Home » Mailing lists » Devel » [PATCH 0/2] Add group awareness to CFS - v2
[PATCH 0/2] Add group awareness to CFS - v2 [message #19110] |
Sat, 23 June 2007 13:15 ![Go to next message Go to next message](/theme/ovz3/images/down.png) |
Srivatsa Vaddagiri
Messages: 241 Registered: August 2006
|
Senior Member |
|
|
Hi Ingo,
Here's an update for the group-aware CFS scheduler that I have been
working on.
(For those reading these patches for the first time:)
The basic idea is to reuse CFS core and other pieces of scheduler like
smpnice-driven load balance for driving fairness between 'schedulable entities'
other than tasks, for ex: users or containers.
The time-sorted rb-tree and nanosecond accurate accounting aspects of
CFS are "repeated" for schedulable entities other than tasks.
For ex: there could be N task-level rb-trees for N users (which stores
tasks) and a single user-level rb-tree which stores user-level entities.
CFS operations on each user's task-level rb-tree drives fairness between tasks
of that user, while CFS operations on user-level rb-tree drives
fairness between users.
v17 CFS introduced basic changes in CFS to support group scheduling.
The two patches to follow build upon them as follows:
Patch 1 => introduces a notion of scheduler hierarchy (of entities) and
applies CFS operations at all levels of this hierarchy.
Patch 2 => hooks up the cpu scheduler with task grouping feature in mm tree
(CONFIG_CONTAINERS) as an interface to task-grouping functionality.
A single config option CONFIG_FAIR_GROUP_SCHED allows the group-scheduling
feature to be turned on/off at compile time.
I have tried my best to ensure there is no impact to existing CFS performance
when CONFIG_FAIR_GROUP_SCHED is disabled. Some results in this regard are
provided at the end.
One noticeable change in functionality may be the /proc/sched_debug output
(I had to rearrange that code a bit to dump group cfs_rq information also).
Changes since last version:
- Fixed some bugs in SMP load balance (pointed by Dmitry)
- Modified sched_debug.c to dump all cfs_rq stats
Todo:
- Weighted fair-share
Currently all groups get "equal" cpu bandwidth. I plan
to support weighted fair-sharing on the lines of task
niceness.
- Separate out tunable
Right now tunable are same for all layers of scheduling.
I strongly think we will need to separate them, esp
sysctl_sched_runtime_limit.
- Optimization
- reduce frequency of timer tick processing at higher levels
- during load balance, pick cache-cold tasks first to migrate
- hierarchy flattening
Experiment with this (to reduce number of hierarchical levels)
as per http://lkml.org/lkml/2007/5/26/81
Some results follows. Legends used in them are:
cfs = base cfs performance (sched-cfs-v2.6.22-rc4-mm2-v18.patch)
cfsgrpdi = base cfs + patches 1-2 applied (CONFIG_FAIR_GROUP_SCHED disabled)
cfsgrpdi = base cfs + patches 1-2 applied (CONFIG_FAIR_GROUP_SCHED enabled)
All tests run on a 4-cpu Intel Xeon (x86_64) box:
A. Overhead Test
lat_ctx (from lmbench)
======================
Context switching - times in microseconds - smaller is better
-------------------------------------------------------------------------
Host OS 2p/0K 2p/16K 2p/64K 8p/16K 8p/64K 16p/16K 16p/64K
ctxsw ctxsw ctxsw ctxsw ctxsw ctxsw ctxsw
--------- ------------- ------ ------ ------ ------ ------ ------- -------
cfs Linux 2.6.22- 6.7400 7.8200 8.0100 8.7900 10.90 8.20000 19.88
cfsgrpdi Linux 2.6.22- 6.7000 7.6700 8.0700 9.0100 11.54 9.34000 18.71
cfsgrpen Linux 2.6.22- 7.8600 7.8700 8.6500 9.4600 10.27 9.44000 19.74
hackbench -pipe 100
===================
Average of 10 runs was taken. Smaller numbers are better.
cfs 4.0171
cfsgrpdi 4.154
cfsgrpen 4.7749
B. UP Group fairness test
These tests were forced to run on a single CPU by making using
of exclusive cpusets.
hackbench
=========
The two user's shell were put in different groups (as explained in Patch 2/2).
