mm/madvise: add cond_resched() in madvise_cold_or_pageout_pte_range()

JiexunWang · akpm00 · commit b2f557a21bc8 · 2023-12-06T16:12:50.000-08:00
I conducted real-time testing and observed that madvise_cold_or_pageout_pte_range() causes significant latency under memory pressure, which can be effectively reduced by adding cond_resched() within the loop. I tested on the LicheePi 4A board using Cylictest for latency testing and Ftrace for latency tracing. The board uses TH1520 processor and has a memory size of 8GB. The kernel version is 6.5.0 with the PREEMPT_RT patch applied. The script I tested is as follows: echo wakeup_rt > /sys/kernel/tracing/current_tracer echo 1 > /sys/kernel/tracing/tracing_on echo 0 > /sys/kernel/tracing/tracing_max_latency stress-ng --vm 8 --vm-bytes 2G & cyclictest --mlockall --smp --priority=99 --distance=0 --duration=30m echo 0 > /sys/kernel/tracing/tracing_on cat /sys/kernel/tracing/trace The tracing results before modification are as follows: # tracer: wakeup_rt # # wakeup_rt latency trace v1.1.5 on 6.5.0-rt6-r1208-00003-g999d221864bf # -------------------------------------------------------------------- # latency: 2552 us, #6/6, CPU#3 | (M:preempt_rt VP:0, KP:0, SP:0 HP:0 #P:4) # ----------------- # | task: cyclictest-196 (uid:0 nice:0 policy:1 rt_prio:99) # ----------------- # # _--------=> CPU# # / _-------=> irqs-off/BH-disabled # | / _------=> need-resched # || / _-----=> need-resched-lazy # ||| / _----=> hardirq/softirq # |||| / _---=> preempt-depth # ||||| / _--=> preempt-lazy-depth # |||||| / _-=> migrate-disable # ||||||| / delay # cmd pid |||||||| time | caller # \ / |||||||| \ | / stress-n-206 3dn.h512 2us : 206:120:R + [003] 196: 0:R cyclictest stress-n-206 3dn.h512 7us : <stack trace> => __ftrace_trace_stack => __trace_stack => probe_wakeup => ttwu_do_activate => try_to_wake_up => wake_up_process => hrtimer_wakeup => __hrtimer_run_queues => hrtimer_interrupt => riscv_timer_interrupt => handle_percpu_devid_irq => generic_handle_domain_irq => riscv_intc_irq => handle_riscv_irq => do_irq stress-n-206 3dn.h512 9us#: 0 stress-n-206 3d...3.. 2544us : __schedule stress-n-206 3d...3.. 2545us : 206:120:R ==> [003] 196: 0:R cyclictest stress-n-206 3d...3.. 2551us : <stack trace> => __ftrace_trace_stack => __trace_stack => probe_wakeup_sched_switch => __schedule => preempt_schedule => migrate_enable => rt_spin_unlock => madvise_cold_or_pageout_pte_range => walk_pgd_range => __walk_page_range => walk_page_range => madvise_pageout => madvise_vma_behavior => do_madvise => sys_madvise => do_trap_ecall_u => ret_from_exception The tracing results after modification are as follows: # tracer: wakeup_rt # # wakeup_rt latency trace v1.1.5 on 6.5.0-rt6-r1208-00004-gca3876fc69a6-dirty # -------------------------------------------------------------------- # latency: 1689 us, #6/6, CPU#0 | (M:preempt_rt VP:0, KP:0, SP:0 HP:0 #P:4) # ----------------- # | task: cyclictest-217 (uid:0 nice:0 policy:1 rt_prio:99) # ----------------- # # _--------=> CPU# # / _-------=> irqs-off/BH-disabled # | / _------=> need-resched # || / _-----=> need-resched-lazy # ||| / _----=> hardirq/softirq # |||| / _---=> preempt-depth # ||||| / _--=> preempt-lazy-depth # |||||| / _-=> migrate-disable # ||||||| / delay # cmd pid |||||||| time | caller # \ / |||||||| \ | / stress-n-232 0dn.h413 1us+: 232:120:R + [000] 217: 0:R cyclictest stress-n-232 0dn.h413 12us : <stack trace> => __ftrace_trace_stack => __trace_stack => probe_wakeup => ttwu_do_activate => try_to_wake_up => wake_up_process => hrtimer_wakeup => __hrtimer_run_queues => hrtimer_interrupt => riscv_timer_interrupt => handle_percpu_devid_irq => generic_handle_domain_irq => riscv_intc_irq => handle_riscv_irq => do_irq stress-n-232 0dn.h413 19us#: 0 stress-n-232 0d...3.. 1671us : __schedule stress-n-232 0d...3.. 1676us+: 232:120:R ==> [000] 217: 0:R cyclictest stress-n-232 0d...3.. 1687us : <stack trace> => __ftrace_trace_stack => __trace_stack => probe_wakeup_sched_switch => __schedule => preempt_schedule => migrate_enable => free_unref_page_list => release_pages => free_pages_and_swap_cache => tlb_batch_pages_flush => tlb_flush_mmu => unmap_page_range => unmap_vmas => unmap_region => do_vmi_align_munmap.constprop.0 => do_vmi_munmap => __vm_munmap => sys_munmap => do_trap_ecall_u => ret_from_exception After the modification, the cause of maximum latency is no longer madvise_cold_or_pageout_pte_range(), so this modification can reduce the latency caused by madvise_cold_or_pageout_pte_range(). Currently the madvise_cold_or_pageout_pte_range() function exhibits significant latency under memory pressure, which can be effectively reduced by adding cond_resched() within the loop. When the batch_count reaches SWAP_CLUSTER_MAX, we reschedule the task to ensure fairness and avoid long lock holding times. Link: https://lkml.kernel.org/r/85363861af65fac66c7a98c251906afc0d9c8098.1695291046.git.wangjiexun@tinylab.org Signed-off-by: Jiexun Wang <wangjiexun@tinylab.org> Cc: Zhangjin Wu <falcon@tinylab.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
diff --git a/mm/madvise.c b/mm/madvise.c
@@ -335,6 +335,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 	struct folio *folio = NULL;
 	LIST_HEAD(folio_list);
 	bool pageout_anon_only_filter;
+	unsigned int batch_count = 0;
 
 	if (fatal_signal_pending(current))
 		return -EINTR;
@@ -416,6 +417,7 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 regular_folio:
 #endif
 	tlb_change_page_size(tlb, PAGE_SIZE);
+restart:
 	start_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	if (!start_pte)
 		return 0;
@@ -424,6 +426,15 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 	for (; addr < end; pte++, addr += PAGE_SIZE) {
 		ptent = ptep_get(pte);
 
+		if (++batch_count == SWAP_CLUSTER_MAX) {
+			batch_count = 0;
+			if (need_resched()) {
+				pte_unmap_unlock(start_pte, ptl);
+				cond_resched();
+				goto restart;
+			}
+		}
+
 		if (pte_none(ptent))
 			continue;
 
