31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
|
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
|
+
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
-
+
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
-
-
-
+
+
+
+
+
+
-
-
+
+
-
-
-
-
+
+
-
-
-
-
-
-
-
+
-
-
+
+
-
+
+
+
+
+
+
+
+
+
-
+
-
-
-
-
-
+
-
+
+
+
+
+
-
+
-
+
-
+
+
+
+
+
-
-
-
-
+
+
+
+
+
+
-
+
+
-
+
+
+
+
+
+
-
-
-
+
+
+
+
-
+
+
+
+
+
+
-
+
-
+
+
+
+
+
-
+
-
+
+
-
+
+
+
+
+
+
-
+
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
-
+
+
-
+
+
-
+
+
+
|
;;======================================================================
;; if a server is either running or in the process of starting call client:setup
;; else return #f to let the calling proc know that there is no server available
;;
(define (rmt:get-connection-info areapath #!key (area-dat #f)) ;; TODO: push areapath down.
(let* ((runremote (or area-dat *runremote*))
(cinfo (if (remote? runremote)
(cinfo (remote-conndat runremote))
(run-id 0))
(if cinfo
cinfo
(if (server:check-if-running areapath)
(client:setup areapath)
#f))))
(remote-conndat runremote)
#f)))
(if cinfo
cinfo
(if (server:check-if-running areapath)
(client:setup areapath)
#f))))
(define *send-receive-mutex* (make-mutex)) ;; should have separate mutex per run-id
;; RA => e.g. usage (rmt:send-receive 'get-var #f (list varname))
;;
(define (rmt:send-receive cmd rid params #!key (attemptnum 1)(area-dat #f)) ;; start attemptnum at 1 so the modulo below works as expected
;;DOT digraph megatest_state_status {
;;DOT ranksep=0;
;;DOT // rankdir=LR;
;;DOT node [shape="box"];
;;DOT "rmt:send-receive" -> MUTEXLOCK;
;;DOT { edge [style=invis];"case 1" -> "case 2" -> "case 3" -> "case 4" -> "case 5" -> "case 6" -> "case 7" -> "case 8" -> "case 9" -> "case 10" -> "case 11"; }
;; do all the prep locked under the rmt-mutex
(mutex-lock! *rmt-mutex*)
;; 1. check if server is started IFF cmd is a write OR if we are not on the homehost, store in runremote
;; 2. check the age of the connections. refresh the connection if it is older than timeout-20 seconds.
;; 3. do the query, if on homehost use local access
;;
(let* ((start-time (current-seconds)) ;; snapshot time so all use cases get same value
(runremote (or area-dat *runremote*)))
(let* ((start-time (current-seconds)) ;; snapshot time so all use cases get same value
(areapath *toppath*);; TODO - resolve from dbstruct to be compatible with multiple areas
(runremote (or area-dat
*runremote*))
(readonly-mode (if (and runremote
(remote-ro-mode-checked runremote))
(remote-ro-mode runremote)
(let* ((dbfile (conc *toppath* "/megatest.db"))
(ro-mode (not (file-write-access? dbfile)))) ;; TODO: use dbstruct or runremote to figure this out in future
(if runremote
(begin
(remote-ro-mode-set! runremote ro-mode)
(remote-ro-mode-checked-set! runremote #t)
ro-mode)
ro-mode)))))
;; DOT INIT_RUNREMOTE; // leaving off - doesn't really add to the clarity
;; DOT MUTEXLOCK -> INIT_RUNREMOTE [label="no remote?"];
;; DOT INIT_RUNREMOTE -> MUTEXLOCK;
;; ensure we have a record for our connection for given area
(if (not runremote) ;; can remove this one. should never get here.
(begin
(set! *runremote* (make-remote))
(set! runremote *runremote*))) ;; new runremote will come from this on next iteration
;; DOT SET_HOMEHOST; // leaving off - doesn't really add to the clarity
;; DOT MUTEXLOCK -> SET_HOMEHOST [label="no homehost?"];
;; DOT SET_HOMEHOST -> MUTEXLOCK;
;; ensure we have a homehost record
(if (not (pair? (remote-hh-dat runremote))) ;; not on homehost
(thread-sleep! 0.1) ;; since we shouldn't get here, delay a little
(remote-hh-dat-set! runremote (common:get-homehost)))
;;(print "BB> readonly-mode is "readonly-mode" dbfile is "dbfile)
(cond
;;DOT EXIT;
;;DOT MUTEXLOCK -> EXIT [label="> 15 attempts"]; {rank=same "case 1" "EXIT" }
;; give up if more than 15 attempts
((> attemptnum 15)
(debug:print 0 *default-log-port* "ERROR: 15 tries to start/connect to server. Giving up.")
