On 8 Jun 2011, at 10:29, Rainer Orth wrote:
Darwin seems to be exceedingly unreliable under load: tests randomly
time out and work again the next time.
If you mean random timeouts in dejagnu - I suspect (but have not yet
proved) that the culprit is insufficient stack allocation in some
component of tcl or expect itself.
One used to find that non-parallel "make check" would be quite
reliable - but parallel very unreliable.
I use the following local (not submitted, unofficial) patch to dejagnu
on Darwin9 - which retries tests that timeout (once) - this has been
enough to eliminate the frustration for me...
YMMV, of course.
cheers
Iain
--- dejagnu-1.4.4/lib/remote.exp 2003-10-11 07:42:46.000000000 +0100
+++ dejagnu-1.4.4-installed/lib/remote.exp 2010-03-12 09:32:49.000000000
+0000
@@ -74,7 +74,7 @@
# or output is redirected. If the program needs to be killed, /bin/sh and
# the kill command will be invoked.
#
-proc local_exec { commandline inp outp timeout } {
+proc one_local_exec { commandline inp outp timeout } {
# Tcl's exec is a pile of crap. It does two very inappropriate things
# firstly, it has no business returning an error if the program being
# executed happens to write to stderr. Secondly, it appends its own
@@ -155,7 +155,7 @@
set got_eof 0
set output ""
-
+ set status 0
# Wait for either $timeout seconds to elapse, or for the program to
# exit.
expect {
@@ -163,16 +163,19 @@
append output $expect_out(buffer)
if { [string length $output] < 512000 } {
exp_continue -continue_timer
+ } else {
+ warning "one_local_exec: (output string overflow)"
}
}
timeout {
- warning "program timed out."
+# warning "one_local_exec: program timed out."
+ set status -2
}
eof {
set got_eof 1
}
}
-
+
# Uuuuuuugh. Now I'm getting really sick.
# If we didn't get an EOF, we have to kill the poor defenseless program.
# However, Tcl has no kill primitive, so we have to execute an external
@@ -207,12 +210,16 @@
set res "wait failed"
}
}
+
if { $r2 != 0 || $res != "" || ! $got_eof } {
verbose "close result is $res"
- set status 1
+ if { $status != -2 } {
+ set status 1
+ }
} else {
set status 0
}
+
verbose "output is $output"
if { $outp == "" } {
return [list $status $output]
@@ -221,6 +228,29 @@
}
}
+proc local_exec { commandline inp outp timeout } {
+ set res [one_local_exec $commandline $inp $outp $timeout]
+ set stat [lindex $res 0]
+# OK?
+ if { $stat != -2 } {
+ return $res
+ }
+# nope...
+# warning "local_exec $commandline timed out : retrying"
+ verbose -log "RE-TRIED: (timeout = $timeout) : $commandline "
+ if { $timeout < 150 } {
+ set timeout [expr {$timeout} * 2]
+ }
+ set res [one_local_exec $commandline $inp $outp $timeout]
+ set stat [lindex $res 0]
+ if { $stat == -2 } {
+ set msg ""
+ warning "TIMED OUT: $commandline timed out after retry"
+ verbose -log "TIMED OUT: $commandline (timeout = $timeout)"
+ }
+ return $res
+}
+
#
# Execute the supplied program on HOSTNAME. There are four optional arguments
# the first is a set of arguments to pass to PROGRAM, the second is an
@@ -1090,7 +1120,8 @@
}
}
timeout {
- warning "program timed out."
+ warning "standard_wait: program timed out"
+ set status -2
}
eof {
if [board_info $dest exists fileid_origid] {
