From 7cc88431e5aa457d16dc1db11e8955dc76c4332c Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 5 Dec 2018 11:13:33 +1100 Subject: [PATCH] mm, memory_hotplug: be more verbose for memory offline failures There is only very limited information printed when the memory offlining fails: [ 1984.506184] rac1 kernel: memory offlining [mem 0x82600000000-0x8267fffffff] failed due to signal backoff This tells us that the failure is triggered by the userspace intervention but it doesn't tell us much more about the underlying reason. It might be that the page migration failes repeatedly and the userspace timeout expires and send a signal or it might be some of the earlier steps (isolation, memory notifier) takes too long. If the migration failes then it would be really helpful to see which page that and its state. The same applies to the isolation phase. If we fail to isolate a page from the allocator then knowing the state of the page would be helpful as well. Dump the page state that fails to get isolated or migrated. This will tell us more about the failure and what to focus on during debugging. Link: http://lkml.kernel.org/r/20181107101830.17405-6-mhocko@kernel.org Signed-off-by: Michal Hocko Reviewed-by: Andrew Morton Reviewed-by: Oscar Salvador Reviewed-by: Anshuman Khandual Cc: Baoquan He Cc: Oscar Salvador Cc: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Stephen Rothwell --- mm/memory_hotplug.c | 12 ++++++++---- mm/page_alloc.c | 1 + 2 files changed, 9 insertions(+), 4 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 88d50e74e3fe..810b03071cfa 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1388,10 +1388,8 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) page_is_file_cache(page)); } else { -#ifdef CONFIG_DEBUG_VM - pr_alert("failed to isolate pfn %lx\n", pfn); + pr_warn("failed to isolate pfn %lx\n", pfn); dump_page(page, "isolation failed"); -#endif put_page(page); /* Because we don't have big zone->lock. we should check this again here. */ @@ -1411,8 +1409,14 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) /* Allocate a new page from the nearest neighbor node */ ret = migrate_pages(&source, new_node_page, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); - if (ret) + if (ret) { + list_for_each_entry(page, &source, lru) { + pr_warn("migrating pfn %lx failed ", + page_to_pfn(page), ret); + dump_page(page, NULL); + } putback_movable_pages(&source); + } } out: return ret; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 365dc0930f8c..33ef96e7a2d8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7854,6 +7854,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, return false; unmovable: WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE); + dump_page(pfn_to_page(pfn+iter), "has_unmovable_pages"); return true; } -- 2.50.1