Each user then ran this script:
i=0
while [ $i -lt 10 ]
do
./hackbench -pipe 100 >> log
i=`expr $i + 1`
done
Time taken to complete this script was measured as follows (note that
both the scripts were made to run simultaneously on /same/ cpu).
vatsa 103.51 s (real)
guest 103.37 s (real)
Inference: Both users completed the same amount of work in (nearly) same time.
kernel compilation
==================
Again the two user's shell were put in different groups.
User vatsa ran "make -s -j4 bzImage", while
User guest ran "make -s -j20 bzImage"
Both are compiling the same sources (and hence should effectively be
doing the same amount of work). Time taken to complete kernel-compile by
both users:
vatsa 777.46 s (real)
guest 778.30 s (real)
Inference: Both users completed the same amount of work in nearly same
time, even though one had higher number of threads dedicated to the job.
C. SMP Fairness test
====================
I used a simple cpu-intensive program which measures how much CPU time it got
(using getrusage) over a minute. N (=4*NUM_CPUS) such tasks were spawned with
N/2 in one group and N/2 in another group. Total CPU time obtained by one group
was compared with total cpu time obtained by another group. While the test
was running, I observed distribution of all tasks across CPUs. I am
quite happy with the results obtained and with the load distribution. I
can share the sources/results of the program/script upon request.
Looking forward to your feedback on these patches!
[P.S : Since I am travelling this weekend, I may not respond promptly ]
--
Regards,
vatsa
_______________________________________________
Containers mailing list
Containers@lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers
|
|
|
[PATCH 1/2] Introduce notion of scheduler hierarchy [message #19111 is a reply to message #19110] |
Sat, 23 June 2007 13:18 ![Go to previous message Go to previous message](/theme/ovz3/images/up.png) ![Go to next message Go to next message](/theme/ovz3/images/down.png) |
Srivatsa Vaddagiri
Messages: 241 Registered: August 2006
|
Senior Member |
|
|
This patch introduces the core changes in CFS required to accomplish
group fairness at higher levels. It also modifies load balance interface
between classes a bit, so that move_tasks (which is centric to load
balance) can be reused to balance between runqueues of various types
(struct rq in case of SCHED_RT tasks, struct lrq in case of
SCHED_NORMAL/BATCH tasks).
Signed-off-by : Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
---
include/linux/sched.h | 17 ++
kernel/sched.c | 174 ++++++++++++++++------------
kernel/sched_debug.c | 31 +++--
kernel/sched_fair.c | 295 ++++++++++++++++++++++++++++++++++++++++++++----
kernel/sched_idletask.c | 11 +
kernel/sched_rt.c | 47 ++++++-
6 files changed, 464 insertions(+), 111 deletions(-)
Index: current/include/linux/sched.h
===================================================================
--- current.orig/include/linux/sched.h
+++ current/include/linux/sched.h
@@ -134,8 +134,11 @@ extern unsigned long nr_iowait(void);
extern unsigned long weighted_cpuload(const int cpu);
struct seq_file;
+struct cfs_rq;
extern void proc_sched_show_task(struct task_struct *p, struct seq_file *m);
extern void proc_sched_set_task(struct task_struct *p);
+extern void
+print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq, u64 now);
/*
* Task state bitmask. NOTE! These bits are also
@@ -865,8 +868,13 @@ struct sched_class {
struct task_struct * (*pick_next_task) (struct rq *rq, u64 now);
void (*put_prev_task) (struct rq *rq, struct task_struct *p, u64 now);
- struct task_struct * (*load_balance_start) (struct rq *rq);
- struct task_struct * (*load_balance_next) (struct rq *rq);
+ int (*load_balance) (struct rq *this_rq, int this_cpu,
+ struct rq *busiest,
+ unsigned long max_nr_move, unsigned long max_load_move,
+ struct sched_domain *sd, enum cpu_idle_type idle,
+ int *all_pinned, unsigned long *total_load_moved);
+
+ void (*set_curr_task) (struct rq *rq);
void (*task_tick) (struct rq *rq, struct task_struct *p);
void (*task_new) (struct rq *rq, struct task_struct *p);
};
@@ -899,6 +907,11 @@ struct sched_entity {
s64 fair_key;
s64 sum_wait_runtime, sum_sleep_runtime;
unsigned long wait_runtime_overruns, wait_runtime_underruns;
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ struct sched_entity *parent;
+ struct cfs_rq *cfs_rq, /* rq on which this entity is (to be) queued */
+ *my_q; /* rq "owned" by this entity/group */
+#endif
};
struct task_struct {
Index: current/kernel/sched.c
===================================================================
--- current.orig/kernel/sched.c
+++ current/kernel/sched.c
@@ -133,6 +133,22 @@ struct cfs_rq {
struct rb_root tasks_timeline;
struct rb_node *rb_leftmost;
struct rb_node *rb_load_balance_curr;
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ /* 'curr' points to currently running entity on this cfs_rq.
