In vmpressure, the pressure level is calculated based on the ratio of how many pages were scanned vs. reclaimed in a given time window. However, there is a possibility that "scanned < reclaimed" for some reasons, e.g., when reclaiming ends by fatal signal in shrink_inactive_list or THP reclaiming, etc. When this happens, we cannot tell anything about the current pressure level. So, with this patch, we just return "low" level when "scanned < reclaimed" happens to inform that there is reclaiming activity. Userland can have a chance to free some memory. Signed-off-by: Hyunhee Kim <hyunhee.kim@xxxxxxxxxxx> Signed-off-by: Kyungmin Park <kyungmin.park@xxxxxxxxxxx> --- mm/vmpressure.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 736a601..915a608 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -119,6 +119,16 @@ static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, unsigned long pressure; /* + * This could happen for some reasons. e.g., reclaiming ends by fatal + * signal in shrink_inactive_list() or THP reclaiming, etc. In this case, + * we cannot tell anything about the pressure level. So, the best way to + * handle this is to notify LOW in order to inform that there is + * reclaiming activity. This gives a chance to userland to free memory. + */ + if (reclaimed > scanned) + return VMPRESSURE_LOW; + + /* * We calculate the ratio (in percents) of how many pages were * scanned vs. reclaimed in a given time frame (window). Note that * time is in VM reclaimer's "ticks", i.e. number of pages -- 1.7.9.5 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>