Megatest

Diff
Login

Differences From Artifact [6319f7b685]:

To Artifact [c83e2578f6]:


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

	     ;; get_next_port goes here
	     (http-transport:try-start-server run-id
					      ipaddrstr
					      (portlogger:open-run-close portlogger:find-port)
					      server-id))
	   (begin

	     (tasks:server-force-clean-run-record (tasks:get-db) run-id ipaddrstr portnum " http-transport:try-start-server")
	     (print "ERROR: Tried and tried but could not start the server"))))
     ;; any error in following steps will result in a retry
     (set! *server-info* (list ipaddrstr portnum))

     (tasks:server-set-interface-port 
		     (tasks:get-db)
		     server-id 
		     ipaddrstr portnum)
     (debug:print 0 "INFO: Trying to start server on " ipaddrstr ":" portnum)
     ;; This starts the spiffy server
     ;; NEED WAY TO SET IP TO #f TO BIND ALL
     ;; (start-server bind-address: ipaddrstr port: portnum)
     (if config-hostname ;; this is a hint to bind directly
	 (start-server port: portnum bind-address: (if (equal? config-hostname "-")
						       ipaddrstr
						       config-hostname))
	 (start-server port: portnum))
     ;;  (portlogger:open-run-close portlogger:set-port portnum "released")

     (tasks:server-force-clean-run-record (tasks:get-db) run-id ipaddrstr portnum " http-transport:try-start-server")
     (debug:print 1 "INFO: server has been stopped"))))

;;======================================================================
;; S E R V E R   U T I L I T I E S 
;;======================================================================








>




>














>







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

	     ;; get_next_port goes here
	     (http-transport:try-start-server run-id
					      ipaddrstr
					      (portlogger:open-run-close portlogger:find-port)
					      server-id))
	   (begin
	     (tasks:wait-on-busy-monitor.db)
	     (tasks:server-force-clean-run-record (tasks:get-db) run-id ipaddrstr portnum " http-transport:try-start-server")
	     (print "ERROR: Tried and tried but could not start the server"))))
     ;; any error in following steps will result in a retry
     (set! *server-info* (list ipaddrstr portnum))
     (tasks:wait-on-busy-monitor.db)
     (tasks:server-set-interface-port 
		     (tasks:get-db)
		     server-id 
		     ipaddrstr portnum)
     (debug:print 0 "INFO: Trying to start server on " ipaddrstr ":" portnum)
     ;; This starts the spiffy server
     ;; NEED WAY TO SET IP TO #f TO BIND ALL
     ;; (start-server bind-address: ipaddrstr port: portnum)
     (if config-hostname ;; this is a hint to bind directly
	 (start-server port: portnum bind-address: (if (equal? config-hostname "-")
						       ipaddrstr
						       config-hostname))
	 (start-server port: portnum))
     ;;  (portlogger:open-run-close portlogger:set-port portnum "released")
     (tasks:wait-on-busy-monitor.db)
     (tasks:server-force-clean-run-record (tasks:get-db) run-id ipaddrstr portnum " http-transport:try-start-server")
     (debug:print 1 "INFO: server has been stopped"))))

;;======================================================================
;; S E R V E R   U T I L I T I E S 
;;======================================================================

254
255
256
257
258
259
260

261
262
263
264
265
266
267
	    exn
	    (debug:print 0 "WARNING: closing connections failed. Server at " fullurl " almost certainly dead")
	    (close-all-connections!))
	   (debug:print 0 "WARNING: Failed to communicate with server, trying again, numretries left: " numretries)
	   (http-transport:client-api-send-receive run-id serverdat cmd params numretries: (- numretries 1)))
	 (begin
	   (mutex-unlock! *http-mutex*)

	   (tasks:kill-server-run-id run-id)
	   #f))
     (begin
       (debug:print-info 11 "fullurl=" fullurl ", cmd=" cmd ", params=" params ", run-id=" run-id "\n")
       ;; set up the http-client here
       (max-retry-attempts 1)
       ;; consider all requests indempotent