+ * It is set to NULL otherwise (i.e when none are currently running).
+ */
+ struct sched_entity *curr;
+ struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */
+
+ /* leaf cfs_rqs are those that hold tasks (lowest schedulable entity in
+ * a hierarchy). Non-leaf lrqs hold other higher schedulable entities
+ * (like users, containers etc.)
+ *
+ * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This
+ * list is used during load balance.
+ */
+ struct list_head leaf_cfs_rq_list; /* Better name : task_cfs_rq_list? */
+#endif
};
/* Real-Time classes' related field in a runqueue: */
@@ -168,6 +184,9 @@ struct rq {
u64 nr_switches;
struct cfs_rq cfs;
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ struct list_head leaf_cfs_rq_list; /* list of leaf cfs_rq on this cpu */
+#endif
struct rt_rq rt;
/*
@@ -342,6 +361,16 @@ static inline unsigned long long rq_cloc
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/* Change a task's ->cfs_rq if it moves across CPUs */
+static inline void set_task_cfs_rq(struct task_struct *p)
+{
+ p->se.cfs_rq = &task_rq(p)->cfs;
+}
+#else
+static inline void set_task_cfs_rq(struct task_struct *p) { }
+#endif
+
#ifndef prepare_arch_switch
# define prepare_arch_switch(next) do { } while (0)
#endif
@@ -738,6 +767,21 @@ static inline void dec_nr_running(struct
}
static void activate_task(struct rq *rq, struct task_struct *p, int wakeup);
+#ifdef CONFIG_SMP
+
+struct rq_iterator {
+ void *arg;
+ struct task_struct *(*start)(void *);
+ struct task_struct *(*next)(void *);
+};
+
+static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ unsigned long max_nr_move, unsigned long max_load_move,
+ struct sched_domain *sd, enum cpu_idle_type idle,
+ int *all_pinned, unsigned long *load_moved,
+ int this_best_prio, int best_prio, int best_prio_seen,
+ struct rq_iterator *iterator);
+#endif
#include "sched_stats.h"
#include "sched_rt.c"
@@ -894,6 +938,7 @@ unsigned long weighted_cpuload(const int
static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
{
task_thread_info(p)->cpu = cpu;
+ set_task_cfs_rq(p);
}
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
@@ -919,6 +964,7 @@ void set_task_cpu(struct task_struct *p,
task_thread_info(p)->cpu = new_cpu;
+ set_task_cfs_rq(p);
}
struct migration_req {
@@ -2003,89 +2049,26 @@ int can_migrate_task(struct task_struct
return 1;
}
-/*
- * Load-balancing iterator: iterate through the hieararchy of scheduling
- * classes, starting with the highest-prio one:
- */
-
-struct task_struct * load_balance_start(struct rq *rq)
-{
- struct sched_class *class = sched_class_highest;
- struct task_struct *p;
-
- do {
- p = class->load_balance_start(rq);
- if (p) {
- rq->load_balance_class = class;
- return p;
- }
- class = class->next;
- } while (class);
-
- return NULL;
-}
-
-struct task_struct * load_balance_next(struct rq *rq)
-{
- struct sched_class *class = rq->load_balance_class;
- struct task_struct *p;
-
- p = class->load_balance_next(rq);
- if (p)
- return p;
- /*
- * Pick up the next class (if any) and attempt to start
- * the iterator there:
- */
- while ((class = class->next)) {
- p = class->load_balance_start(rq);
- if (p) {
- rq->load_balance_class = class;
- return p;
- }
- }
- return NULL;
-}
-
-#define rq_best_prio(rq) (rq)->curr->prio
-
-/*
- * move_tasks tries to move up to max_nr_move tasks and max_load_move weighted
- * load from busiest to this_rq, as part of a balancing operation within
- * "domain". Returns the number of tasks moved.
