19
20
21
22
23
24
25
26
27
28
29
30
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
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
|
;;======================================================================
(use format typed-records) ;; RADT => purpose of json format??
(declare (unit rmt))
(declare (uses api))
(declare (uses http-transport))
(declare (uses dbfile))
(include "common_records.scm")
;; (declare (uses rmtmod))
(import dbfile) ;; rmtmod)
;;
;; THESE ARE ALL CALLED ON THE CLIENT SIDE!!!
;;
;; generate entries for ~/.megatestrc with the following
;;
;; grep define ../rmt.scm | grep rmt: |perl -pi -e 's/\(define\s+\((\S+)\W.*$/\1/'|sort -u
;;======================================================================
;; S U P P O R T F U N C T I O N S
;;======================================================================
;; 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)
(remote-conndat runremote)
#f)))
(if cinfo
cinfo
(if (server:check-if-running areapath)
(client:setup areapath)
#f))))
(define (rmt:on-homehost? runremote)
(let* ((hh-dat (remote-hh-dat runremote)))
(if (pair? hh-dat)
(cdr hh-dat)
(begin
(debug:print-info 0 *default-log-port* "hh-dat="hh-dat)
#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
#;(common:telemetry-log (conc "rmt:"(->string cmd))
payload: `((rid . ,rid)
(params . ,params)))
(if (> attemptnum 2)
(debug:print 0 *default-log-port* "INFO: attemptnum in rmt:send-receive is " attemptnum))
(cond
((> attemptnum 2) (thread-sleep! 0.05))
((> attemptnum 10) (thread-sleep! 0.5))
((> attemptnum 20) (thread-sleep! 1)))
(if (and (> attemptnum 5) (= 0 (modulo attemptnum 15)))
(begin (server:run *toppath*) (thread-sleep! 3)))
;;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
(areapath *toppath*);; TODO - resolve from dbstruct to be compatible with multiple areas
(runremote (or area-dat
*runremote*))
(attemptnum (+ 1 attemptnum))
(readonly-mode (rmtmod:calc-ro-mode runremote *toppath*)))
;; 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))
(let* ((server-info (remote-server-info *runremote*)))
(if server-info
(begin
(remote-server-url-set! *runremote* (server:record->url server-info))
(remote-server-id-set! *runremote* (server:record->id server-info)))))
(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
(let ((hh-data (server:choose-server areapath 'homehost)))
(remote-hh-dat-set! runremote (or hh-data (cons #f #f)))))
;;(print "BB> readonly-mode is "readonly-mode" dbfile is "dbfile)
(cond
#;((> (- (current-seconds)(remote-connect-time runremote)) 180) ;; reconnect to server every 180 seconds
(debug:print 0 *default-log-port* "Forcing reconnect to server(s) due to 180 second timeout.")
(set! *runremote* #f)
;; BUG: close-connections should go here?
(mutex-unlock! *rmt-mutex*)
(rmt:send-receive cmd rid params attemptnum: 1 area-dat: area-dat))
;;DOT EXIT;
;;DOT MUTEXLOCK -> EXIT [label="> 15 attempts"]; {rank=same "case 1" "EXIT" }
;; give up if more than 150 attempts
((> attemptnum 150)
(debug:print 0 *default-log-port* "ERROR: 150 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 (extras-readonly-mode *rmt-mutex* *default-log-port* cmd params))
;; 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)
(> (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.")
(remote-conndat-set! runremote #f) ;; invalidate the connection, thus forcing a new connection.
(http-transport:close-connections area-dat: runremote)
(mutex-unlock! *rmt-mutex*)
(rmt:send-receive cmd rid params attemptnum: attemptnum))
;;DOT CASE5 [label="local\nread"];
;;DOT MUTEXLOCK -> CASE5 [label="server not required,\non homehost,\nread-only query"]; {rank=same "case 5" CASE5};
;;DOT CASE5 -> "rmt:open-qry-close-locally";
;; on homehost and this is a read
((and (not (remote-force-server runremote)) ;; honor forced use of server, i.e. server NOT required
(rmt:on-homehost? runremote)
(member cmd api:read-only-queries)) ;; this is a read
(mutex-unlock! *rmt-mutex*)
(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
;; reinstate this keep-alive section but inject a time condition into the (add ...
#;((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) (remote-server-id runremote)))) ;; server has died. NOTE: this is not a cheap call! Need better approach.
