran into, and the reason for this rework, has to do with using a profiling timer in a process with a large number of threads. It appears that the performance of the old implementation of run_posix_cpu_timers() was at least O(n*3) (where "n" is the number of threads in a process) or worse. Everything is fine with an increasing number of threads until the time taken for that routine to run becomes the same as or greater than the tick time, at which point things degrade rather quickly. This patch fixes bug 9906, "Weird hang with NPTL and SIGPROF." Code Changes This rework corrects the implementation of run_posix_cpu_timers() to make it run in constant time for a particular machine. (Performance may vary between one machine and another depending upon whether the kernel is built as single- or multiprocessor and, in the latter case, depending upon the number of running processors.) To do this, at each tick we now update fields in signal_struct as well as task_struct. The run_posix_cpu_timers() function uses those fields to make its decisions. We define a new structure, "task_cputime," to contain user, system and scheduler times and use these in appropriate places: struct task_cputime { cputime_t utime; cputime_t stime; unsigned long long sum_exec_runtime; }; This is included in the structure "thread_group_cputime," which is a new substructure of signal_struct and which varies for uniprocessor versus multiprocessor kernels. For uniprocessor kernels, it uses "task_cputime" as a simple substructure, while for multiprocessor kernels it is a pointer: struct thread_group_cputime { struct task_cputime totals; }; struct thread_group_cputime { struct task_cputime *totals; }; We also add a new task_cputime substructure directly to signal_struct, to cache the earliest expiration of process-wide timers, and task_cputime also replaces the it_*_expires fields of task_struct (used for earliest expiration of thread timers). The "thread_group_cputime" structure contains process-wide timers that are updated via account_user_time() and friends. In the non-SMP case the structure is a simple aggregator; unfortunately in the SMP case that simplicity was not achievable due to cache-line contention between CPUs (in one measured case performance was actually _worse_ on a 16-cpu system than the same test on a 4-cpu system, due to this contention). For SMP, the thread_group_cputime counters are maintained as a per-cpu structure allocated using alloc_percpu(). The timer functions update only the timer field in the structure corresponding to the running CPU, obtained using per_cpu_ptr(). We define a set of inline functions in sched.h that we use to maintain the thread_group_cputime structure and hide the differences between UP and SMP implementations from the rest of the kernel. The thread_group_cputime_init() function initializes the thread_group_cputime structure for the given task. The thread_group_cputime_alloc() is a no-op for UP; for SMP it calls the out-of-line function thread_group_cputime_alloc_smp() to allocate and fill in the per-cpu structures and fields. The thread_group_cputime_free() function, also a no-op for UP, in SMP frees the per-cpu structures. The thread_group_cputime_clone_thread() function (also a UP no-op) for SMP calls thread_group_cputime_alloc() if the per-cpu structures haven't yet been allocated. The thread_group_cputime() function fills the task_cputime structure it is passed with the contents of the thread_group_cputime fields; in UP it's that simple but in SMP it must also safely check that tsk->signal is non-NULL (if it is it just uses the appropriate fields of task_struct) and, if so, sums the per-cpu values for each online CPU. Finally, the three functions account_group_user_time(), account_group_system_time() and account_group_exec_runtime() are used by timer functions to update the respective fields of the thread_group_cputime structure. Non-SMP operation is trivial and will not be mentioned further. The per-cpu structure is always allocated when a task creates its first new thread, via a call to thread_group_cputime_clone_thread() from copy_signal(). It is freed at process exit via a call to thread_group_cputime_free() from cleanup_signal(). All functions that formerly summed utime/stime/sum_sched_runtime values from from all threads in the thread group now use thread_group_cputime() to snapshot the values in the thread_group_cputime structure or the values in the task structure itself if the per-cpu structure hasn't been allocated. Finally, the code in kernel/posix-cpu-timers.c has changed quite a bit. The run_posix_cpu_timers() function has been split into a fast path and a slow path; the former safely checks whether there are any expired thread timers and, if not, just returns, while the slow path does the heavy lifting. With the dedicated thread group fields, timers are no longer "rebalanced" and the process_timer_rebalance() function and related code has gone away. All summing loops are gone and all code that used them now uses the thread_group_cputime() inline. When process-wide timers are set, the new task_cputime structure in signal_struct is used to cache the earliest expiration; this is checked in the fast path. Performance The fix appears not to add significant overhead to existing operations. It generally performs the same as the current code except in two cases, one in which it performs slightly worse (Case 5 below) and one in which it performs very significantly better (Case 2 below). Overall it's a wash except in those two cases. I've since done somewhat more involved testing on a dual-core Opteron system. Case 1: With no itimer running, for a test with 100,000 threads, the fixed kernel took 1428.5 seconds, 513 seconds more than the unfixed system, all of which was spent in the system. There were twice as many voluntary context switches with the fix as without it. Case 2: With an itimer running at .01 second ticks and 4000 threads (the most an unmodified kernel can handle), the fixed kernel ran the test in eight percent of the time (5.8 seconds as opposed to 70 seconds) and had better tick accuracy (.012 seconds per tick as opposed to .023 seconds per tick). Case 3: A 4000-thread test with an initial timer tick of .01 second and an interval of 10,000 seconds (i.e. a timer that ticks only once) had very nearly the same performance in both cases: 6.3 seconds elapsed for the fixed kernel versus 5.5 seconds for the unfixed kernel. With fewer threads (eight in these tests), the Case 1 test ran in essentially the same time on both the modified and unmodified kernels (5.2 seconds versus 5.8 seconds). The Case 2 test ran in about the same time as well, 5.9 seconds versus 5.4 seconds but again with much better tick accuracy, .013 seconds per tick versus .025 seconds per tick for the unmodified kernel. Since the fix affected the rlimit code, I also tested soft and hard CPU limits. Case 4: With a hard CPU limit of 20 seconds and eight threads (and an itimer running), the modified kernel was very slightly favored in that while it killed the process in 19.997 seconds of CPU time (5.002 seconds of wall time), only .003 seconds of that was system time, the rest was user time. The unmodified kernel killed the process in 20.001 seconds of CPU (5.014 seconds of wall time) of which .016 seconds was system time. Really, though, the results were too close to call. The results were essentially the same with no itimer running. Case 5: With a soft limit of 20 seconds and a hard limit of 2000 seconds (where the hard limit would never be reached) and an itimer running, the modified kernel exhibited worse tick accuracy