From ecde0f3e7f9edf8629f56b2354385dc8d0a6a24d Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Wed, 15 Nov 2017 17:33:38 -0800 Subject: [PATCH] mm, memory_hotplug: remove timeout from __offline_memory We have a hardcoded 120s timeout after which the memory offline fails basically since the hot remove has been introduced. This is essentially a policy implemented in the kernel. Moreover there is no way to adjust the timeout and so we are sometimes facing memory offline failures if the system is under a heavy memory pressure or very intensive CPU workload on large machines. It is not very clear what purpose the timeout actually serves. The offline operation is interruptible by a signal so if userspace wants some timeout based termination this can be done trivially by sending a signal. If there is a strong usecase to do this from the kernel then we should do it properly and have a it tunable from the userspace with the timeout disabled by default along with the explanation who uses it and for what purporse. Link: http://lkml.kernel.org/r/20170918070834.13083-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: KAMEZAWA Hiroyuki Cc: Reza Arbab Cc: Yasuaki Ishimatsu Cc: Xishi Qiu Cc: Igor Mammedov Cc: Vitaly Kuznetsov Cc: Michael Ellerman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 014e9090cb77..fab51a6af962 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1590,9 +1590,9 @@ static void node_states_clear_node(int node, struct memory_notify *arg) } static int __ref __offline_pages(unsigned long start_pfn, - unsigned long end_pfn, unsigned long timeout) + unsigned long end_pfn) { - unsigned long pfn, nr_pages, expire; + unsigned long pfn, nr_pages; long offlined_pages; int ret, node; unsigned long flags; @@ -1630,12 +1630,8 @@ static int __ref __offline_pages(unsigned long start_pfn, goto failed_removal; pfn = start_pfn; - expire = jiffies + timeout; repeat: /* start memory hot removal */ - ret = -EBUSY; - if (time_after(jiffies, expire)) - goto failed_removal; ret = -EINTR; if (signal_pending(current)) goto failed_removal; @@ -1708,7 +1704,7 @@ failed_removal: /* Must be protected by mem_hotplug_begin() or a device_lock */ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { - return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ); + return __offline_pages(start_pfn, start_pfn + nr_pages); } #endif /* CONFIG_MEMORY_HOTREMOVE */