## What changes were proposed in this pull request?
TRIM/LTRIM/RTRIM should not strips characters other than spaces, we were trimming all chars small than ASCII 0x20(space)

## How was this patch tested?
fixed existing tests.

Author: Sandeep Singh <sandeep@techaddict.me>

Closes #14924 from techaddict/SPARK-17299.

The Spark Yarn Shuffle Service doesn't re-initialize the application credentials early enough which causes any other spark executors trying to fetch from that node during a rolling upgrade to fail with "java.lang.NullPointerException: Password cannot be null if SASL is enabled".  Right now the spark shuffle service relies on the Yarn nodemanager to re-register the applications, unfortunately this is after we open the port for other executors to connect. If other executors connected before the re-register they get a null pointer exception which isn't a re-tryable exception and cause them to fail pretty quickly. To solve this I added another leveldb file so that it can save and re-initialize all the applications before opening the port for other executors to connect to it.  Adding another leveldb was simpler from the code structure point of view.

Most of the code changes are moving things to common util class.

Patch was tested manually on a Yarn cluster with rolling upgrade was happing while spark job was running. Without the patch I consistently get the NullPointerException, with the patch the job gets a few Connection refused exceptions but the retries kick in and the it succeeds.

Author: Thomas Graves <tgraves@staydecay.corp.gq1.yahoo.com>

Closes #14718 from tgravescs/SPARK-16711.

## What changes were proposed in this pull request?

Avoid allocating some 0-length arrays, esp. in UTF8String, and by using Array.empty in Scala over Array[T]()

## How was this patch tested?

Jenkins

Author: Sean Owen <sowen@cloudera.com>

Closes #14895 from srowen/SPARK-17331.

## What changes were proposed in this pull request?

Make all Java Loggers static members

## How was this patch tested?

Jenkins

Author: Sean Owen <sowen@cloudera.com>

Closes #14896 from srowen/SPARK-17332.

## What changes were proposed in this pull request?

When a thread is a Netty's FastThreadLocalThread, Netty will use its fast ThreadLocal implementation. It has a better performance than JDK's (See the benchmark results in https://github.com/netty/netty/pull/4417, note: it's not a fix to Netty's FastThreadLocal. It just fixed an issue in Netty's benchmark codes)

This PR just changed the ThreadFactory to Netty's DefaultThreadFactory which will use FastThreadLocalThread. There is also a minor change to the thread names. See https://github.com/netty/netty/blob/netty-4.0.22.Final/common/src/main/java/io/netty/util/concurrent/DefaultThreadFactory.java#L94

## How was this patch tested?

Author: Shixiong Zhu <shixiong@databricks.com>

Closes #14879 from zsxwing/netty-thread.

[SPARK-17231][CORE] Avoid building debug or trace log messages unless the respective log level is enabled

(This PR addresses https://issues.apache.org/jira/browse/SPARK-17231)

## What changes were proposed in this pull request?

While debugging the performance of a large GraphX connected components computation, we found several places in the `network-common` and `network-shuffle` code bases where trace or debug log messages are constructed even if the respective log level is disabled. According to YourKit, these constructions were creating substantial churn in the eden region. Refactoring the respective code to avoid these unnecessary constructions except where necessary led to a modest but measurable reduction in our job's task time, GC time and the ratio thereof.

## How was this patch tested?

We computed the connected components of a graph with about 2.6 billion vertices and 1.7 billion edges four times. We used four different EC2 clusters each with 8 r3.8xl worker nodes. Two test runs used Spark master. Two used Spark master + this PR. The results from the first test run, master and master+PR:
![master](https://cloud.githubusercontent.com/assets/833693/17951634/7471cbca-6a18-11e6-9c26-78afe9319685.jpg)
![logging_perf_improvements](https://cloud.githubusercontent.com/assets/833693/17951632/7467844e-6a18-11e6-9a0e-053dc7650413.jpg)

The results from the second test run, master and master+PR:
![master 2](https://cloud.githubusercontent.com/assets/833693/17951633/746dd6aa-6a18-11e6-8e27-606680b3f105.jpg)
![logging_perf_improvements 2](https://cloud.githubusercontent.com/assets/833693/17951631/74488710-6a18-11e6-8a32-08692f373386.jpg)

Though modest, I believe these results are significant.

