You are viewing a plain text version of this content. The canonical link for it is here.
Posted to gitbox@hive.apache.org by GitBox <gi...@apache.org> on 2021/07/21 15:22:18 UTC
[GitHub] [hive] pgaref opened a new pull request #2513: HIVE-25362: LLAP: ensure tasks with locality have a chance to adjust delay
pgaref opened a new pull request #2513:
URL: https://github.com/apache/hive/pull/2513
Change-Id: Ib2d91faf4ee6d1bd839953f97ef7f7d2a00ef65f
<!--
Thanks for sending a pull request! Here are some tips for you:
1. If this is your first time, please read our contributor guidelines: https://cwiki.apache.org/confluence/display/Hive/HowToContribute
2. Ensure that you have created an issue on the Hive project JIRA: https://issues.apache.org/jira/projects/HIVE/summary
3. Ensure you have added or run the appropriate tests for your PR:
4. If the PR is unfinished, add '[WIP]' in your PR title, e.g., '[WIP]HIVE-XXXXX: Your PR title ...'.
5. Be sure to keep the PR description updated to reflect all changes.
6. Please write your PR title to summarize what this PR proposes.
7. If possible, provide a concise example to reproduce the issue for a faster review.
-->
### What changes were proposed in this pull request?
HIVE-24914 introduced a short-circuit optimization when all nodes are busy returning DELAYED_RESOURCES and reseting locality delay for a given tasks.
However, this may prevent tasks from adjusting their locality delay and being added to the DelayQueue leading sometimes to missed locality chances when all LLap resources are fully utilized.
Handle the two cases separately.
### Why are the changes needed?
Improve locality in Llap scheduler
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such as the documentation fix.
If yes, please clarify the previous behavior and the change this PR proposes - provide the console output, description, screenshot and/or a reproducable example to show the behavior difference if possible.
If possible, please also clarify if this is a user-facing change compared to the released Hive versions or within the unreleased branches such as master.
If no, write 'No'.
-->
No
### How was this patch tested?
<!--
If tests were added, say they were added here. Please make sure to add some test cases that check the changes thoroughly including negative and positive cases if possible.
If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future.
If tests were not added, please describe why they were not added and/or why it was difficult to add.
-->
TestLlapTaskSchedulerService#testAdjustLocalityDelay
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For additional commands, e-mail: gitbox-help@hive.apache.org
[GitHub] [hive] pgaref commented on a change in pull request #2513: HIVE-25362: LLAP: ensure tasks with locality have a chance to adjust delay
Posted by GitBox <gi...@apache.org>.
pgaref commented on a change in pull request #2513:
URL: https://github.com/apache/hive/pull/2513#discussion_r691884007
##########
File path: llap-tez/src/java/org/apache/hadoop/hive/llap/tezplugins/LlapTaskSchedulerService.java
##########
@@ -1845,7 +1845,11 @@ private static boolean removeFromRunningTaskMap(TreeMap<Integer, TreeSet<TaskInf
*/
private boolean shouldCycle(Map<String, List<NodeInfo>> availableHostMap) {
// short-circuit on resource availability
- if (availableHostMap.values().stream().mapToInt(List::size).sum() > 0) return true;
+ int nodeCnt = 0;
Review comment:
Functionality is the same indeed, just wanted to avoid using a stream here along with any performance penalties mapping Integer to Int etc.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For additional commands, e-mail: gitbox-help@hive.apache.org
[GitHub] [hive] abstractdog commented on a change in pull request #2513: HIVE-25362: LLAP: ensure tasks with locality have a chance to adjust delay
Posted by GitBox <gi...@apache.org>.
abstractdog commented on a change in pull request #2513:
URL: https://github.com/apache/hive/pull/2513#discussion_r691880413
##########
File path: llap-tez/src/java/org/apache/hadoop/hive/llap/tezplugins/LlapTaskSchedulerService.java
##########
@@ -1845,7 +1845,11 @@ private static boolean removeFromRunningTaskMap(TreeMap<Integer, TreeSet<TaskInf
*/
private boolean shouldCycle(Map<String, List<NodeInfo>> availableHostMap) {
// short-circuit on resource availability
- if (availableHostMap.values().stream().mapToInt(List::size).sum() > 0) return true;
+ int nodeCnt = 0;
Review comment:
why did you change this one?
