afs: Fix fileserver rotation

Fix the fileserver rotation so that it doesn't use RTT as the basis for
deciding which server and address to use as this doesn't necessarily give a
good indication of the best path.  Instead, use the configurable preference
list in conjunction with whatever probes have succeeded at the time of
looking.

To this end, make the following changes:

 (1) Keep an array of "server states" to track what addresses we've tried
     on each server and move the waitqueue entries there that we'll need
     for probing.

 (2) Each afs_server_state struct is made to pin the corresponding server's
     endpoint state rather than the afs_operation struct carrying a pin on
     the server we're currently looking at.

 (3) Drop the server list preference; we now always rescan the server list.

 (4) afs_wait_for_probes() now uses the server state list to guide it in
     what it waits for (and to provide the waitqueue entries) and returns
     an indication of whether we'd got a response, run out of responsive
     addresses or the endpoint state had been superseded and we need to
     restart the iteration.

 (5) Call afs_get_address_preferences*() occasionally to refresh the
     preference values.

 (6) When picking a server, scan the addresses of the servers for which we
     have as-yet untested communications, looking for the highest priority
     one and use that instead of trying all the addresses for a particular
     server in ascending-RTT order.

 (7) When a Busy or Offline state is seen across all available servers, do
     a short sleep.

 (8) If we detect that we accessed a future RO volume version whilst it is
     undergoing replication, reissue the op against the older version until
     at least half of the servers are replicated.

 (9) Whilst RO replication is ongoing, increase the frequency of Volume
     Location server checks for that volume to every ten minutes instead of
     hourly.

Also add a tracepoint to track progress through the rotation algorithm.

Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org

1 files changed, 69 insertions, 12 deletions

diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index 2df7d0fd3f21..b2e0847eca47 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -230,15 +230,12 @@ enum yfs_cm_operation {
 #define afs_estate_traces \
 	EM(afs_estate_trace_alloc_probe,	"ALLOC prob") \
 	EM(afs_estate_trace_alloc_server,	"ALLOC srvr") \
-	EM(afs_estate_trace_get_fsrotate_set,	"GET fs-rot") \
+	EM(afs_estate_trace_get_server_state,	"GET srv-st") \
 	EM(afs_estate_trace_get_getcaps,	"GET getcap") \
 	EM(afs_estate_trace_put_getcaps,	"PUT getcap") \
-	EM(afs_estate_trace_put_next_server,	"PUT nx-srv") \
-	EM(afs_estate_trace_put_op_failed,	"PUT op-fai") \
-	EM(afs_estate_trace_put_operation,	"PUT op    ") \
 	EM(afs_estate_trace_put_probe,		"PUT probe ") \
-	EM(afs_estate_trace_put_restart_rotate,	"PUT rstrot") \
 	EM(afs_estate_trace_put_server,		"PUT server") \
+	EM(afs_estate_trace_put_server_state,	"PUT srv-st") \
 	E_(afs_estate_trace_free,		"FREE      ")
 
 #define afs_fs_operations \
@@ -448,6 +445,29 @@ enum yfs_cm_operation {
 	EM(afs_cb_break_for_vos_release,	"break-vos-release")	\
 	E_(afs_cb_break_volume_excluded,	"vol-excluded")
 
