Megatest

Check-in [fd3c06195d]
Login
Overview
Comment:Tell calling client to wait and try again if server is overloaded (in terms of parallel api calls over 25)
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | multi-server-hack
Files: files | file ages | folders
SHA1: fd3c06195dae25aaf4cdee9be9eac1f172ac926a
User & Date: matt on 2017-03-24 14:52:47
Other Links: branch diff | manifest | tags
Context
2017-03-24
15:18
Reduced threshold for server pushback on clients to 20 api calls/parallel. Added couple more calls to check if server is running before starting a new one. check-in: 37e149d637 user: matt tags: multi-server-hack
14:52
Tell calling client to wait and try again if server is overloaded (in terms of parallel api calls over 25) check-in: fd3c06195d user: matt tags: multi-server-hack
13:51
Show connection stats every 60 seconds. Remove stat of megatest.db from rmt:send-receive, it was happening on every call. check-in: 6baac6187e user: matt tags: multi-server-hack
Changes

Modified api.scm from [d0edc7e79b] to [b54cac363d].

123
124
125
126
127
128
129


130
131
132
133
134
135
136
     (debug:print 0 *default-log-port* "WARNING: api:execute-requests received an exception from peer")
     (print-call-chain (current-error-port))
     (debug:print 0 *default-log-port* " message: "  ((condition-property-accessor 'exn 'message) exn))       
     (vector #f (vector exn call-chain dat))) ;; return some stuff for debug if an exception happens
   (cond
    ((not (vector? dat))                    ;; it is an error to not receive a vector
     (vector #f #f "remote must be called with a vector")       )


    (else  
     (let* ((cmd-in (vector-ref dat 0))
            (cmd    (if (symbol? cmd-in)
                        cmd-in
                        (string->symbol cmd-in)))
            (params (vector-ref dat 1))
            (start-t (current-milliseconds))







>
>







123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
     (debug:print 0 *default-log-port* "WARNING: api:execute-requests received an exception from peer")
     (print-call-chain (current-error-port))
     (debug:print 0 *default-log-port* " message: "  ((condition-property-accessor 'exn 'message) exn))       
     (vector #f (vector exn call-chain dat))) ;; return some stuff for debug if an exception happens
   (cond
    ((not (vector? dat))                    ;; it is an error to not receive a vector
     (vector #f #f "remote must be called with a vector")       )
    ((> *api-process-request-count* 25)
     (vector #f 'overloaded))
    (else  
     (let* ((cmd-in (vector-ref dat 0))
            (cmd    (if (symbol? cmd-in)
                        cmd-in
                        (string->symbol cmd-in)))
            (params (vector-ref dat 1))
            (start-t (current-milliseconds))

Modified rmt.scm from [4b028f3c38] to [5974ce4c87].

204
205
206
207
208
209
210





211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
	      ((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)))





	    (begin
	      (debug:print 0 *default-log-port* "WARNING: communication failed. Trying again, try num: " attemptnum)
	      (remote-conndat-set!    runremote #f)
	      (remote-server-url-set! runremote #f)
              (debug:print-info 12 *default-log-port* "rmt:send-receive, case  9.1")
	      (mutex-unlock! *rmt-mutex*)
	      (server:start-and-wait *toppath*)
	      (rmt:send-receive cmd rid params attemptnum: (+ attemptnum 1)))))))))

;; (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")







>
>
>
>
>
|
|
|
|
|
|
|
|







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
	      ((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)))
	    (if (eq? res 'overloaded)
		(let ((wait-delay (+ attemptnum (* attemptnum 10))))
		  (debug:print 0 *default-log-port* "WARNING: server is overloaded. Delaying " wait-delay " seconds and trying call again.")
		  (thread-sleep! wait-delay)
		  (rmt:send-receive cmd rid params attemptnum: (+ attemptnum 1)))
		(begin
		  (debug:print 0 *default-log-port* "WARNING: communication failed. Trying again, try num: " attemptnum)
		  (remote-conndat-set!    runremote #f)
		  (remote-server-url-set! runremote #f)
		  (debug:print-info 12 *default-log-port* "rmt:send-receive, case  9.1")
		  (mutex-unlock! *rmt-mutex*)
		  (server:start-and-wait *toppath*)
		  (rmt:send-receive cmd rid params attemptnum: (+ attemptnum 1))))))))))

;; (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")