From 24f7c6b981fb70084757382da464ea85d72af300 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:17:56 +1000 Subject: mm: new shrinker API MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The current shrinker callout API uses an a single shrinker call for multiple functions. To determine the function, a special magical value is passed in a parameter to change the behaviour. This complicates the implementation and return value specification for the different behaviours. Separate the two different behaviours into separate operations, one to return a count of freeable objects in the cache, and another to scan a certain number of objects in the cache for freeing. In defining these new operations, ensure the return values and resultant behaviours are clearly defined and documented. Modify shrink_slab() to use the new API and implement the callouts for all the existing shrinkers. Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Acked-by: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- mm/vmscan.c | 60 ++++++++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 40 insertions(+), 20 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 2cff0d491c6..4d4e859b4b9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -205,19 +205,24 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker, * * Returns the number of slab objects which we shrunk. */ -unsigned long shrink_slab(struct shrink_control *shrink, +unsigned long shrink_slab(struct shrink_control *shrinkctl, unsigned long nr_pages_scanned, unsigned long lru_pages) { struct shrinker *shrinker; - unsigned long ret = 0; + unsigned long freed = 0; if (nr_pages_scanned == 0) nr_pages_scanned = SWAP_CLUSTER_MAX; if (!down_read_trylock(&shrinker_rwsem)) { - /* Assume we'll be able to shrink next time */ - ret = 1; + /* + * If we would return 0, our callers would understand that we + * have nothing else to shrink and give up trying. By returning + * 1 we keep it going and assume we'll be able to shrink next + * time. + */ + freed = 1; goto out; } @@ -225,14 +230,16 @@ unsigned long shrink_slab(struct shrink_control *shrink, unsigned long long delta; long total_scan; long max_pass; - int shrink_ret = 0; long nr; long new_nr; long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; - max_pass = do_shrinker_shrink(shrinker, shrink, 0); - if (max_pass <= 0) + if (shrinker->count_objects) + max_pass = shrinker->count_objects(shrinker, shrinkctl); + else + max_pass = do_shrinker_shrink(shrinker, shrinkctl, 0); + if (max_pass == 0) continue; /* @@ -248,8 +255,8 @@ unsigned long shrink_slab(struct shrink_control *shrink, do_div(delta, lru_pages + 1); total_scan += delta; if (total_scan < 0) { - printk(KERN_ERR "shrink_slab: %pF negative objects to " - "delete nr=%ld\n", + printk(KERN_ERR + "shrink_slab: %pF negative objects to delete nr=%ld\n", shrinker->shrink, total_scan); total_scan = max_pass; } @@ -277,20 +284,33 @@ unsigned long shrink_slab(struct shrink_control *shrink, if (total_scan > max_pass * 2) total_scan = max_pass * 2; - trace_mm_shrink_slab_start(shrinker, shrink, nr, + trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, nr_pages_scanned, lru_pages, max_pass, delta, total_scan); while (total_scan >= batch_size) { - int nr_before; - nr_before = do_shrinker_shrink(shrinker, shrink, 0); - shrink_ret = do_shrinker_shrink(shrinker, shrink, - batch_size); - if (shrink_ret == -1) - break; - if (shrink_ret < nr_before) - ret += nr_before - shrink_ret; + if (shrinker->scan_objects) { + unsigned long ret; + shrinkctl->nr_to_scan = batch_size; + ret = shrinker->scan_objects(shrinker, shrinkctl); + + if (ret == SHRINK_STOP) + break; + freed += ret; + } else { + int nr_before; + long ret; + + nr_before = do_shrinker_shrink(shrinker, shrinkctl, 0); + ret = do_shrinker_shrink(shrinker, shrinkctl, + batch_size); + if (ret == -1) + break; + if (ret < nr_before) + freed += nr_before - ret; + } + count_vm_events(SLABS_SCANNED, batch_size); total_scan -= batch_size; @@ -308,12 +328,12 @@ unsigned long shrink_slab(struct shrink_control *shrink, else new_nr = atomic_long_read(&shrinker->nr_in_batch); - trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr); + trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr); } up_read(&shrinker_rwsem); out: cond_resched(); - return ret; + return freed; } static inline int is_page_cache_freeable(struct page *page) -- cgit v1.2.3 From 0ce3d74450815500e31f16a0b65f6bab687985c3 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:18:03 +1000 Subject: shrinker: add node awareness MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Pass the node of the current zone being reclaimed to shrink_slab(), allowing the shrinker control nodemask to be set appropriately for node aware shrinkers. Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Acked-by: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- mm/vmscan.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 4d4e859b4b9..fe0d5c45844 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2374,12 +2374,16 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, */ if (global_reclaim(sc)) { unsigned long lru_pages = 0; + + nodes_clear(shrink->nodes_to_scan); for_each_zone_zonelist(zone, z, zonelist, gfp_zone(sc->gfp_mask)) { if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; lru_pages += zone_reclaimable_pages(zone); + node_set(zone_to_nid(zone), + shrink->nodes_to_scan); } shrink_slab(shrink, sc->nr_scanned, lru_pages); @@ -2836,6 +2840,8 @@ static bool kswapd_shrink_zone(struct zone *zone, return true; shrink_zone(zone, sc); + nodes_clear(shrink.nodes_to_scan); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); reclaim_state->reclaimed_slab = 0; nr_slab = shrink_slab(&shrink, sc->nr_scanned, lru_pages); @@ -3544,10 +3550,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) * number of slab pages and shake the slab until it is reduced * by the same nr_pages that we used for reclaiming unmapped * pages. - * - * Note that shrink_slab will free memory on all zones and may - * take a long time. */ + nodes_clear(shrink.nodes_to_scan); + node_set(zone_to_nid(zone), shrink.nodes_to_scan); for (;;) { unsigned long lru_pages = zone_reclaimable_pages(zone); -- cgit v1.2.3 From 1d3d4437eae1bb2963faab427f65f90663c64aa1 Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Wed, 28 Aug 2013 10:18:04 +1000 Subject: vmscan: per-node deferred work MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit The list_lru infrastructure already keeps per-node LRU lists in its node-specific list_lru_node arrays and provide us with a per-node API, and the shrinkers are properly equiped with node information. This means that we can now focus our shrinking effort in a single node, but the work that is deferred from one run to another is kept global at nr_in_batch. Work can be deferred, for instance, during direct reclaim under a GFP_NOFS allocation, where situation, all the filesystem shrinkers will be prevented from running and accumulate in nr_in_batch the amount of work they should have done, but could not. This creates an impedance problem, where upon node pressure, work deferred will accumulate and end up being flushed in other nodes. The problem we describe is particularly harmful in big machines, where many nodes can accumulate at the same time, all adding to the global counter nr_in_batch. As we accumulate more and more, we start to ask for the caches to flush even bigger numbers. The result is that the caches are depleted and do not stabilize. To achieve stable steady state behavior, we need to tackle it differently. In this patch we keep the deferred count per-node, in the new array nr_deferred[] (the name is also a bit more descriptive) and will never accumulate that to other nodes. Signed-off-by: Glauber Costa Cc: Dave Chinner Cc: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- mm/vmscan.c | 241 +++++++++++++++++++++++++++++++++++------------------------- 1 file changed, 140 insertions(+), 101 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index fe0d5c45844..799ebceeb4f 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -155,14 +155,31 @@ static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru) } /* - * Add a shrinker callback to be called from the vm + * Add a shrinker callback to be called from the vm. */ -void register_shrinker(struct shrinker *shrinker) +int register_shrinker(struct shrinker *shrinker) { - atomic_long_set(&shrinker->nr_in_batch, 0); + size_t size = sizeof(*shrinker->nr_deferred); + + /* + * If we only have one possible node in the system anyway, save + * ourselves the trouble and disable NUMA aware behavior. This way we + * will save memory and some small loop time later. + */ + if (nr_node_ids == 1) + shrinker->flags &= ~SHRINKER_NUMA_AWARE; + + if (shrinker->flags & SHRINKER_NUMA_AWARE) + size *= nr_node_ids; + + shrinker->nr_deferred = kzalloc(size, GFP_KERNEL); + if (!shrinker->nr_deferred) + return -ENOMEM; + down_write(&shrinker_rwsem); list_add_tail(&shrinker->list, &shrinker_list); up_write(&shrinker_rwsem); + return 0; } EXPORT_SYMBOL(register_shrinker); @@ -186,6 +203,118 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker, } #define SHRINK_BATCH 128 + +static unsigned long +shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, + unsigned long nr_pages_scanned, unsigned