From 630295dfc6cc7209f30f882003a8365738a25881 Mon Sep 17 00:00:00 2001 From: Benjamin Coddington Date: Tue, 15 Sep 2026 08:22:24 -0400 Subject: [PATCH] NFSv4/pnfs: Re-home the data-server cache onto hash buckets The per-net data-server cache is a single list, and every GETDEVICEINFO decode walks all of it looking for a match, so filling the cache costs O(n^2) in the number of data servers -- which a striping mount does in one burst, at the same scale the deviceid cache was just sized for. Key it by the DS address set instead. This patch is the mechanical half: nfs4_pnfs_ds.ds_node becomes an hlist_node, netns init and teardown cover every bucket, and removal uses hlist_del_init (which needs no bucket reference). Insertion still targets bucket 0 and lookup still scans every entry, so behavior is unchanged; the key comes next. Splitting it this way keeps a bisect able to tell a list-conversion bug from a hash-key bug. The buckets live in struct nfs_net, so this costs 2KB per network namespace on 64-bit, paid once nfs.ko is loaded whether or not that namespace ever mounts NFS. Assisted-by: Claude:claude-fable-5 Signed-off-by: Benjamin Coddington Signed-off-by: Anna Schumaker --- fs/nfs/client.c | 6 ++++-- fs/nfs/netns.h | 5 ++++- fs/nfs/pnfs.h | 2 +- fs/nfs/pnfs_nfs.c | 19 +++++++++++-------- 4 files changed, 20 insertions(+), 12 deletions(-) diff --git a/fs/nfs/client.c b/fs/nfs/client.c index 60386330aeec..dbb5131375f8 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -1295,7 +1295,8 @@ void nfs_clients_init(struct net *net) INIT_LIST_HEAD(&nn->nfs_volume_list); #if IS_ENABLED(CONFIG_NFS_V4) idr_init(&nn->cb_ident_idr); - INIT_LIST_HEAD(&nn->nfs4_data_server_cache); + for (int i = 0; i < NFS4_DS_CACHE_HASH_SIZE; i++) + INIT_HLIST_HEAD(&nn->nfs4_data_server_cache[i]); spin_lock_init(&nn->nfs4_data_server_lock); #endif /* CONFIG_NFS_V4 */ spin_lock_init(&nn->nfs_client_lock); @@ -1315,7 +1316,8 @@ void nfs_clients_exit(struct net *net) WARN_ON_ONCE(!list_empty(&nn->nfs_client_list)); WARN_ON_ONCE(!list_empty(&nn->nfs_volume_list)); #if IS_ENABLED(CONFIG_NFS_V4) - WARN_ON_ONCE(!list_empty(&nn->nfs4_data_server_cache)); + for (int i = 0; i < NFS4_DS_CACHE_HASH_SIZE; i++) + WARN_ON_ONCE(!hlist_empty(&nn->nfs4_data_server_cache[i])); #endif /* CONFIG_NFS_V4 */ } diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h index 36658579100d..560fa95726b0 100644 --- a/fs/nfs/netns.h +++ b/fs/nfs/netns.h @@ -31,7 +31,10 @@ struct nfs_net { unsigned short nfs_callback_tcpport; unsigned short nfs_callback_tcpport6; int cb_users[NFS4_MAX_MINOR_VERSION + 1]; - struct list_head nfs4_data_server_cache; +#define NFS4_DS_CACHE_HASH_BITS 8 +#define NFS4_DS_CACHE_HASH_SIZE (1 << NFS4_DS_CACHE_HASH_BITS) + /* every entry is still in bucket 0 until the key is added */ + struct hlist_head nfs4_data_server_cache[NFS4_DS_CACHE_HASH_SIZE]; spinlock_t nfs4_data_server_lock; #endif /* CONFIG_NFS_V4 */ struct nfs_netns_client *nfs_client; diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 18ea4e8e0d85..3a1c012ba18e 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -57,7 +57,7 @@ struct nfs4_pnfs_ds_addr { }; struct nfs4_pnfs_ds { - struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */ + struct hlist_node ds_node; /* nfs_net nfs4_data_server_cache */ char *ds_remotestr; /* comma sep list of addrs */ struct list_head ds_addrs; const struct net *ds_net; diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c index e0e3fc7414e6..f88a9784988a 100644 --- a/fs/nfs/pnfs_nfs.c +++ b/fs/nfs/pnfs_nfs.c @@ -604,7 +604,7 @@ _same_data_server_addrs_locked(const struct list_head *dsaddrs1, } /* - * Lookup DS by addresses and NFS version. nfs4_ds_cache_lock is held + * Lookup DS by addresses and NFS version. nfs4_data_server_lock is held */ static struct nfs4_pnfs_ds * _data_server_lookup_locked(const struct nfs_net *nn, @@ -612,10 +612,13 @@ _data_server_lookup_locked(const struct nfs_net *nn, { struct nfs4_pnfs_ds *ds; - list_for_each_entry(ds, &nn->nfs4_data_server_cache, ds_node) - if (ds->ds_version == version && - _same_data_server_addrs_locked(&ds->ds_addrs, dsaddrs)) - return ds; + for (int i = 0; i < NFS4_DS_CACHE_HASH_SIZE; i++) + hlist_for_each_entry(ds, &nn->nfs4_data_server_cache[i], + ds_node) + if (ds->ds_version == version && + _same_data_server_addrs_locked(&ds->ds_addrs, + dsaddrs)) + return ds; return NULL; } @@ -666,7 +669,7 @@ void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds) struct nfs_net *nn = net_generic(ds->ds_net, nfs_net_id); if (refcount_dec_and_lock(&ds->ds_count, &nn->nfs4_data_server_lock)) { - list_del_init(&ds->ds_node); + hlist_del_init(&ds->ds_node); spin_unlock(&nn->nfs4_data_server_lock); destroy_ds(ds); } @@ -753,11 +756,11 @@ nfs4_pnfs_ds_add(const struct net *net, struct list_head *dsaddrs, u32 version, list_splice_init(dsaddrs, &ds->ds_addrs); ds->ds_remotestr = remotestr; refcount_set(&ds->ds_count, 1); - INIT_LIST_HEAD(&ds->ds_node); + INIT_HLIST_NODE(&ds->ds_node); ds->ds_net = net; ds->ds_clp = NULL; ds->ds_version = version; - list_add(&ds->ds_node, &nn->nfs4_data_server_cache); + hlist_add_head(&ds->ds_node, &nn->nfs4_data_server_cache[0]); dprintk("%s add new data server %s\n", __func__, ds->ds_remotestr); } else {