nfsd: add shrinker to reduce number of slots allocated per session

Add a shrinker which frees unused slots and may ask the clients to use
fewer slots on each session.

We keep a global count of the number of freeable slots, which is the sum
of one less than the current "target" slots in all sessions in all
clients in all net-namespaces. This number is reported by the shrinker.

When the shrinker is asked to free some, we call xxx on each session in
a round-robin asking each to reduce the slot count by 1.  This will
reduce the "target" so the number reported by the shrinker will reduce
immediately.  The memory will only be freed later when the client
confirmed that it is no longer needed.

We use a global list of sessions and move the "head" to after the last
session that we asked to reduce, so the next callback from the shrinker
will move on to the next session.  This pressure should be applied
"evenly" across all sessions over time.

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

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index d29737018f042486ae0ce2363f709b48ccea7ff5..b38b3a1c0307eeb5055823904b0776bb1593f542 100644 (file)
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1909,6 +1909,16 @@ gen_sessionid(struct nfsd4_session *ses)
  */
 #define NFSD_MIN_HDR_SEQ_SZ  (24 + 12 + 44)
 
+static struct shrinker *nfsd_slot_shrinker;
+static DEFINE_SPINLOCK(nfsd_session_list_lock);
+static LIST_HEAD(nfsd_session_list);
+/* The sum of "target_slots-1" on every session.  The shrinker can push this
+ * down, though it can take a little while for the memory to actually
+ * be freed.  The "-1" is because we can never free slot 0 while the
+ * session is active.
+ */
+static atomic_t nfsd_total_target_slots = ATOMIC_INIT(0);
+
 static void
 free_session_slots(struct nfsd4_session *ses, int from)
 {
@@ -1930,8 +1940,11 @@ free_session_slots(struct nfsd4_session *ses, int from)
                kfree(slot);
        }
        ses->se_fchannel.maxreqs = from;
-       if (ses->se_target_maxslots > from)
-               ses->se_target_maxslots = from;
+       if (ses->se_target_maxslots > from) {
+               int new_target = from ?: 1;
+               atomic_sub(ses->se_target_maxslots - new_target, &nfsd_total_target_slots);
+               ses->se_target_maxslots = new_target;
+       }
 }
 
 /**
@@ -1949,7 +1962,7 @@ free_session_slots(struct nfsd4_session *ses, int from)
  * Return value:
  *   The number of slots that the target was reduced by.
  */
-static int __maybe_unused
+static int
 reduce_session_slots(struct nfsd4_session *ses, int dec)
 {
        struct nfsd_net *nn = net_generic(ses->se_client->net,
@@ -1962,6 +1975,7 @@ reduce_session_slots(struct nfsd4_session *ses, int dec)
                return ret;
        ret = min(dec, ses->se_target_maxslots-1);
        ses->se_target_maxslots -= ret;
+       atomic_sub(ret, &nfsd_total_target_slots);
        ses->se_slot_gen += 1;
        if (ses->se_slot_gen == 0) {
                int i;
@@ -2021,6 +2035,7 @@ static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs,
        fattrs->maxreqs = i;
        memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs));
        new->se_target_maxslots = i;
+       atomic_add(i - 1, &nfsd_total_target_slots);
        new->se_cb_slot_avail = ~0U;
        new->se_cb_highest_slot = min(battrs->maxreqs - 1,
                                      NFSD_BC_SLOT_TABLE_SIZE - 1);
@@ -2145,6 +2160,36 @@ static void free_session(struct nfsd4_session *ses)
        __free_session(ses);
 }
 
