Lines Matching defs:inodes
8 * upon dirty inodes against superblocks, and writing back dirty
9 * pages against inodes. ie: data writeback. Writeout of the
60 * seconds), which means most of the time inodes will have their
62 * few inodes might not their timestamps updated for 24 hours.
143 * periodic background write-out of dirty inodes. Since the write-out would
266 * Maximum inodes per isw. A specific value has been chosen to make
309 * list. Only inodes attached to cgwb's are kept on this list.
384 * Multiple inodes can be switched at once. The switching procedure
391 struct inode *inodes[];
472 * many inodes. So just attach inode at the end of the
524 struct backing_dev_info *bdi = inode_to_bdi(isw->inodes[0]);
525 struct bdi_writeback *old_wb = isw->inodes[0]->i_wb;
535 inodep = isw->inodes;
578 for (inodep = isw->inodes; *inodep; inodep++) {
689 isw = kzalloc_flex(*isw, inodes, 2, GFP_ATOMIC);
712 isw->inodes[0] = inode;
735 isw->inodes[*nr] = inode;
745 * cleanup_offline_cgwb - detach associated inodes
748 * Switch all inodes attached to @wb to a nearest living ancestor's wb in order
749 * to eventually release the dying @wb. Returns %true if not all inodes were
760 isw = kzalloc_flex(*isw, inodes, WB_MAX_INODES_PER_ISW);
778 * In addition to the inodes that have completed writeback, also switch
779 * cgwbs for those inodes only with dirty timestamps. Otherwise, those
780 * inodes won't be written back for a long time when lazytime is
791 /* no attached inodes? bail out */
1047 * relation to the total write bandwidth of all wb's w/ dirty inodes on
1076 * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's
1330 * Add in the number of potentially dirty inodes, because each inode
1507 * For inodes being constantly redirtied, dirtied_when can get stuck.
1518 * Move expired (dirtied before dirtied_before) dirty inodes from
1573 * Queue all expired dirty inodes for io, eldest first.
1669 * inodes. This function can be called only by flusher thread - noone else
1670 * processes all inodes in writeback lists and requeueing inodes behind flusher
1693 * is odd for clean inodes, it can happen for some
1950 * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
1972 * Write a portion of b_io inodes which belong to @sb.
1974 * Return the number of pages and/or inodes written.
1997 long total_wrote = 0; /* count both pages and inodes */
2013 * superblock, move all inodes not belonging
2029 * Don't bother with new inodes or inodes being freed, first
2044 * other inodes on s_io.
2166 /* Leave any unwritten inodes on b_io */
2197 * just walks the superblock inode list, writing back any inodes which are
2249 * to include all inodes that need writing. Livelock
2272 * Dirty inodes are moved to b_io for writeback in batches.
2275 * as made some progress on cleaning pages or inodes.
2283 * No more inodes for IO, bail
2576 * Wake up bdi's periodically to make sure dirtytime inodes gets
2580 * inodes on the system. So instead we define a separate delayed work
2662 * refers to a blockdev. Unhashed inodes will never be added to the dirty list
2665 * In short, ensure you hash any inodes _before_ you start marking them dirty.
2748 * list handling so that we don't move inodes under flush worker's
2766 * Only add valid (hashed) inodes to the superblock's
2767 * dirty list. Add blockdev inodes as well.
2843 * inodes that have started writeback after this point.
2845 * Use rcu_read_lock() to keep the inodes around until we have a
2847 * the local list because inodes can be dropped from either by writeback
2937 * writeback_inodes_sb_nr - writeback dirty inodes from given super_block
2942 * Start writeback on some inodes on this super_block. No guarantees are made
2955 * writeback_inodes_sb - writeback dirty inodes from given super_block
2959 * Start writeback on some inodes on this super_block. No guarantees are made
3009 * inodes under writeback and I_DIRTY_TIME inodes ignored by