/* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to perform writeback if the system is over `vm_dirty_ratio'. * If we're over `background_thresh' then pdflush is woken to perform some * writeout. */ static void balance_dirty_pages(struct address_space *mapping) { long nr_reclaimable, bdi_nr_reclaimable; long nr_writeback, bdi_nr_writeback; long background_thresh; long dirty_thresh; long bdi_thresh; unsigned long pages_written = 0; unsigned long write_chunk = sync_writeback_pages(); struct backing_dev_info *bdi = mapping->backing_dev_info; for (;;) { struct writeback_control wbc = { .bdi = bdi, .sync_mode = WB_SYNC_NONE, .older_than_this = NULL, .nr_to_write = write_chunk, .range_cyclic = 1, }; get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); nr_reclaimable = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); nr_writeback = global_page_state(NR_WRITEBACK); bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK); if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh) break; /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts * when the bdi limits are ramping up. */ if (nr_reclaimable + nr_writeback < (background_thresh + dirty_thresh) / 2) break; if (!bdi->dirty_exceeded) bdi->dirty_exceeded = 1; /* Note: nr_reclaimable denotes nr_dirty + nr_unstable. * Unstable writes are a feature of certain networked * filesystems (i.e. NFS) in which data may have been * written to the server's write cache, but has not yet * been flushed to permanent storage. */ if (bdi_nr_reclaimable) { writeback_inodes(&wbc); pages_written += write_chunk - wbc.nr_to_write; get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); } /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (bdi_thresh < 2*bdi_stat_error(bdi)) { bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK); } else if (bdi_nr_reclaimable) { bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK); } if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh) break; if (pages_written >= write_chunk) break; /* We've done our duty */ congestion_wait(WRITE, HZ/10); } if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh && bdi->dirty_exceeded) bdi->dirty_exceeded = 0; if (writeback_in_progress(bdi)) return; /* pdflush is already working this queue */ /* * In laptop mode, we wait until hitting the higher threshold before * starting background writeout, and then write out all the way down * to the lower threshold. So slow writers cause minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if ((laptop_mode && pages_written) || (!laptop_mode && (global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS) > background_thresh))) pdflush_operation(background_writeout, 0); } void set_page_dirty_balance(struct page *page, int page_mkwrite) { if (set_page_dirty(page) || page_mkwrite) { struct address_space *mapping = page_mapping(page); if (mapping) balance_dirty_pages_ratelimited(mapping); } } /** * balance_dirty_pages_ratelimited_nr - balance dirty memory state * @mapping: address_space which was dirtied * @nr_pages_dirtied: number of pages which the caller has just dirtied * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * On really big machines, get_writeback_state is expensive, so try to avoid * calling it too often (ratelimiting). But once we're over the dirty memory * limit we decrease the ratelimiting by a lot, to prevent individual processes * from overshooting the limit by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, unsigned long nr_pages_dirtied) { static DEFINE_PER_CPU(unsigned long, ratelimits) = 0; unsigned long ratelimit; unsigned long *p; ratelimit = ratelimit_pages; if (mapping->backing_dev_info->dirty_exceeded) ratelimit = 8; /* * Check the rate limiting. Also, we do not want to throttle real-time * tasks in balance_dirty_pages(). Period. */ preempt_disable(); p = &__get_cpu_var(ratelimits); *p += nr_pages_dirtied; if (unlikely(*p >= ratelimit)) { *p = 0; preempt_enable(); balance_dirty_pages(mapping); return; } preempt_enable(); } EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr); void throttle_vm_writeout(gfp_t gfp_mask) { long background_thresh; long dirty_thresh; for ( ; ; ) { get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL); /* * Boost the allowable dirty threshold a bit for page * allocators so they don't get DoS'ed by heavy writers */ dirty_thresh += dirty_thresh / 10; /* wheeee... */ if (global_page_state(NR_UNSTABLE_NFS) + global_page_state(NR_WRITEBACK) <= dirty_thresh) break; congestion_wait(WRITE, HZ/10); /* * The caller might hold locks which can prevent IO completion * or progress in the filesystem. So we cannot just sit here * waiting for IO to complete. */ if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO)) break; } }