(debug:print 0 *default-log-port* "WARNING: server appears to have died, trying to reconnect, case 6")
(http-transport:close-connections area-dat: runremote) ;; make sure to clean up
(set! *runremote* (make-remote))
(let* ((server-info (remote-server-info *runremote*)))
(if server-info
(begin
(remote-server-url-set! *runremote* (server:record->url server-info))
(remote-server-id-set! *runremote* (server:record->id server-info)))))
(remote-force-server-set! runremote (common:force-server?))
(mutex-unlock! *rmt-mutex*)
(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
(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
(mutex-unlock! *rmt-mutex*)
(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
(cdr (remote-hh-dat runremote)) ;; have homehost
(not (remote-server-url runremote)) ;; no connection yet
(not (member cmd api:read-only-queries))) ;; not a read-only query
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 8")
(let ((server-info (server:check-if-running *toppath*))) ;; (server:read-dotserver->url *toppath*))) ;; (server:check-if-running *toppath*))) ;; Do NOT want to run server:check-if-running - very expensive to do for every write call
(if server-info
(begin
(remote-server-url-set! runremote (server:record->url server-info)) ;; the string can be consumed by the client setup if needed
(remote-server-id-set! runremote (server:record->id server-info)))
(if (common:force-server?)
(server:start-and-wait *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 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 9, hh-dat: " (remote-hh-dat runremote) " conndat: " (remote-conndat runremote))
(mutex-unlock! *rmt-mutex*)
(if (not (server:check-if-running *toppath*)) ;; who knows, maybe one has started up?
(server:start-and-wait *toppath*))
(remote-conndat-set! runremote (rmt:get-connection-info *toppath*)) ;; calls client:setup which calls client:setup-http
(rmt:send-receive cmd rid params attemptnum: attemptnum)) ;; TODO: add back-off timeout as
;;DOT CASE10 [label="on homehost"];
;;DOT MUTEXLOCK -> CASE10 [label="server not required,\non homehost"]; {rank=same "case 10" CASE10};
;;DOT CASE10 -> "rmt:open-qry-close-locally";
;; all set up if get this far, dispatch the query
((and (not (remote-force-server runremote))
(cdr (remote-hh-dat runremote))) ;; we are on homehost
(mutex-unlock! *rmt-mutex*)
(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 (extras-case-11 *default-log-port* runremote cmd params attemptnum rid)))))
;;DOT }
;; No Title
;; Error: (vector-ref) out of range
;; #(#<condition: (exn type)> (#("db.scm:3740: regex#regexp" #f #f) #("db.scm:3739: regex#string-substitute" #f #f) #("db.scm:3738: base64#base64-decode" #f #f) #("db.scm:3737: z3#z3:decode-buffer" #f #f) #("db.scm:3736: with-input-from-string" #f #f) #("db.scm:3741: s11n#deserialize" #f #f) #("api.scm:374: api:execute-requests" #f #f) #("api.scm:139: call-with-current-continuation" #f #f) #("api.scm:139: with-exception-handler" #f #f) #("api.scm:139: ##sys#call-with-values" #f #f) #("api.scm:158: string->symbol" #f #f) #("api.scm:160: current-milliseconds" #f #f) #("api.scm:161: dbr:dbstruct-read-only" #f #f) #("api.scm:139: k15" #f #f) #("api.scm:139: g19" #f #f) #("api.scm:142: get-call-chain" #f #f)) #("get-test-info-by-id" (1102 507299)))
;; 6
;;
;; Call history:
;;
;; http-transport.scm:306: thread-terminate!
;; http-transport.scm:307: debug:print-info
;; common_records.scm:235: debug:debug-mode
;; rmt.scm:259: k587
;; rmt.scm:259: g591
;; rmt.scm:276: http-transport:server-dat-update-last-access
;; http-transport.scm:364: current-seconds
;; rmt.scm:282: debug:print-info
;; common_records.scm:235: debug:debug-mode
;; rmt.scm:283: mutex-unlock!