+#define afs_rotate_traces						\
+	EM(afs_rotate_trace_aborted,		"Abortd")		\
+	EM(afs_rotate_trace_busy_sleep,		"BsySlp")		\
+	EM(afs_rotate_trace_check_vol_status,	"VolStt")		\
+	EM(afs_rotate_trace_failed,		"Failed")		\
+	EM(afs_rotate_trace_iter,		"Iter  ")		\
+	EM(afs_rotate_trace_iterate_addr,	"ItAddr")		\
+	EM(afs_rotate_trace_next_server,	"NextSv")		\
+	EM(afs_rotate_trace_no_more_servers,	"NoMore")		\
+	EM(afs_rotate_trace_nomem,		"Nomem ")		\
+	EM(afs_rotate_trace_probe_error,	"PrbErr")		\
+	EM(afs_rotate_trace_probe_fileserver,	"PrbFsv")		\
+	EM(afs_rotate_trace_probe_none,		"PrbNon")		\
+	EM(afs_rotate_trace_probe_response,	"PrbRsp")		\
+	EM(afs_rotate_trace_probe_superseded,	"PrbSup")		\
+	EM(afs_rotate_trace_restart,		"Rstart")		\
+	EM(afs_rotate_trace_retry_server,	"RtrySv")		\
+	EM(afs_rotate_trace_selected_server,	"SlctSv")		\
+	EM(afs_rotate_trace_stale_lock,		"StlLck")		\
+	EM(afs_rotate_trace_start,		"Start ")		\
+	EM(afs_rotate_trace_stop,		"Stop  ")		\
+	E_(afs_rotate_trace_stopped,		"Stoppd")
+
 /*
  * Generate enums for tracing information.
  */
@@ -471,6 +491,7 @@ enum afs_file_error		{ afs_file_errors } __mode(byte);
 enum afs_flock_event		{ afs_flock_events } __mode(byte);
 enum afs_flock_operation	{ afs_flock_operations } __mode(byte);
 enum afs_io_error		{ afs_io_errors } __mode(byte);
+enum afs_rotate_trace		{ afs_rotate_traces } __mode(byte);
 enum afs_server_trace		{ afs_server_traces } __mode(byte);
 enum afs_volume_trace		{ afs_volume_traces } __mode(byte);
 
@@ -486,21 +507,22 @@ enum afs_volume_trace		{ afs_volume_traces } __mode(byte);
 
 afs_alist_traces;
 afs_call_traces;
-afs_server_traces;
+afs_cb_break_reasons;
 afs_cell_traces;
-afs_fs_operations;
-afs_vl_operations;
 afs_cm_operations;
-yfs_cm_operations;
 afs_edit_dir_ops;
 afs_edit_dir_reasons;
 afs_eproto_causes;
 afs_estate_traces;
-afs_io_errors;
 afs_file_errors;
-afs_flock_types;
 afs_flock_operations;
-afs_cb_break_reasons;
+afs_flock_types;
+afs_fs_operations;
+afs_io_errors;
+afs_rotate_traces;
+afs_server_traces;
+afs_vl_operations;
+yfs_cm_operations;
 
 /*
  * Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -1519,6 +1541,41 @@ TRACE_EVENT(afs_vl_probe,
 		      &__entry->srx.transport)
 	    );
 
+TRACE_EVENT(afs_rotate,
+	    TP_PROTO(struct afs_operation *op, enum afs_rotate_trace reason, unsigned int extra),
+
+	    TP_ARGS(op, reason, extra),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		op)
+		    __field(unsigned int,		flags)
+		    __field(unsigned int,		extra)
+		    __field(unsigned short,		iteration)
+		    __field(short,			server_index)
+		    __field(short,			addr_index)
+		    __field(enum afs_rotate_trace,	reason)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->op = op->debug_id;
+		    __entry->flags = op->flags;
+		    __entry->iteration = op->nr_iterations;
+		    __entry->server_index = op->server_index;
+		    __entry->addr_index = op->addr_index;
+		    __entry->reason = reason;
+		    __entry->extra = extra;
+			   ),
+
+	    TP_printk("OP=%08x it=%02x %s fl=%x sx=%d ax=%d ext=%d",
+		      __entry->op,
+		      __entry->iteration,
+		      __print_symbolic(__entry->reason, afs_rotate_traces),
+		      __entry->flags,
+		      __entry->server_index,
+		      __entry->addr_index,
+		      __entry->extra)
+	    );
+
 #endif /* _TRACE_AFS_H */
 
 /* This part must be outside protection */