>







257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
	    exn
	    (debug:print 0 "WARNING: closing connections failed. Server at " fullurl " almost certainly dead")
	    (close-all-connections!))
	   (debug:print 0 "WARNING: Failed to communicate with server, trying again, numretries left: " numretries)
	   (http-transport:client-api-send-receive run-id serverdat cmd params numretries: (- numretries 1)))
	 (begin
	   (mutex-unlock! *http-mutex*)
	   (tasks:wait-on-busy-monitor.db)
	   (tasks:kill-server-run-id run-id)
	   #f))
     (begin
       (debug:print-info 11 "fullurl=" fullurl ", cmd=" cmd ", params=" params ", run-id=" run-id "\n")
       ;; set up the http-client here
       (max-retry-attempts 1)
       ;; consider all requests indempotent
367
368
369
370
371
372
373

374
375
376
377
378
379
380
			      sdat
                              (begin
				(debug:print-info 0 "Still waiting, last-sdat=" last-sdat)
                                (sleep 4)
				(if (> (- (current-seconds) start-time) 120) ;; been waiting for two minutes
				    (let ((tdb  (tasks:open-db)))
				      (debug:print 0 "ERROR: transport appears to have died, exiting server " server-id " for run " run-id)

				      (tasks:server-delete-record tdb server-id "failed to start, never received server alive signature")
				      (sqlite3:finalize! tdb)
				      (exit))
				    (loop start-time
					  (equal? sdat last-sdat)
					  sdat)))))))
         (iface       (car server-info))







>







371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
			      sdat
                              (begin
				(debug:print-info 0 "Still waiting, last-sdat=" last-sdat)
                                (sleep 4)
				(if (> (- (current-seconds) start-time) 120) ;; been waiting for two minutes
				    (let ((tdb  (tasks:open-db)))
				      (debug:print 0 "ERROR: transport appears to have died, exiting server " server-id " for run " run-id)
				      (tasks:wait-on-busy-monitor.db)
				      (tasks:server-delete-record tdb server-id "failed to start, never received server alive signature")
				      (sqlite3:finalize! tdb)
				      (exit))
				    (loop start-time
					  (equal? sdat last-sdat)
					  sdat)))))))
         (iface       (car server-info))
402
403
404
405
406
407
408

409
410
411
412
413
414
415
	(debug:print 2 "SYNC: time= " sync-time ", rem-time=" rem-time)

      ;;
      ;; set_running after our first pass through and start the db
      ;;
      (if (eq? server-state 'available)
	  (begin

	    (tasks:server-set-state! tdb server-id "dbprep")
	    (thread-sleep! 5) ;; give some margin for queries to complete before switching from file based access to server based access
	    (set! *inmemdb*  (db:setup run-id))
	    (tasks:server-set-state! tdb server-id "running")))

      (if (and (<= rem-time 4)
	       (> rem-time 0))







>







407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
	(debug:print 2 "SYNC: time= " sync-time ", rem-time=" rem-time)

      ;;
      ;; set_running after our first pass through and start the db
      ;;
      (if (eq? server-state 'available)
	  (begin
	    (tasks:wait-on-busy-monitor.db)
	    (tasks:server-set-state! tdb server-id "dbprep")
	    (thread-sleep! 5) ;; give some margin for queries to complete before switching from file based access to server based access
	    (set! *inmemdb*  (db:setup run-id))
	    (tasks:server-set-state! tdb server-id "running")))

      (if (and (<= rem-time 4)
	       (> rem-time 0))
461
462
463
464
465
466
467

468
469
470
471
472
473
474
	    ;;     (tasks:server-set-state! tdb server-id "running"))
	    ;;
	    (loop 0 server-state))
	  (begin
	    (debug:print-info 0 "Starting to shutdown the server.")
	    ;; need to delete only *my* server entry (future use)
	    (set! *time-to-exit* #t)

	    (if *inmemdb* (db:sync-touched *inmemdb* *run-id* force-sync: #t))
	    ;;
	    ;; start_shutdown
	    ;;
	    (tasks:server-set-state! tdb server-id "shutting-down")
	    (portlogger:open-run-close portlogger:set-port port "released")
	    (thread-sleep! 5)







>







467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
	    ;;     (tasks:server-set-state! tdb server-id "running"))
	    ;;
	    (loop 0 server-state))
	  (begin
	    (debug:print-info 0 "Starting to shutdown the server.")
	    ;; need to delete only *my* server entry (future use)
	    (set! *time-to-exit* #t)
	    (tasks:wait-on-busy-monitor.db) ;; wait here in addition to just before the shutting-down
	    (if *inmemdb* (db:sync-touched *inmemdb* *run-id* force-sync: #t))
	    ;;
	    ;; start_shutdown
	    ;;
	    (tasks:server-set-state! tdb server-id "shutting-down")
	    (portlogger:open-run-close portlogger:set-port port "released")
	    (thread-sleep! 5)
484
485
486
487
488
489
490

