http://bugzilla.suse.com/show_bug.cgi?id=1013629 Bug ID: 1013629 Summary: 100% CPU usage on kswapd0 only on EC2 HVM Classification: openSUSE Product: openSUSE Distribution Version: Leap 42.2 Hardware: Other OS: Other Status: NEW Severity: Normal Priority: P5 - None Component: Kernel Assignee: kernel-maintainers@forge.provo.novell.com Reporter: hguo@suse.com QA Contact: qa-bugs@suse.de Found By: --- Blocker: --- The server is a HVM micro instance running 42.2 on Amazon EC2. The server has 485MB of system memory, it runs several small daemon programs that together cause memory usage to raise to 260MB as indicated by "free". There is a 1GB swap file in / which is on ext4. The load indicator almost always stays below 0.1 and memory usage almost always stays at ~260MB, except when doing zypper update that causes memory usage to climb over 300MB and swap usage climbs to ~10MB. The server has been running smoothly ever since 42.2 release, but beginning from yesterday, even tiny bit of memory pressure such as zypper update will trigger kswap0 to use 100% cpu. Temporary remedy "echo 1 > /proc/sys/vm/drop_caches" helps for a while, until the memory usage gets pressured once again via zypper update. The issue however does not occur, under these circumstances: - An identical server setup on GCE that has 587MB rather than 487MB of memory. - Swap file is turned off. sysctl VM parameters are the following: vm.admin_reserve_kbytes = 8192 vm.block_dump = 0 vm.compact_unevictable_allowed = 1 vm.dirty_background_bytes = 0 vm.dirty_background_ratio = 10 vm.dirty_bytes = 0 vm.dirty_expire_centisecs = 3000 vm.dirty_ratio = 40 vm.dirty_writeback_centisecs = 500 vm.dirtytime_expire_seconds = 43200 vm.drop_caches = 1 vm.extfrag_threshold = 500 vm.hugepages_treat_as_movable = 0 vm.hugetlb_shm_group = 0 vm.laptop_mode = 0 vm.legacy_va_layout = 0 vm.lowmem_reserve_ratio = 256 256 32 1 vm.max_map_count = 65530 vm.memory_failure_early_kill = 0 vm.memory_failure_recovery = 1 vm.min_free_kbytes = 65536 vm.min_slab_ratio = 5 vm.min_unmapped_ratio = 1 vm.mmap_min_addr = 65536 vm.nr_hugepages = 0 vm.nr_hugepages_mempolicy = 0 vm.nr_overcommit_hugepages = 0 vm.nr_pdflush_threads = 0 vm.numa_zonelist_order = default vm.oom_dump_tasks = 1 vm.oom_kill_allocating_task = 0 vm.overcommit_kbytes = 0 vm.overcommit_memory = 0 vm.overcommit_ratio = 50 vm.page-cluster = 3 vm.pagecache_limit_ignore_dirty = 1 vm.pagecache_limit_mb = 0 vm.panic_on_oom = 0 vm.percpu_pagelist_fraction = 0 vm.stat_interval = 1 vm.swappiness = 10 vm.user_reserve_kbytes = 8650 vm.vfs_cache_pressure = 100 vm.watermark_scale_factor = 10 vm.zone_reclaim_mode = 1 -- You are receiving this mail because: You are on the CC list for the bug.