;; rmt.scm:287: extras-transport-succeded <--
;; +-----------------------------------------------------------------------------+
;; | Exit Status : 70
;;
;; bunch of small functions factored out of send-receive to make debug easier
;;
(define (extras-case-11 *default-log-port* runremote cmd params attemptnum rid)
;; (mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 9")
;; (mutex-lock! *rmt-mutex*)
(let* ((conninfo (remote-conndat runremote))
(dat-in (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)
((servermismatch) (vector #f "Server id mismatch" ))
((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))))
(dat (if (and (vector? dat-in) ;; ... check it is a correct size
(> (vector-length dat-in) 1))
dat-in
(vector #f (conc "communications fail (type 2), dat-in=" dat-in))))
(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)))
(http-transport:server-dat-update-last-access conninfo) ;; refresh access time
(begin
(debug:print 0 *default-log-port* "INFO: Should not get here! conninfo=" conninfo)
(set! conninfo #f)
(remote-conndat-set! *runremote* #f) ;; NOTE: *runremote* is global copy of runremote. Purpose: factor out global.
(http-transport:close-connections area-dat: runremote)))
(debug:print-info 13 *default-log-port* "rmt:send-receive, case 9. conninfo=" conninfo " dat=" dat " runremote = " runremote)
(mutex-unlock! *rmt-mutex*)
(if success ;; success only tells us that the transport was
;; successful, have to examine the data to see if
;; there was a detected issue at the other end
(extras-transport-succeded *default-log-port* *rmt-mutex* attemptnum runremote res params rid cmd)
(begin
(debug:print-error 0 *default-log-port* " dat=" dat)
|
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
|
<
|
>
|
|
|
|
|
|
>
>
>
>
>
>
<
|
<
|
|
|
|
|
|
|
|
>
>
>
|
>
>
>
>
|
|
|
<
<
<
<
<
<
|
|
|
>
>
>
>
>
>
>
|
>
>
>
>
|
>
>
>
>
>
>
>
|
>
>
>
>
|
|
|
|
|
|
|
|
|
|
|
<
<
<
|
|
>
|
|
|
|
<
|
<
<
<
<
<
<
<
<
<
|
|
|
|
<
<
<
|
|
|
|
|
|
|
<
<
<
|
|
|
|
|
|
<
<
<
|
|
|
|
|
|
|
>
>
|
<
|
|
<
<
<
<
|
|
|
|
|
|
|
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
|
|
|
|
|
|
|
<
<
<
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
<
|
<
|
|
|
|
|
|
|
|
|
>
|
|
|
<
<
<
>
|
|
|
|
<
|
|
|
19
20
21
22
23
24
25
26
27
28
29
30
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
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
|
;;======================================================================
(use format typed-records) ;; RADT => purpose of json format??
(declare (unit rmt))
(declare (uses api))
(declare (uses http-transport))
(declare (uses commonmod))
(declare (uses dbfile))
;; (declare (uses dbmemmod))
(declare (uses dbmod))
(declare (uses tcp-transportmod))
(include "common_records.scm")
;; (declare (uses rmtmod))
;; used by http-transport
(import dbfile) ;; rmtmod)
(import commonmod
;; dbmemmod
dbfile
dbmod
tcp-transportmod)
;; http - use the old http + in /tmp db
;; tcp - use tcp transport with inmem db
;; nfs - use direct to disk access (read-only)
;;
(define rmt:transport-mode (make-parameter 'http))
;;
;; THESE ARE ALL CALLED ON THE CLIENT SIDE!!!
;;
;; generate entries for ~/.megatestrc with the following
;;
;; grep define ../rmt.scm | grep rmt: |perl -pi -e 's/\(define\s+\((\S+)\W.*$/\1/'|sort -u
;;======================================================================
;; S U P P O R T F U N C T I O N S
;;======================================================================
;; 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 runremote) ;; TODO: push areapath down.
(let* ((cinfo (if (and (remote? runremote)
(remote-api-url runremote)) ;; we have a connection
runremote
#f)))
(if cinfo
cinfo
(if (server:check-if-running areapath)
(client:setup areapath runremote)
#f))))
(define (rmt:on-homehost? runremote)
(let* ((hh-dat (remote-hh-dat runremote)))
(if (pair? hh-dat)
(cdr hh-dat)
(begin
(debug:print-info 0 *default-log-port* "hh-dat="hh-dat)
#f))))
(define (make-and-init-remote areapath)
(case (rmt:transport-mode)
((http)(make-remote))
((tcp) (tt:make-remote areapath))
(else #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
(assert *toppath* "FATAL: rmt:send-receive called with *toppath* not set.")