than the unmodified kernel: .050 seconds/tick versus .028 seconds/tick. Otherwise, performance was almost indistinguishable. With no itimer running this test exhibited virtually identical behavior and times in both cases. In times past I did some limited performance testing. those results are below. On a four-cpu Opteron system without this fix, a sixteen-thread test executed in 3569.991 seconds, of which user was 3568.435s and system was 1.556s. On the same system with the fix, user and elapsed time were about the same, but system time dropped to 0.007 seconds. Performance with eight, four and one thread were comparable. Interestingly, the timer ticks with the fix seemed more accurate: The sixteen-thread test with the fix received 149543 ticks for 0.024 seconds per tick, while the same test without the fix received 58720 for 0.061 seconds per tick. Both cases were configured for an interval of 0.01 seconds. Again, the other tests were comparable. Each thread in this test computed the primes up to 25,000,000. I also did a test with a large number of threads, 100,000 threads, which is impossible without the fix. In this case each thread computed the primes only up to 10,000 (to make the runtime manageable). System time dominated, at 1546.968 seconds out of a total 2176.906 seconds (giving a user time of 629.938s). It received 147651 ticks for 0.015 seconds per tick, still quite accurate. There is obviously no comparable test without the fix. Signed-off-by: Frank Mayhar <fmayhar@google.com> Cc: Roland McGrath <roland@redhat.com> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-09-12 16:54:39 +00:00
account_group_exec_runtime(curtask, delta_exec);
sched: cpu accounting controller (V2) Commit cfb5285660aad4931b2ebbfa902ea48a37dfffa1 removed a useful feature for us, which provided a cpu accounting resource controller. This feature would be useful if someone wants to group tasks only for accounting purpose and doesnt really want to exercise any control over their cpu consumption. The patch below reintroduces the feature. It is based on Paul Menage's original patch (Commit 62d0df64065e7c135d0002f069444fbdfc64768f), with these differences: - Removed load average information. I felt it needs more thought (esp to deal with SMP and virtualized platforms) and can be added for 2.6.25 after more discussions. - Convert group cpu usage to be nanosecond accurate (as rest of the cfs stats are) and invoke cpuacct_charge() from the respective scheduler classes - Make accounting scalable on SMP systems by splitting the usage counter to be per-cpu - Move the code from kernel/cpu_acct.c to kernel/sched.c (since the code is not big enough to warrant a new file and also this rightly needs to live inside the scheduler. Also things like accessing rq->lock while reading cpu usage becomes easier if the code lived in kernel/sched.c) The patch also modifies the cpu controller not to provide the same accounting information. Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com> Tested the patches on top of 2.6.24-rc3. The patches work fine. Ran some simple tests like cpuspin (spin on the cpu), ran several tasks in the same group and timed them. Compared their time stamps with cpuacct.usage. Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-12-02 19:04:49 +00:00
}
}
static inline void
update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
}
/*
* Task is being enqueued - update stats:
*/
static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/*
* Are we enqueueing a waiting task? (for current tasks
* a dequeue/enqueue event is a NOP)
*/
if (se != cfs_rq->curr)
update_stats_wait_start(cfs_rq, se);
}
static void
update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
schedstat_set(se->wait_max, max(se->wait_max,
rq_of(cfs_rq)->clock - se->wait_start));
schedstat_set(se->wait_count, se->wait_count + 1);
schedstat_set(se->wait_sum, se->wait_sum +
rq_of(cfs_rq)->clock - se->wait_start);
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
trace_sched_stat_wait(task_of(se),
rq_of(cfs_rq)->clock - se->wait_start);
}
#endif
schedstat_set(se->wait_start, 0);
}
static inline void
update_stats_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/*
* Mark the end of the wait period if dequeueing a
* waiting task:
*/
if (se != cfs_rq->curr)
update_stats_wait_end(cfs_rq, se);
}
/*
* We are picking a new current task - update its stats:
*/
static inline void
update_stats_curr_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/*
* We are starting a new run period:
*/
se->exec_start = rq_of(cfs_rq)->clock;
}
/**************************************************
* Scheduling class queueing methods:
*/
#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
static void
add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
{
cfs_rq->task_weight += weight;
}
#else
static inline void
add_cfs_task_weight(struct cfs_rq *cfs_rq, unsigned long weight)
{
}
#endif
static void
account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_add(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
inc_cpu_load(rq_of(cfs_rq), se->load.weight);
if (entity_is_task(se)) {
add_cfs_task_weight(cfs_rq, se->load.weight);
list_add(&se->group_node, &cfs_rq->tasks);
}
cfs_rq->nr_running++;
se->on_rq = 1;
}
static void
account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
update_load_sub(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
dec_cpu_load(rq_of(cfs_rq), se->load.weight);
if (entity_is_task(se)) {
add_cfs_task_weight(cfs_rq, -se->load.weight);
list_del_init(&se->group_node);
}
cfs_rq->nr_running--;
se->on_rq = 0;
}
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHEDSTATS
struct task_struct *tsk = NULL;
if (entity_is_task(se))
tsk = task_of(se);
if (se->sleep_start) {
u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
if ((s64)delta < 0)
delta = 0;
if (unlikely(delta > se->sleep_max))
se->sleep_max = delta;
se->sleep_start = 0;
se->sum_sleep_runtime += delta;
if (tsk) {
account_scheduler_latency(tsk, delta >> 10, 1);
trace_sched_stat_sleep(tsk, delta);
}
}
if (se->block_start) {
u64 delta = rq_of(cfs_rq)->clock - se->block_start;
if ((s64)delta < 0)
delta = 0;
if (unlikely(delta > se->block_max))
se->block_max = delta;
se->block_start = 0;
se->sum_sleep_runtime += delta;
if (tsk) {
if (tsk->in_iowait) {
se->iowait_sum += delta;
se->iowait_count++;
trace_sched_stat_iowait(tsk, delta);
}
/*
* Blocking time is in units of nanosecs, so shift by
* 20 to get a milliseconds-range estimation of the
* amount of time that the task spent sleeping:
*/
if (unlikely(prof_on == SLEEP_PROFILING)) {
profile_hits(SLEEP_PROFILING,
(void *)get_wchan(tsk),
delta >> 20);
}
account_scheduler_latency(tsk, delta >> 10, 0);
}
}
#endif
}
static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHED_DEBUG
s64 d = se->vruntime - cfs_rq->min_vruntime;
if (d < 0)
d = -d;
if (d > 3*sysctl_sched_latency)
schedstat_inc(cfs_rq, nr_spread_over);
#endif
}
static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
{
u64 vruntime = cfs_rq->min_vruntime;
/*
* The 'current' period is already promised to the current tasks,
* however the extra weight of the new task will slow them down a
* little, place the new task so that it fits in the slot that
* stays open at the end.
*/
if (initial && sched_feat(START_DEBIT))
vruntime += sched_vslice(cfs_rq, se);
/* sleeps up to a single latency don't count. */
if (!initial && sched_feat(FAIR_SLEEPERS)) {
unsigned long thresh = sysctl_sched_latency;
/*
* Convert the sleeper threshold into virtual time.
* SCHED_IDLE is a special sub-class. We care about
* fairness only relative to other SCHED_IDLE tasks,
* all of which have the same weight.