+static unsigned long
+nfsd_slot_count(struct shrinker *s, struct shrink_control *sc)
+{
+       unsigned long cnt = atomic_read(&nfsd_total_target_slots);
+
+       return cnt ? cnt : SHRINK_EMPTY;
+}
+
+static unsigned long
+nfsd_slot_scan(struct shrinker *s, struct shrink_control *sc)
+{
+       struct nfsd4_session *ses;
+       unsigned long scanned = 0;
+       unsigned long freed = 0;
+
+       spin_lock(&nfsd_session_list_lock);
+       list_for_each_entry(ses, &nfsd_session_list, se_all_sessions) {
+               freed += reduce_session_slots(ses, 1);
+               scanned += 1;
+               if (scanned >= sc->nr_to_scan) {
+                       /* Move starting point for next scan */
+                       list_move(&nfsd_session_list, &ses->se_all_sessions);
+                       break;
+               }
+       }
+       spin_unlock(&nfsd_session_list_lock);
+       sc->nr_scanned = scanned;
+       return freed;
+}
+
 static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses)
 {
        int idx;
@@ -2169,6 +2214,10 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru
        list_add(&new->se_perclnt, &clp->cl_sessions);
        spin_unlock(&clp->cl_lock);
 
+       spin_lock(&nfsd_session_list_lock);
+       list_add_tail(&new->se_all_sessions, &nfsd_session_list);
+       spin_unlock(&nfsd_session_list_lock);
+
        {
                struct sockaddr *sa = svc_addr(rqstp);
                /*
@@ -2238,6 +2287,9 @@ unhash_session(struct nfsd4_session *ses)
        spin_lock(&ses->se_client->cl_lock);
        list_del(&ses->se_perclnt);
        spin_unlock(&ses->se_client->cl_lock);
+       spin_lock(&nfsd_session_list_lock);
+       list_del(&ses->se_all_sessions);
+       spin_unlock(&nfsd_session_list_lock);
 }
 
 /* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */
@@ -2373,8 +2425,12 @@ unhash_client_locked(struct nfs4_client *clp)
        }
        list_del_init(&clp->cl_lru);
        spin_lock(&clp->cl_lock);
-       list_for_each_entry(ses, &clp->cl_sessions, se_perclnt)
+       spin_lock(&nfsd_session_list_lock);
+       list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) {
                list_del_init(&ses->se_hash);
+               list_del_init(&ses->se_all_sessions);
+       }
+       spin_unlock(&nfsd_session_list_lock);
        spin_unlock(&clp->cl_lock);
 }
 
@@ -4380,6 +4436,8 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
                                                GFP_NOWAIT))) {
                                s += 1;
                                session->se_fchannel.maxreqs = s;
+                               atomic_add(s - session->se_target_maxslots,
+                                          &nfsd_total_target_slots);
                                session->se_target_maxslots = s;
                        } else {
                                kfree(slot);
@@ -8770,7 +8828,6 @@ skip_grace:
 }
 
 /* initialization to perform when the nfsd service is started: */
-
 int
 nfs4_state_start(void)
 {
@@ -8780,6 +8837,15 @@ nfs4_state_start(void)
        if (ret)
                return ret;
 
+       nfsd_slot_shrinker = shrinker_alloc(0, "nfsd-DRC-slot");
+       if (!nfsd_slot_shrinker) {
+               rhltable_destroy(&nfs4_file_rhltable);
+               return -ENOMEM;
+       }
+       nfsd_slot_shrinker->count_objects = nfsd_slot_count;
+       nfsd_slot_shrinker->scan_objects = nfsd_slot_scan;
+       shrinker_register(nfsd_slot_shrinker);
+
        set_max_delegations();
        return 0;
 }
@@ -8821,6 +8887,7 @@ void
 nfs4_state_shutdown(void)
 {
        rhltable_destroy(&nfs4_file_rhltable);
+       shrinker_free(nfsd_slot_shrinker);
 }
 
 static void

diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 2b0e6148a87a7a9f1f7d039d9555ae0db9cea8c4..b31a8523c8e50d291b1276c37219b272062c83a6 100644 (file)
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -325,6 +325,7 @@ struct nfsd4_session {
        u32                     se_cb_prog;
        struct list_head        se_hash;        /* hash by sessionid */
        struct list_head        se_perclnt;
+       struct list_head        se_all_sessions;/* global list of sessions */
        struct nfs4_client      *se_client;
        struct nfs4_sessionid   se_sessionid;
        struct nfsd4_channel_attrs se_fchannel;