You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@aurora.apache.org by ma...@apache.org on 2014/05/02 23:37:30 UTC
git commit: Adjusting default health check config values.
Repository: incubator-aurora
Updated Branches:
refs/heads/master 66db66e08 -> 72520c20d
Adjusting default health check config values.
Bugs closed: AURORA-376
Reviewed at https://reviews.apache.org/r/21025/
Project: http://git-wip-us.apache.org/repos/asf/incubator-aurora/repo
Commit: http://git-wip-us.apache.org/repos/asf/incubator-aurora/commit/72520c20
Tree: http://git-wip-us.apache.org/repos/asf/incubator-aurora/tree/72520c20
Diff: http://git-wip-us.apache.org/repos/asf/incubator-aurora/diff/72520c20
Branch: refs/heads/master
Commit: 72520c20d66c99a27b574ad89f6d81891cbc677b
Parents: 66db66e
Author: Maxim Khutornenko <ma...@apache.org>
Authored: Fri May 2 14:37:07 2014 -0700
Committer: Maxim Khutornenko <ma...@apache.org>
Committed: Fri May 2 14:37:07 2014 -0700
----------------------------------------------------------------------
docs/client-commands.md | 2 +-
docs/configuration-reference.md | 6 +++---
docs/configuration-tutorial.md | 6 +++---
src/main/python/apache/aurora/config/schema/base.py | 8 ++++----
.../python/apache/aurora/executor/common/health_checker.py | 2 +-
5 files changed, 12 insertions(+), 12 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/incubator-aurora/blob/72520c20/docs/client-commands.md
----------------------------------------------------------------------
diff --git a/docs/client-commands.md b/docs/client-commands.md
index 098d261..f61fc66 100644
--- a/docs/client-commands.md
+++ b/docs/client-commands.md
@@ -319,7 +319,7 @@ In addition to the required job key argument, there are eight
- `--restart_threshold`: Defaults to `60`, the maximum number of
seconds before a shard must move into the `RUNNING` state before
it's considered a failure.
-- `--watch_secs`: Defaults to `30`, the minimum number of seconds a
+- `--watch_secs`: Defaults to `45`, the minimum number of seconds a
shard must remain in `RUNNING` state before considered a success.
Cron Jobs
http://git-wip-us.apache.org/repos/asf/incubator-aurora/blob/72520c20/docs/configuration-reference.md
----------------------------------------------------------------------
diff --git a/docs/configuration-reference.md b/docs/configuration-reference.md
index 775e652..34f2359 100644
--- a/docs/configuration-reference.md
+++ b/docs/configuration-reference.md
@@ -341,7 +341,7 @@ Parameters for controlling the rate and policy of rolling updates.
| ---------------------------- | :------: | ------------
| ```batch_size``` | Integer | Maximum number of shards to be updated in one iteration (Default: 1)
| ```restart_threshold``` | Integer | Maximum number of seconds before a shard must move into the ```RUNNING``` state before considered a failure (Default: 60)
-| ```watch_secs``` | Integer | Minimum number of seconds a shard must remain in ```RUNNING``` state before considered a success (Default: 30)
+| ```watch_secs``` | Integer | Minimum number of seconds a shard must remain in ```RUNNING``` state before considered a success (Default: 45)
| ```max_per_shard_failures``` | Integer | Maximum number of restarts per shard during update. Increments total failure count when this limit is exceeded. (Default: 0)
| ```max_total_failures``` | Integer | Maximum number of shard failures to be tolerated in total during an update. Cannot be greater than or equal to the total number of tasks in a job. (Default: 0)
@@ -351,8 +351,8 @@ Parameters for controlling a task's health checks via HTTP.
| object | type | description
| ------- | :-------: | --------
-| ```initial_interval_secs``` | Integer | Initial delay for performing an HTTP health check. (Default: 60)
-| ```interval_secs``` | Integer | Interval on which to check the task's health via HTTP. (Default: 30)
+| ```initial_interval_secs``` | Integer | Initial delay for performing an HTTP health check. (Default: 15)
+| ```interval_secs``` | Integer | Interval on which to check the task's health via HTTP. (Default: 10)
| ```timeout_secs``` | Integer | HTTP request timeout. (Default: 1)
| ```max_consecutive_failures``` | Integer | Maximum number of consecutive failures that tolerated before considering a task unhealthy (Default: 0)
http://git-wip-us.apache.org/repos/asf/incubator-aurora/blob/72520c20/docs/configuration-tutorial.md
----------------------------------------------------------------------
diff --git a/docs/configuration-tutorial.md b/docs/configuration-tutorial.md
index c7d970c..67998e9 100644
--- a/docs/configuration-tutorial.md
+++ b/docs/configuration-tutorial.md
@@ -589,7 +589,7 @@ The final three Job attributes each take an object as their value.