(if (not (eq? (rmt:transport-mode) 'nfs))
(begin
(if (> attemptnum 2)
(debug:print 0 *default-log-port* "INFO: attemptnum in rmt:send-receive is " attemptnum))
(cond
((> attemptnum 2) (thread-sleep! 0.05))
((> attemptnum 10) (thread-sleep! 0.5))
((> attemptnum 20) (thread-sleep! 1)))
;; I'm turning this off, it may make sense to move it
;; into http-transport-handler
(if (and (> attemptnum 5) (= 0 (modulo attemptnum 15)))
(begin
(debug:print 0 *default-log-port* "ERROR: can't connect to server, trying to start a server.")
(case (rmt:transport-mode)
((http)
(server:run *toppath*)
(thread-sleep! 3))
(else
(thread-sleep! 1) ;; for tcp the server is started by routines in tcp-transportmod. For nfs there is no server
))))))
;; 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
(areapath *toppath*);; TODO - resolve from dbstruct to be compatible with multiple areas
(runremote (or area-dat
*runremote*))
(attemptnum (+ 1 attemptnum))
(readonly-mode (rmtmod:calc-ro-mode runremote *toppath*))
(testsuite (common:get-testsuite-name))
(mtexe (common:find-local-megatest)))
(case (rmt:transport-mode)
((http)(http-transport-handler runremote cmd rid params attemptnum area-dat areapath readonly-mode))
((tcp) (tcp-transport-handler runremote cmd rid params attemptnum area-dat areapath readonly-mode testsuite mtexe))
((nfs) (nfs-transport-handler runremote cmd rid params attemptnum area-dat areapath readonly-mode testsuite mtexe))
)))
(define (nfs-transport-handler runremote cmd run-id params attemptnum area-dat areapath readonly-mode testsuite mtexe)
(let* ((keys (common:get-fields *configdat*))
(dbstruct (dbmod:nfs-get-dbstruct run-id keys (dbfile:db-init-proc) areapath)))
(api:dispatch-request dbstruct cmd run-id params)))
(define (tcp-transport-handler runremote cmd run-id params attemptnum area-dat areapath readonly-mode testsuite mtexe)
(if (not runremote)
(let* ((newremote (make-and-init-remote areapath)))
(set! *runremote* newremote)
(set! runremote newremote)))
(let* ((dbfname (conc (dbfile:run-id->dbnum run-id)".db"))) ;;(dbfile:run-id->path areapath run-id)))
(tt:handler runremote cmd run-id params attemptnum area-dat areapath readonly-mode dbfname testsuite mtexe)))
(define (http-transport-handler runremote cmd rid params attemptnum area-dat areapath readonly-mode)
;; do all the prep locked under the rmt-mutex
(mutex-lock! *rmt-mutex*)
;; 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-and-init-remote areapath))
(let* ((server-info (remote-server-info *runremote*)))
(if server-info
(begin
(remote-server-url-set! *runremote* (server:record->url server-info))
(remote-server-id-set! *runremote* (server:record->id server-info)))))
(set! runremote *runremote*))) ;; new runremote will come from this on next iteration
;; ensure we have a homehost record
(if (or (not (pair? (remote-hh-dat runremote))) ;; not on homehost
(not (cdr (remote-hh-dat runremote)))) ;; not on homehost
(thread-sleep! 0.1) ;; since we shouldn't get here, delay a little
(let ((hh-data (server:choose-server areapath 'homehost)))
(remote-hh-dat-set! runremote (or hh-data (cons #f #f)))))
(cond
;; give up if more than 150 attempts
((> attemptnum 150)
(debug:print 0 *default-log-port* "ERROR: 150 tries to start/connect to server. Giving up.")
(exit 1))
;; 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)
)
;; readonly mode, write request. Do nothing, return #f
(readonly-mode (extras-readonly-mode *rmt-mutex* *default-log-port* cmd params))
;; 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)
;;
;; reset the connection if it has been unused too long
((and runremote
(remote-api-url runremote)
(> (current-seconds) ;; if it has been more than server-timeout seconds since last contact, close this connection and start a new on
(+ (remote-last-access runremote)
(remote-server-timeout runremote))))
(debug:print-info 0 *default-log-port* "Connection to " (remote-server-url runremote) " expired due to no accesses in " (remote-server-timeout runremote) " seconds, forcing new connection.")