long lru_pages) +{ + unsigned long freed = 0; + unsigned long long delta; + long total_scan; + long max_pass; + long nr; + long new_nr; + int nid = shrinkctl->nid; + long batch_size = shrinker->batch ? shrinker->batch + : SHRINK_BATCH; + + if (shrinker->count_objects) + max_pass = shrinker->count_objects(shrinker, shrinkctl); + else + max_pass = do_shrinker_shrink(shrinker, shrinkctl, 0); + if (max_pass == 0) + return 0; + + /* + * copy the current shrinker scan count into a local variable + * and zero it so that other concurrent shrinker invocations + * don't also do this scanning work. + */ + nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); + + total_scan = nr; + delta = (4 * nr_pages_scanned) / shrinker->seeks; + delta *= max_pass; + do_div(delta, lru_pages + 1); + total_scan += delta; + if (total_scan < 0) { + printk(KERN_ERR + "shrink_slab: %pF negative objects to delete nr=%ld\n", + shrinker->shrink, total_scan); + total_scan = max_pass; + } + + /* + * We need to avoid excessive windup on filesystem shrinkers + * due to large numbers of GFP_NOFS allocations causing the + * shrinkers to return -1 all the time. This results in a large + * nr being built up so when a shrink that can do some work + * comes along it empties the entire cache due to nr >>> + * max_pass. This is bad for sustaining a working set in + * memory. + * + * Hence only allow the shrinker to scan the entire cache when + * a large delta change is calculated directly. + */ + if (delta < max_pass / 4) + total_scan = min(total_scan, max_pass / 2); + + /* + * Avoid risking looping forever due to too large nr value: + * never try to free more than twice the estimate number of + * freeable entries. + */ + if (total_scan > max_pass * 2) + total_scan = max_pass * 2; + + trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, + nr_pages_scanned, lru_pages, + max_pass, delta, total_scan); + + while (total_scan >= batch_size) { + + if (shrinker->scan_objects) { + unsigned long ret; + shrinkctl->nr_to_scan = batch_size; + ret = shrinker->scan_objects(shrinker, shrinkctl); + + if (ret == SHRINK_STOP) + break; + freed += ret; + } else { + int nr_before; + long ret; + + nr_before = do_shrinker_shrink(shrinker, shrinkctl, 0); + ret = do_shrinker_shrink(shrinker, shrinkctl, + batch_size); + if (ret == -1) + break; + if (ret < nr_before) + freed += nr_before - ret; + } + + count_vm_events(SLABS_SCANNED, batch_size); + total_scan -= batch_size; + + cond_resched(); + } + + /* + * move the unused scan count back into the shrinker in a + * manner that handles concurrent updates. If we exhausted the + * scan, there is no need to do an update. + */ + if (total_scan > 0) + new_nr = atomic_long_add_return(total_scan, + &shrinker->nr_deferred[nid]); + else + new_nr = atomic_long_read(&shrinker->nr_deferred[nid]); + + trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr); + return freed; +} + /* * Call the shrink functions to age shrinkable caches * @@ -227,108 +356,18 @@ unsigned long shrink_slab(struct shrink_control *shrinkctl, } list_for_each_entry(shrinker, &shrinker_list, list) { - unsigned long long delta; - long total_scan; - long max_pass; - long nr; - long new_nr; - long batch_size = shrinker->batch ? shrinker->batch - : SHRINK_BATCH; - - if (shrinker->count_objects) - max_pass = shrinker->count_objects(shrinker, shrinkctl); - else - max_pass = do_shrinker_shrink(shrinker, shrinkctl, 0); - if (max_pass == 0) - continue; - - /* - * copy the current shrinker scan count into a local variable - * and zero it so that other concurrent shrinker invocations - * don't also do this scanning work. - */ - nr = atomic_long_xchg(&shrinker->nr_in_batch, 0); - - total_scan = nr; - delta = (4 * nr_pages_scanned) / shrinker->seeks; - delta *= max_pass; - do_div(delta, lru_pages + 1); - total_scan += delta; - if (total_scan < 0) { - printk(KERN_ERR - "shrink_slab: %pF negative objects to delete nr=%ld\n", - shrinker->shrink, total_scan); - total_scan = max_pass; - } - - /* - * We need to avoid excessive windup on filesystem shrinkers - * due to large numbers of GFP_NOFS allocations causing the - * shrinkers to return -1 all the time. This results in a large - * nr being built up so when a shrink that can do some work - * comes along it empties the entire cache due to nr >>> - * max_pass. This is bad for sustaining a working set in - * memory. - * - * Hence only allow the shrinker to scan the entire cache when - * a large delta change is calculated directly. - */ - if (delta < max_pass / 4) - total_scan = min(total_scan, max_pass / 2); - - /* - * Avoid risking looping forever due to too large nr value: - * never try to free more than twice