59  * MAKING RESERVATIONS, FLUSHING NORMALLY (non-priority)
88  * MAKING RESERVATIONS, FLUSHING HIGH PRIORITY
95  * THE FLUSHING STATES
320 	 * If we aren't flushing all things, let us overcommit up to  in calc_available_free_space()
512 		 * flushing loops and hope for the best.  Delalloc will expand  in shrink_delalloc()
544 		 * marked clean.  We don't use filemap_fwrite for flushing  in shrink_delalloc()
590 		 * flushing so we can stop flushing if we decide we don't need  in shrink_delalloc()
721 	 * We may be flushing because suddenly we have less space than we had  in btrfs_calc_reclaim_metadata_size()
724 	 * appropriate pressure on the flushing state machine.  in btrfs_calc_reclaim_metadata_size()
753 	 * that devoted to other reservations then there's no sense in flushing,  in need_preemptive_reclaim()
754 	 * we don't have a lot of things that need flushing.  in need_preemptive_reclaim()
768 	 * pinned then we want to start flushing.  in need_preemptive_reclaim()
808 	 * around.  Preemptive flushing is only useful in that it can free up  in need_preemptive_reclaim()
818 	 * clearly be heavy enough to warrant preemptive flushing.  In the case  in need_preemptive_reclaim()
819 	 * of heavy DIO or ordered reservations, preemptive flushing will just  in need_preemptive_reclaim()
824 	 * can keep flushing.  This is to avoid the case where we start  in need_preemptive_reclaim()
825 	 * flushing, and now delalloc == ordered and we stop preemptively  in need_preemptive_reclaim()
826 	 * flushing when we could still have several gigs of delalloc to flush.  in need_preemptive_reclaim()
869  * maybe_fail_all_tickets - we've exhausted our flushing, start failing tickets
871  * @space_info - the space info we were flushing
873  * We call this when we've exhausted our flushing ability and haven't made
914 		 * We're just throwing tickets away, so more flushing may not  in maybe_fail_all_tickets()
973 		 * under heavy pressure, so allow one trip through the flushing  in btrfs_async_reclaim_metadata_space()
985 		 * through the flushing state machine skip ALLOC_CHUNK_FORCE and  in btrfs_async_reclaim_metadata_space()
1010  * This handles pre-flushing of metadata space before we get to the point that
1014  * watermark of space by flushing whichever reservation pool is currently the
1067 		 * We really want to avoid flushing delalloc too much, as it  in btrfs_preempt_reclaim_metadata_space()
1110  *   Space is freed from flushing delalloc in one of two ways.
1317  * Do the appropriate flushing and waiting for a ticket
1394  * This returns true if this flush state will go through the ordinary flushing
1413 	 * and freeing space, like there is with flushing delayed refs or  in maybe_clamp_preempt()
1431  * flush out space to make room.  It will do this by flushing delalloc if
1487 	 * the list and we will do our own flushing further down.  in __reserve_bytes()
1505 				 * our preemptive flushing is unable to keep  in __reserve_bytes()
1507 				 * preemptive flushing in order to keep up with  in __reserve_bytes()
1557  * flush out space to make room.  It will do this by flushing delalloc if