(http-transport:close-connections runremote)
;; moving this setting of runremote conndat to #f to inside the http-transport:close-connections
;; (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))
;; on homehost and this is a read
((and (not (remote-force-server runremote)) ;; honor forced use of server, i.e. server NOT required
(rmt:on-homehost? runremote)
(member cmd api:read-only-queries)) ;; this is a read
(mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 5")
(rmt:open-qry-close-locally cmd 0 params))
;; 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
(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 (needed to sync written data back)
(mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 4.1")
(rmt:open-qry-close-locally cmd 0 params))
;; 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
(cdr (remote-hh-dat runremote)) ;; have homehost
(not (remote-server-url runremote)) ;; no connection yet
(not (member cmd api:read-only-queries))) ;; not a read-only query
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 8")
(let ((server-info (server:check-if-running *toppath*))) ;; (server:read-dotserver->url *toppath*))) ;; (server:check-if-running *toppath*))) ;; Do NOT want to run server:check-if-running - very expensive to do for every write call
(if server-info
(begin
(remote-server-url-set! runremote (server:record->url server-info)) ;; the string can be consumed by the client setup if needed
(remote-server-id-set! runremote (server:record->id server-info)))
(if (common:force-server?)
(server:start-and-wait *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 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-api-url runremote)))
(and (not (cdr (remote-hh-dat runremote))) ;; not on a homehost
(not (remote-api-url runremote)))) ;; and no connection
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 9, hh-dat: " (remote-hh-dat runremote) " runremote: " (remote->alist runremote))
(mutex-unlock! *rmt-mutex*)
(if (not (server:check-if-running *toppath*)) ;; who knows, maybe one has started up?
(server:start-and-wait *toppath*))
;; was: (remote-conndat-set! runremote (rmt:get-connection-info *toppath* runremote)) ;; calls client:setup which calls client:setup-http
(set! runremote (rmt:get-connection-info *toppath* runremote)) ;; calls client:setup which calls client:setup-http
(rmt:send-receive cmd rid params attemptnum: attemptnum)) ;; TODO: add back-off timeout as
;;DOT CASE10 [label="on homehost"];
;;DOT MUTEXLOCK -> CASE10 [label="server not required,\non homehost"]; {rank=same "case 10" CASE10};
;;DOT CASE10 -> "rmt:open-qry-close-locally";
;; all set up if get this far, dispatch the query
((and (not (remote-force-server runremote))
(cdr (remote-hh-dat runremote))) ;; we are on homehost
(mutex-unlock! *rmt-mutex*)
(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 (extras-case-11 *default-log-port* runremote cmd params attemptnum rid))))
;; bunch of small functions factored out of send-receive to make debug easier
;;
(define (extras-case-11 *default-log-port* runremote cmd params attemptnum rid)
;; (mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 9")
;; (mutex-lock! *rmt-mutex*)
(let* (;; (conninfo (remote-conndat runremote))
(dat-in (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 runremote cmd params)
;; (http-transport:client-api-send-receive 0 conninfo cmd params runremote)
((servermismatch) (vector #f "Server id mismatch" ))
((commfail)(vector #f "communications fail"))
((exn)(vector #f "other fail" (print-call-chain)))))
(dat (if (and (vector? dat-in) ;; ... check it is a correct size
(> (vector-length dat-in) 1))
dat-in
(vector #f (conc "communications fail (type 2), dat-in=" dat-in))))
(success (if (vector? dat) (vector-ref dat 0) #f))
(res (if (vector? dat) (vector-ref dat 1) #f)))
(if (and (remote? runremote)
(remote-api-url runremote)) ;; (and (vector? conninfo) (< 5 (vector-length conninfo)))
(remote-last-access-set! runremote (current-seconds)) ;; refresh access time
(begin
(debug:print 0 *default-log-port* "INFO: Should not get here! runremote="(remote->alist runremote))
;; (set! conninfo #f)
(http-transport:close-connections runremote)))
(debug:print-info 13 *default-log-port* "rmt:send-receive, case 9. runremote=" (remote->alist runremote) " dat=" dat " runremote = " runremote)
(mutex-unlock! *rmt-mutex*)
(if success ;; success only tells us that the transport was
;; successful, have to examine the data to see if
;; there was a detected issue at the other end
(extras-transport-succeded *default-log-port* *rmt-mutex* attemptnum runremote res params rid cmd)
(begin
(debug:print-error 0 *default-log-port* " dat=" dat)
|
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
|
(define (rmt:test-set-archive-block-id run-id test-id archive-block-id)
(assert (number? run-id) "FATAL: Run id required.")