491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510

511
512
513
514
515
516

517
518
519
520
521

522
523
524
525
526
527
528
	    (debug:print-info 0 "Average non-cached time   "
			      (if (eq? *number-non-write-queries* 0)
				  "n/a (no queries)"
				  (/ *total-non-write-delay* 
				     *number-non-write-queries*))
			      " ms")
	    (debug:print-info 0 "Server shutdown complete. Exiting")

	    (tasks:server-delete-record tdb server-id " http-transport:keep-running")
	    (exit))))))

;; all routes though here end in exit ...
;;
;; start_server? 
;;
(define (http-transport:launch run-id)
  (set! *run-id*   run-id)
  (if (args:get-arg "-daemonize")
      (begin
	(daemon:ize)
	(if *alt-log-file* ;; we should re-connect to this port, I think daemon:ize disrupts it
	    (begin
	      (current-error-port *alt-log-file*)
	      (current-output-port *alt-log-file*)))))
  (if (server:check-if-running run-id)
      (begin
	(debug:print 0 "INFO: Server for run-id " run-id " already running")
	(exit 0)))

  (let loop ((server-id (tasks:server-lock-slot (tasks:get-db) run-id))
	     (remtries  4))
    (if (not server-id)
	(if (> remtries 0)
	    (begin
	      (thread-sleep! 2)

	      (loop (tasks:server-lock-slot (tasks:get-db) run-id)
		    (- remtries 1)))
	    (begin
	      ;; since we didn't get the server lock we are going to clean up and bail out
	      (debug:print-info 2 "INFO: server pid=" (current-process-id) ", hostname=" (get-host-name) " not starting due to other candidates ahead in start queue")

	      (tasks:server-delete-records-for-this-pid (tasks:get-db) " http-transport:launch")
	      ))
	(let* ((th2 (make-thread (lambda ()
				   (debug:print-info 0 "Server run thread started")
				   (http-transport:run 
				    (if (args:get-arg "-server")
					(args:get-arg "-server")







>




















>






>





>







491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
	    (debug:print-info 0 "Average non-cached time   "
			      (if (eq? *number-non-write-queries* 0)
				  "n/a (no queries)"
				  (/ *total-non-write-delay* 
				     *number-non-write-queries*))
			      " ms")
	    (debug:print-info 0 "Server shutdown complete. Exiting")
	    (tasks:wait-on-busy-monitor.db)
	    (tasks:server-delete-record tdb server-id " http-transport:keep-running")
	    (exit))))))

;; all routes though here end in exit ...
;;
;; start_server? 
;;
(define (http-transport:launch run-id)
  (set! *run-id*   run-id)
  (if (args:get-arg "-daemonize")
      (begin
	(daemon:ize)
	(if *alt-log-file* ;; we should re-connect to this port, I think daemon:ize disrupts it
	    (begin
	      (current-error-port *alt-log-file*)
	      (current-output-port *alt-log-file*)))))
  (if (server:check-if-running run-id)
      (begin
	(debug:print 0 "INFO: Server for run-id " run-id " already running")
	(exit 0)))
  (tasks:wait-on-busy-monitor.db)
  (let loop ((server-id (tasks:server-lock-slot (tasks:get-db) run-id))
	     (remtries  4))
    (if (not server-id)
	(if (> remtries 0)
	    (begin
	      (thread-sleep! 2)
	      (tasks:wait-on-busy-monitor.db)
	      (loop (tasks:server-lock-slot (tasks:get-db) run-id)
		    (- remtries 1)))
	    (begin
	      ;; since we didn't get the server lock we are going to clean up and bail out
	      (debug:print-info 2 "INFO: server pid=" (current-process-id) ", hostname=" (get-host-name) " not starting due to other candidates ahead in start queue")
	      (tasks:wait-on-busy-monitor.db)
	      (tasks:server-delete-records-for-this-pid (tasks:get-db) " http-transport:launch")
	      ))
	(let* ((th2 (make-thread (lambda ()
				   (debug:print-info 0 "Server run thread started")
				   (http-transport:run 
				    (if (args:get-arg "-server")
					(args:get-arg "-server")