From f183324133ea535db4127f9fad3e19725ca88bf3 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 7 Apr 2021 20:57:36 -0700 Subject: percpu: implement partial chunk depopulation From Roman ("percpu: partial chunk depopulation"): In our [Facebook] production experience the percpu memory allocator is sometimes struggling with returning the memory to the system. A typical example is a creation of several thousands memory cgroups (each has several chunks of the percpu data used for vmstats, vmevents, ref counters etc). Deletion and complete releasing of these cgroups doesn't always lead to a shrinkage of the percpu memory, so that sometimes there are several GB's of memory wasted. The underlying problem is the fragmentation: to release an underlying chunk all percpu allocations should be released first. The percpu allocator tends to top up chunks to improve the utilization. It means new small-ish allocations (e.g. percpu ref counters) are placed onto almost filled old-ish chunks, effectively pinning them in memory. This patchset solves this problem by implementing a partial depopulation of percpu chunks: chunks with many empty pages are being asynchronously depopulated and the pages are returned to the system. To illustrate the problem the following script can be used: -- cd /sys/fs/cgroup mkdir percpu_test echo "+memory" > percpu_test/cgroup.subtree_control cat /proc/meminfo | grep Percpu for i in `seq 1 1000`; do mkdir percpu_test/cg_"${i}" for j in `seq 1 10`; do mkdir percpu_test/cg_"${i}"_"${j}" done done cat /proc/meminfo | grep Percpu for i in `seq 1 1000`; do for j in `seq 1 10`; do rmdir percpu_test/cg_"${i}"_"${j}" done done sleep 10 cat /proc/meminfo | grep Percpu for i in `seq 1 1000`; do rmdir percpu_test/cg_"${i}" done rmdir percpu_test -- It creates 11000 memory cgroups and removes every 10 out of 11. It prints the initial size of the percpu memory, the size after creating all cgroups and the size after deleting most of them. Results: vanilla: ./percpu_test.sh Percpu: 7488 kB Percpu: 481152 kB Percpu: 481152 kB with this patchset applied: ./percpu_test.sh Percpu: 7488 kB Percpu: 481408 kB Percpu: 135552 kB The total size of the percpu memory was reduced by more than 3.5 times. This patch: This patch implements partial depopulation of percpu chunks. As of now, a chunk can be depopulated only as a part of the final destruction, if there are no more outstanding allocations. However to minimize a memory waste it might be useful to depopulate a partially filed chunk, if a small number of outstanding allocations prevents the chunk from being fully reclaimed. This patch implements the following depopulation process: it scans over the chunk pages, looks for a range of empty and populated pages and performs the depopulation. To avoid races with new allocations, the chunk is previously isolated. After the depopulation the chunk is sidelined to a special list or freed. New allocations prefer using active chunks to sidelined chunks. If a sidelined chunk is used, it is reintegrated to the active lists. The depopulation is scheduled on the free path if the chunk is all of the following: 1) has more than 1/4 of total pages free and populated 2) the system has enough free percpu pages aside of this chunk 3) isn't the reserved chunk 4) isn't the first chunk If it's already depopulated but got free populated pages, it's a good target too. The chunk is moved to a special slot, pcpu_to_depopulate_slot, chunk->isolated is set, and the balance work item is scheduled. On isolation, these pages are removed from the pcpu_nr_empty_pop_pages. It is constantly replaced to the to_depopulate_slot when it meets these qualifications. pcpu_reclaim_populated() iterates over the to_depopulate_slot until it becomes empty. The depopulation is performed in the reverse direction to keep populated pages close to the beginning. Depopulated chunks are sidelined to preferentially avoid them for new allocations. When no active chunk can suffice a new allocation, sidelined chunks are first checked before creating a new chunk. Signed-off-by: Roman Gushchin Co-developed-by: Dennis Zhou Signed-off-by: Dennis Zhou Tested-by: Pratik Sampat Signed-off-by: Dennis Zhou --- mm/percpu.c | 180 +++++++++++++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 165 insertions(+), 15 deletions(-) (limited to 'mm/percpu.c') diff --git a/mm/percpu.c b/mm/percpu.c