From 5b9265ad19d6596a8b599eccc64accb67e3c664e Mon Sep 17 00:00:00 2001 From: Magnus Henoch Date: Mon, 21 Nov 2016 11:48:54 +0000 Subject: Remove vestiges of watchdog support in heart Hardware watchdog support was removed from heart in R13A, but there were still some vestiges in the code and the documentation. - Remove mentions of the HW_WD_DISABLE variable, as it's no longer used. - Remove the HEART_BEAT_BOOT_DELAY variable, as it was only used for the hardware watchdog. --- erts/etc/common/heart.c | 40 ++++------------------ lib/kernel/doc/src/heart.xml | 17 +++------ lib/kernel/src/heart.erl | 15 +++----- lib/sasl/test/release_handler_SUITE_data/start | 3 +- .../test/release_handler_SUITE_data/start_client | 3 +- 5 files changed, 18 insertions(+), 60 deletions(-) diff --git a/erts/etc/common/heart.c b/erts/etc/common/heart.c index d67b997d6d..bc353e384e 100644 --- a/erts/etc/common/heart.c +++ b/erts/etc/common/heart.c @@ -48,13 +48,10 @@ * * HEART_BEATING * - * This program expects a heart beat messages. If it does not receive a - * heart beat message from Erlang within heart_beat_timeout seconds, it - * reboots the system. The variable heart_beat_timeout is exported (so - * that it can be set from the shell in VxWorks, as is the variable - * heart_beat_report_delay). When using Solaris, the system is rebooted - * by executing the command stored in the environment variable - * HEART_COMMAND. + * This program expects a heart beat message. If it does not receive a + * heart beat message from Erlang within heart_beat_timeout seconds, it + * reboots the system. The system is rebooted by executing the command + * stored in the environment variable HEART_COMMAND. * * BLOCKING DESCRIPTORS * @@ -149,27 +146,17 @@ struct msg { /* Maybe interesting to change */ /* Times in seconds */ -#define HEART_BEAT_BOOT_DELAY 60 /* 1 minute */ #define SELECT_TIMEOUT 5 /* Every 5 seconds we reset the watchdog timer */ /* heart_beat_timeout is the maximum gap in seconds between two - consecutive heart beat messages from Erlang, and HEART_BEAT_BOOT_DELAY - is the the extra delay that wd_keeper allows for, to give heart a - chance to reboot in the "normal" way before the hardware watchdog - enters the scene. heart_beat_report_delay is the time allowed for reporting - before rebooting under VxWorks. */ + consecutive heart beat messages from Erlang. */ int heart_beat_timeout = 60; -int heart_beat_report_delay = 30; -int heart_beat_boot_delay = HEART_BEAT_BOOT_DELAY; /* All current platforms have a process identifier that fits in an unsigned long and where 0 is an impossible or invalid value */ unsigned long heart_beat_kill_pid = 0; -#define VW_WD_TIMEOUT (heart_beat_timeout+heart_beat_report_delay+heart_beat_boot_delay) -#define SOL_WD_TIMEOUT (heart_beat_timeout+heart_beat_boot_delay) - /* reasons for reboot */ #define R_TIMEOUT (1) #define R_CLOSED (2) @@ -297,7 +284,6 @@ free_env_val(char *value) static void get_arguments(int argc, char** argv) { int i = 1; int h; - int w; unsigned long p; while (i < argc) { @@ -313,15 +299,6 @@ static void get_arguments(int argc, char** argv) { i++; } break; - case 'w': - if (strcmp(argv[i], "-wt") == 0) - if (sscanf(argv[i+1],"%i",&w) ==1) - if ((w > 10) && (w <= 65535)) { - heart_beat_boot_delay = w; - fprintf(stderr,"heart_beat_boot_delay = %d\n",w); - i++; - } - break; case 'p': if (strcmp(argv[i], "-pid") == 0) if (sscanf(argv[i+1],"%lu",&p) ==1){ @@ -347,7 +324,7 @@ static void get_arguments(int argc, char** argv) { } i++; } - debugf("arguments -ht %d -wt %d -pid %lu\n",h,w,p); + debugf("arguments -ht %d -pid %lu\n",h,p); } int main(int argc, char **argv) { @@ -674,11 +651,6 @@ void win_system(char *command) */ static void do_terminate(int erlin_fd, int reason) { - /* - When we get here, we have HEART_BEAT_BOOT_DELAY secs to finish - (plus heart_beat_report_delay if under VxWorks), so we don't need - to call wd_reset(). - */ int ret = 0, tmo=0; char *tmo_env; diff --git a/lib/kernel/doc/src/heart.xml b/lib/kernel/doc/src/heart.xml index 59a046bf4d..5b5b71e521 100644 --- a/lib/kernel/doc/src/heart.xml +++ b/lib/kernel/doc/src/heart.xml @@ -37,10 +37,7 @@ the heart port program is to check that the Erlang runtime system it is supervising is still running. If the port program has not received any heartbeats within HEART_BEAT_TIMEOUT seconds - (defaults to 60 seconds), the system can be rebooted. Also, if - the system is equipped with a hardware watchdog timer and is - running Solaris, the watchdog can be used to supervise the entire - system.