(exit 1))
;;DOT CASE2 [label="local\nreadonly\nquery"];
;;DOT MUTEXLOCK -> CASE2; {rank=same "case 2" CASE2}
;;DOT CASE2 -> "rmt:open-qry-close-locally";
;; readonly mode, read request- handle it - case 2
((and readonly-mode
(member cmd api:read-only-queries))
(mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 2")
(rmt:open-qry-close-locally cmd 0 params)
)
;;DOT CASE3 [label="write in\nread-only mode"];
;;DOT MUTEXLOCK -> CASE3 [label="readonly\nmode?"]; {rank=same "case 3" CASE3}
;;DOT CASE3 -> "#f";
;; readonly mode, write request. Do nothing, return #f
(readonly-mode
(mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 3")
(debug:print 0 *default-log-port* "WARNING: write transaction requested on a readonly area. cmd="cmd" params="params)
#f)
;; This block was for pre-emptively resetting the connection if there had been no communication for some time.
;; I don't think it adds any value. If the server is not there, just fail and start a new connection.
;; also, the expire-time calculation might not be correct. We want, time-since-last-server-access > (server:get-timeout)
;;
;;DOT CASE4 [label="reset\nconnection"];
;;DOT MUTEXLOCK -> CASE4 [label="have connection,\nlast_access > expire_time"]; {rank=same "case 4" CASE4}
;;DOT CASE4 -> "rmt:send-receive";
;; reset the connection if it has been unused too long
((and runremote
(remote-conndat runremote)
(let ((expire-time (+ (- start-time (remote-server-timeout runremote))(random 30)))) ;; add 30 seconds of noise so that not all running tests expire at the same time causing a storm of server starts
(< (http-transport:server-dat-get-last-access (remote-conndat runremote)) expire-time)))
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 8")
(remote-conndat-set! runremote #f)
(> (current-seconds) ;; if it has been more than server-timeout seconds since last contact, close this connection and start a new on
(+ (http-transport:server-dat-get-last-access (remote-conndat runremote))
(remote-server-timeout runremote))))
(debug:print-info 0 *default-log-port* "Connection to " (remote-server-url runremote) " expired due to no accesses, forcing new connection.")
(http-transport:close-connections area-dat: runremote)
(remote-conndat-set! runremote #f) ;; invalidate the connection, thus forcing a new connection.
(mutex-unlock! *rmt-mutex*)
(rmt:send-receive cmd rid params attemptnum: attemptnum))
;; ensure we have a record for our connection for given area
((not runremote)
;;DOT CASE5 [label="local\nread"];
(set! *runremote* (make-remote))
(mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 1")
(rmt:send-receive cmd rid params attemptnum: attemptnum))
;; ensure we have a homehost record
((not (pair? (remote-hh-dat runremote))) ;; not on homehost
(thread-sleep! 0.1) ;; since we shouldn't get here, delay a little
(remote-hh-dat-set! runremote (common:get-homehost))
(mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 2")
(rmt:send-receive cmd rid params attemptnum: attemptnum))
((and (cdr (remote-hh-dat runremote)) ;; on homehost
(member cmd api:read-only-queries)) ;; this is a read
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 3")
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 5")
(rmt:open-qry-close-locally cmd 0 params))
;;DOT CASE6 [label="init\nremote"];
;;DOT MUTEXLOCK -> CASE6 [label="on homehost,\nwrite query,\nhave server,\ncan't reach it"]; {rank=same "case 6" CASE6};
;;DOT CASE6 -> "rmt:send-receive";
;; on homehost and this is a write, we already have a server, but server has died
((and (cdr (remote-hh-dat runremote)) ;; on homehost
(not (member cmd api:read-only-queries)) ;; this is a write
(remote-server-url runremote) ;; have a server
(not (server:ping (remote-server-url runremote)))) ;; server has died. NOTE: this is not a cheap call! Need better approach.
;; on homehost and this is a write, we already have a server, but server has died
((and (cdr (remote-hh-dat runremote)) ;; on homehost
(not (member cmd api:read-only-queries)) ;; this is a write
(remote-server-url runremote) ;; have a server
(not (server:check-if-running *toppath*))) ;; server has died.
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 4.1")
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 6")
(rmt:send-receive cmd rid params attemptnum: attemptnum))
;;DOT CASE7 [label="homehost\nwrite"];
;;DOT MUTEXLOCK -> CASE7 [label="server not required,\non homehost,\na write,\nhave a server"]; {rank=same "case 7" CASE7};
;;DOT CASE7 -> "rmt:open-qry-close-locally";
;; on homehost and this is a write, we already have a server
((and (not (remote-force-server runremote)) ;; honor forced use of server, i.e. server NOT required
((and (cdr (remote-hh-dat runremote)) ;; on homehost
(remote-server-url runremote)) ;; have a server
(remote-server-url runremote)) ;; have a server
(mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 4")
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 4.1")
(rmt:open-qry-close-locally cmd 0 params))
;;DOT CASE8 [label="force\nserver"];
;;DOT MUTEXLOCK -> CASE8 [label="server not required,\nhave homehost info,\nno connection yet,\nnot a read-only query"]; {rank=same "case 8" CASE8};
;;DOT CASE8 -> "rmt:open-qry-close-locally";
;; on homehost, no server contact made and this is a write, passively start a server
((and (not (remote-force-server runremote)) ;; honor forced use of server, i.e. server NOT required
((and (cdr (remote-hh-dat runremote)) ; new
(not (remote-server-url runremote))
(not (member cmd api:read-only-queries)))
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 5")
(server:kind-run *toppath*)))
(server:kind-run *toppath*))))
(remote-force-server-set! runremote (common:force-server?))
(mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 5.1")
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 8.1")
(rmt:open-qry-close-locally cmd 0 params))
;;DOT CASE9 [label="force server\nnot on homehost"];
;;DOT MUTEXLOCK -> CASE9 [label="no connection\nand either require server\nor not on homehost"]; {rank=same "case 9" CASE9};
;;DOT CASE9 -> "start\nserver" -> "rmt:send-receive";
((or (and (remote-force-server runremote) ;; we are forcing a server and don't yet have a connection to one
(not (remote-conndat runremote)))
((and (not (cdr (remote-hh-dat runremote))) ;; not on a homehost
(not (remote-conndat runremote))) ;; and no connection
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 6 hh-dat: " (remote-hh-dat runremote) " conndat: " (remote-conndat runremote))
(server:start-and-wait *toppath*)
((cdr (remote-hh-dat runremote)) ;; we are on homehost
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 7")
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 10")
(rmt:open-qry-close-locally cmd (if rid rid 0) params))
;;DOT CASE11 [label="send_receive"];
;;DOT MUTEXLOCK -> CASE11 [label="else"]; {rank=same "case 11" CASE11};
;;DOT CASE11 -> "rmt:send-receive" [label="call failed"];
;;DOT CASE11 -> "RESULT" [label="call succeeded"];
;; not on homehost, do server query
(else
(mutex-unlock! *rmt-mutex*)
;; (mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 9")
(mutex-lock! *rmt-mutex*)
;; (mutex-lock! *rmt-mutex*)
(let* ((conninfo (remote-conndat runremote))
(dat (case (remote-transport runremote)
((http) (condition-case ;; handling here has caused a lot of problems. However it is needed to deal with attemtped communication to servers that have gone away
(http-transport:client-api-send-receive 0 conninfo cmd params)
((commfail)(vector #f "communications fail"))
((exn)(vector #f "other fail" (print-call-chain)))))
(else
(debug:print 0 *default-log-port* "ERROR: transport " (remote-transport runremote) " not supported")
(exit))))
(success (if (vector? dat) (vector-ref dat 0) #f))
(res (if (vector? dat) (vector-ref dat 1) #f)))
(if (and (vector? conninfo) (< 5 (vector-length conninfo)))
(if (vector? conninfo)(http-transport:server-dat-update-last-access conninfo)) ;; refresh access time
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 9. conninfo=" conninfo " dat=" dat " runremote = "runremote)
(debug:print-info 13 *default-log-port* "rmt:send-receive, case 9. conninfo=" conninfo " dat=" dat " runremote = " runremote)
(if success
(case (remote-transport runremote)
((http)
(mutex-unlock! *rmt-mutex*)
res)
(else
(debug:print 0 *default-log-port* "ERROR: transport " (remote-transport runremote) " is unknown")
(mutex-unlock! *rmt-mutex*)
(exit 1)))
(remote-conndat-set! runremote #f)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 9.1")
(server:start-and-wait *toppath*)
;; (server:start-and-wait *toppath*))
(rmt:send-receive cmd rid params attemptnum: (+ attemptnum 1)))))))))
;;DOT }
;; (define (rmt:update-db-stats run-id rawcmd params duration)
;; (mutex-lock! *db-stats-mutex*)
;; (handle-exceptions
;; exn
;; (begin
;; (debug:print 0 *default-log-port* "WARNING: stats collection failed in update-db-stats")
;; (debug:print 0 *default-log-port* " message: " ((condition-property-accessor 'exn 'message) exn))
|
725
726
727
728
729
730
731
732
733
734
735
736
737
738
|
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
|
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
|
(rmt:send-receive 'tasks-add #f (list action owner target runname testpatt params)))
(define (rmt:tasks-set-state-given-param-key param-key new-state)
(rmt:send-receive 'tasks-set-state-given-param-key #f (list param-key new-state)))
(define (rmt:tasks-get-last target runname)
(rmt:send-receive 'tasks-get-last #f (list target runname)))
;;======================================================================
;; N O S Y N C D B
;;======================================================================
(define (rmt:no-sync-set var val)
(rmt:send-receive 'no-sync-set #f `(,var ,val)))
(define (rmt:no-sync-get/default var default)
(rmt:send-receive 'no-sync-get/default #f `(,var ,default)))
(define (rmt:no-sync-del! var)
(rmt:send-receive 'no-sync-del! #f `(,var)))
(define (rmt:no-sync-get-lock keyname)
(rmt:send-receive 'no-sync-get-lock #f `(,keyname)))
;;======================================================================
;; A R C H I V E S
;;======================================================================
(define (rmt:archive-get-allocations testname itempath dneeded)
(rmt:send-receive 'archive-get-allocations #f (list testname itempath dneeded)))
|