Lines Matching full:reclaim
98 * do not reclaim anything from the anonymous working set right now. in get_scan_count_hyperhold()
162 * their relative recent reclaim efficiency. in get_scan_count_hyperhold()
268 * aren't eligible for reclaim - either because they in shrink_anon()
405 * thrashing, try to reclaim those first before touching in shrink_node_hyperhold()
447 * runaway file reclaim problem, but rather just in shrink_node_hyperhold()
448 * extreme pressure. Reclaim as per usual then. in shrink_node_hyperhold()
473 * If reclaim is isolating dirty pages under writeback, in shrink_node_hyperhold()
479 * device. The only option is to throttle from reclaim in shrink_node_hyperhold()
486 * immediate reclaim and stall if any are encountered in shrink_node_hyperhold()
492 /* Allow kswapd to start writing pages during reclaim. */ in shrink_node_hyperhold()
498 * reclaim and under writeback (nr_immediate), it in shrink_node_hyperhold()
515 * Stall direct reclaim for IO completions if underlying BDIs in shrink_node_hyperhold()
529 * many failures to reclaim anything from them and goes to in shrink_node_hyperhold()
530 * sleep. On reclaim progress, reset the failure counter. A in shrink_node_hyperhold()
531 * successful direct reclaim run will revive a dormant kswapd. in shrink_node_hyperhold()