You are viewing a plain text version of this content. The canonical link for it is here.
Posted to reviews@spark.apache.org by jongwook <gi...@git.apache.org> on 2017/02/13 19:40:11 UTC
[GitHub] spark pull request #16916: [SPARK-19501] Reduce the number of HDFS RPCs duri...
GitHub user jongwook opened a pull request:
https://github.com/apache/spark/pull/16916
[SPARK-19501] Reduce the number of HDFS RPCs during YARN deployment
## What changes were proposed in this pull request?
As discussed in [JIRA](https://issues.apache.org/jira/browse/SPARK-19501), this patch addresses the problem where too many HDFS RPCs are made when there are many URIs specified in `spark.yarn.jars`, potentially adding hundreds of RTTs to YARN before the application launches. This becomes significant when submitting the application to a non-local YARN cluster (where the RTT may be in order of 100ms, for example). For each URI specified, the current implementation makes at least two HDFS RPCs, for:
- [Calling `getFileStatus()` before uploading each file to the distributed cache in `ClientDistributedCacheManager.addResource()`](https://github.com/apache/spark/blob/v2.1.0/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManager.scala#L71).
- [Resolving any symbolic links in each of the file URI](https://github.com/apache/spark/blob/v2.1.0/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala#L377-L379), which repeatedly makes HDFS RPCs until the all symlinks are resolved. (see [`FileContext.resolve(Path)`](https://github.com/apache/hadoop/blob/release-2.7.1/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FileContext.java#L2189-L2195), [`FSLinkResolver.resolve(FileContext, Path)`](https://github.com/apache/hadoop/blob/release-2.7.1/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/FSLinkResolver.java#L79-L112), and [`AbstractFileSystem.resolvePath()`](https://github.com/apache/hadoop/blob/release-2.7.1/hadoop-common-project/hadoop-common/src/main/java/org/apache/hadoop/fs/AbstractFileSystem.java#L464-L468).)
The first `getFileStatus` RPC can be removed, using `statCache` populated with the file statuses retrieved with [the previous `globStatus` call](https://github.com/apache/spark/blob/v2.1.0/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala#L531).
The second one can be largely reduced by caching the symlink resolution results in a mutable.HashMap. This patch adds a local variable in `yarn.Client.prepareLocalResources()` and passes it as an additional parameter to `yarn.Client.copyFileToRemote`. [The symlink resolution code was added in 2013](https://github.com/apache/spark/commit/a35472e1dd2ea1b5a0b1fb6b382f5a98f5aeba5a#diff-b050df3f55b82065803d6e83453b9706R187) and has not changed since. I am assuming that this is still required, but otherwise we can remove using `symlinkCache` and symlink resolution altogether.
## How was this patch tested?
This patch is based off 8e8afb3, currently the latest YARN patch on master. All tests except a few in spark-hive passed with `./dev/run-tests` on my machine, using JDK 1.8.0_112 on macOS 10.12.3; also tested myself with this modified version of SPARK 2.2.0-SNAPSHOT which performed a normal deployment and execution on a YARN cluster without errors.
You can merge this pull request into a Git repository by running:
$ git pull https://github.com/jongwook/spark SPARK-19501
Alternatively you can review and apply these changes as the patch at:
https://github.com/apache/spark/pull/16916.patch
To close this pull request, make a commit to your master/trunk branch
with (at least) the following in the commit message:
This closes #16916
----
commit 984d8180babb9f7d8b5992f97523447d6a7ca910
Author: Jong Wook Kim <jo...@nyu.edu>
Date: 2017-02-13T17:47:09Z
[SPARK-19501] Reduce the number of HDFS RPCs during YARN deployment
----
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the issue:
https://github.com/apache/spark/pull/16916
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/72832/
Test PASSed.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by vanzin <gi...@git.apache.org>.
Github user vanzin commented on the issue:
https://github.com/apache/spark/pull/16916
Merging to master.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by jongwook <gi...@git.apache.org>.
Github user jongwook commented on the issue:
https://github.com/apache/spark/pull/16916
Let me know if any further modification is needed before committing this to master. Once it is merged, I will prepare the backports to branch-2.0 and branch-2.1. Thanks.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the issue:
https://github.com/apache/spark/pull/16916
Can one of the admins verify this patch?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark pull request #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPC...