the estimate number of - * freeable entries. - */ - if (total_scan > max_pass * 2) - total_scan = max_pass * 2; - - trace_mm_shrink_slab_start(shrinker, shrinkctl, nr, - nr_pages_scanned, lru_pages, - max_pass, delta, total_scan); - - while (total_scan >= batch_size) { - - if (shrinker->scan_objects) { - unsigned long ret; - shrinkctl->nr_to_scan = batch_size; - ret = shrinker->scan_objects(shrinker, shrinkctl); + for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) { + if (!node_online(shrinkctl->nid)) + continue; - if (ret == SHRINK_STOP) - break; - freed += ret; - } else { - int nr_before; - long ret; - - nr_before = do_shrinker_shrink(shrinker, shrinkctl, 0); - ret = do_shrinker_shrink(shrinker, shrinkctl, - batch_size); - if (ret == -1) - break; - if (ret < nr_before) - freed += nr_before - ret; - } + if (!(shrinker->flags & SHRINKER_NUMA_AWARE) && + (shrinkctl->nid != 0)) + break; - count_vm_events(SLABS_SCANNED, batch_size); - total_scan -= batch_size; + freed += shrink_slab_node(shrinkctl, shrinker, + nr_pages_scanned, lru_pages); - cond_resched(); } - - /* - * move the unused scan count back into the shrinker in a - * manner that handles concurrent updates. If we exhausted the - * scan, there is no need to do an update. - */ - if (total_scan > 0) - new_nr = atomic_long_add_return(total_scan, - &shrinker->nr_in_batch); - else - new_nr = atomic_long_read(&shrinker->nr_in_batch); - - trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr); } up_read(&shrinker_rwsem); out: -- cgit v1.2.3 From a0b02131c5fcd8545b867db72224b3659e813f10 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Wed, 28 Aug 2013 10:18:16 +1000 Subject: shrinker: Kill old ->shrink API. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit There are no more users of this API, so kill it dead, dead, dead and quietly bury the corpse in a shallow, unmarked grave in a dark forest deep in the hills... [glommer@openvz.org: added flowers to the grave] Signed-off-by: Dave Chinner Signed-off-by: Glauber Costa Reviewed-by: Greg Thelen Acked-by: Mel Gorman Cc: "Theodore Ts'o" Cc: Adrian Hunter Cc: Al Viro Cc: Artem Bityutskiy Cc: Arve Hjønnevåg Cc: Carlos Maiolino Cc: Christoph Hellwig Cc: Chuck Lever Cc: Daniel Vetter Cc: David Rientjes Cc: Gleb Natapov Cc: Greg Thelen Cc: J. Bruce Fields Cc: Jan Kara Cc: Jerome Glisse Cc: John Stultz Cc: KAMEZAWA Hiroyuki Cc: Kent Overstreet Cc: Kirill A. Shutemov Cc: Marcelo Tosatti Cc: Mel Gorman Cc: Steven Whitehouse Cc: Thomas Hellstrom Cc: Trond Myklebust Signed-off-by: Andrew Morton Signed-off-by: Al Viro --- mm/vmscan.c | 41 ++++++++--------------------------------- 1 file changed, 8 insertions(+), 33 deletions(-) (limited to 'mm/vmscan.c') diff --git a/mm/vmscan.c b/mm/vmscan.c index 799ebceeb4f..e3645422061 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -194,14 +194,6 @@ void unregister_shrinker(struct shrinker *shrinker) } EXPORT_SYMBOL(unregister_shrinker); -static inline int do_shrinker_shrink(struct shrinker *shrinker, - struct shrink_control *sc, - unsigned long nr_to_scan) -{ - sc->nr_to_scan = nr_to_scan; - return (*shrinker->shrink)(shrinker, sc); -} - #define SHRINK_BATCH 128 static unsigned long @@ -218,10 +210,7 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, long batch_size = shrinker->batch ? shrinker->batch : SHRINK_BATCH; - if (shrinker->count_objects) - max_pass = shrinker->count_objects(shrinker, shrinkctl); - else - max_pass = do_shrinker_shrink(shrinker, shrinkctl, 0); + max_pass = shrinker->count_objects(shrinker, shrinkctl); if (max_pass == 0) return 0; @@ -240,7 +229,7 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, if (total_scan < 0) { printk(KERN_ERR "shrink_slab: %pF negative objects to delete nr=%ld\n", - shrinker->shrink, total_scan); + shrinker->scan_objects, total_scan); total_scan = max_pass; } @@ -272,27 +261,13 @@ shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker, max_pass, delta, total_scan); while (total_scan >= batch_size) { + unsigned long ret; - if (shrinker->scan_objects) { - unsigned long ret; - shrinkctl->nr_to_scan = batch_size; - ret = shrinker->scan_objects(shrinker, shrinkctl); - - if (ret == SHRINK_STOP) - break; - freed += ret; - } else { - int nr_before; - long ret; - - nr_before = do_shrinker_shrink(shrinker, shrinkctl, 0); - ret = do_shrinker_shrink(shrinker, shrinkctl, - batch_size); - if (ret == -1) - break; - if (ret < nr_before) - freed += nr_before - ret; - } + shrinkctl->nr_to_scan = batch_size; + ret = shrinker->scan_objects(shrinker, shrinkctl); + if (ret == SHRINK_STOP) + break; + freed += ret; count_vm_events(SLABS_SCANNED, batch_size); total_scan -= batch_size; -- cgit v1.2.3