nfsd: filecache: introduce NFSD_FILE_RECENT

The filecache lru is walked in 2 circumstances for 2 different reasons.

1/ When called from the shrinker we want to discard the first few
   entries on the list, ignoring any with NFSD_FILE_REFERENCED set
   because they should really be at the end of the LRU as they have been
   referenced recently.  So those ones are ROTATED.

2/ When called from the nfsd_file_gc() timer function we want to discard
   anything that hasn't been used since before the previous call, and
   mark everything else as unused at this point in time.

Using the same flag for both of these can result in some unexpected
outcomes.  If the shrinker callback clears NFSD_FILE_REFERENCED then
nfsd_file_gc() will think the file hasn't been used in a while, while
really it has.

I think it is easier to reason about the behaviour if we instead have
two flags.

 NFSD_FILE_REFERENCED means "this should be at the end of the LRU, please
     put it there when convenient"
 NFSD_FILE_RECENT means "this has been used recently - since the last
     run of nfsd_file_gc()

When either caller finds an NFSD_FILE_REFERENCED entry, that entry
should be moved to the end of the LRU and the flag cleared.  This can
safely happen at any time.  The actual order on the lru might not be
strictly least-recently-used, but that is normal for linux lrus.

The shrinker callback can ignore the "recent" flag.  If it ends up
freeing something that is "recent" that simply means that memory
pressure is sufficient to limit the acceptable cache age to less than
the nfsd_file_gc frequency.

The gc callback should primarily focus on NFSD_FILE_RECENT.  It should
free everything that doesn't have this flag set, and should clear the
flag on everything else.  When it clears the flag it is convenient to
clear the "REFERENCED" flag and move to the end of the LRU too.

With this, calls from the shrinker do not prematurely age files.  It
will focus only on freeing those that are least recently used.

Signed-off-by: NeilBrown <neilb@suse.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 79de1638415fa72f9bf7ea1750b5aefc3ac8b12e..542721e3a8ac1446fb3e6ee9bf660edab15484af 100644 (file)
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -319,10 +319,10 @@ nfsd_file_check_writeback(struct nfsd_file *nf)
                mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK);
 }
 
-
 static bool nfsd_file_lru_add(struct nfsd_file *nf)
 {
        set_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
+       set_bit(NFSD_FILE_RECENT, &nf->nf_flags);
        if (list_lru_add_obj(&nfsd_file_lru, &nf->nf_lru)) {
                trace_nfsd_file_lru_add(nf);
                return true;
@@ -534,6 +534,24 @@ nfsd_file_lru_cb(struct list_head *item, struct list_lru_one *lru,
        return LRU_REMOVED;
 }
 
+static enum lru_status
+nfsd_file_gc_cb(struct list_head *item, struct list_lru_one *lru,
+                void *arg)
+{
+       struct nfsd_file *nf = list_entry(item, struct nfsd_file, nf_lru);
+
+       if (test_and_clear_bit(NFSD_FILE_RECENT, &nf->nf_flags)) {
+               /*
+                * "REFERENCED" really means "should be at the end of the
+                * LRU. As we are putting it there we can clear the flag.
+                */
+               clear_bit(NFSD_FILE_REFERENCED, &nf->nf_flags);
+               trace_nfsd_file_gc_aged(nf);
+               return LRU_ROTATE;
+       }
+       return nfsd_file_lru_cb(item, lru, arg);
+}
+
 static void
 nfsd_file_gc(void)
 {
@@ -544,7 +562,7 @@ nfsd_file_gc(void)
        for_each_node_state(nid, N_NORMAL_MEMORY) {
                unsigned long nr = list_lru_count_node(&nfsd_file_lru, nid);
 
-               ret += list_lru_walk_node(&nfsd_file_lru, nid, nfsd_file_lru_cb,
+               ret += list_lru_walk_node(&nfsd_file_lru, nid, nfsd_file_gc_cb,
                                          &dispose, &nr);
        }
        trace_nfsd_file_gc_removed(ret, list_lru_count(&nfsd_file_lru));

diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index d5db6b34ba302cc061a4b2eeed5e9a66d31d1db6..de5b8aa7fcb0fbd17b60804ea2dfa4cdfc83714a 100644 (file)
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -38,6 +38,7 @@ struct nfsd_file {
 #define NFSD_FILE_PENDING      (1)
 #define NFSD_FILE_REFERENCED   (2)
 #define NFSD_FILE_GC           (3)
+#define NFSD_FILE_RECENT       (4)
        unsigned long           nf_flags;
        refcount_t              nf_ref;
        unsigned char           nf_may;

diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 49bbd26ffcdb36173047569b8d4b41efdec4880b..d93573504fa4d3055a4bf483d8a0786e66eeac1f 100644 (file)
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1050,6 +1050,7 @@ DEFINE_CLID_EVENT(confirmed_r);
                { 1 << NFSD_FILE_HASHED,        "HASHED" },             \
                { 1 << NFSD_FILE_PENDING,       "PENDING" },            \
                { 1 << NFSD_FILE_REFERENCED,    "REFERENCED" },         \
+               { 1 << NFSD_FILE_RECENT,        "RECENT" },             \
                { 1 << NFSD_FILE_GC,            "GC" })
 
 DECLARE_EVENT_CLASS(nfsd_file_class,
@@ -1328,6 +1329,7 @@ DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_lru_del_disposed);
 DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_in_use);
 DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_writeback);
 DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_referenced);
+DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_aged);
 DEFINE_NFSD_FILE_GC_EVENT(nfsd_file_gc_disposed);
 
 DECLARE_EVENT_CLASS(nfsd_file_lruwalk_class,
@@ -1357,6 +1359,7 @@ DEFINE_EVENT(nfsd_file_lruwalk_class, name,                               \
        TP_ARGS(removed, remaining))
 
 DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_gc_removed);
+DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_gc_recent);
 DEFINE_NFSD_FILE_LRUWALK_EVENT(nfsd_file_shrinker_removed);
 
 TRACE_EVENT(nfsd_file_close,