AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-11-27 06:30:56 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
917b627d4d
linux_dsm_epyc7002/include/linux/init_task.h
Gregory Haskins 917b627d4d sched: create "pushable_tasks" list to limit pushing to one attempt 
The RT scheduler employs a "push/pull" design to actively balance tasks
within the system (on a per disjoint cpuset basis).  When a task is
awoken, it is immediately determined if there are any lower priority
cpus which should be preempted.  This is opposed to the way normal
SCHED_OTHER tasks behave, which will wait for a periodic rebalancing
operation to occur before spreading out load.

When a particular RQ has more than 1 active RT task, it is said to
be in an "overloaded" state.  Once this occurs, the system enters
the active balancing mode, where it will try to push the task away,
or persuade a different cpu to pull it over.  The system will stay
in this state until the system falls back below the <= 1 queued RT
task per RQ.

However, the current implementation suffers from a limitation in the
push logic.  Once overloaded, all tasks (other than current) on the
RQ are analyzed on every push operation, even if it was previously
unpushable (due to affinity, etc).  Whats more, the operation stops
at the first task that is unpushable and will not look at items
lower in the queue.  This causes two problems:

1) We can have the same tasks analyzed over and over again during each
   push, which extends out the fast path in the scheduler for no
   gain.  Consider a RQ that has dozens of tasks that are bound to a
   core.  Each one of those tasks will be encountered and skipped
   for each push operation while they are queued.

2) There may be lower-priority tasks under the unpushable task that
   could have been successfully pushed, but will never be considered
   until either the unpushable task is cleared, or a pull operation
   succeeds.  The net result is a potential latency source for mid
   priority tasks.

This patch aims to rectify these two conditions by introducing a new
priority sorted list: "pushable_tasks".  A task is added to the list
each time a task is activated or preempted.  It is removed from the
list any time it is deactivated, made current, or fails to push.

This works because a task only needs to be attempted to push once.
After an initial failure to push, the other cpus will eventually try to
pull the task when the conditions are proper.  This also solves the
problem that we don't completely analyze all tasks due to encountering
an unpushable tasks.  Now every task will have a push attempted (when
appropriate).

This reduces latency both by shorting the critical section of the
rq->lock for certain workloads, and by making sure the algorithm
considers all eligible tasks in the system.

[ rostedt: added a couple more BUG_ONs ]

Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Acked-by: Steven Rostedt <srostedt@redhat.com>
2008-12-29 09:39:53 -05:00