- *
- * Called with both runqueues locked.
- */
-static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
unsigned long max_nr_move, unsigned long max_load_move,
struct sched_domain *sd, enum cpu_idle_type idle,
- int *all_pinned)
+ int *all_pinned, unsigned long *load_moved,
+ int this_best_prio, int best_prio, int best_prio_seen,
+ struct rq_iterator *iterator)
{
- int pulled = 0, pinned = 0, this_best_prio, best_prio,
- best_prio_seen, skip_for_load;
+ int pulled = 0, pinned = 0, skip_for_load;
struct task_struct *p;
- long rem_load_move;
+ long rem_load_move = max_load_move;
if (max_nr_move == 0 || max_load_move == 0)
goto out;
- rem_load_move = max_load_move;
pinned = 1;
- this_best_prio = rq_best_prio(this_rq);
- best_prio = rq_best_prio(busiest);
- /*
- * Enable handling of the case where there is more than one task
- * with the best priority. If the current running task is one
- * of those with prio==best_prio we know it won't be moved
- * and therefore it's safe to override the skip (based on load) of
- * any task we find with that prio.
- */
- best_prio_seen = best_prio == busiest->curr->prio;
/*
* Start the load-balancing iterator:
*/
- p = load_balance_start(busiest);
+ p = iterator->start(iterator->arg);
next:
if (!p)
goto out;
@@ -2102,7 +2085,7 @@ next:
!can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
best_prio_seen |= p->prio == best_prio;
- p = load_balance_next(busiest);
+ p = iterator->next(iterator->arg);
goto next;
}
@@ -2117,7 +2100,7 @@ next:
if (pulled < max_nr_move && rem_load_move > 0) {
if (p->prio < this_best_prio)
this_best_prio = p->prio;
- p = load_balance_next(busiest);
+ p = iterator->next(iterator->arg);
goto next;
}
out:
@@ -2130,10 +2113,40 @@ out:
if (all_pinned)
*all_pinned = pinned;
+ *load_moved = max_load_move - rem_load_move;
return pulled;
}
/*
+ * move_tasks tries to move up to max_nr_move tasks and max_load_move weighted
+ * load from busiest to this_rq, as part of a balancing operation within
+ * "domain". Returns the number of tasks moved.
+ *
+ * Called with both runqueues locked.
+ */
+static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest,
+ unsigned long max_nr_move, unsigned long max_load_move,
+ struct sched_domain *sd, enum cpu_idle_type idle,
+ int *all_pinned)
+{
+ struct sched_class *class = sched_class_highest;
+ unsigned long load_moved, total_nr_moved = 0, nr_moved;
+ long rem_load_move = max_load_move;
+
+ do {
+ nr_moved = class->load_balance(this_rq, this_cpu, busiest,
+ max_nr_move, (unsigned long)rem_load_move,
+ sd, idle, all_pinned, &load_moved);
+ total_nr_moved += nr_moved;
+ max_nr_move -= nr_moved;
+ rem_load_move -= load_moved;
+ class = class->next;
+ } while (class && max_nr_move && rem_load_move > 0);
+
+ return total_nr_moved;
+}
+
+/*
* find_busiest_group finds and returns the busiest CPU group within the
* domain. It calculates and returns the amount of weighted load w
...
|
|
|
[PATCH 2/2] Hook up to (process) container feature in mm tree [message #19112 is a reply to message #19110] |
Sat, 23 June 2007 13:20 ![Go to previous message Go to previous message](/theme/ovz3/images/up.png) ![Go to next message Go to next message](/theme/ovz3/images/down.png) |
Srivatsa Vaddagiri
Messages: 241 Registered: August 2006
|
Senior Member |
|
|
This patch hooks up cpu scheduler with Paul Menage's container infrastructure.
The container patches allows administrator to create arbitrary groups of tasks
and define resource allocation for each group. By registering with container
infrastructure, cpu scheduler is made aware of group membership information for
each task, creation/deletion of groups etc and can use that information to
provide fairness between groups.
This mechanism can indirectly be used to provide fairness between users
also. All that is needed is a user-space program (which is being working
upon) which monitors for PROC_EVENT_UID events (using process event connector)
and moves the task to appropriate user-directory in container filesystem.
