From: Zhengjun Xing <zhengjun.xing@xxxxxxxxxxxxxxx>
In the system with very few file pages, it is easy to reproduce
"nr_isolated_file > nr_inactive_file", then too_many_isolated return true,
shrink_inactive_list enter "msleep(100)", the long latency will happen.
The test case to reproduce it is very simple, allocate a lot of huge pages
(near the DRAM size), then do free, repeat the same operation many times.
There is a 3/10 rate to reproduce the issue. In the test, sc-> gfp_mask
is 0x342cca ("_GFP_IO" and "__GFP_FS" is masked),it is more easy to enter
“inactive >>=3”, then “isolated > inactive” will easy to be true.
So I have a proposal to set a threshold number for the total file pages
to ignore the system with very few file pages, and then bypass the 100ms
sleep. It is hard to set a perfect number for the threshold, so I
just give an example of "256" for it, need more inputs for it.
Signed-off-by: Zhengjun Xing <zhengjun.xing@xxxxxxxxxxxxxxx>
---
mm/vmscan.c | 11 +++++++++--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 562e87cbd7a1..a1926463455c 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -168,6 +168,7 @@ struct scan_control {
* From 0 .. 200. Higher means more swappy.
*/
int vm_swappiness = 60;
+int lru_list_threshold = SWAP_CLUSTER_MAX << 3;
static void set_task_reclaim_state(struct task_struct *task,
struct reclaim_state *rs)
@@ -1785,7 +1786,7 @@ int isolate_lru_page(struct page *page)
static int too_many_isolated(struct pglist_data *pgdat, int file,
struct scan_control *sc)
{
- unsigned long inactive, isolated;
+ unsigned long inactive, isolated, active, nr_lru_pages;
if (current_is_kswapd())
return 0;
@@ -1796,11 +1797,13 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
if (file) {
inactive = node_page_state(pgdat, NR_INACTIVE_FILE);
isolated = node_page_state(pgdat, NR_ISOLATED_FILE);
+ active = node_page_state(pgdat, NR_ACTIVE_FILE);
} else {
inactive = node_page_state(pgdat, NR_INACTIVE_ANON);
isolated = node_page_state(pgdat, NR_ISOLATED_ANON);
+ active = node_page_state(pgdat, NR_ACTIVE_ANON);
}
-
+ nr_lru_pages = inactive + active;
/*
* GFP_NOIO/GFP_NOFS callers are allowed to isolate more pages, so they
* won't get blocked by normal direct-reclaimers, forming a circular
@@ -1809,6 +1812,10 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
if ((sc->gfp_mask & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS))
inactive >>= 3;
+ if (isolated > inactive)
+ if (nr_lru_pages < lru_list_threshold)
+ return 0;
+
return isolated > inactive;
}
--
2.17.1