/* * writeback at least _min_pages, and keep writing until the amount of dirty * memory is less than the background threshold, or until we're all clean. */ static void background_writeout(unsigned long _min_pages) { long min_pages = _min_pages; struct writeback_control wbc = { .bdi = NULL, .sync_mode = WB_SYNC_NONE, .older_than_this = NULL, .nr_to_write = 0, .nonblocking = 1, .range_cyclic = 1, }; for ( ; ; ) { unsigned long background_thresh; unsigned long dirty_thresh; get_dirty_limits(&background_thresh, &dirty_thresh, NULL, NULL); if (global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS) < background_thresh && min_pages <= 0) break; wbc.more_io = 0; wbc.encountered_congestion = 0; wbc.nr_to_write = MAX_WRITEBACK_PAGES; wbc.pages_skipped = 0; writeback_inodes(&wbc); min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) { /* Wrote less than expected */ if (wbc.encountered_congestion || wbc.more_io) congestion_wait(WRITE, HZ/10); else break; } } } /* * Start writeback of `nr_pages' pages. If `nr_pages' is zero, write back * the whole world. Returns 0 if a pdflush thread was dispatched. Returns * -1 if all pdflush threads were busy. */ int wakeup_pdflush(long nr_pages) { if (nr_pages == 0) nr_pages = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); return pdflush_operation(background_writeout, nr_pages); } static void wb_timer_fn(unsigned long unused); static void laptop_timer_fn(unsigned long unused); static DEFINE_TIMER(wb_timer, wb_timer_fn, 0, 0); static DEFINE_TIMER(laptop_mode_wb_timer, laptop_timer_fn, 0, 0); /* * Periodic writeback of "old" data. * * Define "old": the first time one of an inode's pages is dirtied, we mark the * dirtying-time in the inode's address_space. So this periodic writeback code * just walks the superblock inode list, writing back any inodes which are * older than a specific point in time. * * Try to run once per dirty_writeback_interval. But if a writeback event * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * * older_than_this takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static void wb_kupdate(unsigned long arg) { unsigned long oldest_jif; unsigned long start_jif; unsigned long next_jif; long nr_to_write; struct writeback_control wbc = { .bdi = NULL, .sync_mode = WB_SYNC_NONE, .older_than_this = &oldest_jif, .nr_to_write = 0, .nonblocking = 1, .for_kupdate = 1, .range_cyclic = 1, }; sync_supers(); oldest_jif = jiffies - msecs_to_jiffies(dirty_expire_interval); start_jif = jiffies; next_jif = start_jif + msecs_to_jiffies(dirty_writeback_interval * 10); nr_to_write = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS) + (inodes_stat.nr_inodes - inodes_stat.nr_unused); while (nr_to_write > 0) { wbc.more_io = 0; wbc.encountered_congestion = 0; wbc.nr_to_write = MAX_WRITEBACK_PAGES; writeback_inodes(&wbc); if (wbc.nr_to_write > 0) { if (wbc.encountered_congestion || wbc.more_io) congestion_wait(WRITE, HZ/10); else break; /* All the old data is written */ } nr_to_write -= MAX_WRITEBACK_PAGES - wbc.nr_to_write; } if (time_before(next_jif, jiffies + HZ)) next_jif = jiffies + HZ; if (dirty_writeback_interval) mod_timer(&wb_timer, next_jif); } /* * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs */ int dirty_writeback_centisecs_handler(ctl_table *table, int write, struct file *file, void __user *buffer, size_t *length, loff_t *ppos) { proc_dointvec(table, write, file, buffer, length, ppos); if (dirty_writeback_interval) mod_timer(&wb_timer, jiffies + msecs_to_jiffies(dirty_writeback_interval * 10)); else del_timer(&wb_timer); return 0; }
/* * balance_dirty_pages() must be called by processes which are generating dirty * data. It looks at the number of dirty pages in the machine and will force * the caller to perform writeback if the system is over `vm_dirty_ratio'. * If we're over `background_thresh' then the writeback threads are woken to * perform some writeout. */ static void balance_dirty_pages(struct address_space *mapping, unsigned long write_chunk) { long nr_reclaimable, bdi_nr_reclaimable; long nr_writeback, bdi_nr_writeback; long ub_dirty, ub_writeback; long ub_thresh, ub_background_thresh; unsigned long background_thresh; unsigned long dirty_thresh; unsigned long bdi_thresh; unsigned long pages_written = 0; unsigned long pause = 1; struct user_beancounter *ub = get_io_ub(); struct backing_dev_info *bdi = mapping->backing_dev_info; for (;;) { struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .older_than_this = NULL, .nr_to_write = write_chunk, .range_cyclic = 1, }; get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); if (ub_dirty_limits(&ub_background_thresh, &ub_thresh, ub)) { ub_dirty = ub_stat_get(ub, dirty_pages); ub_writeback = ub_stat_get(ub, writeback_pages); } else { ub_dirty = ub_writeback = 0; ub_thresh = ub_background_thresh = LONG_MAX / 2; } nr_reclaimable = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); nr_writeback = global_page_state(NR_WRITEBACK); bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK); /* * Check thresholds, set dirty_exceeded flags and * start background writeback before throttling. */ if (bdi_nr_reclaimable + bdi_nr_writeback > bdi_thresh) { if (!bdi->dirty_exceeded) bdi->dirty_exceeded = 1; if (!writeback_in_progress(bdi)) bdi_start_background_writeback(bdi, NULL); } else if (ub_dirty + ub_writeback > ub_thresh) { if (!test_bit(UB_DIRTY_EXCEEDED, &ub->ub_flags)) set_bit(UB_DIRTY_EXCEEDED, &ub->ub_flags); if (!writeback_in_progress(bdi)) bdi_start_background_writeback(bdi, ub); } else break; /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts * when the bdi limits are ramping up. */ if (bdi_cap_account_writeback(bdi) && nr_reclaimable + nr_writeback < (background_thresh + dirty_thresh) / 2 && ub_dirty + ub_writeback < (ub_background_thresh + ub_thresh) / 2) break; /* Note: nr_reclaimable denotes nr_dirty + nr_unstable. * Unstable writes are a feature of certain networked * filesystems (i.e. NFS) in which data may have been * written to the server's write cache, but has not yet * been flushed to permanent storage. * Only move pages to writeback if this bdi is over its * threshold otherwise wait until the disk writes catch * up. */ trace_wbc_balance_dirty_start(&wbc, bdi); if (bdi_nr_reclaimable > bdi_thresh) { writeback_inodes_wb(&bdi->wb, &wbc); pages_written += write_chunk - wbc.nr_to_write; trace_wbc_balance_dirty_written(&wbc, bdi); get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); } else if (ub_dirty > ub_thresh) { wbc.wb_ub = ub; writeback_inodes_wb(&bdi->wb, &wbc); pages_written += write_chunk - wbc.nr_to_write; trace_wbc_balance_dirty_written(&wbc, bdi); ub_dirty = ub_stat_get(ub, dirty_pages); ub_writeback = ub_stat_get(ub, writeback_pages); wbc.wb_ub = NULL; } /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (bdi_thresh < 2*bdi_stat_error(bdi)) { bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK); } else if (bdi_nr_reclaimable) { bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK); } /* fixup ub-stat per-cpu drift to avoid false-positive */ if (ub_dirty + ub_writeback > ub_thresh && ub_dirty + ub_writeback - ub_thresh < UB_STAT_BATCH * num_possible_cpus()) { ub_dirty = ub_stat_get_exact(ub, dirty_pages); ub_writeback = ub_stat_get_exact(ub, writeback_pages); } if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh && ub_dirty + ub_writeback <= ub_thresh) break; if (pages_written >= write_chunk) break; /* We've done our duty */ trace_wbc_balance_dirty_wait(&wbc, bdi); __set_current_state(TASK_KILLABLE); io_schedule_timeout(pause); /* * Increase the delay for each loop, up to our previous * default of taking a 100ms nap. */ pause <<= 1; if (pause > HZ / 10) pause = HZ / 10; if (fatal_signal_pending(current)) break; } if(pages_written) trace_mm_balancedirty_writeout(pages_written); if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh && bdi->dirty_exceeded) bdi->dirty_exceeded = 0; if (ub_dirty + ub_writeback < ub_thresh && test_bit(UB_DIRTY_EXCEEDED, &ub->ub_flags)) clear_bit(UB_DIRTY_EXCEEDED, &ub->ub_flags); virtinfo_notifier_call(VITYPE_IO, VIRTINFO_IO_BALANCE_DIRTY, (void*)write_chunk); /* * Even if this is filtered writeback for other ub it will write * inodes for this ub, because ub->dirty_exceeded is set. */ if (writeback_in_progress(bdi)) return; /* * In laptop mode, we wait until hitting the higher threshold before * starting background writeout, and then write out all the way down * to the lower threshold. So slow writers cause minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if ((laptop_mode && pages_written) || (!laptop_mode && ((global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS)) > background_thresh))) bdi_start_background_writeback(bdi, NULL); else if ((laptop_mode && pages_written) || (!laptop_mode && ub_dirty > ub_background_thresh)) bdi_start_background_writeback(bdi, ub); } void set_page_dirty_balance(struct page *page, int page_mkwrite) { if (set_page_dirty(page) || page_mkwrite) { struct address_space *mapping = page_mapping(page); if (mapping) balance_dirty_pages_ratelimited(mapping); } } static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0; /** * balance_dirty_pages_ratelimited_nr - balance dirty memory state * @mapping: address_space which was dirtied * @nr_pages_dirtied: number of pages which the caller has just dirtied * * Processes which are dirtying memory should call in here once for each page * which was newly dirtied. The function will periodically check the system's * dirty state and will initiate writeback if needed. * * On really big machines, get_writeback_state is expensive, so try to avoid * calling it too often (ratelimiting). But once we're over the dirty memory * limit we decrease the ratelimiting by a lot, to prevent individual processes * from overshooting the limit by (ratelimit_pages) each. */ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, unsigned long nr_pages_dirtied) { unsigned long ratelimit; unsigned long *p; ratelimit = ratelimit_pages; if (mapping->backing_dev_info->dirty_exceeded || test_bit(UB_DIRTY_EXCEEDED, &get_io_ub()->ub_flags)) ratelimit = 8; /* * Check the rate limiting. Also, we do not want to throttle real-time * tasks in balance_dirty_pages(). Period. */ preempt_disable(); p = &__get_cpu_var(bdp_ratelimits); *p += nr_pages_dirtied; if (unlikely(*p >= ratelimit)) { ratelimit = sync_writeback_pages(*p); *p = 0; preempt_enable(); balance_dirty_pages(mapping, ratelimit); return; } preempt_enable(); }
