summaryrefslogtreecommitdiff
path: root/fs/nfs/nfs4trace.h
diff options
context:
space:
mode:
authorJeff Layton <jlayton@poochiereds.net>2016-05-17 19:28:47 +0300
committerAnna Schumaker <Anna.Schumaker@Netapp.com>2016-05-17 22:48:12 +0300
commit183d9e7b112aaed0d19c16ffcf0f8c3a86dc71e0 (patch)
treee78c3b12f7a309b7a364dff4ebcab69fab66cfae /fs/nfs/nfs4trace.h
parent83026d80a16ea6a4e4f06a994fc7831b1d8d6375 (diff)
downloadlinux-183d9e7b112aaed0d19c16ffcf0f8c3a86dc71e0.tar.xz
pnfs: rework LAYOUTGET retry handling
There are several problems in the way a stateid is selected for a LAYOUTGET operation: We pick a stateid to use in the RPC prepare op, but that makes it difficult to serialize LAYOUTGETs that use the open stateid. That serialization is done in pnfs_update_layout, which occurs well before the rpc_prepare operation. Between those two events, the i_lock is dropped and reacquired. pnfs_update_layout can find that the list has lsegs in it and not do any serialization, but then later pnfs_choose_layoutget_stateid ends up choosing the open stateid. This patch changes the client to select the stateid to use in the LAYOUTGET earlier, when we're searching for a usable layout segment. This way we can do it all while holding the i_lock the first time, and ensure that we serialize any LAYOUTGET call that uses a non-layout stateid. This also means a rework of how LAYOUTGET replies are handled, as we must now get the latest stateid if we want to retransmit in response to a retryable error. Most of those errors boil down to the fact that the layout state has changed in some fashion. Thus, what we really want to do is to re-search for a layout when it fails with a retryable error, so that we can avoid reissuing the RPC at all if possible. While the LAYOUTGET RPC is async, the initiating thread always waits for it to complete, so it's effectively synchronous anyway. Currently, when we need to retry a LAYOUTGET because of an error, we drive that retry via the rpc state machine. This means that once the call has been submitted, it runs until it completes. So, we must move the error handling for this RPC out of the rpc_call_done operation and into the caller. In order to handle errors like NFS4ERR_DELAY properly, we must also pass a pointer to the sliding timeout, which is now moved to the stack in pnfs_update_layout. The complicating errors are -NFS4ERR_RECALLCONFLICT and -NFS4ERR_LAYOUTTRYLATER, as those involve a timeout after which we give up and return NULL back to the caller. So, there is some special handling for those errors to ensure that the layers driving the retries can handle that appropriately. Signed-off-by: Jeff Layton <jeff.layton@primarydata.com> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>
Diffstat (limited to 'fs/nfs/nfs4trace.h')
-rw-r--r--fs/nfs/nfs4trace.h10
1 files changed, 8 insertions, 2 deletions
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 2c8d05dae5b1..9c150b153782 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -1520,6 +1520,8 @@ DEFINE_NFS4_INODE_EVENT(nfs4_layoutreturn_on_close);
{ PNFS_UPDATE_LAYOUT_FOUND_CACHED, "found cached" }, \
{ PNFS_UPDATE_LAYOUT_RETURN, "layoutreturn" }, \
{ PNFS_UPDATE_LAYOUT_BLOCKED, "layouts blocked" }, \
+ { PNFS_UPDATE_LAYOUT_INVALID_OPEN, "invalid open" }, \
+ { PNFS_UPDATE_LAYOUT_RETRY, "retrying" }, \
{ PNFS_UPDATE_LAYOUT_SEND_LAYOUTGET, "sent layoutget" })
TRACE_EVENT(pnfs_update_layout,
@@ -1528,9 +1530,10 @@ TRACE_EVENT(pnfs_update_layout,
u64 count,
enum pnfs_iomode iomode,
struct pnfs_layout_hdr *lo,
+ struct pnfs_layout_segment *lseg,
enum pnfs_update_layout_reason reason
),
- TP_ARGS(inode, pos, count, iomode, lo, reason),
+ TP_ARGS(inode, pos, count, iomode, lo, lseg, reason),
TP_STRUCT__entry(
__field(dev_t, dev)
__field(u64, fileid)
@@ -1540,6 +1543,7 @@ TRACE_EVENT(pnfs_update_layout,
__field(enum pnfs_iomode, iomode)
__field(int, layoutstateid_seq)
__field(u32, layoutstateid_hash)
+ __field(long, lseg)
__field(enum pnfs_update_layout_reason, reason)
),
TP_fast_assign(
@@ -1559,11 +1563,12 @@ TRACE_EVENT(pnfs_update_layout,
__entry->layoutstateid_seq = 0;
__entry->layoutstateid_hash = 0;
}
+ __entry->lseg = (long)lseg;
),
TP_printk(
"fileid=%02x:%02x:%llu fhandle=0x%08x "
"iomode=%s pos=%llu count=%llu "
- "layoutstateid=%d:0x%08x (%s)",
+ "layoutstateid=%d:0x%08x lseg=0x%lx (%s)",
MAJOR(__entry->dev), MINOR(__entry->dev),
(unsigned long long)__entry->fileid,
__entry->fhandle,
@@ -1571,6 +1576,7 @@ TRACE_EVENT(pnfs_update_layout,
(unsigned long long)__entry->pos,
(unsigned long long)__entry->count,
__entry->layoutstateid_seq, __entry->layoutstateid_hash,
+ __entry->lseg,
show_pnfs_update_layout_reason(__entry->reason)
)
);