*/
if (sched_feat(NORMALIZED_SLEEPER) && (!entity_is_task(se) ||
task_of(se)->policy != SCHED_IDLE))
thresh = calc_delta_fair(thresh, se);
/*
* Halve their sleep time's effect, to allow
* for a gentler effect of sleepers:
*/
if (sched_feat(GENTLE_FAIR_SLEEPERS))
thresh >>= 1;
vruntime -= thresh;
}
/* ensure we never gain time by being placed backwards. */
vruntime = max_vruntime(se->vruntime, vruntime);
se->vruntime = vruntime;
}
static void
enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int wakeup)
{
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
account_entity_enqueue(cfs_rq, se);
if (wakeup) {
place_entity(cfs_rq, se, 0);
enqueue_sleeper(cfs_rq, se);
}
update_stats_enqueue(cfs_rq, se);
check_spread(cfs_rq, se);
if (se != cfs_rq->curr)
__enqueue_entity(cfs_rq, se);
}
static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
if (!se || cfs_rq->last == se)
cfs_rq->last = NULL;
if (!se || cfs_rq->next == se)
cfs_rq->next = NULL;
}
static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
for_each_sched_entity(se)
__clear_buddies(cfs_rq_of(se), se);
}
static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
{
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
update_stats_dequeue(cfs_rq, se);
if (sleep) {
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
struct task_struct *tsk = task_of(se);
if (tsk->state & TASK_INTERRUPTIBLE)
se->sleep_start = rq_of(cfs_rq)->clock;
if (tsk->state & TASK_UNINTERRUPTIBLE)
se->block_start = rq_of(cfs_rq)->clock;
}
#endif
}
clear_buddies(cfs_rq, se);
if (se != cfs_rq->curr)
__dequeue_entity(cfs_rq, se);
account_entity_dequeue(cfs_rq, se);
update_min_vruntime(cfs_rq);
}
/*
* Preempt the current task with a newly woken task if needed:
*/
static void
check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
unsigned long ideal_runtime, delta_exec;
ideal_runtime = sched_slice(cfs_rq, curr);
delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
if (delta_exec > ideal_runtime) {
resched_task(rq_of(cfs_rq)->curr);
/*
* The current task ran long enough, ensure it doesn't get
* re-elected due to buddy favours.
*/
clear_buddies(cfs_rq, curr);
sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 21:09:22 +00:00
return;
}
/*
* Ensure that a task that missed wakeup preemption by a
* narrow margin doesn't have to wait for a full slice.
* This also mitigates buddy induced latencies under load.
*/
if (!sched_feat(WAKEUP_PREEMPT))
return;
if (delta_exec < sysctl_sched_min_granularity)
return;
if (cfs_rq->nr_running > 1) {
struct sched_entity *se = __pick_next_entity(cfs_rq);
s64 delta = curr->vruntime - se->vruntime;
if (delta > ideal_runtime)
resched_task(rq_of(cfs_rq)->curr);
}
}
static void
set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
/* 'current' is not kept within the tree. */
if (se->on_rq) {
/*
* Any task has to be enqueued before it get to execute on
* a CPU. So account for the time it spent waiting on the
* runqueue.
*/
update_stats_wait_end(cfs_rq, se);
__dequeue_entity(cfs_rq, se);
}
update_stats_curr_start(cfs_rq, se);
cfs_rq->curr = se;
#ifdef CONFIG_SCHEDSTATS
/*
* Track our maximum slice length, if the CPU's load is at
* least twice that of our own weight (i.e. dont track it
* when there are only lesser-weight tasks around):
*/
if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
se->slice_max = max(se->slice_max,
se->sum_exec_runtime - se->prev_sum_exec_runtime);
}
#endif
se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
struct sched_entity *se = __pick_next_entity(cfs_rq);
sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 21:09:22 +00:00
struct sched_entity *left = se;
sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 21:09:22 +00:00
if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1)
se = cfs_rq->next;
sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 21:09:22 +00:00
/*
* Prefer last buddy, try to return the CPU to a preempted task.
*/
if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1)
se = cfs_rq->last;
clear_buddies(cfs_rq, se);
return se;
}
static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
{
/*
* If still on the runqueue then deactivate_task()
* was not called and update_curr() has to be done:
*/
if (prev->on_rq)
update_curr(cfs_rq);
check_spread(cfs_rq, prev);
if (prev->on_rq) {
update_stats_wait_start(cfs_rq, prev);
/* Put 'current' back into the tree. */
__enqueue_entity(cfs_rq, prev);
}
cfs_rq->curr = NULL;
}
static void
entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
{
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
#ifdef CONFIG_SCHED_HRTICK
/*
* queued ticks are scheduled to match the slice, so don't bother
* validating it and just reschedule.
*/
if (queued) {
resched_task(rq_of(cfs_rq)->curr);
return;
}
/*
* don't let the period tick interfere with the hrtick preemption
*/
if (!sched_feat(DOUBLE_TICK) &&
hrtimer_active(&rq_of(cfs_rq)->hrtick_timer))
return;
#endif
if (cfs_rq->nr_running > 1 || !sched_feat(WAKEUP_PREEMPT))
check_preempt_tick(cfs_rq, curr);
}
/**************************************************
* CFS operations on tasks:
*/
#ifdef CONFIG_SCHED_HRTICK
static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
WARN_ON(task_rq(p) != rq);
if (hrtick_enabled(rq) && cfs_rq->nr_running > 1) {
u64 slice = sched_slice(cfs_rq, se);
u64 ran = se->sum_exec_runtime - se->prev_sum_exec_runtime;
s64 delta = slice - ran;
if (delta < 0) {
if (rq->curr == p)
resched_task(p);
return;
}
/*
* Don't schedule slices shorter than 10000ns, that just
* doesn't make sense. Rely on vruntime for fairness.
*/
sched, x86: clean up hrtick implementation random uvesafb failures were reported against Gentoo: http://bugs.gentoo.org/show_bug.cgi?id=222799 and Mihai Moldovan bisected it back to: > 8f4d37ec073c17e2d4aa8851df5837d798606d6f is first bad commit > commit 8f4d37ec073c17e2d4aa8851df5837d798606d6f > Author: Peter Zijlstra <a.p.zijlstra@chello.nl> > Date: Fri Jan 25 21:08:29 2008 +0100 > > sched: high-res preemption tick Linus suspected it to be hrtick + vm86 interaction and observed: > Btw, Peter, Ingo: I think that commit is doing bad things. They aren't > _incorrect_ per se, but they are definitely bad. > > Why? > > Using random _TIF_WORK_MASK flags is really impolite for doing > "scheduling" work. There's a reason that arch/x86/kernel/entry_32.S > special-cases the _TIF_NEED_RESCHED flag: we don't want to exit out of > vm86 mode unnecessarily. > > See the "work_notifysig_v86" label, and how it does that > "save_v86_state()" thing etc etc. Right, I never liked having to fiddle with those TIF flags. Initially I needed it because the hrtimer base lock could not nest in the rq lock. That however is fixed these days. Currently the only reason left to fiddle with the TIF flags is remote wakeups. We cannot program a remote cpu's hrtimer. I've been thinking about using the new and improved IPI function call stuff to implement hrtimer_start_on(). However that does require that smp_call_function_single(.wait=0) works from interrupt context - /me looks at the latest series from Jens - Yes that does seem to be supported, good. Here's a stab at cleaning this stuff up ... Mihai reported test success as well. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Tested-by: Mihai Moldovan <ionic@ionic.de> Cc: Michal Januszewski <spock@gentoo.org> Cc: Antonino Daplas <adaplas@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-18 16:01:23 +00:00
if (rq->curr != p)
delta = max_t(s64, 10000LL, delta);
sched, x86: clean up hrtick implementation random uvesafb failures were reported against Gentoo: http://bugs.gentoo.org/show_bug.cgi?id=222799 and Mihai Moldovan bisected it back to: > 8f4d37ec073c17e2d4aa8851df5837d798606d6f is first bad commit > commit 8f4d37ec073c17e2d4aa8851df5837d798606d6f > Author: Peter Zijlstra <a.p.zijlstra@chello.nl> > Date: Fri Jan 25 21:08:29 2008 +0100 > > sched: high-res preemption tick Linus suspected it to be hrtick + vm86 interaction and observed: > Btw, Peter, Ingo: I think that commit is doing bad things. They aren't > _incorrect_ per se, but they are definitely bad. > > Why? > > Using random _TIF_WORK_MASK flags is really impolite for doing > "scheduling" work. There's a reason that arch/x86/kernel/entry_32.S > special-cases the _TIF_NEED_RESCHED flag: we don't want to exit out of > vm86 mode unnecessarily. > > See the "work_notifysig_v86" label, and how it does that > "save_v86_state()" thing etc etc. Right, I never liked having to fiddle with those TIF flags. Initially I needed it because the hrtimer base lock could not nest in the rq lock. That however is fixed these days. Currently the only reason left to fiddle with the TIF flags is remote wakeups. We cannot program a remote cpu's hrtimer. I've been thinking about using the new and improved IPI function call stuff to implement hrtimer_start_on(). However that does require that smp_call_function_single(.wait=0) works from interrupt context - /me looks at the latest series from Jens - Yes that does seem to be supported, good. Here's a stab at cleaning this stuff up ... Mihai reported test success as well. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Tested-by: Mihai Moldovan <ionic@ionic.de> Cc: Michal Januszewski <spock@gentoo.org> Cc: Antonino Daplas <adaplas@gmail.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-07-18 16:01:23 +00:00
hrtick_start(rq, delta);
}
}
/*
* called from enqueue/dequeue and updates the hrtick when the
* current task is from our class and nr_running is low enough
* to matter.
