Overview
Comment: | make client:setup honor transport specified in server table; not global version; incidentally may have found/corrected an endless loop where client:setup-http retries would be infinite, not decrementing from 20 (client:setup did not pass remaining-tries to client:setup-http); also client:setup-http, making killing off a running server that doesnt respond more aggressive (now a kill-9). ; these last two may want to go in mainline. |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | rpc-transport |
Files: | files | file ages | folders |
SHA1: |
e851c26e615c06c9da0e97003de939c2 |
User & Date: | bjbarcla on 2016-11-01 00:32:56 |
Other Links: | branch diff | manifest | tags |
Context
2016-11-01
| ||
00:56 | did a little tidying up check-in: febd54396c user: bjbarcla tags: rpc-transport | |
00:32 | make client:setup honor transport specified in server table; not global version; incidentally may have found/corrected an endless loop where client:setup-http retries would be infinite, not decrementing from 20 (client:setup did not pass remaining-tries to client:setup-http); also client:setup-http, making killing off a running server that doesnt respond more aggressive (now a kill-9). ; these last two may want to go in mainline. check-in: e851c26e61 user: bjbarcla tags: rpc-transport | |
2016-10-26
| ||
21:47 | got port to listen. still wonky -- accepts connections but response is never seen. also when server times out -- stack dump instead of graceful exit check-in: d0162a768f user: bjbarcla tags: rpc-transport | |
Changes
Modified client.scm from [c5821d20e2] to [273ab1265b].
︙ | |||
46 47 48 49 50 51 52 | 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 | - - + + + + + + + + + + + + + + + + + + + + + + + + - - + + + + + + + + + + + + + + + + + + + + + + + + + + | (define (client:connect iface port) (case (server:get-transport) ((rpc) (rpc:client-connect iface port)) ((http) (http:client-connect iface port)) ((zmq) (zmq:client-connect iface port)) (else (rpc:client-connect iface port)))) |
︙ | |||
93 94 95 96 97 98 99 | 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 | - + | ;; (thread-sleep! 5) ;; (client:setup run-id remaining-tries: 10)) ;; (- remaining-tries 1))) ;; (begin ;; (debug:print 25 *default-log-port* "INFO: client:setup failed to connect, start-res=" start-res ", run-id=" run-id ", host-info=" host-info) ;; (thread-sleep! 5) ;; (client:setup run-id remaining-tries: (- remaining-tries 1)))))) ;; ;; YUK: rename server-dat here |
︙ | |||
150 151 152 153 154 155 156 | 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 | - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - | ;; 2. We are a run tests, list runs or other interactive process and we must figure out ;; *transport-type* and *runremote* from the monitor.db ;; ;; client:setup ;; ;; lookup_server, need to remove *runremote* stuff ;; |
︙ |
Modified rmt.scm from [bb562bf1d7] to [ef5e4d35bf].
︙ | |||
79 80 81 82 83 84 85 | 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 | - + | ;; clean out old connections ;; (mutex-lock! *db-multi-sync-mutex*) (let ((expire-time (- (current-seconds) (server:get-timeout) 10))) ;; don't forget the 10 second margin (for-each (lambda (run-id) (let ((connection (hash-table-ref/default *runremote* run-id #f))) (if (and (vector? connection) |
︙ | |||
104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 | 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 | + - + - + + - + | ((http)(condition-case (http-transport:client-api-send-receive run-id connection-info cmd params) ((commfail)(vector #f "communications fail")) ((exn)(vector #f "other fail")))) ;; ((nmsg)(condition-case ;; (nmsg-transport:client-api-send-receive run-id connection-info cmd params) ;; ((timeout)(vector #f "timeout talking to server")))) ((rpc) (rpc-transport:client-api-send-receive run-id connection-info cmd params)) (else (exit)))) (success (if (vector? dat) (vector-ref dat 0) #f)) (res (if (vector? dat) (vector-ref dat 1) #f))) (if (vector? connection-info)(http-transport:server-dat-update-last-access connection-info)) (if success (begin ;; (mutex-unlock! *send-receive-mutex*) (case *transport-type* |
︙ |
Modified rpc-transport.scm from [c9788c2658] to [702db23fbc].
︙ | |||
190 191 192 193 194 195 196 | 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 | - + | (let ((server-dat (list iface port #f #f #f))) (hash-table-set! *runremote* run-id server-dat) server-dat) (begin (server:try-running run-id) (thread-sleep! 2) (rpc-transport:client-setup run-id (- remtries 1))))) |
︙ |
Modified server.scm from [281247cf14] to [12fee161db].
︙ | |||
70 71 72 73 74 75 76 | 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 | - + | (or (args:get-arg "-transport") (configf:lookup *configdat* "server" "transport") "http")))) (set! *transport-type* ttype) ttype)) ;; Get the transport |
︙ | |||
183 184 185 186 187 188 189 | 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 | - + | (define (server:try-running run-id) (if (eq? run-id 0) (server:run run-id) (rmt:start-server run-id))) (define (server:check-if-running run-id) (let ((tdbdat (tasks:open-db))) |
︙ | |||
218 219 220 221 222 223 224 | 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 | - + | (define (server:ping run-id host:port) (let ((tdbdat (tasks:open-db))) (let* ((host-port (let ((slst (string-split host:port ":"))) (if (eq? (length slst) 2) (list (car slst)(string->number (cadr slst))) #f))) (toppath (launch:setup)) |
︙ |
Modified tasks.scm from [4abcc42496] to [b6453842af].
︙ | |||
325 326 327 328 329 330 331 | 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 | + + + + + + + + + + + + + + + - + - + - + - - + + | (lambda (a . b) (set! res (cons (apply vector a b) res))) mdb (conc "SELECT " selstr " FROM servers WHERE run_id=? AND state in ('available','running','dbprep') ORDER BY start_time DESC;") run-id) (vector header res))) ;; BB> bb opinion - want to push responsibility into api (encapsulation), like waiting if db is busy and finding the db handle in the first place. why should the caller need to be concerned?? If my opinion carries, we'll remove the bb- and make other needful adjustments. (define (bb-mdb-inserter mdb-expecting-proc mdbless-args) (let ((mdb (db:delay-if-busy (tasks:open-db)))) (apply mdb-expecting-proc (cons mdb args)))) (define (tasks:bb-get-server-info . args) (bb-mdb-inserter tasks:get-server-info args)) (define (tasks:bb-num-in-available-state . args) (bb-mdb-inserter tasks:num-in-available-state args)) ;; BB: renaming tasks:get-server to get-server-info to make clear we aren't creating servers here |
︙ | |||
392 393 394 395 396 397 398 | 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 | - + - + | ;; (else ;; #f)))) ;; try to start a server and wait for it to be available ;; (define (tasks:start-and-wait-for-server tdbdat run-id delay-max-tries) ;; ensure a server is running for this run |
︙ | |||
441 442 443 444 445 446 447 | 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 | - + - + | (unsetenv "TARGETHOST_LOGF") (unsetenv "TARGETHOST")) ;; look up a server by run-id and send it a kill, also delete the record for that server ;; (define (tasks:kill-server-run-id run-id #!key (tag "default")) (let* ((tdbdat (tasks:open-db)) |
︙ |