Author: Michael Allman <michael@videoamp.com>

Closes #14798 from mallman/spark-17231-logging_perf_improvements.

## # What changes were proposed in this pull request?

From the spark of version 2.0.0 , when MemoryMode.OFF_HEAP is set , whether the architecture supports unaligned access or not is checked. If the check doesn't pass, exception is raised.

We know that AArch64 also supports unaligned access , but now only i386, x86, amd64, and X86_64 are included.

I think we should include aarch64 when performing the check.

## How was this patch tested?

Unit test suite

Author: Richael <Richael.Zhuang@arm.com>

Closes #14700 from yimuxi/zym_change_unsafe.

Author: Josh Rosen <joshrosen@databricks.com>

Closes #14499 from JoshRosen/hotfix.

## What changes were proposed in this pull request?

Shuffle fetch on large intermediate dataset is slow because the shuffle service open/close the index file for each shuffle fetch. This change introduces a cache for the index information so that we can avoid accessing the index files for each block fetch

## How was this patch tested?

Tested by running a job on the cluster and the shuffle read time was reduced by 50%.

Author: Sital Kedia <skedia@fb.com>

Closes #12944 from sitalkedia/shuffle_service.

[SPARK-16535][BUILD] In pom.xml, remove groupId which is redundant definition and inherited from the parent

https://issues.apache.org/jira/browse/SPARK-16535

## What changes were proposed in this pull request?

When I scan through the pom.xml of sub projects, I found this warning as below and attached screenshot
```
Definition of groupId is redundant, because it's inherited from the parent
```
![screen shot 2016-07-13 at 3 13 11 pm](https://cloud.githubusercontent.com/assets/3925641/16823121/744f893e-4916-11e6-8a52-042f83b9db4e.png)

I've tried to remove some of the lines with groupId definition, and the build on my local machine is still ok.
```
<groupId>org.apache.spark</groupId>
```
As I just find now `<maven.version>3.3.9</maven.version>` is being used in Spark 2.x, and Maven-3 supports versionless parent elements: Maven 3 will remove the need to specify the parent version in sub modules. THIS is great (in Maven 3.1).

ref: http://stackoverflow.com/questions/3157240/maven-3-worth-it/3166762#3166762

## How was this patch tested?

I've tested by re-building the project, and build succeeded.

Author: Xin Ren <iamshrek@126.com>

Closes #14189 from keypointt/SPARK-16535.

## What changes were proposed in this pull request?

This PR fixes four java linter `LineLength` errors. Those are all `LineLength` errors, but we had better remove all java linter errors before release.

## How was this patch tested?

After pass the Jenkins, `./dev/lint-java`.

Author: Dongjoon Hyun <dongjoon@apache.org>

Closes #14255 from dongjoon-hyun/minor_java_linter.

This prevents the NM from starting when something is wrong, which would
lead to later errors which are confusing and harder to debug.

Added a unit test to verify startup fails if something is wrong.

Author: Marcelo Vanzin <vanzin@cloudera.com>

Closes #14162 from vanzin/SPARK-16505.

## What changes were proposed in this pull request?

Due to the changes of [SPARK-14963](https://issues.apache.org/jira/browse/SPARK-14963), external shuffle recovery file name is changed mistakenly, so here change it back to the previous file name.

This only affects the master branch, branch-2.0 is correct [here](https://github.com/apache/spark/blob/branch-2.0/common/network-yarn/src/main/java/org/apache/spark/network/yarn/YarnShuffleService.java#L195).

## How was this patch tested?

N/A

Author: jerryshao <sshao@hortonworks.com>

Closes #14197 from jerryshao/fix-typo-file-name.

## What changes were proposed in this pull request?

Fix Java style errors and remove unused imports, which are randomly found

## How was this patch tested?

Tested on my local machine.

Author: Xin Ren <iamshrek@126.com>

Closes #14161 from keypointt/SPARK-16437.

