From 1d615482547584b9a8bb6316a58fed6ce90dd9ff Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Tue, 17 Nov 2009 14:54:03 +0100 Subject: sched: Convert pi_lock to raw_spinlock Convert locks which cannot be sleeping locks in preempt-rt to raw_spinlocks. Signed-off-by: Thomas Gleixner Acked-by: Peter Zijlstra Acked-by: Ingo Molnar --- kernel/fork.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 1415dc4598a..9bd91447e05 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -939,9 +939,9 @@ SYSCALL_DEFINE1(set_tid_address, int __user *, tidptr) static void rt_mutex_init_task(struct task_struct *p) { - spin_lock_init(&p->pi_lock); + raw_spin_lock_init(&p->pi_lock); #ifdef CONFIG_RT_MUTEXES - plist_head_init(&p->pi_waiters, &p->pi_lock); + plist_head_init_raw(&p->pi_waiters, &p->pi_lock); p->pi_blocked_on = NULL; #endif } -- cgit From 569b846df54ffb2827b83ce3244c5f032394cba4 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 15 Dec 2009 16:47:03 -0800 Subject: memcg: coalesce uncharge during unmap/truncate In massive parallel enviroment, res_counter can be a performance bottleneck. One strong techinque to reduce lock contention is reducing calls by coalescing some amount of calls into one. Considering charge/uncharge chatacteristic, - charge is done one by one via demand-paging. - uncharge is done by - in chunk at munmap, truncate, exit, execve... - one by one via vmscan/paging. It seems we have a chance to coalesce uncharges for improving scalability at unmap/truncation. This patch is a for coalescing uncharge. For avoiding scattering memcg's structure to functions under /mm, this patch adds memcg batch uncharge information to the task. A reason for per-task batching is for making use of caller's context information. We do batched uncharge (deleyed uncharge) when truncation/unmap occurs but do direct uncharge when uncharge is called by memory reclaim (vmscan.c). The degree of coalescing depends on callers - at invalidate/trucate... pagevec size - at unmap ....ZAP_BLOCK_SIZE (memory itself will be freed in this degree.) Then, we'll not coalescing too much. On x86-64 8cpu server, I tested overheads of memcg at page fault by running a program which does map/fault/unmap in a loop. Running a task per a cpu by taskset and see sum of the number of page faults in 60secs. [without memcg config] 40156968 page-faults # 0.085 M/sec ( +- 0.046% ) 27.67 cache-miss/faults [root cgroup] 36659599 page-faults # 0.077 M/sec ( +- 0.247% ) 31.58 miss/faults [in a child cgroup] 18444157 page-faults # 0.039 M/sec ( +- 0.133% ) 69.96 miss/faults [child with this patch] 27133719 page-faults # 0.057 M/sec ( +- 0.155% ) 47.16 miss/faults We can see some amounts of improvement. (root cgroup doesn't affected by this patch) Another patch for "charge" will follow this and above will be improved more. Changelog(since 2009/10/02): - renamed filed of memcg_batch (as pages to bytes, memsw to memsw_bytes) - some clean up and commentary/description updates. - added initialize code to copy_process(). (possible bug fix) Changelog(old): - fixed !CONFIG_MEM_CGROUP case. - rebased onto the latest mmotm + softlimit fix patches. - unified patch for callers - added commetns. - make ->do_batch as bool. - removed css_get() at el. We don't need it. Signed-off-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Cc: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 9bd91447e05..b6cbd33dde8 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1127,6 +1127,10 @@ static struct task_struct *copy_process(unsigned long clone_flags, #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif +#ifdef CONFIG_CGROUP_MEM_RES_CTLR + p->memcg_batch.do_batch = 0; + p->memcg_batch.memcg = NULL; +#endif p->bts = NULL; -- cgit From 6580807da14c423f0d0a708108e6df6ebc8bc83d Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Tue, 15 Dec 2009 16:47:16 -0800 Subject: ptrace: copy_process() should disable stepping If the tracee calls fork() after PTRACE_SINGLESTEP, the forked child starts with TIF_SINGLESTEP/X86_EFLAGS_TF bits copied from ptraced parent. This is not right, especially when the new child is not auto-attaced: in this case it is killed by SIGTRAP. Change copy_process() to call user_disable_single_step(). Tested on x86. Test-case: #include #include #include #include #include #include int main(void) { int pid, status; if (!(pid = fork())) { assert(ptrace(PTRACE_TRACEME) == 0); kill(getpid(), SIGSTOP); if (!fork()) { /* kernel bug: this child will be killed by SIGTRAP */ printf("Hello world\n"); return 43; } wait(&status); return WEXITSTATUS(status); } for (;;) { assert(pid == wait(&status)); if (WIFEXITED(status)) break; assert(ptrace(PTRACE_SINGLESTEP, pid, 0,0) == 0); } assert(WEXITSTATUS(status) == 43); return 0; } Signed-off-by: Oleg Nesterov Acked-by: Roland McGrath Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index b6cbd33dde8..202a0ba63d3 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1210,9 +1210,10 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->sas_ss_sp = p->sas_ss_size = 0; /* - * Syscall tracing should be turned off in the child regardless - * of CLONE_PTRACE. + * Syscall tracing and stepping should be turned off in the + * child regardless of CLONE_PTRACE. */ + user_disable_single_step(p); clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE); #ifdef TIF_SYSCALL_EMU clear_tsk_thread_flag(p, TIF_SYSCALL_EMU); -- cgit From 9cd80bbb07fcd6d4d037fad4297496d3b132ac6b Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 17 Dec 2009 15:27:15 -0800 Subject: do_wait() optimization: do not place sub-threads on task_struct->children list Thanks to Roland who pointed out de_thread() issues. Currently we add sub-threads to ->real_parent->children list. This buys nothing but slows down do_wait(). With this patch ->children contains only main threads (group leaders). The only complication is that forget_original_parent() should iterate over sub-threads by hand, and de_thread() needs another list_replace() when it changes ->group_leader. Henceforth do_wait_thread() can never see task_detached() && !EXIT_DEAD tasks, we can remove this check (and we can unify do_wait_thread() and ptrace_do_wait()). This change can confuse the optimistic search in mm_update_next_owner(), but this is fixable and minor. Perhaps badness() and oom_kill_process() should be updated, but they should be fixed in any case. Signed-off-by: Oleg Nesterov Cc: Roland McGrath Cc: Ingo Molnar Cc: Ratan Nalumasu Cc: Vitaly Mayatskikh Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/fork.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 202a0ba63d3..5b2959b3ffc 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1291,7 +1291,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, } if (likely(p->pid)) { - list_add_tail(&p->sibling, &p->real_parent->children); tracehook_finish_clone(p, clone_flags, trace); if (thread_group_leader(p)) { @@ -1303,6 +1302,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->signal->tty = tty_kref_get(current->signal->tty); attach_pid(p, PIDTYPE_PGID, task_pgrp(current)); attach_pid(p, PIDTYPE_SID, task_session(current)); + list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); __get_cpu_var(process_counts)++; } -- cgit