*/
static void hrtick_update(struct rq *rq)
{
struct task_struct *curr = rq->curr;
if (curr->sched_class != &fair_sched_class)
return;
if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency)
hrtick_start_fair(rq, curr);
}
#else /* !CONFIG_SCHED_HRTICK */
static inline void
hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
}
static inline void hrtick_update(struct rq *rq)
{
}
#endif
/*
* The enqueue_task method is called before nr_running is
* increased. Here we update the fair scheduling stats and
* then put the task into the rbtree:
*/
static void enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
for_each_sched_entity(se) {
if (se->on_rq)
break;
cfs_rq = cfs_rq_of(se);
enqueue_entity(cfs_rq, se, wakeup);
wakeup = 1;
}
hrtick_update(rq);
}
/*
* The dequeue_task method is called before nr_running is
* decreased. We remove the task from the rbtree and
* update the fair scheduling stats:
*/
static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
dequeue_entity(cfs_rq, se, sleep);
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight)
break;
sleep = 1;
}
hrtick_update(rq);
}
/*
* sched_yield() support is very simple - we dequeue and enqueue.
*
* If compat_yield is turned on then we requeue to the end of the tree.
*/
static void yield_task_fair(struct rq *rq)
{
struct task_struct *curr = rq->curr;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
struct sched_entity *rightmost, *se = &curr->se;
/*
* Are we the only task in the tree?
*/
if (unlikely(cfs_rq->nr_running == 1))
return;
clear_buddies(cfs_rq, se);
if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
update_rq_clock(rq);
/*
* Update run-time statistics of the 'current'.
*/
update_curr(cfs_rq);
return;
}
/*
* Find the rightmost entry in the rbtree:
*/
rightmost = __pick_last_entity(cfs_rq);
/*
* Already in the rightmost position?
*/
if (unlikely(!rightmost || entity_before(rightmost, se)))
return;
/*
* Minimally necessary key value to be last in the tree:
* Upon rescheduling, sched_class::put_prev_task() will place
* 'current' within the tree based on its new key value.
*/
se->vruntime = rightmost->vruntime + 1;
}
#ifdef CONFIG_SMP
#ifdef CONFIG_FAIR_GROUP_SCHED
/*
* effective_load() calculates the load change as seen from the root_task_group
*
* Adding load to a group doesn't make a group heavier, but can cause movement
* of group shares between cpus. Assuming the shares were perfectly aligned one
* can calculate the shift in shares.
*
* The problem is that perfectly aligning the shares is rather expensive, hence
* we try to avoid doing that too often - see update_shares(), which ratelimits
* this change.
*
* We compensate this by not only taking the current delta into account, but
* also considering the delta between when the shares were last adjusted and
* now.
*
* We still saw a performance dip, some tracing learned us that between
* cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
* significantly. Therefore try to bias the error in direction of failing
* the affine wakeup.
*
*/
static long effective_load(struct task_group *tg, int cpu,
long wl, long wg)
{
struct sched_entity *se = tg->se[cpu];
if (!tg->parent)
return wl;
/*
* By not taking the decrease of shares on the other cpu into
* account our error leans towards reducing the affine wakeups.
*/
if (!wl && sched_feat(ASYM_EFF_LOAD))
return wl;
for_each_sched_entity(se) {
long S, rw, s, a, b;
long more_w;
/*
* Instead of using this increment, also add the difference
* between when the shares were last updated and now.
*/
more_w = se->my_q->load.weight - se->my_q->rq_weight;
wl += more_w;
wg += more_w;
S = se->my_q->tg->shares;
s = se->my_q->shares;
rw = se->my_q->rq_weight;
a = S*(rw + wl);
b = S*rw + s*wg;
wl = s*(a-b);
if (likely(b))
wl /= b;
/*
* Assume the group is already running and will
* thus already be accounted for in the weight.
*
* That is, moving shares between CPUs, does not
* alter the group weight.
*/
wg = 0;
}
return wl;
}
#else
static inline unsigned long effective_load(struct task_group *tg, int cpu,
unsigned long wl, unsigned long wg)
{
return wl;
}
#endif
static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
{
struct task_struct *curr = current;
unsigned long this_load, load;
int idx, this_cpu, prev_cpu;
unsigned long tl_per_task;
unsigned int imbalance;
struct task_group *tg;
unsigned long weight;
int balanced;
idx = sd->wake_idx;
this_cpu = smp_processor_id();
prev_cpu = task_cpu(p);
load = source_load(prev_cpu, idx);
this_load = target_load(this_cpu, idx);
if (sync) {
if (sched_feat(SYNC_LESS) &&
(curr->se.avg_overlap > sysctl_sched_migration_cost ||
p->se.avg_overlap > sysctl_sched_migration_cost))
sync = 0;
} else {
if (sched_feat(SYNC_MORE) &&
(curr->se.avg_overlap < sysctl_sched_migration_cost &&
p->se.avg_overlap < sysctl_sched_migration_cost))
sync = 1;
}
/*
* If sync wakeup then subtract the (maximum possible)
* effect of the currently running task from the load
* of the current CPU:
*/
if (sync) {
tg = task_group(current);
weight = current->se.load.weight;
this_load += effective_load(tg, this_cpu, -weight, -weight);
load += effective_load(tg, prev_cpu, 0, -weight);
}
tg = task_group(p);
weight = p->se.load.weight;
imbalance = 100 + (sd->imbalance_pct - 100) / 2;
/*
* In low-load situations, where prev_cpu is idle and this_cpu is idle
* due to the sync cause above having dropped this_load to 0, we'll
* always have an imbalance, but there's really nothing you can do
* about that, so that's good too.
*
* Otherwise check if either cpus are near enough in load to allow this
* task to be woken on this_cpu.
