Lines Matching defs:writeback

3  * mm/page-writeback.c
24 #include <linux/writeback.h>
41 #include <trace/events/writeback.h>
65 * will look to see if it needs to force writeback or throttling.
72 * Start background writeback (via writeback threads) at this percentage
89 * The generator of dirty data starts writeback at this percentage
252 * requiring writeback.
434 * global_dirty_limits - background-writeback and dirty-throttling thresholds
1034 * 1% by default. Without strictlimit feature, fuse writeback may
1535 * time, a small pool of dirty/writeback pages may go empty and disk go
1666 * If we're over `background_thresh' then the writeback threads are woken to
1718 unsigned long filepages, headroom, writeback;
1725 &mdtc->dirty, &writeback);
1726 mdtc->dirty += writeback;
1757 * Throttle it only when the background writeback cannot
1786 /* Start writeback even when in laptop mode */
1982 * dirty state and will initiate writeback if needed.
2056 * dirty state and will initiate writeback if needed.
2072 * Determines whether background writeback should keep writing @wb or it's
2075 * Return: %true if writeback should continue.
2089 * as we're trying to decide whether to put more under writeback.
2108 unsigned long filepages, headroom, writeback;
2111 &writeback);
2113 domain_dirty_limits(mdtc); /* ditto, ignore writeback */
2144 * Writing 0 to dirty_writeback_interval will disable periodic writeback
2145 * and a different non-zero value will wakeup the writeback threads.
2167 * We've spun up the disk and we're in laptop mode: schedule writeback
2178 * caused another writeback to be scheduled by laptop_io_completion.
2179 * Nothing needs to be written back anymore, so we unschedule the writeback.
2299 * Called early on to tune the page writeback dirty limits.
2318 cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online",
2320 cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL,
2336 * TOWRITE tag to identify pages eligible for writeback. This mechanism is
2337 * used to avoid livelocking of writeback by a process steadily creating new
2371 * if it's dirty. This is desirable behaviour for memory-cleaning writeback,
2385 * To avoid deadlocks between range_cyclic writeback and callers that hold
2388 * lock/page writeback access order inversion - we should only ever lock
2479 * writeback. There's no need to continue for
2480 * background writeback. Just push done_index
2483 * writeback, we must process the entire dirty
2506 * we tagged for writeback prior to entering this loop.
2569 * Lacking an allocation context or the locality or writeback
2571 * writeback activity on the local node. It's as good a
2579 * but if there's constant writeback being submitted, this makes sure
2580 * writeback bandwidth is updated once in a while.
2634 * Helper function for deaccounting dirty page without writeback.
2716 * @wbc: The writeback control.
2880 * cause the writeback.
2931 * Make sure estimate of writeback throughput gets updated after
2932 * writeback completed. We delay the update by BANDWIDTH_INTERVAL
2934 * that if multiple inodes end writeback at a similar time, they get
3043 * If writeback has been triggered on a page that cannot be made
3053 * folio_wait_writeback - Wait for a folio to finish writeback.
3061 * If the folio is not locked, writeback may start again after writeback
3074 * folio_wait_writeback_killable - Wait for a folio to finish writeback.
3082 * If the folio is not locked, writeback may start again after writeback
3099 * folio_wait_stable() - wait for writeback to finish, if necessary.
3103 * device that requires folio contents to be held stable during writeback.
3104 * If so, then it will wait for any pending writeback to complete.
3108 * If the folio is not locked, writeback may start again after writeback