diff options
| -rw-r--r-- | Documentation/admin-guide/sysctl/vm.rst | 9 | ||||
| -rw-r--r-- | mm/page_alloc.c | 27 |
2 files changed, 34 insertions, 2 deletions
diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index f48eaa98d22d..8290177b4f75 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -28,6 +28,7 @@ Currently, these files are in /proc/sys/vm: - compact_memory - compaction_proactiveness - compact_unevictable_allowed +- defrag_mode - dirty_background_bytes - dirty_background_ratio - dirty_bytes @@ -145,6 +146,14 @@ On CONFIG_PREEMPT_RT the default value is 0 in order to avoid a page fault, due to compaction, which would block the task from becoming active until the fault is resolved. +defrag_mode +=========== + +When set to 1, the page allocator tries harder to avoid fragmentation +and maintain the ability to produce huge pages / higher-order pages. + +It is recommended to enable this right after boot, as fragmentation, +once it occurred, can be long-lasting or even permanent. dirty_background_bytes ====================== diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5b92b1acda0e..f849eb7146b9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -273,6 +273,7 @@ int min_free_kbytes = 1024; int user_min_free_kbytes = -1; static int watermark_boost_factor __read_mostly = 15000; static int watermark_scale_factor = 10; +static int defrag_mode; /* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */ int movable_zone; @@ -3389,6 +3390,11 @@ alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask) */ alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM); + if (defrag_mode) { + alloc_flags |= ALLOC_NOFRAGMENT; + return alloc_flags; + } + #ifdef CONFIG_ZONE_DMA32 if (!zone) return alloc_flags; @@ -3480,7 +3486,7 @@ retry: continue; } - if (no_fallback && nr_online_nodes > 1 && + if (no_fallback && !defrag_mode && nr_online_nodes > 1 && zone != zonelist_zone(ac->preferred_zoneref)) { int local_nid; @@ -3591,7 +3597,7 @@ try_this_zone: * It's possible on a UMA machine to get through all zones that are * fragmented. If avoiding fragmentation, reset and try again. */ - if (no_fallback) { + if (no_fallback && !defrag_mode) { alloc_flags &= ~ALLOC_NOFRAGMENT; goto retry; } @@ -4128,6 +4134,9 @@ gfp_to_alloc_flags(gfp_t gfp_mask, unsigned int order) alloc_flags = gfp_to_alloc_flags_cma(gfp_mask, alloc_flags); + if (defrag_mode) + alloc_flags |= ALLOC_NOFRAGMENT; + return alloc_flags; } @@ -4510,6 +4519,11 @@ retry: &compaction_retries)) goto retry; + /* Reclaim/compaction failed to prevent the fallback */ + if (defrag_mode) { + alloc_flags &= ALLOC_NOFRAGMENT; + goto retry; + } /* * Deal with possible cpuset update races or zonelist updates to avoid @@ -6287,6 +6301,15 @@ static const struct ctl_table page_alloc_sysctl_table[] = { .extra2 = SYSCTL_THREE_THOUSAND, }, { + .procname = "defrag_mode", + .data = &defrag_mode, + .maxlen = sizeof(defrag_mode), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { .procname = "percpu_pagelist_high_fraction", .data = &percpu_pagelist_high_fraction, .maxlen = sizeof(percpu_pagelist_high_fraction), |