index d462222f4adc..79eebc80860d 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -136,6 +136,8 @@ static int pcpu_nr_units __ro_after_init; static int pcpu_atom_size __ro_after_init; int pcpu_nr_slots __ro_after_init; int pcpu_free_slot __ro_after_init; +int pcpu_sidelined_slot __ro_after_init; +int pcpu_to_depopulate_slot __ro_after_init; static size_t pcpu_chunk_struct_size __ro_after_init; /* cpus with the lowest and highest unit addresses */ @@ -562,10 +564,41 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) { int nslot = pcpu_chunk_slot(chunk); + /* leave isolated chunks in-place */ + if (chunk->isolated) + return; + if (oslot != nslot) __pcpu_chunk_move(chunk, nslot, oslot < nslot); } +static void pcpu_isolate_chunk(struct pcpu_chunk *chunk) +{ + enum pcpu_chunk_type type = pcpu_chunk_type(chunk); + struct list_head *pcpu_slot = pcpu_chunk_list(type); + + lockdep_assert_held(&pcpu_lock); + + if (!chunk->isolated) { + chunk->isolated = true; + pcpu_nr_empty_pop_pages[type] -= chunk->nr_empty_pop_pages; + } + list_move(&chunk->list, &pcpu_slot[pcpu_to_depopulate_slot]); +} + +static void pcpu_reintegrate_chunk(struct pcpu_chunk *chunk) +{ + enum pcpu_chunk_type type = pcpu_chunk_type(chunk); + + lockdep_assert_held(&pcpu_lock); + + if (chunk->isolated) { + chunk->isolated = false; + pcpu_nr_empty_pop_pages[type] += chunk->nr_empty_pop_pages; + pcpu_chunk_relocate(chunk, -1); + } +} + /* * pcpu_update_empty_pages - update empty page counters * @chunk: chunk of interest @@ -578,7 +611,7 @@ static void pcpu_chunk_relocate(struct pcpu_chunk *chunk, int oslot) static inline void pcpu_update_empty_pages(struct pcpu_chunk *chunk, int nr) { chunk->nr_empty_pop_pages += nr; - if (chunk != pcpu_reserved_chunk) + if (chunk != pcpu_reserved_chunk && !chunk->isolated) pcpu_nr_empty_pop_pages[pcpu_chunk_type(chunk)] += nr; } @@ -1778,7 +1811,7 @@ static void __percpu *pcpu_alloc(size_t size, size_t align, bool reserved, restart: /* search through normal chunks */ - for (slot = pcpu_size_to_slot(size); slot < pcpu_nr_slots; slot++) { + for (slot = pcpu_size_to_slot(size); slot <= pcpu_free_slot; slot++) { list_for_each_entry_safe(chunk, next, &pcpu_slot[slot], list) { off = pcpu_find_block_fit(chunk, bits, bit_align, is_atomic); @@ -1789,9 +1822,10 @@ restart: } off = pcpu_alloc_area(chunk, bits, bit_align, off); - if (off >= 0) + if (off >= 0) { + pcpu_reintegrate_chunk(chunk); goto area_found; - + } } } @@ -1952,10 +1986,13 @@ void __percpu *__alloc_reserved_percpu(size_t size, size_t align) /** * pcpu_balance_free - manage the amount of free chunks * @type: chunk type + * @empty_only: free chunks only if there are no populated pages * - * Reclaim all fully free chunks except for the first one. + * If empty_only is %false, reclaim all fully free chunks regardless of the + * number of populated pages. Otherwise, only reclaim chunks that have no + * populated pages. */ -static void pcpu_balance_free(enum pcpu_chunk_type type) +static void pcpu_balance_free(enum pcpu_chunk_type type, bool empty_only) { LIST_HEAD(to_free); struct list_head *pcpu_slot = pcpu_chunk_list(type); @@ -1975,7 +2012,8 @@ static void pcpu_balance_free(enum pcpu_chunk_type type) if (chunk == list_first_entry(free_head, struct pcpu_chunk, list)) continue; - list_move(&chunk->list, &to_free); + if (!empty_only || chunk->nr_empty_pop_pages == 0) + list_move(&chunk->list, &to_free); } spin_unlock_irq(&pcpu_lock); @@ -2083,20 +2121,121 @@ retry_pop: } } +/** + * pcpu_reclaim_populated - scan over to_depopulate chunks and free empty pages + * @type: chunk type + * + * Scan over chunks in the depopulate list and try to release unused populated + * pages back to the system. Depopulated chunks are sidelined to prevent + * repopulating these pages unless required. Fully free chunks are reintegrated + * and freed accordingly (1 is kept around). If we drop below the empty + * populated pages threshold, reintegrate the chunk if it has empty free pages. + * Each chunk is scanned in the reverse order to keep populated pages close to + * the beginning of the chunk. + */ +static void pcpu_reclaim_populated(enum pcpu_chunk_type type) +{ + struct list_head *pcpu_slot = pcpu_chunk_list(type); + struct pcpu_chunk *chunk; + struct pcpu_block_md *block; + int i, end; + + spin_lock_irq(&pcpu_lock); + +restart: + /* + * Once a chunk is isolated to the to_depopulate