Changing the retry to start at NFS4_POLL_RETRY_MIN and exponentially grow
to NFS4_POLL_RETRY_MAX allow for faster handling of these error conditions.
Additionally this alleviates an interoperability problem with the AIX NFSv4
Server. The AIX server frequently (2 out of 3) returns NFS4ERR_DELAY, on a
close when it happens in close proximity to a RELEASE_LOCKOWNER. This would
cause a linux client to hang for 15 seconds.
Signed-off-by: Dave Chiluk <chiluk@xxxxxxxxxxxxx>
---
fs/nfs/nfs4proc.c | 12 ++++++++++++
include/linux/sunrpc/sched.h | 1 +
2 files changed, 13 insertions(+)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0ad025e..37dad27 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4006,6 +4006,18 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
#endif /* CONFIG_NFS_V4_1 */
case -NFS4ERR_DELAY:
nfs_inc_server_stats(server, NFSIOS_DELAY);
+ /* Do an exponential backoff of retries from
+ * NFS4_POLL_RETRY_MIN to NFS4_POLL_RETRY_MAX. */
+ task->tk_timeout = NFS4_POLL_RETRY_MIN <<
+ (task->tk_delays*2);
+ if (task->tk_timeout > NFS4_POLL_RETRY_MAX)
+ rpc_delay(task, NFS4_POLL_RETRY_MAX);
+ else {
+ task->tk_delays++;
+ rpc_delay(task, task->tk_timeout);
+ }
+ task->tk_status = 0;
+ return -EAGAIN;
case -NFS4ERR_GRACE:
rpc_delay(task, NFS4_POLL_RETRY_MAX);
task->tk_status = 0;
diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index 84ca436..60f82bf 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -62,6 +62,7 @@ struct rpc_task {
void * tk_calldata;
unsigned long tk_timeout; /* timeout for rpc_sleep() */
+ unsigned short tk_delays; /* number of times task delayed */
unsigned long tk_runstate; /* Task run status */
struct workqueue_struct *tk_workqueue; /* Normally rpciod, but could
* be any workqueue
--
1.7.9.5
--
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
