[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-changelog] [xen master] oxenstored: add a safe net mechanism for existing ill-behaved clients



commit 0074c64aefc7e2b552503bbbd0d1b5dd08b11144
Author:     Zheng Li <dev@xxxxxxxx>
AuthorDate: Thu Sep 25 18:35:01 2014 +0100
Commit:     Ian Campbell <ian.campbell@xxxxxxxxxx>
CommitDate: Wed Oct 8 14:18:46 2014 +0100

    oxenstored: add a safe net mechanism for existing ill-behaved clients
    
    In previous commit, we moved from exhaustively scanning all domain 
connections
    to only processing those have correctly notified us by events. The benefits 
are
    not only efficiency but also correctness, because it could potentially 
block an
    ill-behaved client and have it waiting on its own mistake. If someone makes 
a
    mistake on this when developing a piece of code, he/she would immediately
    notice the problem (as the process being blocked), so that he/she could fix 
it
    rightaway before anything else. Note that the chances of making such 
mistakes
    are rare in reality, because most client code would use the libxenstore 
library
    (which has all the notification logic built in correctly) instead of having 
to
    implement raw accessing from scratch.
    
    On the other hand, we did notice that there were some legacy code that 
didn't do
    the notification correctly. As some code might be still running in wild, it
    would be bad if they break by this change (e.g. after an upgrade). This 
patch
    introduces a safe net mechanism to ensure ill-behaved clients continue to 
work,
    but still retain most of the performance benefits here.
    
      * We add a checker to still scan all the rings periodically, so that we 
can
        still pick up these messages at an acceptable frequency.
    
      * Internally, we introduce an io_credit concept for domain connections. It
        represents the rounds of ring scan we are going to perform on a domain
        connection. For well-behaved connections, this value is changing 
between 0
        and 1; but for connections detected as ill-behaved, we'll bump its 
credit
        to a high value so that we'll unconditionally scan its ring for the next
        $n$ rounds. This way, the client won't hiccupped by the interval between
        checker's running (especially during periods when it continously 
interacts
        with oxenstored); and oxenstored doesn't have to keep scanning these
        rings indefinitely (with the credit running out), as they are usually 
quite
        most of the time.
    
      * We log an message when a domain connection is suspected as ill-behaved.
        Enable [info] level logging if you want/need to see it in action. Note 
that
        this information won't be accurate, as false positives are possible due 
to
        time window (e.g. we detect a client has written to the ring and we get 
no
        notificiation from it for the time being, but still the notification 
could
        potentially arrive at some time later). It's no harm to give a domain
        connection extra credit though.
    
    Signed-off-by: Zheng Li <dev@xxxxxxxx>
    Reviewed-by: David Scott <dave.scott@xxxxxxxxxx>
---
 tools/ocaml/xenstored/domain.ml       |   11 ++++-
 tools/ocaml/xenstored/oxenstored.conf |    3 +
 tools/ocaml/xenstored/xenstored.ml    |   76 ++++++++++++++++++++++++---------
 3 files changed, 69 insertions(+), 21 deletions(-)

diff --git a/tools/ocaml/xenstored/domain.ml b/tools/ocaml/xenstored/domain.ml
index 06d5749..ab34314 100644
--- a/tools/ocaml/xenstored/domain.ml
+++ b/tools/ocaml/xenstored/domain.ml
@@ -28,6 +28,9 @@ type t =
        eventchn: Event.t;
        mutable port: Xeneventchn.t option;
        mutable bad_client: bool;
+       mutable io_credit: int; (* the rounds of ring process left to do, 
default is 0,
+                                  usually set to 1 when there is work 
detected, could
+                                  also set to n to give "lazy" clients extra 
credit *)
 }
 
 let get_path dom = "/local/domain/" ^ (sprintf "%u" dom.id)
@@ -40,6 +43,11 @@ let get_port d = d.port
 let is_bad_domain domain = domain.bad_client
 let mark_as_bad domain = domain.bad_client <- true
 