*/
balanced = !this_load ||
100*(this_load + effective_load(tg, this_cpu, weight, weight)) <=
imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
/*
* If the currently running task will sleep within
* a reasonable amount of time then attract this newly
* woken task:
*/
if (sync && balanced)
return 1;
schedstat_inc(p, se.nr_wakeups_affine_attempts);
tl_per_task = cpu_avg_load_per_task(this_cpu);
if (balanced ||
(this_load <= load &&
this_load + target_load(prev_cpu, idx) <= tl_per_task)) {
/*
* This domain has SD_WAKE_AFFINE and
* p is cache cold in this domain, and
* there is no bad imbalance.
*/
schedstat_inc(sd, ttwu_move_affine);
schedstat_inc(p, se.nr_wakeups_affine);
return 1;
}
return 0;
}
/*
* find_idlest_group finds and returns the least busy CPU group within the
* domain.
*/
static struct sched_group *
find_idlest_group(struct sched_domain *sd, struct task_struct *p,
int this_cpu, int load_idx)
{
struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups;
unsigned long min_load = ULONG_MAX, this_load = 0;
int imbalance = 100 + (sd->imbalance_pct-100)/2;
do {
unsigned long load, avg_load;
int local_group;
int i;
/* Skip over this group if it has no CPUs allowed */
if (!cpumask_intersects(sched_group_cpus(group),
&p->cpus_allowed))
continue;
local_group = cpumask_test_cpu(this_cpu,
sched_group_cpus(group));
/* Tally up the load of all CPUs in the group */
avg_load = 0;
for_each_cpu(i, sched_group_cpus(group)) {
/* Bias balancing toward cpus of our domain */
if (local_group)
load = source_load(i, load_idx);
else
load = target_load(i, load_idx);
avg_load += load;
}
/* Adjust by relative CPU power of the group */
avg_load = (avg_load * SCHED_LOAD_SCALE) / group->cpu_power;
if (local_group) {
this_load = avg_load;
this = group;
} else if (avg_load < min_load) {
min_load = avg_load;
idlest = group;
}
} while (group = group->next, group != sd->groups);
if (!idlest || 100*this_load < imbalance*min_load)
return NULL;
return idlest;
}
/*
* find_idlest_cpu - find the idlest cpu among the cpus in group.
*/
static int
find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
{
unsigned long load, min_load = ULONG_MAX;
int idlest = -1;
int i;
/* Traverse only the allowed CPUs */
for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
load = weighted_cpuload(i);
if (load < min_load || (load == min_load && i == this_cpu)) {
min_load = load;
idlest = i;
}
}
return idlest;
}
/*
* Try and locate an idle CPU in the sched_domain.
*/
static int
select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target)
{
int cpu = smp_processor_id();
int prev_cpu = task_cpu(p);
int i;
/*
* If this domain spans both cpu and prev_cpu (see the SD_WAKE_AFFINE
* test in select_task_rq_fair) and the prev_cpu is idle then that's
* always a better target than the current cpu.
*/
if (target == cpu && !cpu_rq(prev_cpu)->cfs.nr_running)
return prev_cpu;
/*
* Otherwise, iterate the domain and find an elegible idle cpu.
*/
for_each_cpu_and(i, sched_domain_span(sd), &p->cpus_allowed) {
if (!cpu_rq(i)->cfs.nr_running) {
target = i;
break;
}
}
return target;
}
/*
* sched_balance_self: balance the current task (running on cpu) in domains
* that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and
* SD_BALANCE_EXEC.
*
* Balance, ie. select the least loaded group.
*
* Returns the target CPU number, or the same CPU if no balancing is needed.
*
* preempt must be disabled.
*/
static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags)
{
struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
int cpu = smp_processor_id();
int prev_cpu = task_cpu(p);
int new_cpu = cpu;
int want_affine = 0;
int want_sd = 1;
int sync = wake_flags & WF_SYNC;
if (sd_flag & SD_BALANCE_WAKE) {
if (sched_feat(AFFINE_WAKEUPS) &&
cpumask_test_cpu(cpu, &p->cpus_allowed))
want_affine = 1;
new_cpu = prev_cpu;
}
for_each_domain(cpu, tmp) {
/*
* If power savings logic is enabled for a domain, see if we
* are not overloaded, if so, don't balance wider.
*/
if (tmp->flags & (SD_POWERSAVINGS_BALANCE|SD_PREFER_LOCAL)) {
unsigned long power = 0;
unsigned long nr_running = 0;
unsigned long capacity;
int i;
for_each_cpu(i, sched_domain_span(tmp)) {
power += power_of(i);
nr_running += cpu_rq(i)->cfs.nr_running;
}
capacity = DIV_ROUND_CLOSEST(power, SCHED_LOAD_SCALE);
if (tmp->flags & SD_POWERSAVINGS_BALANCE)
nr_running /= 2;
if (nr_running < capacity)
want_sd = 0;
}
/*
* While iterating the domains looking for a spanning
* WAKE_AFFINE domain, adjust the affine target to any idle cpu
* in cache sharing domains along the way.
*/
if (want_affine) {
int target = -1;
/*
* If both cpu and prev_cpu are part of this domain,
* cpu is a valid SD_WAKE_AFFINE target.
*/
if (cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
target = cpu;
/*
* If there's an idle sibling in this domain, make that
* the wake_affine target instead of the current cpu.
*/
if (tmp->flags & SD_PREFER_SIBLING)
target = select_idle_sibling(p, tmp, target);
if (target >= 0) {
if (tmp->flags & SD_WAKE_AFFINE) {
affine_sd = tmp;
want_affine = 0;
}
cpu = target;
}
}
if (!want_sd && !want_affine)
break;
if (!(tmp->flags & sd_flag))
continue;
if (want_sd)
sd = tmp;
}
if (sched_feat(LB_SHARES_UPDATE)) {
/*
* Pick the largest domain to update shares over
*/
tmp = sd;
if (affine_sd && (!tmp ||
cpumask_weight(sched_domain_span(affine_sd)) >
cpumask_weight(sched_domain_span(sd))))
tmp = affine_sd;
if (tmp)
update_shares(tmp);
}
if (affine_sd && wake_affine(affine_sd, p, sync))
return cpu;
while (sd) {
int load_idx = sd->forkexec_idx;
struct sched_group *group;
int weight;
if (!(sd->flags & sd_flag)) {
sd = sd->child;
continue;
}
if (sd_flag & SD_BALANCE_WAKE)
load_idx = sd->wake_idx;
group = find_idlest_group(sd, p, cpu, load_idx);
if (!group) {
sd = sd->child;
continue;
}
new_cpu = find_idlest_cpu(group, p, cpu);
if (new_cpu == -1 || new_cpu == cpu) {
/* Now try balancing at a lower domain level of cpu */
sd = sd->child;
continue;
}
/* Now try balancing at a lower domain level of new_cpu */
cpu = new_cpu;
weight = cpumask_weight(sched_domain_span(sd));
sd = NULL;
for_each_domain(cpu, tmp) {
if (weight <= cpumask_weight(sched_domain_span(tmp)))
break;
if (tmp->flags & sd_flag)
sd = tmp;
}
/* while loop will break here if sd == NULL */
}
return new_cpu;
}
#endif /* CONFIG_SMP */
/*
* Adaptive granularity
*
* se->avg_wakeup gives the average time a task runs until it does a wakeup,
* with the limit of wakeup_gran -- when it never does a wakeup.