I guess the stream oneliner does the same, am I missing something?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For additional commands, e-mail: gitbox-help@hive.apache.org
[GitHub] [hive] abstractdog commented on a change in pull request #2513: HIVE-25362: LLAP: ensure tasks with locality have a chance to adjust delay
Posted by GitBox <gi...@apache.org>.
abstractdog commented on a change in pull request #2513:
URL: https://github.com/apache/hive/pull/2513#discussion_r674637137
##########
File path: llap-tez/src/test/org/apache/hadoop/hive/llap/tezplugins/TestLlapTaskSchedulerService.java
##########
@@ -904,6 +904,48 @@ private void forceLocalityTest1(boolean forceLocality) throws IOException, Inter
}
}
+ @Test(timeout = 10000)
Review comment:
this unit test passes also without the patch, could you please include some assertion proving this fix? I believe it should assert that in case of no available hosts request.resetLocalityDelayInfo() is not called
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For additional commands, e-mail: gitbox-help@hive.apache.org
[GitHub] [hive] pgaref commented on a change in pull request #2513: HIVE-25362: LLAP: ensure tasks with locality have a chance to adjust delay
Posted by GitBox <gi...@apache.org>.
pgaref commented on a change in pull request #2513:
URL: https://github.com/apache/hive/pull/2513#discussion_r684351582
##########
File path: llap-tez/src/test/org/apache/hadoop/hive/llap/tezplugins/TestLlapTaskSchedulerService.java
##########
@@ -904,6 +904,48 @@ private void forceLocalityTest1(boolean forceLocality) throws IOException, Inter
}
}
+ @Test(timeout = 10000)
Review comment:
Sure, TaskInfo can not be mocked directly so had to play with the adjustedLocalityDelay.
This should do though
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For additional commands, e-mail: gitbox-help@hive.apache.org
[GitHub] [hive] pgaref merged pull request #2513: HIVE-25362: LLAP: ensure tasks with locality have a chance to adjust delay
Posted by GitBox <gi...@apache.org>.
pgaref merged pull request #2513:
URL: https://github.com/apache/hive/pull/2513
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For additional commands, e-mail: gitbox-help@hive.apache.org
[GitHub] [hive] abstractdog commented on a change in pull request #2513: HIVE-25362: LLAP: ensure tasks with locality have a chance to adjust delay
Posted by GitBox <gi...@apache.org>.
abstractdog commented on a change in pull request #2513:
URL: https://github.com/apache/hive/pull/2513#discussion_r674637137
##########
File path: llap-tez/src/test/org/apache/hadoop/hive/llap/tezplugins/TestLlapTaskSchedulerService.java
##########
@@ -904,6 +904,48 @@ private void forceLocalityTest1(boolean forceLocality) throws IOException, Inter
}
}
+ @Test(timeout = 10000)
Review comment:
this unit test passes also without the patch, could you please include some assertion proving this fix? I believe it should assert that in case of no available hosts request.resetLocalityDelayInfo() is not called (if I understood the point of this patch correctly)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For additional commands, e-mail: gitbox-help@hive.apache.org
[GitHub] [hive] pgaref commented on a change in pull request #2513: HIVE-25362: LLAP: ensure tasks with locality have a chance to adjust delay
Posted by GitBox <gi...@apache.org>.
pgaref commented on a change in pull request #2513:
URL: https://github.com/apache/hive/pull/2513#discussion_r691884007
##########
File path: llap-tez/src/java/org/apache/hadoop/hive/llap/tezplugins/LlapTaskSchedulerService.java
##########
@@ -1845,7 +1845,11 @@ private static boolean removeFromRunningTaskMap(TreeMap<Integer, TreeSet<TaskInf
*/
private boolean shouldCycle(Map<String, List<NodeInfo>> availableHostMap) {
// short-circuit on resource availability
- if (availableHostMap.values().stream().mapToInt(List::size).sum() > 0) return true;
+ int nodeCnt = 0;
Review comment:
Functionality is the same indeed, just wanted to avoid using a stream here to avoid any performance penalties mapping Integer to Int etc.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For additional commands, e-mail: gitbox-help@hive.apache.org
[GitHub] [hive] abstractdog commented on a change in pull request #2513: HIVE-25362: LLAP: ensure tasks with locality have a chance to adjust delay
Posted by GitBox <gi...@apache.org>.
abstractdog commented on a change in pull request #2513:
URL: https://github.com/apache/hive/pull/2513#discussion_r691884339
##########
File path: llap-tez/src/java/org/apache/hadoop/hive/llap/tezplugins/LlapTaskSchedulerService.java
##########
@@ -1845,7 +1845,7 @@ private static boolean removeFromRunningTaskMap(TreeMap<Integer, TreeSet<TaskInf
*/
private boolean shouldCycle(Map<String, List<NodeInfo>> availableHostMap) {
Review comment:
could you please clarify here how changes in shouldCycle are related to the original patch (I mean the changes in selectHost) if related at all? (sorry I'm not really familiar with this part)
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
---------------------------------------------------------------------
To unsubscribe, e-mail: gitbox-unsubscribe@hive.apache.org
For additional commands, e-mail: gitbox-help@hive.apache.org