+let get_io_credit domain = domain.io_credit
+let set_io_credit ?(n=1) domain = domain.io_credit <- max 0 n
+let incr_io_credit domain = domain.io_credit <- domain.io_credit + 1
+let decr_io_credit domain = domain.io_credit <- max 0 (domain.io_credit - 1)
+
 let string_of_port = function
 | None -> "None"
 | Some x -> string_of_int (Xeneventchn.to_int x)
@@ -74,7 +82,8 @@ let make id mfn remote_port interface eventchn = {
        interface = interface;
        eventchn = eventchn;
        port = None;
-       bad_client = false
+       bad_client = false;
+       io_credit = 0;
 }
 
 let is_dom0 d = d.id = 0
diff --git a/tools/ocaml/xenstored/oxenstored.conf 
b/tools/ocaml/xenstored/oxenstored.conf
index 13ee770..dd20eda 100644
--- a/tools/ocaml/xenstored/oxenstored.conf
+++ b/tools/ocaml/xenstored/oxenstored.conf
@@ -33,3 +33,6 @@ persistent = false
 # acesss-log-nb-chars = 180
 # access-log-special-ops = false
 
+# Perodically scanning all the rings as a safenet for lazy clients.
+# Define the interval in seconds, set to negative to disable.
+# ring-scan-interval = 20
diff --git a/tools/ocaml/xenstored/xenstored.ml 
b/tools/ocaml/xenstored/xenstored.ml
index b13393c..bfe689b 100644
--- a/tools/ocaml/xenstored/xenstored.ml
+++ b/tools/ocaml/xenstored/xenstored.ml
@@ -54,13 +54,14 @@ let process_connection_fds store cons domains rset wset =
 let process_domains store cons domains =
        let do_io_domain domain =
                if not (Domain.is_bad_domain domain) then
-                       let con = Connections.find_domain cons (Domain.get_id 
domain) in
+                       let io_credit = Domain.get_io_credit domain in
+                       if io_credit > 0 then (
+                               let con = Connections.find_domain cons 
(Domain.get_id domain) in
                                Process.do_input store cons domains con;
-                               Process.do_output store cons domains con in
-       List.iter
-               (fun c ->
-                match Connection.get_domain c with
-                | Some d -> do_io_domain d | _ -> ())
+                               Process.do_output store cons domains con;
+                               Domain.decr_io_credit domain;
+                       ) in
+       Domains.iter domains do_io_domain
 
 let sigusr1_handler store =
        try
@@ -82,6 +83,8 @@ let config_filename cf =
 
 let default_pidfile = "/var/run/xenstored.pid"
 
+let ring_scan_interval = ref 20
+
 let parse_config filename =
        let pidfile = ref default_pidfile in
        let options = [
@@ -108,6 +111,7 @@ let parse_config filename =
                ("access-log-transactions-ops", Config.Set_bool 
Logging.access_log_transaction_ops);
                ("access-log-special-ops", Config.Set_bool 
Logging.access_log_special_ops);
                ("allow-debug", Config.Set_bool Process.allow_debug);
+               ("ring-scan-interval", Config.Set_int ring_scan_interval);
                ("pid-file", Config.Set_string pidfile); ] in
        begin try Config.read filename options (fun _ _ -> raise Not_found)
        with
@@ -318,7 +322,8 @@ let _ =
                                )
                                else
                                        let c = Connections.find_domain_by_port 
cons port in
-                                       process_domains store cons domains [c]
+                                       match Connection.get_domain c with
+                                       | Some dom -> Domain.incr_io_credit dom 
| None -> ()
                                ) (fun () -> Event.unmask eventchn port)
                and do_if_set fd set fct =
                        if List.mem fd set then
@@ -327,11 +332,30 @@ let _ =
                maybe (fun fd -> do_if_set fd rset (accept_connection true)) 
rw_sock;
                maybe (fun fd -> do_if_set fd rset (accept_connection false)) 
ro_sock;
                do_if_set (Event.fd eventchn) rset (handle_eventchn)
-               in
+       in
+
+       let ring_scan_checker dom =
+               (* no need to scan domains already marked as for processing *)
+               if not (Domain.get_io_credit dom > 0) then
+                       let con = Connections.find_domain cons (Domain.get_id 
dom) in
+                       if not (Connection.has_more_work con) then (
+                               Process.do_output store cons domains con;
+                               Process.do_input store cons domains con;
+                               if Connection.has_more_work con then
+                                       (* Previously thought as no work, but 
detect some after scan (as
+                                          processing a new message involves 
multiple steps.) It's very
+                                          likely to be a "lazy" client, bump 
its credit. It could be false
+                                          positive though (due to time 
window), but it's no harm to give a
+                                          domain extra credit. *)
+                                       let n = 32 + 2 * (Domains.number 
domains) in
+                                       info "found lazy domain %d, credit %d" 
(Domain.get_id dom) n;
+                                       Domain.set_io_credit ~n dom
+                       ) in
 