196 lines
5.4 KiB
C
Raw Blame History

#ifndef _LINUX__INIT_TASK_H
#define _LINUX__INIT_TASK_H
#include <linux/rcupdate.h>
#include <linux/irqflags.h>
#include <linux/utsname.h>
#include <linux/lockdep.h>
#include <linux/ipc.h>
#include <linux/pid_namespace.h>
#include <linux/user_namespace.h>
#include <linux/securebits.h>
#include <net/net_namespace.h>
extern struct files_struct init_files;
#define INIT_KIOCTX(name, which_mm) \
{ \
.users = ATOMIC_INIT(1), \
.dead = 0, \
.mm = &which_mm, \
.user_id = 0, \
.next = NULL, \
.wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.wait), \
.ctx_lock = __SPIN_LOCK_UNLOCKED(name.ctx_lock), \
.reqs_active = 0U, \
.max_reqs = ~0U, \
}
#define INIT_MM(name) \
{ \
.mm_rb = RB_ROOT, \
.pgd = swapper_pg_dir, \
.mm_users = ATOMIC_INIT(2), \
.mm_count = ATOMIC_INIT(1), \
.mmap_sem = __RWSEM_INITIALIZER(name.mmap_sem), \
.page_table_lock = __SPIN_LOCK_UNLOCKED(name.page_table_lock), \
.mmlist = LIST_HEAD_INIT(name.mmlist), \
.cpu_vm_mask = CPU_MASK_ALL, \
}
#define INIT_SIGNALS(sig) { \
.count = ATOMIC_INIT(1), \
.wait_chldexit = __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
.shared_pending = { \
.list = LIST_HEAD_INIT(sig.shared_pending.list), \
.signal = {{0}}}, \
.posix_timers = LIST_HEAD_INIT(sig.posix_timers), \
.cpu_timers = INIT_CPU_TIMERS(sig.cpu_timers), \
.rlim = INIT_RLIMITS, \
}
extern struct nsproxy init_nsproxy;
#define INIT_NSPROXY(nsproxy) { \
.pid_ns = &init_pid_ns, \
.count = ATOMIC_INIT(1), \
.uts_ns = &init_uts_ns, \
.mnt_ns = NULL, \
INIT_NET_NS(net_ns) \
INIT_IPC_NS(ipc_ns) \
.user_ns = &init_user_ns, \
}
#define INIT_SIGHAND(sighand) { \
.count = ATOMIC_INIT(1), \
.action = { { { .sa_handler = NULL, } }, }, \
.siglock = __SPIN_LOCK_UNLOCKED(sighand.siglock), \
.signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(sighand.signalfd_wqh), \
}
extern struct group_info init_groups;
#define INIT_STRUCT_PID { \
.count = ATOMIC_INIT(1), \
.tasks = { \
{ .first = &init_task.pids[PIDTYPE_PID].node }, \
{ .first = &init_task.pids[PIDTYPE_PGID].node }, \
{ .first = &init_task.pids[PIDTYPE_SID].node }, \
}, \
.rcu = RCU_HEAD_INIT, \
.level = 0, \
.numbers = { { \
.nr = 0, \
.ns = &init_pid_ns, \
.pid_chain = { .next = NULL, .pprev = NULL }, \
}, } \
}
#define INIT_PID_LINK(type) \
{ \
.node = { \
.next = NULL, \
.pprev = &init_struct_pid.tasks[type].first, \
}, \
.pid = &init_struct_pid, \
}
#ifdef CONFIG_AUDITSYSCALL
#define INIT_IDS \
.loginuid = -1, \
.sessionid = -1,
#else
#define INIT_IDS
#endif
#ifdef CONFIG_SECURITY_FILE_CAPABILITIES
/*
* Because of the reduced scope of CAP_SETPCAP when filesystem
* capabilities are in effect, it is safe to allow CAP_SETPCAP to
* be available in the default configuration.
*/
# define CAP_INIT_BSET CAP_FULL_SET
#else
# define CAP_INIT_BSET CAP_INIT_EFF_SET
#endif
/*
* INIT_TASK is used to set up the first task table, touch at
* your own risk!. Base=0, limit=0x1fffff (=2MB)
*/
#define INIT_TASK(tsk) \
{ \
.state = 0, \
.stack = &init_thread_info, \
.usage = ATOMIC_INIT(2), \
.flags = PF_KTHREAD, \
.lock_depth = -1, \
.prio = MAX_PRIO-20, \
.static_prio = MAX_PRIO-20, \
.normal_prio = MAX_PRIO-20, \
.policy = SCHED_NORMAL, \
.cpus_allowed = CPU_MASK_ALL, \
.mm = NULL, \
.active_mm = &init_mm, \
.se = { \
.group_node = LIST_HEAD_INIT(tsk.se.group_node), \
}, \
.rt = { \
.run_list = LIST_HEAD_INIT(tsk.rt.run_list), \
.time_slice = HZ, \
.nr_cpus_allowed = NR_CPUS, \
}, \
.tasks = LIST_HEAD_INIT(tsk.tasks), \
.pushable_tasks = PLIST_NODE_INIT(tsk.pushable_tasks, MAX_PRIO), \
.ptraced = LIST_HEAD_INIT(tsk.ptraced), \
.ptrace_entry = LIST_HEAD_INIT(tsk.ptrace_entry), \
.real_parent = &tsk, \
.parent = &tsk, \
.children = LIST_HEAD_INIT(tsk.children), \
.sibling = LIST_HEAD_INIT(tsk.sibling), \
.group_leader = &tsk, \
.group_info = &init_groups, \
.cap_effective = CAP_INIT_EFF_SET, \
.cap_inheritable = CAP_INIT_INH_SET, \
.cap_permitted = CAP_FULL_SET, \
.cap_bset = CAP_INIT_BSET, \
.securebits = SECUREBITS_DEFAULT, \
.user = INIT_USER, \
.comm = "swapper", \
.thread = INIT_THREAD, \
.fs = &init_fs, \
.files = &init_files, \
.signal = &init_signals, \
.sighand = &init_sighand, \
.nsproxy = &init_nsproxy, \
.pending = { \
.list = LIST_HEAD_INIT(tsk.pending.list), \
.signal = {{0}}}, \
.blocked = {{0}}, \
.alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \
.journal_info = NULL, \
.cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \
.fs_excl = ATOMIC_INIT(0), \
.pi_lock = __SPIN_LOCK_UNLOCKED(tsk.pi_lock), \
.timer_slack_ns = 50000, /* 50 usec default slack */ \
.pids = { \
[PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \
[PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \
[PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \
}, \
.dirties = INIT_PROP_LOCAL_SINGLE(dirties), \
INIT_IDS \
INIT_TRACE_IRQFLAGS \
INIT_LOCKDEP \
}
#define INIT_CPU_TIMERS(cpu_timers) \
{ \
LIST_HEAD_INIT(cpu_timers[0]), \
LIST_HEAD_INIT(cpu_timers[1]), \
LIST_HEAD_INIT(cpu_timers[2]), \
}
#endif
Reference in New Issue View Git Blame Copy Permalink