NFSv4.1: Retry pNFS after a 2 minute timeout

If we had to fall back to read/write through MDS, then assume that we should
retry pNFS after a suitable timeout period.
The following patch sets a timeout of 2 minutes.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

2 files changed, 15 insertions, 1 deletions

diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index f46f9bc4f767..2c59da5511db 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -35,6 +35,7 @@
 #include "iostat.h"
 
 #define NFSDBG_FACILITY         NFSDBG_PNFS
+#define PNFS_LAYOUTGET_RETRY_TIMEOUT (120*HZ)
 
 /* Locking:
  *
@@ -248,6 +249,7 @@ pnfs_iomode_to_fail_bit(u32 iomode)
 static void
 pnfs_layout_io_set_failed(struct pnfs_layout_hdr *lo, u32 iomode)
 {
+        lo->plh_retry_timestamp = jiffies;
         set_bit(pnfs_iomode_to_fail_bit(iomode), &lo->plh_flags);
         dprintk("%s Setting layout IOMODE_%s fail bit\n", __func__,
                         iomode == IOMODE_RW ?  "RW" : "READ");
@@ -256,7 +258,18 @@ pnfs_layout_io_set_failed(struct pnfs_layout_hdr *lo, u32 iomode)
 static bool
 pnfs_layout_io_test_failed(struct pnfs_layout_hdr *lo, u32 iomode)
 {
-        return test_bit(pnfs_iomode_to_fail_bit(iomode), &lo->plh_flags) != 0;
+        unsigned long start, end;
+        if (test_bit(pnfs_iomode_to_fail_bit(iomode), &lo->plh_flags) == 0)
+                return false;
+        end = jiffies;
+        start = end - PNFS_LAYOUTGET_RETRY_TIMEOUT;
+        if (!time_in_range(lo->plh_retry_timestamp, start, end)) {
+                /* It is time to retry the failed layoutgets */
+                clear_bit(NFS_LAYOUT_RW_FAILED, &lo->plh_flags);
+                clear_bit(NFS_LAYOUT_RO_FAILED, &lo->plh_flags);
+                return false;
+        }
+        return true;
 }
 
 static void
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index e3eb7d1b17a8..bc8e5001203d 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -140,6 +140,7 @@ struct pnfs_layout_hdr {
         atomic_t                plh_outstanding; /* number of RPCs out */
         unsigned long           plh_block_lgets; /* block LAYOUTGET if >0 */
         u32                     plh_barrier; /* ignore lower seqids */
+        unsigned long           plh_retry_timestamp;
         unsigned long           plh_flags;
         loff_t                  plh_lwb; /* last write byte for layoutcommit */
         struct rpc_cred         *plh_lc_cred; /* layoutcommit cred */