As an example for "HOWTO use this feature", follow these steps:
1. Define CONFIG_FAIR_GROUP_SCHED (General Setup->Fair Group Scheduler)
and compile the kernel
2. After booting:
# cd /dev
# mkdir cpuctl
# mount -t container -ocpuctl none /dev/cpuctl
# cd cpuctl
# mkdir grpA
# mkdir grpB
# echo some_pid1 > grpA/tasks
# echo some_pid2 > grpA/tasks
# echo some_pid3 > grpA/tasks
# echo some_pid4 > grpA/tasks
...
# echo another_pidX > grpB/tasks
# echo another_pidY > grpB/tasks
All tasks in grpA/tasks should cumulatively share same CPU as all tasks
in grpB/tasks.
Signed-off-by : Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
---
include/linux/container_subsys.h | 6
init/Kconfig | 10 +
kernel/sched.c | 250 +++++++++++++++++++++++++++++++++++++--
kernel/sched_fair.c | 3
4 files changed, 256 insertions(+), 13 deletions(-)
Index: current/include/linux/container_subsys.h
===================================================================
--- current.orig/include/linux/container_subsys.h
+++ current/include/linux/container_subsys.h
@@ -24,3 +24,9 @@ SUBSYS(debug)
#endif
/* */
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+SUBSYS(cpuctlr)
+#endif
+
+/* */
Index: current/init/Kconfig
===================================================================
--- current.orig/init/Kconfig
+++ current/init/Kconfig
@@ -328,6 +328,16 @@ config CPUSETS
Say N if unsure.
+config FAIR_GROUP_SCHED
+ bool "Fair group scheduler"
+ depends on EXPERIMENTAL
+ select CONTAINERS
+ help
+ This option enables you to group tasks and control CPU resource
+ allocation to such groups.
+
+ Say N if unsure.
+
config SYSFS_DEPRECATED
bool "Create deprecated sysfs files"
default y
Index: current/kernel/sched.c
===================================================================
--- current.orig/kernel/sched.c
+++ current/kernel/sched.c
@@ -120,6 +120,56 @@ struct load_stat {
u64 delta_fair, delta_exec, delta_stat;
};
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
+#include <linux/container.h>
+
+struct cfs_rq;
+
+/* task container/group related information */
+struct task_grp {
+ struct container_subsys_state css;
+ /* schedulable entities of this group on each cpu */
+ struct sched_entity **se;
+ /* runqueue "owned" by this group on each cpu */
+ struct cfs_rq **cfs_rq;
+};
+
+static DEFINE_PER_CPU(struct sched_entity, init_sched_entity);
+static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp;
+
+static struct sched_entity *init_sched_entity_p[CONFIG_NR_CPUS];
+static struct cfs_rq *init_cfs_rq_p[CONFIG_NR_CPUS];
+
+/* Default task group.
+ * Every task in system belong to this group at bootup and
+ * until administrator moves a task explicitly to another group.
+ */
+static struct task_grp init_task_grp = {
+ .se = init_sched_entity_p,
+ .cfs_rq = init_cfs_rq_p,
+ };
+
+/* return group to which a task belongs */
+static inline struct task_grp *task_grp(struct task_struct *p)
+{
+ return container_of(task_subsys_state(p, cpuctlr_subsys_id),
+ struct task_grp, css);
+}
+
+/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */
+static inline void set_task_cfs_rq(struct task_struct *p)
+{
+ p->se.cfs_rq = task_grp(p)->cfs_rq[task_cpu(p)];
+ p->se.parent = task_grp(p)->se[task_cpu(p)];
+}
+
+#else
+
+static inline void set_task_cfs_rq(struct task_struct *p) { }
+
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
/* CFS-related fields in a runqueue */
struct cfs_rq {
struct load_weight load;
@@ -148,6 +198,7 @@ struct cfs_rq {
* list is used during load balance.