*
* So the smaller avg_wakeup is the faster we want this task to preempt,
* but we don't want to treat the preemptee unfairly and therefore allow it
* to run for at least the amount of time we'd like to run.
*
* NOTE: we use 2*avg_wakeup to increase the probability of actually doing one
*
* NOTE: we use *nr_running to scale with load, this nicely matches the
* degrading latency on load.
*/
static unsigned long
adaptive_gran(struct sched_entity *curr, struct sched_entity *se)
{
u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running;
u64 gran = 0;
if (this_run < expected_wakeup)
gran = expected_wakeup - this_run;
return min_t(s64, gran, sysctl_sched_wakeup_granularity);
}
static unsigned long
wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
{
unsigned long gran = sysctl_sched_wakeup_granularity;
if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN))
gran = adaptive_gran(curr, se);
/*
* Since its curr running now, convert the gran from real-time
* to virtual-time in his units.
*/
if (sched_feat(ASYM_GRAN)) {
/*
* By using 'se' instead of 'curr' we penalize light tasks, so
* they get preempted easier. That is, if 'se' < 'curr' then
* the resulting gran will be larger, therefore penalizing the
* lighter, if otoh 'se' > 'curr' then the resulting gran will
* be smaller, again penalizing the lighter task.
*
* This is especially important for buddies when the leftmost
* task is higher priority than the buddy.
*/
if (unlikely(se->load.weight != NICE_0_LOAD))
gran = calc_delta_fair(gran, se);
} else {
if (unlikely(curr->load.weight != NICE_0_LOAD))
gran = calc_delta_fair(gran, curr);
}
return gran;
}
/*
* Should 'se' preempt 'curr'.
*
* |s1
* |s2
* |s3
* g
* |<--->|c
*
* w(c, s1) = -1
* w(c, s2) = 0
* w(c, s3) = 1
*
*/
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
{
s64 gran, vdiff = curr->vruntime - se->vruntime;
if (vdiff <= 0)
return -1;
gran = wakeup_gran(curr, se);
if (vdiff > gran)
return 1;
return 0;
}
static void set_last_buddy(struct sched_entity *se)
{
if (likely(task_of(se)->policy != SCHED_IDLE)) {
for_each_sched_entity(se)
cfs_rq_of(se)->last = se;
}
}
static void set_next_buddy(struct sched_entity *se)
{
if (likely(task_of(se)->policy != SCHED_IDLE)) {
for_each_sched_entity(se)
cfs_rq_of(se)->next = se;
}
}
/*
* Preempt the current task with a newly woken task if needed:
*/
static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
{
struct task_struct *curr = rq->curr;
struct sched_entity *se = &curr->se, *pse = &p->se;
struct cfs_rq *cfs_rq = task_cfs_rq(curr);
int sync = wake_flags & WF_SYNC;
sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 21:09:22 +00:00
int scale = cfs_rq->nr_running >= sched_nr_latency;
if (unlikely(rt_prio(p->prio)))
goto preempt;
if (unlikely(p->sched_class != &fair_sched_class))
return;
if (unlikely(se == pse))
return;
sched: Strengthen buddies and mitigate buddy induced latencies This patch restores the effectiveness of LAST_BUDDY in preventing pgsql+oltp from collapsing due to wakeup preemption. It also switches LAST_BUDDY to exclusively do what it does best, namely mitigate the effects of aggressive wakeup preemption, which improves vmark throughput markedly, and restores mysql+oltp scalability. Since buddies are about scalability, enable them beginning at the point where we begin expanding sched_latency, namely sched_nr_latency. Previously, buddies were cleared aggressively, which seriously reduced their effectiveness. Not clearing aggressively however, produces a small drop in mysql+oltp throughput immediately after peak, indicating that LAST_BUDDY is actually doing some harm. This is right at the point where X on the desktop in competition with another load wants low latency service. Ergo, do not enable until we need to scale. To mitigate latency induced by buddies, or by a task just missing wakeup preemption, check latency at tick time. Last hunk prevents buddies from stymieing BALANCE_NEWIDLE via CACHE_HOT_BUDDY. Supporting performance tests: tip = v2.6.32-rc5-1497-ga525b32 tipx = NO_GENTLE_FAIR_SLEEPERS NEXT_BUDDY granularity knobs = 31 knobs + 31 buddies tip+x = NO_GENTLE_FAIR_SLEEPERS granularity knobs = 31 knobs (Three run averages except where noted.) vmark: ------ tip 108466 messages per second tip+ 125307 messages per second tip+x 125335 messages per second tipx 117781 messages per second 2.6.31.3 122729 messages per second mysql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 9949.89 18690.20 34801.24 34460.04 32682.88 30765.97 28305.27 25059.64 19548.08 tip+ 10013.90 18526.84 34900.38 34420.14 33069.83 32083.40 30578.30 28010.71 25605.47 tipx 9698.71 18002.70 34477.56 33420.01 32634.30 31657.27 29932.67 26827.52 21487.18 2.6.31.3 8243.11 18784.20 34404.83 33148.38 31900.32 31161.90 29663.81 25995.94 18058.86 pgsql+oltp: ----------- clients 1 2 4 8 16 32 64 128 256 .......................................................................................... tip 13686.37 26609.25 51934.28 51347.81 49479.51 45312.65 36691.91 26851.57 24145.35 tip+ (1x) 13907.85 27135.87 52951.98 52514.04 51742.52 50705.43 49947.97 48374.19 46227.94 tip+x 13906.78 27065.81 52951.19 52542.59 52176.11 51815.94 50838.90 49439.46 46891.00 tipx 13742.46 26769.81 52351.99 51891.73 51320.79 50938.98 50248.65 48908.70 46553.84 2.6.31.3 13815.35 26906.46 52683.34 52061.31 51937.10 51376.80 50474.28 49394.47 47003.25 Signed-off-by: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-10-23 21:09:22 +00:00
if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK))
set_next_buddy(pse);
/*
* We can come here with TIF_NEED_RESCHED already set from new task
* wake up path.
*/
if (test_tsk_need_resched(curr))
return;
/*
* Batch and idle tasks do not preempt (their preemption is driven by
* the tick):
*/
if (unlikely(p->policy != SCHED_NORMAL))
return;
/* Idle tasks are by definition preempted by everybody. */
if (unlikely(curr->policy == SCHED_IDLE))
goto preempt;
if (sched_feat(WAKEUP_SYNC) && sync)
goto preempt;
if (sched_feat(WAKEUP_OVERLAP) &&
se->avg_overlap < sysctl_sched_migration_cost &&
pse->avg_overlap < sysctl_sched_migration_cost)
goto preempt;
if (!sched_feat(WAKEUP_PREEMPT))
return;
update_curr(cfs_rq);
find_matching_se(&se, &pse);
BUG_ON(!pse);
if (wakeup_preempt_entity(se, pse) == 1)
goto preempt;
return;
preempt:
resched_task(curr);
/*
* Only set the backward buddy when the current task is still
* on the rq. This can happen when a wakeup gets interleaved
* with schedule on the ->pre_schedule() or idle_balance()
* point, either of which can * drop the rq lock.
*
* Also, during early boot the idle thread is in the fair class,
* for obvious reasons its a bad idea to schedule back to it.
