Overview
| Comment: | Add forced reconnect to allow old servers to gracefully die |
|---|---|
| Downloads: | Tarball | ZIP archive | SQL archive |
| Timelines: | family | ancestors | descendants | both | v1.70-refactor-procedures |
| Files: | files | file ages | folders |
| SHA1: |
f1ba33210eb39c42db71ad3916266f73 |
| User & Date: | matt on 2022-06-01 06:08:44 |
| Other Links: | branch diff | manifest | tags |
Context
|
2022-06-01
| ||
| 21:14 | speculative fix check-in: 2f1850785d user: matt tags: v1.70-refactor-procedures | |
| 06:08 | Add forced reconnect to allow old servers to gracefully die check-in: f1ba33210e user: matt tags: v1.70-refactor-procedures | |
|
2022-05-31
| ||
| 06:01 | Stop touching log after 600 seconds, clobber *runremote* on client side insteade of setting the remote in the record check-in: a732b9439d user: matt tags: v1.70-refactor-procedures | |
Changes
Modified common.scm from [49d3d99fc7] to [fda00ca967].
| ︙ | ︙ | |||
308 309 310 311 312 313 314 315 316 317 318 319 320 321 | (defstruct remote (hh-dat (common:get-homehost)) ;; homehost record ( addr . hhflag ) (server-url #f) ;; (server:check-if-running *toppath*) #f)) (server-id #f) (server-info (if *toppath* (server:check-if-running *toppath*) #f)) (last-server-check 0) ;; last time we checked to see if the server was alive (conndat #f) (transport *transport-type*) (server-timeout (server:expiration-timeout)) (force-server #f) (ro-mode #f) (ro-mode-checked #f)) ;; flag that indicates we have checked for ro-mode | > | 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 | (defstruct remote (hh-dat (common:get-homehost)) ;; homehost record ( addr . hhflag ) (server-url #f) ;; (server:check-if-running *toppath*) #f)) (server-id #f) (server-info (if *toppath* (server:check-if-running *toppath*) #f)) (last-server-check 0) ;; last time we checked to see if the server was alive (connect-time (current-seconds)) (conndat #f) (transport *transport-type*) (server-timeout (server:expiration-timeout)) (force-server #f) (ro-mode #f) (ro-mode-checked #f)) ;; flag that indicates we have checked for ro-mode |
| ︙ | ︙ |
Modified rmt.scm from [8bbca69519] to [f2baad3376].
| ︙ | ︙ | |||
62 63 64 65 66 67 68 |
;; 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)))
| | | 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 |
;; 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)))
|
| ︙ | ︙ | |||
118 119 120 121 122 123 124 125 126 127 128 129 130 131 |
;; 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
(remote-hh-dat-set! runremote (common:get-homehost)))
;;(print "BB> readonly-mode is "readonly-mode" dbfile is "dbfile)
(cond
;;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))
| > > > > > > > | 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
;; 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
(remote-hh-dat-set! runremote (common:get-homehost)))
;;(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))
|
| ︙ | ︙ |