list, the chunk is no + * longer discoverable to allocations whom may populate pages. The only + * other accessor is the free path which only returns area back to the + * allocator not touching the populated bitmap. + */ + while (!list_empty(&pcpu_slot[pcpu_to_depopulate_slot])) { + chunk = list_first_entry(&pcpu_slot[pcpu_to_depopulate_slot], + struct pcpu_chunk, list); + WARN_ON(chunk->immutable); + + /* + * Scan chunk's pages in the reverse order to keep populated + * pages close to the beginning of the chunk. + */ + for (i = chunk->nr_pages - 1, end = -1; i >= 0; i--) { + /* no more work to do */ + if (chunk->nr_empty_pop_pages == 0) + break; + + /* reintegrate chunk to prevent atomic alloc failures */ + if (pcpu_nr_empty_pop_pages[type] < + PCPU_EMPTY_POP_PAGES_HIGH) { + pcpu_reintegrate_chunk(chunk); + goto restart; + } + + /* + * If the page is empty and populated, start or + * extend the (i, end) range. If i == 0, decrease + * i and perform the depopulation to cover the last + * (first) page in the chunk. + */ + block = chunk->md_blocks + i; + if (block->contig_hint == PCPU_BITMAP_BLOCK_BITS && + test_bit(i, chunk->populated)) { + if (end == -1) + end = i; + if (i > 0) + continue; + i--; + } + + /* depopulate if there is an active range */ + if (end == -1) + continue; + + spin_unlock_irq(&pcpu_lock); + pcpu_depopulate_chunk(chunk, i + 1, end + 1); + cond_resched(); + spin_lock_irq(&pcpu_lock); + + pcpu_chunk_depopulated(chunk, i + 1, end + 1); + + /* reset the range and continue */ + end = -1; + } + + if (chunk->free_bytes == pcpu_unit_size) + pcpu_reintegrate_chunk(chunk); + else + list_move(&chunk->list, + &pcpu_slot[pcpu_sidelined_slot]); + } + + spin_unlock_irq(&pcpu_lock); +} + /** * pcpu_balance_workfn - manage the amount of free chunks and populated pages * @work: unused * - * Call pcpu_balance_free() and pcpu_balance_populated() for each chunk type. + * For each chunk type, manage the number of fully free chunks and the number of + * populated pages. An important thing to consider is when pages are freed and + * how they contribute to the global counts. */ static void pcpu_balance_workfn(struct work_struct *work) { enum pcpu_chunk_type type; + /* + * pcpu_balance_free() is called twice because the first time we may + * trim pages in the active pcpu_nr_empty_pop_pages which may cause us + * to grow other chunks. This then gives pcpu_reclaim_populated() time + * to move fully free chunks to the active list to be freed if + * appropriate. + */ for (type = 0; type < PCPU_NR_CHUNK_TYPES; type++) { mutex_lock(&pcpu_alloc_mutex); - pcpu_balance_free(type); + pcpu_balance_free(type, false); + pcpu_reclaim_populated(type); pcpu_balance_populated(type); + pcpu_balance_free(type, true); mutex_unlock(&pcpu_alloc_mutex); } } @@ -2137,8 +2276,12 @@ void free_percpu(void __percpu *ptr) pcpu_memcg_free_hook(chunk, off, size); - /* if there are more than one fully free chunks, wake up grim reaper */ - if (chunk->free_bytes == pcpu_unit_size) { + /* + * If there are more than one fully free chunks, wake up grim reaper. + * If the chunk is isolated, it may be in the process of being + * reclaimed. Let reclaim manage cleaning up of that chunk. + */ + if (!chunk->isolated && chunk->free_bytes == pcpu_unit_size) { struct pcpu_chunk *pos; list_for_each_entry(pos, &pcpu_slot[pcpu_free_slot], list) @@ -2146,6 +2289,9 @@ void free_percpu(void __percpu *ptr) need_balance = true; break; } + } else if (pcpu_should_reclaim_chunk(chunk)) { + pcpu_isolate_chunk(chunk); + need_balance = true; } trace_percpu_free_percpu(chunk->base_addr, off, ptr); @@ -2560,11 +2706,15 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, pcpu_stats_save_ai(ai); /* - * Allocate chunk slots. The additional last slot is for - * empty chunks. + * Allocate chunk slots. The slots after the active slots are: + * sidelined_slot - isolated, depopulated chunks + * free_slot - fully free chunks + * to_depopulate_slot - isolated, chunks to depopulate */ - pcpu_free_slot = __pcpu_size_to_slot(pcpu_unit_size) + 1; - pcpu_nr_slots = pcpu_free_slot + 1; + pcpu_sidelined_slot = __pcpu_size_to_slot(pcpu_unit_size) + 1; + pcpu_free_slot = pcpu_sidelined_slot + 1; + pcpu_to_depopulate_slot = pcpu_free_slot + 1; + pcpu_nr_slots = pcpu_to_depopulate_slot + 1; pcpu_chunk_lists = memblock_alloc(pcpu_nr_slots * sizeof(pcpu_chunk_lists[0]) * PCPU_NR_CHUNK_TYPES, -- cgit v1.2.3