Index: http-transport.scm ================================================================== --- http-transport.scm +++ http-transport.scm @@ -306,10 +306,11 @@ 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))) (close-connection! api-dat) + (close-idle-connections!) #t)) #f))) (define (make-http-transport:server-dat)(make-vector 6)) Index: rmt.scm ================================================================== --- rmt.scm +++ rmt.scm @@ -230,13 +230,13 @@ ;;DOT MUTEXLOCK -> CASE11 [label="else"]; {rank=same "case 11" CASE11}; ;;DOT CASE11 -> "rmt:send-receive" [label="call failed"]; ;;DOT CASE11 -> "RESULT" [label="call succeeded"]; ;; not on homehost, do server query (else - (mutex-unlock! *rmt-mutex*) + ;; (mutex-unlock! *rmt-mutex*) (debug:print-info 12 *default-log-port* "rmt:send-receive, case 9") - (mutex-lock! *rmt-mutex*) + ;; (mutex-lock! *rmt-mutex*) (let* ((conninfo (remote-conndat runremote)) (dat (case (remote-transport runremote) ((http) (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 conninfo cmd params) ((commfail)(vector #f "communications fail")) Index: runs.scm ================================================================== --- runs.scm +++ runs.scm @@ -326,13 +326,13 @@ (thread-start! th1) (thread-join! th2))))) (set-signal-handler! signal/int sighand) (set-signal-handler! signal/term sighand)) - ;; force the starting of a server - (debug:print 0 *default-log-port* "waiting on server...") - (server:start-and-wait *toppath*) + ;; force the starting of a server -- removed BB 17ww28 - no longer needed. + ;;(debug:print 0 *default-log-port* "waiting on server...") + ;;(server:start-and-wait *toppath*) (runs:set-megatest-env-vars run-id inkeys: keys inrunname: runname) ;; these may be needed by the launching process (set! runconf (if (common:file-exists? runconfigf) (setup-env-defaults runconfigf run-id *already-seen-runconfig-info* keyvals target) (begin @@ -596,10 +596,11 @@ '() reg))) (define runs:nothing-left-in-queue-count 0) +;; BB: for future reference - suspect target vars are not expanded to env vars at this point (item expansion using [items]\nwhatever [system echo $TARGETVAR] doesnt work right whereas [system echo #{targetvar}] does.. Tal and Randy have tix on this. on first pass, var not set, on second pass, ok. (define (runs:expand-items hed tal reg reruns regfull newtal jobgroup max-concurrent-jobs run-id waitons item-path testmode test-record can-run-more items runname tconfig reglen test-registry test-records itemmaps) (let* ((loop-list (list hed tal reg reruns)) (prereqs-not-met (let ((res (rmt:get-prereqs-not-met run-id waitons hed item-path mode: testmode itemmaps: itemmaps))) (if (list? res) res @@ -1271,17 +1272,18 @@ itemmaps: itemmaps ;; prereqs-not-met: prereqs-not-met ))) (runs:dat-regfull-set! runsdat regfull) + ;; -- removed BB 17ww28 - no longer needed. ;; every 15 minutes verify the server is there for this run - (if (and (common:low-noise-print 240 "try start server" run-id) - (not (or (and *runremote* - (remote-server-url *runremote*) - (server:ping (remote-server-url *runremote*))) - (server:check-if-running *toppath*)))) - (server:kind-run *toppath*)) + ;; (if (and (common:low-noise-print 240 "try start server" run-id) + ;; (not (or (and *runremote* + ;; (remote-server-url *runremote*) + ;; (server:ping (remote-server-url *runremote*))) + ;; (server:check-if-running *toppath*)))) + ;; (server:kind-run *toppath*)) (if (> num-running 0) (set! last-time-some-running (current-seconds))) (if (> (current-seconds)(+ last-time-some-running (or (configf:lookup *configdat* "setup" "give-up-waiting") 36000))) @@ -1409,11 +1411,11 @@ (loop (car tal)(cdr tal) reg reruns))) ;; if items is a proc then need to run items:get-items-from-config, get the list and loop ;; - but only do that if resources exist to kick off the job ;; EXPAND ITEMS - ((or (procedure? items)(eq? items 'have-procedure)) + ((or (procedure? items)(eq? items 'have-procedure)) ;; BB - target vars are env vars here? to allow expansion of [items]\nsomething [system echo $SOMETARGVAR], which is wonky (let ((can-run-more (runs:can-run-more-tests runsdat run-id jobgroup max-concurrent-jobs))) (if (and (list? can-run-more) (car can-run-more)) (let ((loop-list (runs:expand-items hed tal reg reruns regfull newtal jobgroup max-concurrent-jobs run-id waitons item-path testmode test-record can-run-more items runname tconfig reglen test-registry test-records itemmaps))) (if loop-list