*/
struct list_head leaf_cfs_rq_list; /* Better name : task_cfs_rq_list? */
+ struct task_grp *tg; /* group that "owns" this runqueue */
#endif
};
@@ -361,16 +412,6 @@ static inline unsigned long long rq_cloc
#define task_rq(p) cpu_rq(task_cpu(p))
#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
-#ifdef CONFIG_FAIR_GROUP_SCHED
-/* Change a task's ->cfs_rq if it moves across CPUs */
-static inline void set_task_cfs_rq(struct task_struct *p)
-{
- p->se.cfs_rq = &task_rq(p)->cfs;
-}
-#else
-static inline void set_task_cfs_rq(struct task_struct *p) { }
-#endif
-
#ifndef prepare_arch_switch
# define prepare_arch_switch(next) do { } while (0)
#endif
@@ -6232,7 +6273,23 @@ void __init sched_init(void)
init_cfs_rq(&rq->cfs, rq);
#ifdef CONFIG_FAIR_GROUP_SCHED
INIT_LIST_HEAD(&rq->leaf_cfs_rq_list);
- list_add(&rq->cfs.leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
+ {
+ struct cfs_rq *cfs_rq = &per_cpu(init_cfs_rq, i);
+ struct sched_entity *se =
+ &per_cpu(init_sched_entity, i);
+
+ init_cfs_rq_p[i] = cfs_rq;
+ init_cfs_rq(cfs_rq, rq);
+ cfs_rq->tg = &init_task_grp;
+ list_add(&cfs_rq->leaf_cfs_rq_list,
+ &rq->leaf_cfs_rq_list);
+
+ init_sched_entity_p[i] = se;
+ se->cfs_rq = &rq->cfs;
+ se->my_q = cfs_rq;
+ se->load.weight = NICE_0_LOAD;
+ se->parent = NULL;
+ }
#endif
for (j = 0; j < CPU_LOAD_IDX_MAX; j++)
@@ -6417,3 +6474,174 @@ void set_curr_task(int cpu, struct task_
}
#endif
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
+/* return corresponding task_grp object of a container */
+static inline struct task_grp *container_tg(struct container *cont)
+{
+ return container_of(container_subsys_state(cont, cpuctlr_subsys_id),
+ struct task_grp, css);
+}
+
+/* allocate runqueue etc for a new task group */
+static int sched_create_group(struct container_subsys *ss,
+ struct container *cont)
+{
+ struct task_grp *tg;
+ struct cfs_rq *cfs_rq;
+ struct sched_entity *se;
+ int i;
+
+ if (!cont->parent) {
+ /* This is early initialization for the top container */
+ cont->subsys[cpuctlr_subsys_id] = &init_task_grp.css;
+ init_task_grp.css.container = cont;
+ return 0;
+ }
+
+ /* we support only 1-level deep hierarchical scheduler atm */
+ if (cont->parent->parent)
+ return -EINVAL;
+
+ tg = kzalloc(sizeof(*tg), GFP_KERNEL);
+ if (!tg)
+ return -ENOMEM;
+
+ tg->cfs_rq = kzalloc(sizeof(cfs_rq) * num_possible_cpus(), GFP_KERNEL);
+ if (!tg->cfs_rq)
+ goto err;
+ tg->se = kzalloc(sizeof(se) * num_possible_cpus(), GFP_KERNEL);
+ if (!tg->se)
+ goto err;
+
+ for_each_possible_cpu(i) {
+ struct rq *rq = cpu_rq(i);
+
+ cfs_rq = kmalloc_node(sizeof(struct cfs_rq), GFP_KERNEL,
+ cpu_to_node(i));
+ if (!cfs_rq)
+ goto err;
+
+ se = kmalloc_node(sizeof(struct sched_entity), GFP_KERNEL,
+ cpu_to_node(i));
+ if (!se)
+ goto err;
+
+ memset(cfs_rq, 0, sizeof(struct cfs_rq));
+ memset(se, 0, sizeof(struct sched_entity));
+
+ tg->cfs_rq[i] = cfs_rq;
+ init_cfs_rq(cfs_rq, rq);
+ cfs_rq->tg = tg;
+ list_add_rcu(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list);
+
+ tg->se[i] = se;
+ se->cfs_rq = &rq->cfs;
+ se->my_q = cfs_rq;
+ se->load.weight = NICE_0_LOAD;
+ se->parent = NULL;
+ }
+
+ /* Bind the container to task_grp object we just created */
+ cont->subsys[cpuctlr_subsys_id] = &tg->css;
+ tg->css.container = cont;
+
+ return 0;
+
+err:
+ for_each_possible_cpu(i) {
+ if (tg->cfs_rq && tg->cfs_rq[i])
+ kfree(tg->cfs_rq[i]);
+ if (tg->se && tg->se[i])
+ kfree(tg->se[i]);
+ }
+ if (tg->cfs_rq)
+ kfree(tg->cfs_rq);
