Megatest

Check-in [22f2c33711]
Login
Overview
Comment:last of overt connection issues addressed. TCP connections growing very slowly. However now the db issues are manifesting.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | v1.80-transport-cleanish | v1.80-refactor
Files: files | file ages | folders
SHA1: 22f2c337119577ef0e97e6805926030e324d6df3
User & Date: matt on 2023-01-16 12:17:40
Other Links: branch diff | manifest | tags
Context
2023-01-16
14:09
Cleaned up prepared db statements handling. check-in: 2639de81a8 user: matt tags: v1.80-refactor
12:17
last of overt connection issues addressed. TCP connections growing very slowly. However now the db issues are manifesting. check-in: 22f2c33711 user: matt tags: v1.80-transport-cleanish, v1.80-refactor
10:00
Major refactor/clean up of client connection stuff. Removed old crufty approach of having both client and server side calls in http-transport. Plan would be to eventually get rid of http-transport.

Open files slowly grows. bad argument type in http-transport. Line 285 (close-connection! fullurl) is wrong. check-in: 67b18cc991 user: matt tags: v1.80-refactor

Changes

Modified client.scm from [c0f004bcfc] to [754a2985af].

120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
		     (if ping-res
			 (if runremote
			     (begin
			       (debug:print-info 2 *default-log-port* "connected to " (client:get-url runremote))
			       runremote)
			     (client:setup-http areapath runremote remaining-tries: (- remaining-tries 1)))
			 (begin    ;; login failed but have a server record, clean out the record and try again
			   (debug:print-info 0 *default-log-port* "client:setup, login unsuccessful, will attempt to start server ... start-res=" start-res ", server-dat=" server-dat) ;; had runid.  Fixes part of Randy;s ticket 1405717332
			   (http-transport:close-connections runremote)
			   (thread-sleep! 1)
			   (client:setup-http-baby areapath runremote remaining-tries: (- remaining-tries 1))
			   )))
		   (begin    ;; no server registered
		     ;; (server:kind-run areapath)
		     (server:start-and-wait areapath)
		     (debug:print-info 0 *default-log-port* "client:setup, no server registered, remaining-tries=" remaining-tries)
		     (thread-sleep! 1) ;; (+ 5 (random (- 20 remaining-tries))))  ;; give server a little time to start up, randomize a little to avoid start storms.
		     (client:setup-http areapath runremote remaining-tries: (- remaining-tries 1)))))







|


|







120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
		     (if ping-res
			 (if runremote
			     (begin
			       (debug:print-info 2 *default-log-port* "connected to " (client:get-url runremote))
			       runremote)
			     (client:setup-http areapath runremote remaining-tries: (- remaining-tries 1)))
			 (begin    ;; login failed but have a server record, clean out the record and try again
			   (debug:print-info 0 *default-log-port* "client:setup, login unsuccessful, will attempt to start server ... ping-res=" ping-res) ;; had runid.  Fixes part of Randy;s ticket 1405717332
			   (http-transport:close-connections runremote)
			   (thread-sleep! 1)
			   (client:setup-http areapath runremote remaining-tries: (- remaining-tries 1))
			   )))
		   (begin    ;; no server registered
		     ;; (server:kind-run areapath)
		     (server:start-and-wait areapath)
		     (debug:print-info 0 *default-log-port* "client:setup, no server registered, remaining-tries=" remaining-tries)
		     (thread-sleep! 1) ;; (+ 5 (random (- 20 remaining-tries))))  ;; give server a little time to start up, randomize a little to avoid start storms.
		     (client:setup-http areapath runremote remaining-tries: (- remaining-tries 1)))))

Modified http-transport.scm from [7539e23e31] to [5e153aef1a].