*/
if (unlikely(!se->on_rq || curr == rq->idle))
return;
if (sched_feat(LAST_BUDDY) && scale && entity_is_task(se))
set_last_buddy(se);
}
static struct task_struct *pick_next_task_fair(struct rq *rq)
{
struct task_struct *p;
struct cfs_rq *cfs_rq = &rq->cfs;
struct sched_entity *se;
if (!cfs_rq->nr_running)
return NULL;
do {
se = pick_next_entity(cfs_rq);
set_next_entity(cfs_rq, se);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
p = task_of(se);
hrtick_start_fair(rq, p);
return p;
}
/*
* Account for a descheduled task:
*/
static void put_prev_task_fair(struct rq *rq, struct task_struct *prev)
{
struct sched_entity *se = &prev->se;
struct cfs_rq *cfs_rq;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
put_prev_entity(cfs_rq, se);
}
}
#ifdef CONFIG_SMP
/**************************************************
* Fair scheduling class load-balancing methods:
*/
/*
* Load-balancing iterator. Note: while the runqueue stays locked
* during the whole iteration, the current task might be
* dequeued so the iterator has to be dequeue-safe. Here we
* achieve that by always pre-iterating before returning
* the current task:
*/
static struct task_struct *
__load_balance_iterator(struct cfs_rq *cfs_rq, struct list_head *next)
{
struct task_struct *p = NULL;
struct sched_entity *se;
if (next == &cfs_rq->tasks)
return NULL;
se = list_entry(next, struct sched_entity, group_node);
p = task_of(se);
cfs_rq->balance_iterator = next->next;
return p;
}
static struct task_struct *load_balance_start_fair(void *arg)
{
struct cfs_rq *cfs_rq = arg;
return __load_balance_iterator(cfs_rq, cfs_rq->tasks.next);
}
static struct task_struct *load_balance_next_fair(void *arg)
{
struct cfs_rq *cfs_rq = arg;
return __load_balance_iterator(cfs_rq, cfs_rq->balance_iterator);
}
static unsigned long
__load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move, struct sched_domain *sd,
enum cpu_idle_type idle, int *all_pinned, int *this_best_prio,
struct cfs_rq *cfs_rq)
{
struct rq_iterator cfs_rq_iterator;
cfs_rq_iterator.start = load_balance_start_fair;
cfs_rq_iterator.next = load_balance_next_fair;
cfs_rq_iterator.arg = cfs_rq;
return balance_tasks(this_rq, this_cpu, busiest,
max_load_move, sd, idle, all_pinned,
this_best_prio, &cfs_rq_iterator);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
sched: simplify move_tasks() The move_tasks() function is currently multiplexed with two distinct capabilities: 1. attempt to move a specified amount of weighted load from one run queue to another; and 2. attempt to move a specified number of tasks from one run queue to another. The first of these capabilities is used in two places, load_balance() and load_balance_idle(), and in both of these cases the return value of move_tasks() is used purely to decide if tasks/load were moved and no notice of the actual number of tasks moved is taken. The second capability is used in exactly one place, active_load_balance(), to attempt to move exactly one task and, as before, the return value is only used as an indicator of success or failure. This multiplexing of sched_task() was introduced, by me, as part of the smpnice patches and was motivated by the fact that the alternative, one function to move specified load and one to move a single task, would have led to two functions of roughly the same complexity as the old move_tasks() (or the new balance_tasks()). However, the new modular design of the new CFS scheduler allows a simpler solution to be adopted and this patch addresses that solution by: 1. adding a new function, move_one_task(), to be used by active_load_balance(); and 2. making move_tasks() a single purpose function that tries to move a specified weighted load and returns 1 for success and 0 for failure. One of the consequences of these changes is that neither move_one_task() or the new move_tasks() care how many tasks sched_class.load_balance() moves and this enables its interface to be simplified by returning the amount of load moved as its result and removing the load_moved pointer from the argument list. This helps simplify the new move_tasks() and slightly reduces the amount of work done in each of sched_class.load_balance()'s implementations. Further simplification, e.g. changes to balance_tasks(), are possible but (slightly) complicated by the special needs of load_balance_fair() so I've left them to a later patch (if this one gets accepted). NB Since move_tasks() gets called with two run queue locks held even small reductions in overhead are worthwhile. [ mingo@elte.hu ] this change also reduces code size nicely: text data bss dec hex filename 39216 3618 24 42858 a76a sched.o.before 39173 3618 24 42815 a73f sched.o.after Signed-off-by: Peter Williams <pwil3058@bigpond.net.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-08-09 09:16:46 +00:00
static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
sched: fix bug in balance_tasks() There are two problems with balance_tasks() and how it used: 1. The variables best_prio and best_prio_seen (inherited from the old move_tasks()) were only required to handle problems caused by the active/expired arrays, the order in which they were processed and the possibility that the task with the highest priority could be on either. These issues are no longer present and the extra overhead associated with their use is unnecessary (and possibly wrong). 2. In the absence of CONFIG_FAIR_GROUP_SCHED being set, the same this_best_prio variable needs to be used by all scheduling classes or there is a risk of moving too much load. E.g. if the highest priority task on this at the beginning is a fairly low priority task and the rt class migrates a task (during its turn) then that moved task becomes the new highest priority task on this_rq but when the sched_fair class initializes its copy of this_best_prio it will get the priority of the original highest priority task as, due to the run queue locks being held, the reschedule triggered by pull_task() will not have taken place. This could result in inappropriate overriding of skip_for_load and excessive load being moved. The attached patch addresses these problems by deleting all reference to best_prio and best_prio_seen and making this_best_prio a reference parameter to the various functions involved. load_balance_fair() has also been modified so that this_best_prio is only reset (in the loop) if CONFIG_FAIR_GROUP_SCHED is set. This should preserve the effect of helping spread groups' higher priority tasks around the available CPUs while improving system performance when CONFIG_FAIR_GROUP_SCHED isn't set. Signed-off-by: Peter Williams <pwil3058@bigpond.net.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-08-09 09:16:46 +00:00
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, int *this_best_prio)
{
long rem_load_move = max_load_move;
int busiest_cpu = cpu_of(busiest);
struct task_group *tg;
rcu_read_lock();
update_h_load(busiest_cpu);
list_for_each_entry_rcu(tg, &task_groups, list) {
struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu];
unsigned long busiest_h_load = busiest_cfs_rq->h_load;
unsigned long busiest_weight = busiest_cfs_rq->load.weight;
u64 rem_load, moved_load;
/*
* empty group
*/
if (!busiest_cfs_rq->task_weight)
continue;
rem_load = (u64)rem_load_move * busiest_weight;
rem_load = div_u64(rem_load, busiest_h_load + 1);
moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
rem_load, sd, idle, all_pinned, this_best_prio,
tg->cfs_rq[busiest_cpu]);
if (!moved_load)
continue;