+ if (tg->se)
+ kfree(tg->se);
+ if (tg)
+ kfree(tg);
+
+ return -ENOMEM;
+}
+
+
+/* destroy runqueue etc associated with a task group */
+static void sched_destroy_group(struct container_subsys *ss,
+ struct container *cont)
+{
+ struct task_grp *tg = container_tg(cont);
+ struct cfs_rq *cfs_rq;
+ struct sched_entity *se;
+ int i;
+
+ for_each_possible_cpu(i) {
+ cfs_rq = tg->cfs_rq[i];
+ list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
+ }
+
+ /* wait for possible concurrent references to cfs_rqs complete */
+ synchronize_sched();
+
+ /* now it should be safe to free those cfs_rqs */
+ for_each_possible_cpu(i) {
+ cfs_rq = tg->cfs_rq[i];
+ kfree(cfs_rq);
+
+ se = tg->se[i];
+ kfree(se);
+ }
+
+ kfree(tg);
+}
+
+/* change task's runqueue when it moves between groups */
+static void sched_move_task(struct container_subsys *ss, struct container *cont,
+ struct container *old_cont, struct task_struct *tsk)
+{
+ int on_rq;
+ unsigned long flags;
+ struct rq *rq;
+
+ rq = task_rq_lock(tsk, &flags);
+
+ on_rq = tsk->se.on_rq;
+ if (on_rq)
+ deactivate_task(rq, tsk, 0);
+
+ if (unlikely(rq->curr == tsk) && tsk->sched_class == &fair_sched_class)
+ tsk->sched_class->put_prev_task(rq, tsk, rq_clock(rq));
+
+ set_task_cfs_rq(tsk);
+
+ /* todo: change task's load_weight to reflect its new group */
+
+ if (on_rq)
+ activate_task(rq, tsk, 0);
+
+ if (unlikely(rq->curr == tsk) && tsk->sched_class == &fair_sched_class)
+ tsk->sched_class->set_curr_task(rq);
+
+ task_rq_unlock(rq, &flags);
+}
+
+
+static int sched_populate(struct container_subsys *ss, struct container *cont)
+{
+ /* todo: create a cpu_shares file to modify group weight */
+
+ return 0;
+}
+
+struct container_subsys cpuctlr_subsys = {
+ .name = "cpuctl",
+ .create = sched_create_group,
+ .destroy = sched_destroy_group,
+ .attach = sched_move_task,
+ .populate = sched_populate,
+ .subsys_id = cpuctlr_subsys_id,
+ .early_init = 1,
+};
+
+#endif /* CONFIG_FAIR_GROUP_SCHED */
Index: current/kernel/sched_fair.c
===================================================================
--- current.orig/kernel/sched_fair.c
+++ current/kernel/sched_fair.c
@@ -743,8 +743,7 @@ static inline struct cfs_rq *group_cfs_r
*/
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
- /* A later patch will take group into account */
- return &cpu_rq(this_cpu)->cfs;
+ return cfs_rq->tg->cfs_rq[this_cpu];
}
/* Iterate thr' all leaf cfs_rq's on a runqueue */
--
Regards,
vatsa
_______________________________________________
Containers mailing list
Containers@lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers
|
|
|
Re: [PATCH 0/2] Add group awareness to CFS - v2 [message #19128 is a reply to message #19110] |
Tue, 26 June 2007 08:52 ![Go to previous message Go to previous message](/theme/ovz3/images/up.png) |
Ingo Molnar
Messages: 51 Registered: December 2005
|
Member |
|
|
* Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com> wrote:
> Hi Ingo,
> Here's an update for the group-aware CFS scheduler that I have
> been working on.
thanks. I've carried your patch #1 (core changes) for the past few days
and it's looking pretty good so far! This makes the container-scheduling
patch (patch #2) a pretty painless add-on.
Ingo
_______________________________________________
Containers mailing list
Containers@lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/containers
|
|
|
Goto Forum:
Current Time: Tue Sep 10 18:28:06 GMT 2024
Total time taken to generate the page: 0.04963 seconds
|