278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
                                                      (debug:print 0 *default-log-port* "WARNING: failure in with-input-from-request to " fullurl ".")
                                                      (debug:print 0 *default-log-port* " message: " msg ", exn=" exn)
                                                      (debug:print 0 *default-log-port* " cmd: " cmd " params: " params " key:" (or server-id "thekey"))
                                                      (debug:print 0 *default-log-port* " call-chain: " call-chain)))
						;; what if another thread is communicating ok? Can't happen due to mutex
						(http-transport:close-connections runremote)
						(mutex-unlock! *http-mutex*)
						(close-connection! fullurl)
						(db:obj->string #f))
					      (with-input-from-request ;; was dat
					       fullurl 
					       (list (cons 'key (or server-id   "thekey"))
						     (cons 'cmd cmd)
						     (cons 'params sparams))
					       read-string))







|







278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
                                                      (debug:print 0 *default-log-port* "WARNING: failure in with-input-from-request to " fullurl ".")
                                                      (debug:print 0 *default-log-port* " message: " msg ", exn=" exn)
                                                      (debug:print 0 *default-log-port* " cmd: " cmd " params: " params " key:" (or server-id "thekey"))
                                                      (debug:print 0 *default-log-port* " call-chain: " call-chain)))
						;; what if another thread is communicating ok? Can't happen due to mutex
						(http-transport:close-connections runremote)
						(mutex-unlock! *http-mutex*)
						;; (close-connection! fullurl)
						(db:obj->string #f))
					      (with-input-from-request ;; was dat
					       fullurl 
					       (list (cons 'key (or server-id   "thekey"))
						     (cons 'cmd cmd)
						     (cons 'params sparams))
					       read-string))
335
336
337
338
339
340
341
342


343
344
345
346
347
348
349
350
351
  (if (remote? runremote)
      (let ((api-dat (remote-api-uri runremote)))
	(handle-exceptions
	    exn
	  (begin
	    (print-call-chain *default-log-port*)
	    (debug:print-error 0 *default-log-port* " closing connection failed with error: " ((condition-property-accessor 'exn 'message) exn) ", exn=" exn))
	  (if (args:any-defined? "-server" "-execute" "-run")


	      (debug:print-info 0 *default-log-port* "Closing connections to "api-dat))
	  (close-connection! api-dat)
	  (remote-conndat-set! runremote #f)
	  #t))
      #f))

;; run http-transport:keep-running in a parallel thread to monitor that the db is being 
;; used and to shutdown after sometime if it is not.
;;







|
>
>
|
|







335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
  (if (remote? runremote)
      (let ((api-dat (remote-api-uri runremote)))
	(handle-exceptions
	    exn
	  (begin
	    (print-call-chain *default-log-port*)
	    (debug:print-error 0 *default-log-port* " closing connection failed with error: " ((condition-property-accessor 'exn 'message) exn) ", exn=" exn))
	  (if (and (args:any-defined? "-server" "-execute" "-run")
		   api-dat)
	      (begin ;; NOTE: Verify this actually ever gets hit. Jan 16, 2023.
		(debug:print-info 0 *default-log-port* "Closing connections to "api-dat)
		(close-connection! api-dat)))
	  (remote-conndat-set! runremote #f)
	  #t))
      #f))

;; run http-transport:keep-running in a parallel thread to monitor that the db is being 
;; used and to shutdown after sometime if it is not.
;;

Modified rmt.scm from [ef90d475fb] to [599b82a5a9].

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
;; 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 (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! conninfo=" conninfo)
	  (set! conninfo #f)
	  (http-transport:close-connections 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) 







<
|








<









|


|
<

|







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
;; 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* ((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)

			     ((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 (remote? runremote)
	(remote-last-access-set! runremote (current-seconds)) ;; refresh access time
	(begin
	  (debug:print 0 *default-log-port* "INFO: Should not get here! runremote="runremote)

	  (http-transport:close-connections runremote)))
    (debug:print-info 13 *default-log-port* "rmt:send-receive, case  9. runremote="runremote " dat=" dat)
    (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)