The patch titled oom: suppress show_mem() for many nodes in irq context on page alloc failure has been removed from the -mm tree. Its filename was oom-suppress-show_mem-for-many-nodes-in-irq-context-on-page-alloc-failure.patch This patch was dropped because it was merged into mainline or a subsystem tree The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: oom: suppress show_mem() for many nodes in irq context on page alloc failure From: David Rientjes <rientjes@xxxxxxxxxx> When a page allocation failure occurs, show_mem() is called to dump the state of the VM so users may understand what happened to get into that condition. This output, however, can be extremely verbose. In irq context, it may result in significant delays that incur NMI watchdog timeouts when the machine is large (we use CONFIG_NODES_SHIFT > 8 here to define a "large" machine since the length of the show_mem() output is proportional to the number of possible nodes). This patch suppresses the show_mem() call in irq context when the kernel has CONFIG_NODES_SHIFT > 8. Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx> Cc: Mel Gorman <mel@xxxxxxxxx> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/page_alloc.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff -puN mm/page_alloc.c~oom-suppress-show_mem-for-many-nodes-in-irq-context-on-page-alloc-failure mm/page_alloc.c --- a/mm/page_alloc.c~oom-suppress-show_mem-for-many-nodes-in-irq-context-on-page-alloc-failure +++ a/mm/page_alloc.c @@ -1714,6 +1714,20 @@ try_next_zone: return page; } +/* + * Large machines with many possible nodes should not always dump per-node + * meminfo in irq context. + */ +static inline bool should_suppress_show_mem(void) +{ + bool ret = false; + +#if NODES_SHIFT > 8 + ret = in_interrupt(); +#endif + return ret; +} + static inline int should_alloc_retry(gfp_t gfp_mask, unsigned int order, unsigned long pages_reclaimed) @@ -2161,7 +2175,8 @@ nopage: " order:%d, mode:0x%x\n", current->comm, order, gfp_mask); dump_stack(); - show_mem(); + if (!should_suppress_show_mem()) + show_mem(); } return page; got_pg: _ Patches currently in -mm which might be from rientjes@xxxxxxxxxx are origin.patch jbd-remove-dependency-on-__gfp_nofail.patch memcg-res_counter_read_u64-fix-potential-races-on-32-bit-machines.patch memcg-give-current-access-to-memory-reserves-if-its-trying-to-die.patch memcg-document-cgroup-dirty-memory-interfaces.patch memcg-add-page_cgroup-flags-for-dirty-page-tracking.patch memcg-add-dirty-page-accounting-infrastructure.patch memcg-add-kernel-calls-for-memcg-dirty-page-stats.patch memcg-add-dirty-limits-to-mem_cgroup.patch memcg-add-cgroupfs-interface-to-memcg-dirty-limits.patch memcg-add-dirty-limiting-routines.patch memcg-check-memcg-dirty-limits-in-page-writeback.patch memcg-make-background-writeback-memcg-aware.patch cpuset-remove-unneeded-nodemask_alloc-in-cpuset_sprintf_memlist.patch cpuset-remove-unneeded-nodemask_alloc-in-cpuset_sprintf_memlist-v2.patch cpuset-remove-unneeded-nodemask_alloc-in-cpuset_attch.patch cpuset-fix-unchecked-calls-to-nodemask_alloc.patch cpuset-fix-unchecked-calls-to-nodemask_alloc-v2.patch cpuset-hold-callback_mutex-in-cpuset_clone.patch sysctl-add-some-missing-input-constraint-checks.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html