Workqueue code has an assumption that the numa mapping is stable after system booted. It is incorrectly currently.
Yasuaki Ishimatsu hit a allocation failure bug when the numa mapping between CPU and node is changed. This was the last scene: SLUB: Unable to allocate memory on node 2 (gfp=0x80d0) cache: kmalloc-192, object size: 192, buffer size: 192, default order: 1, min order: 0 node 0: slabs: 6172, objs: 259224, free: 245741 node 1: slabs: 3261, objs: 136962, free: 127656 Yasuaki Ishimatsu investigated that it happened in the following situation: 1) System Node/CPU before offline/online: | CPU ------------------------ node 0 | 0-14, 60-74 node 1 | 15-29, 75-89 node 2 | 30-44, 90-104 node 3 | 45-59, 105-119 2) A system-board (contains node2 and node3) is offline: | CPU ------------------------ node 0 | 0-14, 60-74 node 1 | 15-29, 75-89 3) A new system-board is online, two new node IDs are allocated for the two node of the SB, but the old CPU IDs are allocated for the SB, here the NUMA mapping between node and CPU is changed. (the node of CPU#30 is changed from node#2 to node#4, for example) | CPU ------------------------ node 0 | 0-14, 60-74 node 1 | 15-29, 75-89 node 4 | 30-59 node 5 | 90-119 4) now, the NUMA mapping is changed, but wq_numa_possible_cpumask which is the convenient NUMA mapping cache in workqueue.c is still outdated. thus pool->node calculated by get_unbound_pool() is incorrect. 5) when the create_worker() is called with the incorrect offlined pool->node, it is failed and the pool can't make any progress. To fix this bug, we need to fixup the wq_numa_possible_cpumask and the pool->node, it is done in patch2 and patch3. patch1 fixes memory leak related wq_numa_possible_cpumask. patch4 kill another assumption about how the numa mapping changed. patch5 reduces the allocation fails when the node is offline or the node is lack of memory. The patchset is untested. It is sent for earlier review. Thanks, Lai. Reported-by: Yasuaki Ishimatsu <isimatu.yasu...@jp.fujitsu.com> Cc: Tejun Heo <t...@kernel.org> Cc: Yasuaki Ishimatsu <isimatu.yasu...@jp.fujitsu.com> Cc: "Gu, Zheng" <guz.f...@cn.fujitsu.com> Cc: tangchen <tangc...@cn.fujitsu.com> Cc: Hiroyuki KAMEZAWA <kamezawa.hir...@jp.fujitsu.com> Lai Jiangshan (5): workqueue: fix memory leak in wq_numa_init() workqueue: update wq_numa_possible_cpumask workqueue: fixup existing pool->node workqueue: update NUMA affinity for the node lost CPU workqueue: retry on NUMA_NO_NODE when create_worker() fails kernel/workqueue.c | 129 ++++++++++++++++++++++++++++++++++++++++++++-------- 1 files changed, 109 insertions(+), 20 deletions(-) -- 1.7.4.4 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/