static void balance_dirty_pages(struct address_space *mapping, unsigned long write_chunk) { long nr_reclaimable, bdi_nr_reclaimable; long nr_writeback, bdi_nr_writeback; unsigned long background_thresh; unsigned long dirty_thresh; unsigned long bdi_thresh; unsigned long pages_written = 0; unsigned long pause = 1; struct backing_dev_info *bdi = mapping->backing_dev_info; for (;;) { struct writeback_control wbc = { .sync_mode = WB_SYNC_NONE, .older_than_this = NULL, .nr_to_write = write_chunk, .range_cyclic = 1, }; get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); nr_reclaimable = global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS); nr_writeback = global_page_state(NR_WRITEBACK); bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK); if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh) break; /* * Throttle it only when the background writeback cannot * catch-up. This avoids (excessively) small writeouts * when the bdi limits are ramping up. */ if (nr_reclaimable + nr_writeback < (background_thresh + dirty_thresh) / 2) break; if (!bdi->dirty_exceeded) bdi->dirty_exceeded = 1; /* Note: nr_reclaimable denotes nr_dirty + nr_unstable. * Unstable writes are a feature of certain networked * filesystems (i.e. NFS) in which data may have been * written to the server's write cache, but has not yet * been flushed to permanent storage. * Only move pages to writeback if this bdi is over its * threshold otherwise wait until the disk writes catch * up. */ if (bdi_nr_reclaimable > bdi_thresh) { writeback_inodes_wb(&bdi->wb, &wbc); pages_written += write_chunk - wbc.nr_to_write; get_dirty_limits(&background_thresh, &dirty_thresh, &bdi_thresh, bdi); } /* * In order to avoid the stacked BDI deadlock we need * to ensure we accurately count the 'dirty' pages when * the threshold is low. * * Otherwise it would be possible to get thresh+n pages * reported dirty, even though there are thresh-m pages * actually dirty; with m+n sitting in the percpu * deltas. */ if (bdi_thresh < 2*bdi_stat_error(bdi)) { bdi_nr_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE); bdi_nr_writeback = bdi_stat_sum(bdi, BDI_WRITEBACK); } else if (bdi_nr_reclaimable) { bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE); bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK); } if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh) break; if (pages_written >= write_chunk) break; /* We've done our duty */ __set_current_state(TASK_INTERRUPTIBLE); io_schedule_timeout(pause); /* * Increase the delay for each loop, up to our previous * default of taking a 100ms nap. */ pause <<= 1; if (pause > HZ / 10) pause = HZ / 10; } if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh && bdi->dirty_exceeded) bdi->dirty_exceeded = 0; if (writeback_in_progress(bdi)) return; /* * In laptop mode, we wait until hitting the higher threshold before * starting background writeout, and then write out all the way down * to the lower threshold. So slow writers cause minimal disk activity. * * In normal mode, we start background writeout at the lower * background_thresh, to keep the amount of dirty memory low. */ if ((laptop_mode && pages_written) || (!laptop_mode && ((global_page_state(NR_FILE_DIRTY) + global_page_state(NR_UNSTABLE_NFS)) > background_thresh))) bdi_start_background_writeback(bdi); } void set_page_dirty_balance(struct page *page, int page_mkwrite) { if (set_page_dirty(page) || page_mkwrite) { struct address_space *mapping = page_mapping(page); if (mapping) balance_dirty_pages_ratelimited(mapping); } } static DEFINE_PER_CPU(unsigned long, bdp_ratelimits) = 0; void balance_dirty_pages_ratelimited_nr(struct address_space *mapping, unsigned long nr_pages_dirtied) { unsigned long ratelimit; unsigned long *p; ratelimit = ratelimit_pages; if (mapping->backing_dev_info->dirty_exceeded) ratelimit = 8; /* * Check the rate limiting. Also, we do not want to throttle real-time * tasks in balance_dirty_pages(). Period. */ preempt_disable(); p = &__get_cpu_var(bdp_ratelimits); *p += nr_pages_dirtied; if (unlikely(*p >= ratelimit)) { ratelimit = sync_writeback_pages(*p); *p = 0; preempt_enable(); balance_dirty_pages(mapping, ratelimit); return; } preempt_enable(); }