@@ -1343,6 +1343,8 @@ The following nested keys are defined.
same semantics as vm.swappiness applied to memcg reclaim with
all the existing limitations and potential future extensions.
+ Setting swappiness=max exclusively reclaims anonymous memory.
+
memory.peak
A read-write single value file which exists on non-root cgroups.
@@ -419,6 +419,10 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
#define MEMCG_RECLAIM_PROACTIVE (1 << 2)
#define MIN_SWAPPINESS 0
#define MAX_SWAPPINESS 200
+
+/* Just recliam from anon folios in proactive memory reclaim */
+#define SWAPPINESS_ANON_ONLY (MAX_SWAPPINESS + 1)
+
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
unsigned long nr_pages,
gfp_t gfp_mask,
@@ -4291,11 +4291,13 @@ static ssize_t memory_oom_group_write(struct kernfs_open_file *of,
enum {
MEMORY_RECLAIM_SWAPPINESS = 0,
+ MEMORY_RECLAIM_SWAPPINESS_MAX,
MEMORY_RECLAIM_NULL,
};
static const match_table_t tokens = {
{ MEMORY_RECLAIM_SWAPPINESS, "swappiness=%d"},
+ { MEMORY_RECLAIM_SWAPPINESS_MAX, "swappiness=max"},
{ MEMORY_RECLAIM_NULL, NULL },
};
@@ -4329,6 +4331,9 @@ static ssize_t memory_reclaim(struct kernfs_open_file *of, char *buf,
if (swappiness < MIN_SWAPPINESS || swappiness > MAX_SWAPPINESS)
return -EINVAL;
break;
+ case MEMORY_RECLAIM_SWAPPINESS_MAX:
+ swappiness = SWAPPINESS_ANON_ONLY;
+ break;
default:
return -EINVAL;
}
@@ -2438,6 +2438,13 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
goto out;
}
+ /* Proactive reclaim initiated by userspace for anonymous memory only */
+ if (swappiness == SWAPPINESS_ANON_ONLY) {
+ WARN_ON_ONCE(!sc->proactive);
+ scan_balance = SCAN_ANON;
+ goto out;
+ }
+
/*
* Do not apply any pressure balancing cleverness when the
* system is close to OOM, scan both anon and file equally
With this patch 'commit <68cd9050d871> ("mm: add swappiness= arg to memory.reclaim")', we can submit an additional swappiness=<val> argument to memory.reclaim. It is very useful because we can dynamically adjust the reclamation ratio based on the anonymous folios and file folios of each cgroup. For example,when swappiness is set to 0, we only reclaim from file folios. However,we have also encountered a new issue: when swappiness is set to the MAX_SWAPPINESS, it may still only reclaim file folios. So, we hope to add a new arg 'swappiness=max' in memory.reclaim where proactive memory reclaim only reclaims from anonymous folios when swappiness is set to max. The swappiness semantics from a user perspective remain unchanged. For example, something like this: echo "2M swappiness=max" > /sys/fs/cgroup/memory.reclaim will perform reclaim on the rootcg with a swappiness setting of 'max' (a new mode) regardless of the file folios. Users have a more comprehensive view of the application's memory distribution because there are many metrics available. For example, if we find that a certain cgroup has a large number of inactive anon folios, we can reclaim only those and skip file folios, because with the zram/zswap, the IO tradeoff that cache_trim_mode or other file first logic is making doesn't hold - file refaults will cause IO, whereas anon decompression will not. With this patch, the swappiness argument of memory.reclaim has a new mode 'max', means reclaiming just from anonymous folios both in traditional LRU and MGLRU. Here is the previous discussion: https://lore.kernel.org/all/20250314033350.1156370-1-hezhongkun.hzk@bytedance.com/ https://lore.kernel.org/all/20250312094337.2296278-1-hezhongkun.hzk@bytedance.com/ Suggested-by: Yosry Ahmed <yosry.ahmed@linux.dev> Signed-off-by: Zhongkun He <hezhongkun.hzk@bytedance.com> --- V2: Make the code clearer. -- from yosry's suggestions Documentation/admin-guide/cgroup-v2.rst | 2 ++ include/linux/swap.h | 4 ++++ mm/memcontrol.c | 5 +++++ mm/vmscan.c | 7 +++++++ 4 files changed, 18 insertions(+)