- `restart_threshold`: An integer, defaulting to `60`, specifying
the maximum number of seconds before a shard must move into the
`RUNNING` state before considered a failure.
- - `watch_secs`: An integer, defaulting to `30`, specifying the
+ - `watch_secs`: An integer, defaulting to `45`, specifying the
minimum number of seconds a shard must remain in the `RUNNING`
state before considered a success.
- `max_per_shard_failures`: An integer, defaulting to `0`,
@@ -604,9 +604,9 @@ The final three Job attributes each take an object as their value.
parameters for controlling a Task's health checks via HTTP. Only
used if a health port was assigned with a command line wildcard. The
`HealthCheckConfig` parameters are:
- - `initial_interval_secs`: An integer, defaulting to `60`,
+ - `initial_interval_secs`: An integer, defaulting to `15`,
specifying the initial delay for doing an HTTP health check.
- - `interval_secs`: An integer, defaulting to `30`, specifying the
+ - `interval_secs`: An integer, defaulting to `10`, specifying the
number of seconds in the interval between checking the Task's
health.
- `timeout_secs`: An integer, defaulting to `1`, specifying the
http://git-wip-us.apache.org/repos/asf/incubator-aurora/blob/72520c20/src/main/python/apache/aurora/config/schema/base.py
----------------------------------------------------------------------
diff --git a/src/main/python/apache/aurora/config/schema/base.py b/src/main/python/apache/aurora/config/schema/base.py
index 89931ab..61a6680 100644
--- a/src/main/python/apache/aurora/config/schema/base.py
+++ b/src/main/python/apache/aurora/config/schema/base.py
@@ -52,15 +52,15 @@ class PackerObject(Struct):
class UpdateConfig(Struct):
batch_size = Default(Integer, 1)
restart_threshold = Default(Integer, 60)
- watch_secs = Default(Integer, 30)
+ watch_secs = Default(Integer, 45)
max_per_shard_failures = Default(Integer, 0)
max_total_failures = Default(Integer, 0)
rollback_on_failure = Default(Boolean, True)
class HealthCheckConfig(Struct):
- initial_interval_secs = Default(Float, 60.0)
- interval_secs = Default(Float, 30.0)
+ initial_interval_secs = Default(Float, 15.0)
+ interval_secs = Default(Float, 10.0)
timeout_secs = Default(Float, 1.0)
max_consecutive_failures = Default(Integer, 0)
@@ -86,7 +86,7 @@ class MesosTaskInstance(Struct):
role = Required(String)
announce = Announcer
environment = Default(String, DEFAULT_ENVIRONMENT)
- health_check_interval_secs = Default(Integer, 30) # DEPRECATED (MESOS-2649)
+ health_check_interval_secs = Default(Integer, 10) # DEPRECATED (MESOS-2649)
health_check_config = Default(HealthCheckConfig, HealthCheckConfig())
http://git-wip-us.apache.org/repos/asf/incubator-aurora/blob/72520c20/src/main/python/apache/aurora/executor/common/health_checker.py
----------------------------------------------------------------------
diff --git a/src/main/python/apache/aurora/executor/common/health_checker.py b/src/main/python/apache/aurora/executor/common/health_checker.py
index 503d5c6..4a1b0af 100644
--- a/src/main/python/apache/aurora/executor/common/health_checker.py
+++ b/src/main/python/apache/aurora/executor/common/health_checker.py
@@ -39,7 +39,7 @@ class HealthCheckerThread(StatusChecker, ExceptionalThread):
"""
def __init__(self,
health_checker,
- interval_secs=30,
+ interval_secs=10,
initial_interval_secs=None,
max_consecutive_failures=0,
clock=time):