oxenstored: don't wake to issue no conflict-credit

In the main loop, when choosing the timeout for the select function
call, we were setting it so as to wake up to issue conflict-credit to
any domains that could accept it. When xenstore is idle, this would
mean waking up every 50ms (by default) to do no work. With this
commit, we check whether any domain is below its cap, and if not then
we set the timeout for longer (the same timeout as before the
conflict-protection feature was added).

Reported-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Thomas Sanders <thomas.sanders@citrix.com>
Reviewed-by: Jonathan Davies <jonathan.davies@citrix.com>

diff --git a/tools/ocaml/xenstored/domains.ml b/tools/ocaml/xenstored/domains.ml
index 63c6ad5daa689f89ab1dbd92b1ff719f1191939b..25fd59224451496578e9450ffd60cb4f2184c41c 100644 (file)
--- a/tools/ocaml/xenstored/domains.ml
+++ b/tools/ocaml/xenstored/domains.ml
@@ -35,8 +35,9 @@ type domains = {
        on_first_conflict_pause: unit -> unit;
 
        (* If config is set to use individual instead of aggregate conflict-rate-limiting,
-          we use this instead of the queues. *)
-       mutable n_paused: int;
+          we use these counts instead of the queues. The second one includes the first. *)
+       mutable n_paused: int;    (* Number of domains with zero or negative credit *)
+       mutable n_penalised: int; (* Number of domains with less than maximum credit *)
 }
 
 let init eventchn on_first_conflict_pause = {
@@ -46,6 +47,7 @@ let init eventchn on_first_conflict_pause = {
        doms_with_conflict_penalty = Queue.create ();
        on_first_conflict_pause = on_first_conflict_pause;
        n_paused = 0;
+       n_penalised = 0;
 }
 let del doms id = Hashtbl.remove doms.table id
 let exist doms id = Hashtbl.mem doms.table id
@@ -53,6 +55,23 @@ let find doms id = Hashtbl.find doms.table id
 let number doms = Hashtbl.length doms.table
 let iter doms fct = Hashtbl.iter (fun _ b -> fct b) doms.table
 
+let rec is_empty_queue q =
+       Queue.is_empty q ||
+               if !(Queue.peek q) = None
+               then (
+                       ignore (Queue.pop q);
+                       is_empty_queue q
+               ) else false
+
+let all_at_max_credit doms =
+       if !Define.conflict_rate_limit_is_aggregate
+       then
+               (* Check both becuase if burst limit is 1.0 then a domain can go straight
+                * from max-credit to paused without getting into the penalty queue. *)
+               is_empty_queue doms.doms_with_conflict_penalty
+               && is_empty_queue doms.doms_conflict_paused
+       else doms.n_penalised = 0
+
 (* Functions to handle queues of domains given that the domain might be deleted while in a queue. *)
 let push dom queue =
        Queue.push (ref (Some dom)) queue
@@ -132,13 +151,16 @@ let decr_conflict_credit doms dom =
        let before = dom.Domain.conflict_credit in
        let after = max (-1.0) (before -. 1.0) in
        dom.Domain.conflict_credit <- after;
+       let newly_penalised =
+               before >= !Define.conflict_burst_limit
+               && after < !Define.conflict_burst_limit in
+       let newly_paused = before > 0.0 && after <= 0.0 in
        if !Define.conflict_rate_limit_is_aggregate then (
-               if before >= !Define.conflict_burst_limit
-               && after < !Define.conflict_burst_limit
+               if newly_penalised
                && after > 0.0
                then (
                        push dom doms.doms_with_conflict_penalty
-               ) else if before > 0.0 && after <= 0.0
+               ) else if newly_paused
                then (
                        let first_pause = Queue.is_empty doms.doms_conflict_paused in
                        push dom doms.doms_conflict_paused;
@@ -146,9 +168,12 @@ let decr_conflict_credit doms dom =
                ) else (
                        (* The queues are correct already: no further action needed. *)
                )
-       ) else if before > 0.0 && after <= 0.0 then (
-               doms.n_paused <- doms.n_paused + 1;
-               if doms.n_paused = 1 then doms.on_first_conflict_pause ()
+       ) else (
+               if newly_penalised then doms.n_penalised <- doms.n_penalised + 1;
+               if newly_paused then (
+                       doms.n_paused <- doms.n_paused + 1;
+                       if doms.n_paused = 1 then doms.on_first_conflict_pause ()
+               )
        )
 
 (* Give one point of credit to one domain, and update the queues appropriately. *)
@@ -177,9 +202,13 @@ let incr_conflict_credit doms =
                        let before = dom.Domain.conflict_credit in
                        let after = min (before +. 1.0) !Define.conflict_burst_limit in
                        dom.Domain.conflict_credit <- after;
+
                        if before <= 0.0 && after > 0.0
-                       then doms.n_paused <- doms.n_paused - 1
+                       then doms.n_paused <- doms.n_paused - 1;
+
+                       if before < !Define.conflict_burst_limit
+                       && after >= !Define.conflict_burst_limit
+                       then doms.n_penalised <- doms.n_penalised - 1
                in
-               (* Scope for optimisation (probably tiny): avoid iteration if all domains are at max credit *)
-               iter doms inc
+               if doms.n_penalised > 0 then iter doms inc
        )

diff --git a/tools/ocaml/xenstored/xenstored.ml b/tools/ocaml/xenstored/xenstored.ml
index c0097018e27b1136b070fa6590a17dd5b12d09be..8c82fe94afcf9c680401b2e7dd5d485d736adc7d 100644 (file)
--- a/tools/ocaml/xenstored/xenstored.ml
+++ b/tools/ocaml/xenstored/xenstored.ml
@@ -436,7 +436,10 @@ let _ =
                        peaceful_mw;
                let start_time = Unix.gettimeofday () in
                let timeout =
-                       let until_next_activity = min (max 0. (!next_frequent_ops -. start_time)) period_ops_interval in
+                       let until_next_activity =
+                               if Domains.all_at_max_credit domains
+                               then period_ops_interval
+                               else min (max 0. (!next_frequent_ops -. start_time)) period_ops_interval in
                        if peaceful_mw <> [] then 0. else until_next_activity
                in
                let inset, outset = Connections.select ~only_if:is_peaceful cons in