## What changes were proposed in this pull request?

Since externalShuffleService is essential for spark, better monitoring for shuffle service is necessary. In order to do so, we added various metrics in shuffle service and imported into ExternalShuffleServiceSource for metric system.
Metrics added in shuffle service:
* registeredExecutorsSize
* openBlockRequestLatencyMillis
* registerExecutorRequestLatencyMillis
* blockTransferRateBytes

JIRA Issue: https://issues.apache.org/jira/browse/SPARK-16405

## How was this patch tested?

Some test cases are added to verify metrics as expected in metric system. Those unit test cases are shown in `ExternalShuffleBlockHandlerSuite `

Author: Yangyang Liu <yangyangliu@fb.com>

Closes #14080 from lovexi/yangyang-metrics.

## What changes were proposed in this pull request?
After SPARK-16476 (committed earlier today as #14128), we can finally bump the version number.

## How was this patch tested?
N/A

Author: Reynold Xin <rxin@databricks.com>

Closes #14130 from rxin/SPARK-16477.

## What changes were proposed in this pull request?

This uses the try/finally pattern to ensure streams are closed after use. `UnsafeShuffleWriter` wasn't closing compression streams, causing them to leak resources until garbage collected. This was causing a problem with codecs that use off-heap memory.

## How was this patch tested?

Current tests are sufficient. This should not change behavior.

Author: Ryan Blue <blue@apache.org>

Closes #14093 from rdblue/SPARK-16420-unsafe-shuffle-writer-leak.

## What changes were proposed in this pull request?

This patches `MemoryAllocator` to fill clean and freed memory with known byte values, similar to https://github.com/jemalloc/jemalloc/wiki/Use-Case:-Find-a-memory-corruption-bug . Memory filling is flag-enabled in test only by default.

## How was this patch tested?

Unit test that it's on in test.

cc sameeragarwal

Author: Eric Liang <ekl@databricks.com>

Closes #13983 from ericl/spark-16021.

## What changes were proposed in this pull request?
Shade the netty.io namespace so that we can use it in shuffle independent of the dependencies being pulled by hadoop jars.

## How was this patch tested?
Ran a decent job involving shuffle write/read and tested the new spark-x-yarn-shuffle jar. After shading netty.io namespace, the nodemanager loads and shuffle job completes successfully.

Author: Dhruve Ashar <dhruveashar@gmail.com>

Closes #13739 from dhruve/bug/SPARK-16018.

## What changes were proposed in this pull request?

Currently, the memory for temporary buffer used by TimSort is always allocated as on-heap without bookkeeping, it could cause OOM both in on-heap and off-heap mode.

This PR will try to manage that by preallocate it together with the pointer array, same with RadixSort. It both works for on-heap and off-heap mode.

This PR also change the loadFactor of BytesToBytesMap to 0.5 (it was 0.70), it enables use to radix sort also makes sure that we have enough memory for timsort.

## How was this patch tested?

Existing tests.

Author: Davies Liu <davies@databricks.com>

Closes #13318 from davies/fix_timsort.

## What changes were proposed in this pull request?

This change resolves a number of build warnings that have accumulated, before 2.x. It does not address a large number of deprecation warnings, especially related to the Accumulator API. That will happen separately.

## How was this patch tested?

Jenkins

Author: Sean Owen <sowen@cloudera.com>

Closes #13377 from srowen/BuildWarnings.

## What changes were proposed in this pull request?

Remove call to Process.isAlive -- Java 8 only. Introduced in https://github.com/apache/spark/pull/13042 / SPARK-15263

## How was this patch tested?

Jenkins tests

Author: Sean Owen <sowen@cloudera.com>

Closes #13174 from srowen/SPARK-15386.

## What changes were proposed in this pull request?

Jira: https://issues.apache.org/jira/browse/SPARK-15263

The current logic for directory cleanup is slow because it does directory listing, recurses over child directories, checks for symbolic links, deletes leaf files and finally deletes the dirs when they are empty. There is back-and-forth switching from kernel space to user space while doing this. Since most of the deployment backends would be Unix systems, we could essentially just do `rm -rf` so that entire deletion logic runs in kernel space.