Posted by asfgit <gi...@git.apache.org>.
Github user asfgit closed the pull request at:
https://github.com/apache/spark/pull/16916
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by vanzin <gi...@git.apache.org>.
Github user vanzin commented on the issue:
https://github.com/apache/spark/pull/16916
Merged to branch-2.1 and branch-2.0 too (after running yarn tests).
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by vanzin <gi...@git.apache.org>.
Github user vanzin commented on the issue:
https://github.com/apache/spark/pull/16916
ok to test
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the issue:
https://github.com/apache/spark/pull/16916
**[Test build #72832 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/72832/testReport)** for PR 16916 at commit [`523c58c`](https://github.com/apache/spark/commit/523c58c35fc9f046c601e99a0389d7ca7c3e508f).
* This patch passes all tests.
* This patch merges cleanly.
* This patch adds no public classes.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by vanzin <gi...@git.apache.org>.
Github user vanzin commented on the issue:
https://github.com/apache/spark/pull/16916
I see. Makes sense. Pinging @tgravescs too, he wrote the original stuff that introduced symlink resolution, maybe he can comment on whether it's really necessary.
If it is, then the patch looks good to me, otherwise we could get rid of it.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by tgravescs <gi...@git.apache.org>.
Github user tgravescs commented on the issue:
https://github.com/apache/spark/pull/16916
we should not remove symlink resolution.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by jongwook <gi...@git.apache.org>.
Github user jongwook commented on the issue:
https://github.com/apache/spark/pull/16916
@vanzin [`statCache` stores the result of `getFileStatus`](https://github.com/jongwook/spark/blob/523c58c35fc9f046c601e99a0389d7ca7c3e508f/resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/ClientDistributedCacheManager.scala#L173-L185) or [`globStatus` calls to HDFS](https://github.com/jongwook/spark/blob/523c58c35fc9f046c601e99a0389d7ca7c3e508f/resource-managers/yarn/src/main/scala/org/apache/spark/deploy/yarn/Client.scala#L505-L507), which do not resolve symlinks, so unless we give up symlink resolution, I don't think that merging them is sufficient.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the issue:
https://github.com/apache/spark/pull/16916
**[Test build #72832 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/72832/testReport)** for PR 16916 at commit [`523c58c`](https://github.com/apache/spark/commit/523c58c35fc9f046c601e99a0389d7ca7c3e508f).
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the issue:
https://github.com/apache/spark/pull/16916
Merged build finished. Test PASSed.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by jongwook <gi...@git.apache.org>.
Github user jongwook commented on the issue:
https://github.com/apache/spark/pull/16916
Cool! Thank you :)
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by vanzin <gi...@git.apache.org>.
Github user vanzin commented on the issue:
https://github.com/apache/spark/pull/16916
Is it possible to merge the stat cache and the symlink cache? It seems both are sort of doing the same thing.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the issue:
https://github.com/apache/spark/pull/16916
**[Test build #72828 has finished](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/72828/testReport)** for PR 16916 at commit [`dac61b5`](https://github.com/apache/spark/commit/dac61b5e82fccd721b0e65b1a8e45381504ac2f7).
* This patch passes all tests.
* This patch merges cleanly.
* This patch adds no public classes.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by SparkQA <gi...@git.apache.org>.
Github user SparkQA commented on the issue:
https://github.com/apache/spark/pull/16916
**[Test build #72828 has started](https://amplab.cs.berkeley.edu/jenkins/job/SparkPullRequestBuilder/72828/testReport)** for PR 16916 at commit [`dac61b5`](https://github.com/apache/spark/commit/dac61b5e82fccd721b0e65b1a8e45381504ac2f7).
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the issue:
https://github.com/apache/spark/pull/16916
Merged build finished. Test PASSed.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org
[GitHub] spark issue #16916: [SPARK-19501][YARN] Reduce the number of HDFS RPCs durin...
Posted by AmplabJenkins <gi...@git.apache.org>.
Github user AmplabJenkins commented on the issue:
https://github.com/apache/spark/pull/16916
Test PASSed.
Refer to this link for build results (access rights to CI server needed):
https://amplab.cs.berkeley.edu/jenkins//job/SparkPullRequestBuilder/72828/
Test PASSed.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at infrastructure@apache.org or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org