+ (defaults to 60 seconds), the system can be rebooted.

An Erlang runtime system to be monitored by a heart program is to be started with command-line flag -heart (see also erl(1)). @@ -51,17 +48,13 @@ or a terminated Erlang runtime system, environment variable HEART_COMMAND must be set before the system is started. If this variable is not set, a warning text is printed but - the system does not reboot. However, if the hardware watchdog is - used, it still triggers a reboot HEART_BEAT_BOOT_DELAY - seconds later (defaults to 60 seconds).

+ the system does not reboot.

To reboot on Windows, HEART_COMMAND can be set to heart -shutdown (included in the Erlang delivery) or to any other suitable program that can activate a reboot.

-

The hardware watchdog is not started under Solaris if - environment variable HW_WD_DISABLE is set.

-

The environment variables HEART_BEAT_TIMEOUT and - HEART_BEAT_BOOT_DELAY can be used to configure the heart - time-outs; they can be set in the operating system shell before Erlang +

The environment variable HEART_BEAT_TIMEOUT + can be used to configure the heart + time-outs; it can be set in the operating system shell before Erlang is started or be specified at the command line:

 % erl -heart -env HEART_BEAT_TIMEOUT 30 ...
diff --git a/lib/kernel/src/heart.erl b/lib/kernel/src/heart.erl index eea78aabdf..8fa48d56fb 100644 --- a/lib/kernel/src/heart.erl +++ b/lib/kernel/src/heart.erl @@ -198,16 +198,11 @@ start_portprogram() -> end. get_heart_timeouts() -> - HeartOpts = case os:getenv("HEART_BEAT_TIMEOUT") of - false -> ""; - H when is_list(H) -> - "-ht " ++ H - end, - HeartOpts ++ case os:getenv("HEART_BEAT_BOOT_DELAY") of - false -> ""; - W when is_list(W) -> - " -wt " ++ W - end. + case os:getenv("HEART_BEAT_TIMEOUT") of + false -> ""; + H when is_list(H) -> + "-ht " ++ H + end. check_start_heart() -> case init:get_argument(heart) of diff --git a/lib/sasl/test/release_handler_SUITE_data/start b/lib/sasl/test/release_handler_SUITE_data/start index 87275045b1..eab2b77aed 100755 --- a/lib/sasl/test/release_handler_SUITE_data/start +++ b/lib/sasl/test/release_handler_SUITE_data/start @@ -21,8 +21,7 @@ then fi HEART_COMMAND=$ROOTDIR/bin/start -HW_WD_DISABLE=true -export HW_WD_DISABLE HEART_COMMAND +export HEART_COMMAND START_ERL_DATA=${1:-$RELDIR/start_erl.data} diff --git a/lib/sasl/test/release_handler_SUITE_data/start_client b/lib/sasl/test/release_handler_SUITE_data/start_client index 5ea94d6f7c..05d744f06e 100755 --- a/lib/sasl/test/release_handler_SUITE_data/start_client +++ b/lib/sasl/test/release_handler_SUITE_data/start_client @@ -24,8 +24,7 @@ RELDIR=$CLIENTDIR/releases # Note that this scripts is modified an copied to $CLIENTDIR/bin/start # in release_handler_SUITE:copy_client - therefore HEART_COMMAND is as follows: HEART_COMMAND=$CLIENTDIR/bin/start -HW_WD_DISABLE=true -export HW_WD_DISABLE HEART_COMMAND +export HEART_COMMAND START_ERL_DATA=${1:-$RELDIR/start_erl.data} -- cgit v1.2.3