The current Java based impl in Spark seems to be similar to what standard libraries like guava and commons IO do (eg. http://svn.apache.org/viewvc/commons/proper/io/trunk/src/main/java/org/apache/commons/io/FileUtils.java?view=markup#l1540). However, guava removed this method in favour of shelling out to an operating system command (like in this PR). See the `Deprecated` note in older javadocs for guava for details : http://google.github.io/guava/releases/10.0.1/api/docs/com/google/common/io/Files.html#deleteRecursively(java.io.File)

Ideally, Java should be providing such APIs so that users won't have to do such things to get platform specific code. Also, its not just about speed, but also handling race conditions while doing at FS deletions is tricky. I could find this bug for Java in similar context : http://bugs.java.com/bugdatabase/view_bug.do?bug_id=7148952

## How was this patch tested?

I am relying on existing test cases to test the method. If there are suggestions about testing it, welcome to hear about it.

## Performance gains

*Input setup* : Created a nested directory structure of depth 3 and each entry having 50 sub-dirs. The input being cleaned up had total ~125k dirs.

Ran both approaches (in isolation) for 6 times to get average numbers:

Native Java cleanup  | `rm -rf` as a separate process
------------ | -------------
10.04 sec | 4.11 sec

This change made deletion 2.4 times faster for the given test input.

Author: Tejas Patil <tejasp@fb.com>

Closes #13042 from tejasapatil/delete_recursive.

## What changes were proposed in this pull request?

(See https://github.com/apache/spark/pull/12416 where most of this was already reviewed and committed; this is just the module structure and move part. This change does not move the annotations into test scope, which was the apparently problem last time.)

Rename `spark-test-tags` -> `spark-tags`; move common annotations like `Since` to `spark-tags`

## How was this patch tested?

Jenkins tests.

Author: Sean Owen <sowen@cloudera.com>

Closes #13074 from srowen/SPARK-15290.

## What changes were proposed in this pull request?

From Hadoop 2.5+, Yarn NM supports NM recovery which using recovery path for auxiliary services such as spark_shuffle, mapreduce_shuffle. So here change to use this path install of NM local dir if NM recovery is enabled.

## How was this patch tested?

Unit test + local test.

Author: jerryshao <sshao@hortonworks.com>

Closes #12994 from jerryshao/SPARK-14963.

## What changes were proposed in this pull request?
Remove LazyFileRegion instead use netty's DefaultFileRegion, since It was created so that we didn't create a file descriptor before having to send the file.

## How was this patch tested?
Existing tests

Author: Sandeep Singh <sandeep@techaddict.me>

Closes #12977 from techaddict/SPARK-15178.

[SPARK-15134][EXAMPLE] Indent SparkSession builder patterns and update binary_classification_metrics_example.py

## What changes were proposed in this pull request?

This issue addresses the comments in SPARK-15031 and also fix java-linter errors.
- Use multiline format in SparkSession builder patterns.
- Update `binary_classification_metrics_example.py` to use `SparkSession`.
- Fix Java Linter errors (in SPARK-13745, SPARK-15031, and so far)

## How was this patch tested?

After passing the Jenkins tests and run `dev/lint-java` manually.

Author: Dongjoon Hyun <dongjoon@apache.org>

Closes #12911 from dongjoon-hyun/SPARK-15134.

## What changes were proposed in this pull request?

Add more informative logging in the external shuffle service to aid in debugging who is connecting to the YARN Nodemanager when the external shuffle service runs under it.

## How was this patch tested?

Ran and saw logs coming out in log file.

Author: Thomas Graves <tgraves@staydecay.corp.gq1.yahoo.com>

Closes #12900 from tgravescs/SPARK-15121.

This reverts commit dae538a4.

## What changes were proposed in this pull request?

This PR adds `since` tag into the matrix and vector classes in spark-mllib-local.

## How was this patch tested?

Scala-style checks passed.

Author: Pravin Gadakh <prgadakh@in.ibm.com>

Closes #12416 from pravingadakh/SPARK-14613.

## What changes were proposed in this pull request?

Use Long.parseLong which returns a primative.
Use a series of appends() reduces the creation of an extra StringBuilder type

## How was this patch tested?

Unit tests

Author: Azeem Jiva <azeemj@gmail.com>

Closes #12520 from javawithjiva/minor.

## What changes were proposed in this pull request?
SPARK-12130 make 2.0 shuffle service incompatible with 1.x. So from discussion: [http://apache-spark-developers-list.1001551.n3.nabble.com/YARN-Shuffle-service-and-its-compatibility-td17222.html](url) we should maintain compatibility between Spark 1.x and Spark 2.x's shuffle service.
I put string comparison into executor's register at first avoid string comparison in getBlockData every time.