moved_load *= busiest_h_load;
moved_load = div_u64(moved_load, busiest_weight + 1);
rem_load_move -= moved_load;
if (rem_load_move < 0)
break;
}
rcu_read_unlock();
sched: simplify move_tasks() The move_tasks() function is currently multiplexed with two distinct capabilities: 1. attempt to move a specified amount of weighted load from one run queue to another; and 2. attempt to move a specified number of tasks from one run queue to another. The first of these capabilities is used in two places, load_balance() and load_balance_idle(), and in both of these cases the return value of move_tasks() is used purely to decide if tasks/load were moved and no notice of the actual number of tasks moved is taken. The second capability is used in exactly one place, active_load_balance(), to attempt to move exactly one task and, as before, the return value is only used as an indicator of success or failure. This multiplexing of sched_task() was introduced, by me, as part of the smpnice patches and was motivated by the fact that the alternative, one function to move specified load and one to move a single task, would have led to two functions of roughly the same complexity as the old move_tasks() (or the new balance_tasks()). However, the new modular design of the new CFS scheduler allows a simpler solution to be adopted and this patch addresses that solution by: 1. adding a new function, move_one_task(), to be used by active_load_balance(); and 2. making move_tasks() a single purpose function that tries to move a specified weighted load and returns 1 for success and 0 for failure. One of the consequences of these changes is that neither move_one_task() or the new move_tasks() care how many tasks sched_class.load_balance() moves and this enables its interface to be simplified by returning the amount of load moved as its result and removing the load_moved pointer from the argument list. This helps simplify the new move_tasks() and slightly reduces the amount of work done in each of sched_class.load_balance()'s implementations. Further simplification, e.g. changes to balance_tasks(), are possible but (slightly) complicated by the special needs of load_balance_fair() so I've left them to a later patch (if this one gets accepted). NB Since move_tasks() gets called with two run queue locks held even small reductions in overhead are worthwhile. [ mingo@elte.hu ] this change also reduces code size nicely: text data bss dec hex filename 39216 3618 24 42858 a76a sched.o.before 39173 3618 24 42815 a73f sched.o.after Signed-off-by: Peter Williams <pwil3058@bigpond.net.au> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2007-08-09 09:16:46 +00:00
return max_load_move - rem_load_move;
}
#else
static unsigned long
load_balance_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
int *all_pinned, int *this_best_prio)
{
return __load_balance_fair(this_rq, this_cpu, busiest,
max_load_move, sd, idle, all_pinned,
this_best_prio, &busiest->cfs);
}
#endif
static int
move_one_task_fair(struct rq *this_rq, int this_cpu, struct rq *busiest,
struct sched_domain *sd, enum cpu_idle_type idle)
{
struct cfs_rq *busy_cfs_rq;
struct rq_iterator cfs_rq_iterator;
cfs_rq_iterator.start = load_balance_start_fair;
cfs_rq_iterator.next = load_balance_next_fair;
for_each_leaf_cfs_rq(busiest, busy_cfs_rq) {
/*
* pass busy_cfs_rq argument into
* load_balance_[start|next]_fair iterators
*/
cfs_rq_iterator.arg = busy_cfs_rq;
if (iter_move_one_task(this_rq, this_cpu, busiest, sd, idle,
&cfs_rq_iterator))
return 1;
}
return 0;
}
static void rq_online_fair(struct rq *rq)
{
update_sysctl();
}
static void rq_offline_fair(struct rq *rq)
{
update_sysctl();
}
#endif /* CONFIG_SMP */
/*
* scheduler tick hitting a task of our scheduling class:
*/
static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &curr->se;
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
entity_tick(cfs_rq, se, queued);
}
}
/*
* called on fork with the child task as argument from the parent's context
* - child not yet on the tasklist
* - preemption disabled
*/
static void task_fork_fair(struct task_struct *p)
{
struct cfs_rq *cfs_rq = task_cfs_rq(current);
struct sched_entity *se = &p->se, *curr = cfs_rq->curr;
int this_cpu = smp_processor_id();
struct rq *rq = this_rq();
unsigned long flags;
raw_spin_lock_irqsave(&rq->lock, flags);
if (unlikely(task_cpu(p) != this_cpu))
__set_task_cpu(p, this_cpu);
update_curr(cfs_rq);
if (curr)
se->vruntime = curr->vruntime;
place_entity(cfs_rq, se, 1);
if (sysctl_sched_child_runs_first && curr && entity_before(curr, se)) {
/*
* Upon rescheduling, sched_class::put_prev_task() will place
* 'current' within the tree based on its new key value.
*/
swap(curr->vruntime, se->vruntime);
resched_task(rq->curr);
}
raw_spin_unlock_irqrestore(&rq->lock, flags);
}
/*
* Priority of the task has changed. Check to see if we preempt
* the current task.
*/
static void prio_changed_fair(struct rq *rq, struct task_struct *p,
int oldprio, int running)
{
/*
* Reschedule if we are currently running on this runqueue and
* our priority decreased, or if we are not currently running on
* this runqueue and our priority is higher than the current's
*/
if (running) {
if (p->prio > oldprio)
resched_task(rq->curr);
} else
check_preempt_curr(rq, p, 0);
}
/*
* We switched to the sched_fair class.
*/
static void switched_to_fair(struct rq *rq, struct task_struct *p,
int running)
{
/*
* We were most likely switched from sched_rt, so
* kick off the schedule if running, otherwise just see
* if we can still preempt the current task.
*/
if (running)
resched_task(rq->curr);
else
check_preempt_curr(rq, p, 0);
}
/* Account for a task changing its policy or group.
*
* This routine is mostly called to set cfs_rq->curr field when a task
* migrates between groups/classes.
*/
static void set_curr_task_fair(struct rq *rq)
{
struct sched_entity *se = &rq->curr->se;
for_each_sched_entity(se)
set_next_entity(cfs_rq_of(se), se);
}
#ifdef CONFIG_FAIR_GROUP_SCHED
static void moved_group_fair(struct task_struct *p)
{
struct cfs_rq *cfs_rq = task_cfs_rq(p);
update_curr(cfs_rq);
place_entity(cfs_rq, &p->se, 1);
}
#endif
unsigned int get_rr_interval_fair(struct rq *rq, struct task_struct *task)
{
struct sched_entity *se = &task->se;
unsigned int rr_interval = 0;
/*
* Time slice is 0 for SCHED_OTHER tasks that are on an otherwise
* idle runqueue:
*/
if (rq->cfs.load.weight)
rr_interval = NS_TO_JIFFIES(sched_slice(&rq->cfs, se));
return rr_interval;
}
/*
* All the scheduling class methods:
*/
static const struct sched_class fair_sched_class = {
.next = &idle_sched_class,
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
.yield_task = yield_task_fair,
.check_preempt_curr = check_preempt_wakeup,
.pick_next_task = pick_next_task_fair,
.put_prev_task = put_prev_task_fair,
#ifdef CONFIG_SMP
.select_task_rq = select_task_rq_fair,
.load_balance = load_balance_fair,
.move_one_task = move_one_task_fair,
.rq_online = rq_online_fair,
.rq_offline = rq_offline_fair,
#endif
.set_curr_task = set_curr_task_fair,
.task_tick = task_tick_fair,
.task_fork = task_fork_fair,
.prio_changed = prio_changed_fair,
.switched_to = switched_to_fair,
.get_rr_interval = get_rr_interval_fair,
#ifdef CONFIG_FAIR_GROUP_SCHED
.moved_group = moved_group_fair,
#endif
};
#ifdef CONFIG_SCHED_DEBUG
static void print_cfs_stats(struct seq_file *m, int cpu)
{
struct cfs_rq *cfs_rq;
rcu_read_lock();
for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
print_cfs_rq(m, cpu, cfs_rq);
rcu_read_unlock();
}
#endif