As soon as we detect a server failure, we quickly handle replication
recovery without waiting for all the active commands to finish from the
failed server. The first error would cause us to work with a different
(replicated) server.
Any later failures from the old server are indistinguishable from the
new replicated server. These failures from the old server trigger a
spurious replication recovery again. To avoid this, we add start time to
nfs_client. If this is a recent enough nfs_client, we don't handle
replication recovery and just retry the request instead.
Signed-off-by: Malahal Naineni <malahal@xxxxxxxxxx>
---
fs/nfs/client.c | 1 +
fs/nfs/nfs4namespace.c | 23 +++++++++++++++++++++++
include/linux/nfs_fs_sb.h | 1 +
3 files changed, 25 insertions(+), 0 deletions(-)
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 000ebdb..f0d8d24 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1477,6 +1477,7 @@ int nfs4_clone_client(struct nfs_client *clp, const struct sockaddr *sap,
* lose state.
*/
new->cl_boot_time = clp->cl_boot_time;
+ new->cl_start_time = jiffies;
dprintk("<-- %s moved (%llx:%llx) to nfs_client %p\n", __func__,
(unsigned long long)server->fsid.major,
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index ee75e27..617d6bf 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -356,6 +356,29 @@ int nfs4_replace_transport(struct nfs_server *server)
unsigned int i;
int error;
+ /*
+ * As soon as we detect a server failure, we quickly handle
+ * replication recovery without waiting for all the active
+ * commands to finish from the failed server. The first error
+ * would cause us to work with a different (replicated) server.
+ *
+ * Any later failures from the old server are indistinguishable
+ * from the new replicated server. These failures from the old
+ * server trigger a spurious replication recovery again. To
+ * avoid this, we add start time to nfs_client. If this is a
+ * recent enough nfs_client, we don't handle replication
+ * recovery and just retry the request instead.
+ */
+#define NFS_REPLI_SETTLE(rclient) (2 * (rclient)->cl_timeout->to_initval)
+ if (time_before(jiffies, server->nfs_client->cl_start_time +
+ NFS_REPLI_SETTLE(server->client))) {
+ dprintk("%s() ignoring spurious replication request, "
+ "current: %lu, client start: %lu, repli_settle: %lu\n",
+ __func__, jiffies, server->nfs_client->cl_start_time,
+ NFS_REPLI_SETTLE(server->client));
+ return 0;
+ }
+
sap = kmalloc(addr_bufsize, GFP_KERNEL);
if (sap == NULL) {
error = -ENOMEM;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 8c16ec5..9d79a0e 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -88,6 +88,7 @@ struct nfs_client {
#endif
struct server_scope *server_scope; /* from exchange_id */
+ unsigned long cl_start_time;
};
/*
--
1.7.8.3
--
To unsubscribe from this list: send the line "unsubscribe linux-nfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