(rmt:send-receive 'test-set-archive-block-id run-id (list run-id test-id archive-block-id)))
(define (rmt:test-get-archive-block-info archive-block-id)
(rmt:send-receive 'test-get-archive-block-info #f (list archive-block-id)))
(define (rmtmod:calc-ro-mode runremote *toppath*)
(if (and runremote
(remote-ro-mode-checked runremote))
(remote-ro-mode runremote)
(let* ((mtcfgfile (conc *toppath* "/megatest.config"))
(ro-mode (not (file-write-access? mtcfgfile)))) ;; 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))))
(define (extras-readonly-mode rmt-mutex log-port cmd params)
(mutex-unlock! rmt-mutex)
(debug:print-info 12 log-port "rmt:send-receive, case 3")
(debug:print 0 log-port "WARNING: write transaction requested on a readonly area. cmd="cmd" params="params)
#f)
(define (extras-transport-failed *default-log-port* *rmt-mutex* attemptnum runremote cmd rid params)
(debug:print 0 *default-log-port* "WARNING: communication failed. Trying again, try num: " attemptnum)
(mutex-lock! *rmt-mutex*)
(remote-conndat-set! runremote #f)
(http-transport:close-connections area-dat: runremote)
(remote-server-url-set! runremote #f)
(mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 9.1")
(rmt:send-receive cmd rid params attemptnum: (+ attemptnum 1)))
(define (extras-transport-succeded *default-log-port* *rmt-mutex* attemptnum runremote res params rid cmd)
(if (and (vector? res)
(eq? (vector-length res) 2)
|
<
>
>
|
|
|
|
|
|
|
|
|
|
|
>
>
>
>
>
>
>
>
>
>
>
>
<
|
|
|
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
|
(define (rmt:test-set-archive-block-id run-id test-id archive-block-id)
(assert (number? run-id) "FATAL: Run id required.")
(rmt:send-receive 'test-set-archive-block-id run-id (list run-id test-id archive-block-id)))
(define (rmt:test-get-archive-block-info archive-block-id)
(rmt:send-receive 'test-get-archive-block-info #f (list archive-block-id)))
(define (rmtmod:calc-ro-mode runremote *toppath*)
(case (rmt:transport-mode)
((http)
(if (and runremote
(remote-ro-mode-checked runremote))
(remote-ro-mode runremote)
(let* ((mtcfgfile (conc *toppath* "/megatest.config"))
(ro-mode (not (file-write-access? mtcfgfile)))) ;; 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))))
((tcp)
(if (and runremote
(tt-ro-mode-checked runremote))
(tt-ro-mode runremote)
(let* ((mtcfgfile (conc *toppath* "/megatest.config"))
(ro-mode (not (file-write-access? mtcfgfile)))) ;; TODO: use dbstruct or runremote to figure this out in future
(if runremote
(begin
(tt-ro-mode-set! runremote ro-mode)
(tt-ro-mode-checked-set! runremote #t)
ro-mode)
ro-mode))))))
(define (extras-readonly-mode rmt-mutex log-port cmd params)
(mutex-unlock! rmt-mutex)
(debug:print-info 12 log-port "rmt:send-receive, case 3")
(debug:print 0 log-port "WARNING: write transaction requested on a readonly area. cmd="cmd" params="params)
#f)
(define (extras-transport-failed *default-log-port* *rmt-mutex* attemptnum runremote cmd rid params)
(debug:print 0 *default-log-port* "WARNING: communication failed. Trying again, try num: " attemptnum)
(mutex-lock! *rmt-mutex*)
(http-transport:close-connections runremote)
;; (remote-server-url-set! runremote #f)
(mutex-unlock! *rmt-mutex*)
(debug:print-info 12 *default-log-port* "rmt:send-receive, case 9.1")
(rmt:send-receive cmd rid params attemptnum: (+ attemptnum 1)))
(define (extras-transport-succeded *default-log-port* *rmt-mutex* attemptnum runremote res params rid cmd)
(if (and (vector? res)
(eq? (vector-length res) 2)
|