        let last_stat_time = ref 0. in
-       let periodic_ops_counter = ref 0 in
-       let periodic_ops () =
+       let last_scan_time = ref 0. in
+
+       let periodic_ops now =
                (* we garbage collect the string->int dictionary after a 
sizeable amount of operations,
                 * there's no need to be really fast even if we got loose
                 * objects since names are often reuse.
@@ -344,10 +368,13 @@ let _ =
                        Symbol.garbage ()
                end;
 
+               (* scan all the xs rings as a safenet for ill-behaved clients *)
+               if !ring_scan_interval >= 0 && now > (!last_scan_time +. float 
!ring_scan_interval) then
+                       (last_scan_time := now; Domains.iter domains 
ring_scan_checker);
+
                (* make sure we don't print general stats faster than 2 min *)
-               let ntime = Unix.gettimeofday () in
-               if ntime > (!last_stat_time +. 120.) then (
-                       last_stat_time := ntime;
+               if now > (!last_stat_time +. 120.) then (
+                       last_stat_time := now;
 
                        let gc = Gc.stat () in
                        let (lanon, lanon_ops, lanon_watchs,
@@ -368,16 +395,20 @@ let _ =
                )
                in
 
+               let period_ops_interval = 15. in
+               let period_start = ref 0. in
+
        let main_loop () =
-               incr periodic_ops_counter;
-               if !periodic_ops_counter > 20 then (
-                       periodic_ops_counter := 0;
-                       periodic_ops ();
-               );
 
                let mw = Connections.has_more_work cons in
+               List.iter
+                       (fun c ->
+                        match Connection.get_domain c with
+                        | None -> () | Some d -> Domain.incr_io_credit d)
+                       mw;
+               let timeout =
+                       if List.length mw > 0 then 0. else period_ops_interval 
in
                let inset, outset = Connections.select cons in
-               let timeout = if List.length mw > 0 then 0. else -1. in
                let rset, wset, _ =
                try
                        Select.select (spec_fds @ inset) outset [] timeout
@@ -389,7 +420,12 @@ let _ =
                        process_special_fds sfds;
                if List.length cfds > 0 || List.length wset > 0 then
                        process_connection_fds store cons domains cfds wset;
-               process_domains store cons domains mw
+               if timeout <> 0. then (
+                       let now = Unix.gettimeofday () in
+                       if now > !period_start +. period_ops_interval then
+                               (period_start := now; periodic_ops now)
+               );
+               process_domains store cons domains
                in
 
        while not !quit
--
generated by git-patchbot for /home/xen/git/xen.git#master

_______________________________________________
Xen-changelog mailing list
Xen-changelog@xxxxxxxxxxxxx
http://lists.xensource.com/xen-changelog


 


Rackspace

Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.