If anything in start_new_log did logging (for example, by sending a
statustext), we end up infinitely recursing.
With the patch:
diff --git a/libraries/AP_Logger/AP_Logger_File.cpp b/libraries/AP_Logger/AP_Logger_File.cpp
index 69b8ef0431..eb422d10f8 100644
--- a/libraries/AP_Logger/AP_Logger_File.cpp
+++ b/libraries/AP_Logger/AP_Logger_File.cpp
@@ -778,6 +778,7 @@ void AP_Logger_File::PrepForArming()
*/
void AP_Logger_File::start_new_log(void)
{
+ gcs().send_text(MAV_SEVERITY_WARNING, "Starting new log");
stop_logging();
start_new_log_reset_variables();
pbarker@bluebottle:~/rc/ardupilot(master)$
We see:
at ../../libraries/AP_Logger/AP_Logger_File.cpp:781
this=0x555555ad9d30, pBuffer=0x7fffff8209d0, size=75, is_critical=true)
at ../../libraries/AP_Logger/AP_Logger_Backend.cpp:372
this=0x555555ad9d30, pBuffer=0x7fffff8209d0, size=75)
at ../../libraries/AP_Logger/AP_Logger_Backend.h:32
this=0x555555ad9d30, message=0x7fffff820b10 "Starting new log")
at ../../libraries/AP_Logger/LogFile.cpp:466
this=0x555555a6d758 <copter+11384>,
message=0x7fffff820b10 "Starting new log")
at ../../libraries/AP_Logger/AP_Logger.cpp:752
this=0x555555a6e708 <copter+15400>, severity=MAV_SEVERITY_WARNING,
fmt=0x5555557d64d0 "Starting new log", arg_list=0x7fffff820be0,
dest_bitmask=1 '\001') at ../../libraries/GCS_MAVLink/GCS_Common.cpp:1847
this=0x555555a6e708 <copter+15400>, severity=MAV_SEVERITY_WARNING,
fmt=0x5555557d64d0 "Starting new log", arg_list=0x7fffff820be0)
at ../../libraries/GCS_MAVLink/GCS.cpp:53
this=0x555555a6e708 <copter+15400>, severity=MAV_SEVERITY_WARNING,
fmt=0x5555557d64d0 "Starting new log")
at ../../libraries/GCS_MAVLink/GCS.cpp:60
at ../../libraries/AP_Logger/AP_Logger_File.cpp:781
this=0x555555ad9d30, pBuffer=0x7fffff820dc0, size=75, is_critical=true)
at ../../libraries/AP_Logger/AP_Logger_Backend.cpp:372
I'm not aware of any instances in the code where this will actually
happen - but it could easily sneak in.
now that we persist logging for 15s after disarm we need to also delay
the log rotation if LOG_FILE_DSRMROT=1. Otherwise we will put the log
data into the next log, which defeats the purpose of the 15s
persistance
Setting a dataflash-file buffer size of less than or equal to 2kiB would
cause the startup-messagewriter to never push any messages other than
FMT out to the logs.
This is a combination of the return values of
critical_message_reserved_space and
non_messagewriter_message_reserved_space
This patch forces the startup messages out to the logs by ignoring the
space constraints every 100ms
this avoids getting invalid data base for stat() for the current log
file.
It also only gives up writing to a log file if writes fail for 2
seconds. This avoids a temporary write failure causing the log to be
closed (that can happen on ChibiOS with directory listing while writing)
Peter Barker
Iampete1
Andrew Tridgell
murata
Tom Pittenger
Michael du Breuil
Francisco Ferreira
Lucas De Marchi
LukeMike