Overview
Comment: | More close-connections fixes. |
---|---|
Downloads: | Tarball | ZIP archive | SQL archive |
Timelines: | family | ancestors | descendants | both | v1.80 |
Files: | files | file ages | folders |
SHA1: |
3e016c5af52582f6784dcde42ed5b1a2 |
User & Date: | matt on 2023-01-12 20:02:19 |
Other Links: | branch diff | manifest | tags |
Context
2023-01-12
| ||
21:49 | Calling db:with-db inside a transaction was bad. Disallowed calling db:with-db with db and factored out few calls to take db. TCP connections seems stable. Fingers crossed. check-in: fb48802dd5 user: matt tags: v1.80 | |
20:02 | More close-connections fixes. check-in: 3e016c5af5 user: matt tags: v1.80 | |
17:48 | Added tasks_queue to db:sync-main-list to sync this table to NFS check-in: d461a68372 user: mmgraham tags: v1.80 | |
Changes
Modified client.scm from [2a6738b25e] to [04727fe923].
︙ | ︙ | |||
105 106 107 108 109 110 111 | (begin (remote-conndat-set! runremote start-res) ;; (hash-table-set! runremote run-id start-res) (debug:print-info 2 *default-log-port* "connected to " (http-transport:server-dat-make-url start-res)) start-res) (client:setup-http-baby areapath 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 | < | < < < | 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 | (begin (remote-conndat-set! runremote start-res) ;; (hash-table-set! runremote run-id start-res) (debug:print-info 2 *default-log-port* "connected to " (http-transport:server-dat-make-url start-res)) start-res) (client:setup-http-baby areapath 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 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) |
︙ | ︙ |
Modified http-transport.scm from [01982440a6] to [4037b30aac].
︙ | ︙ | |||
343 344 345 346 347 348 349 | (signal (make-composite-condition (make-property-condition 'timeout 'message "nmsg-transport:client-api-send-receive-raw timed out talking to server"))))))) ;; careful closing of connections stored in *runremote* ;; | | | | 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 | (signal (make-composite-condition (make-property-condition 'timeout 'message "nmsg-transport:client-api-send-receive-raw timed out talking to server"))))))) ;; careful closing of connections stored in *runremote* ;; (define (http-transport:close-connections runremote) (let* (;; (runremote (or area-dat *runremote*)) (server-dat (if runremote (remote-conndat runremote) #f))) ;; (hash-table-ref/default *runremote* run-id #f))) (if (vector? server-dat) (let ((api-dat (http-transport:server-dat-get-api-uri server-dat))) (handle-exceptions exn |
︙ | ︙ |
Modified rmt.scm from [d02e4b3389] to [53cc395259].
︙ | ︙ | |||
173 174 175 176 177 178 179 | ;; reset the connection if it has been unused too long ((and runremote (remote-conndat runremote) (> (current-seconds) ;; if it has been more than server-timeout seconds since last contact, close this connection and start a new on (+ (http-transport:server-dat-get-last-access (remote-conndat runremote)) (remote-server-timeout runremote)))) (debug:print-info 0 *default-log-port* "Connection to " (remote-server-url runremote) " expired due to no accesses, forcing new connection.") | | | 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 | ;; reset the connection if it has been unused too long ((and runremote (remote-conndat runremote) (> (current-seconds) ;; if it has been more than server-timeout seconds since last contact, close this connection and start a new on (+ (http-transport:server-dat-get-last-access (remote-conndat runremote)) (remote-server-timeout runremote)))) (debug:print-info 0 *default-log-port* "Connection to " (remote-server-url runremote) " expired due to no accesses, forcing new connection.") (http-transport:close-connections runremote) ;; moving this setting of runremote conndat to #f to inside the http-transport:close-connections ;; (remote-conndat-set! runremote #f) ;; invalidate the connection, thus forcing a new connection. (mutex-unlock! *rmt-mutex*) (rmt:send-receive cmd rid params attemptnum: attemptnum)) ;;DOT CASE5 [label="local\nread"]; ;;DOT MUTEXLOCK -> CASE5 [label="server not required,\non homehost,\nread-only query"]; {rank=same "case 5" CASE5}; |
︙ | ︙ | |||
338 339 340 341 342 343 344 | (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))) (http-transport:server-dat-update-last-access conninfo) ;; refresh access time (begin (debug:print 0 *default-log-port* "INFO: Should not get here! conninfo=" conninfo) (set! conninfo #f) | < | | 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 | (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))) (http-transport:server-dat-update-last-access conninfo) ;; 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 |
︙ | ︙ | |||
1066 1067 1068 1069 1070 1071 1072 | (debug:print-info 12 log-port "rmt:send-receive, case 3") (debug:print 0 log-port "WARNING: write transaction requested on a readonly area. cmd="cmd" params="params) #f) (define (extras-transport-failed *default-log-port* *rmt-mutex* attemptnum runremote cmd rid params) (debug:print 0 *default-log-port* "WARNING: communication failed. Trying again, try num: " attemptnum) (mutex-lock! *rmt-mutex*) | < | | 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 | (debug:print-info 12 log-port "rmt:send-receive, case 3") (debug:print 0 log-port "WARNING: write transaction requested on a readonly area. cmd="cmd" params="params) #f) (define (extras-transport-failed *default-log-port* *rmt-mutex* attemptnum runremote cmd rid params) (debug:print 0 *default-log-port* "WARNING: communication failed. Trying again, try num: " attemptnum) (mutex-lock! *rmt-mutex*) (http-transport:close-connections runremote) (remote-server-url-set! runremote #f) (mutex-unlock! *rmt-mutex*) (debug:print-info 12 *default-log-port* "rmt:send-receive, case 9.1") (rmt:send-receive cmd rid params attemptnum: (+ attemptnum 1))) (define (extras-transport-succeded *default-log-port* *rmt-mutex* attemptnum runremote res params rid cmd) (if (and (vector? res) |
︙ | ︙ | |||
1095 1096 1097 1098 1099 1100 1101 | ;; server is ;; overloaded and we ;; want to ease off ;; the queries (let ((wait-delay (+ attemptnum (* attemptnum 10)))) (debug:print 0 *default-log-port* "WARNING: server is overloaded. Delaying " wait-delay " seconds and trying call again.") (mutex-lock! *rmt-mutex*) | | | 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 | ;; server is ;; overloaded and we ;; want to ease off ;; the queries (let ((wait-delay (+ attemptnum (* attemptnum 10)))) (debug:print 0 *default-log-port* "WARNING: server is overloaded. Delaying " wait-delay " seconds and trying call again.") (mutex-lock! *rmt-mutex*) (http-transport:close-connections runremote) (set! *runremote* #f) ;; force starting over (mutex-unlock! *rmt-mutex*) (thread-sleep! wait-delay) (rmt:send-receive cmd rid params attemptnum: (+ attemptnum 1))) res)) ;; All good, return res #;(set-functions rmt:send-receive remote-server-url-set! http-transport:close-connections remote-conndat-set! debug:print debug:print-info remote-ro-mode remote-ro-mode-set! remote-ro-mode-checked-set! remote-ro-mode-checked) |