## How was this patch tested?
N/A

Author: Lianhui Wang <lianhuiwang09@gmail.com>

Closes #12568 from lianhuiwang/SPARK-14731.

## What changes were proposed in this pull request?
The sort shuffle manager has been the default since Spark 1.2. It is time to remove the old hash shuffle manager.

## How was this patch tested?
Removed some tests related to the old manager.

Author: Reynold Xin <rxin@databricks.com>

Closes #12423 from rxin/SPARK-14667.

## What changes were proposed in this pull request?
This patch changes the connection creation logic in the network client module to avoid DNS resolution when reusing connections.

## How was this patch tested?
Testing in production. This is too difficult to test in isolation (for high fidelity unit tests, we'd need to change the DNS resolution behavior in the JVM).

Author: Reynold Xin <rxin@databricks.com>

Closes #12315 from rxin/SPARK-14547.

The current package name uses a dash, which is a little weird but seemed
to work. That is, until a new test tried to mock a class that references
one of those shaded types, and then things started failing.

Most changes are just noise to fix the logging configs.

For reference, SPARK-8815 also raised this issue, although at the time it
did not cause any issues in Spark, so it was not addressed.

Author: Marcelo Vanzin <vanzin@cloudera.com>

Closes #11941 from vanzin/SPARK-14134.

## What changes were proposed in this pull request?
When netty transfer data that is not `FileRegion`, data will be in format of `ByteBuf`, If the data is large, there will occur significant performance issue because there is memory copy underlying in `sun.nio.ch.IOUtil.write`, the CPU is 100% used, and network is very low.

In this PR, if data size is large, we will split it into small chunks to call `WritableByteChannel.write()`, so that avoid wasting of memory copy. Because the data can't be written within a single write, and it will call `transferTo` multiple times.

## How was this patch tested?
Spark unit test and manual test.
Manual test:
`sc.parallelize(Array(1,2,3),3).mapPartitions(a=>Array(new Array[Double](1024 * 1024 * 50)).iterator).reduce((a,b)=> a).length`

For more details, please refer to [SPARK-14290](https://issues.apache.org/jira/browse/SPARK-14290)

Author: Zhang, Liye <liye.zhang@intel.com>

Closes #12083 from liyezhang556520/spark-14290.

## What changes were proposed in this pull request?

This PR contains the following 5 types of maintenance fix over 59 files (+94 lines, -93 lines).
- Fix typos(exception/log strings, testcase name, comments) in 44 lines.
- Fix lint-java errors (MaxLineLength) in 6 lines. (New codes after SPARK-14011)
- Use diamond operators in 40 lines. (New codes after SPARK-13702)
- Fix redundant semicolon in 5 lines.
- Rename class `InferSchemaSuite` to `CSVInferSchemaSuite` in CSVInferSchemaSuite.scala.

## How was this patch tested?

Manual and pass the Jenkins tests.

Author: Dongjoon Hyun <dongjoon@apache.org>

Closes #12139 from dongjoon-hyun/SPARK-14355.

This patch adds support for caching blocks in the executor processes using direct / off-heap memory.

## User-facing changes

**Updated semantics of `OFF_HEAP` storage level**: In Spark 1.x, the `OFF_HEAP` storage level indicated that an RDD should be cached in Tachyon. Spark 2.x removed the external block store API that Tachyon caching was based on (see #10752 / SPARK-12667), so `OFF_HEAP` became an alias for `MEMORY_ONLY_SER`. As of this patch, `OFF_HEAP` means "serialized and cached in off-heap memory or on disk". Via the `StorageLevel` constructor, `useOffHeap` can be set if `serialized == true` and can be used to construct custom storage levels which support replication.

**Storage UI reporting**: the storage UI will now report whether in-memory blocks are stored on- or off-heap.

**Only supported by UnifiedMemoryManager**: for simplicity, this feature is only supported when the default UnifiedMemoryManager is used; applications which use the legacy memory manager (`spark.memory.useLegacyMode=true`) are not currently able to allocate off-heap storage memory, so using off-heap caching will fail with an error when legacy memory management is enabled. Given that we plan to eventually remove the legacy memory manager, this is not a significant restriction.

**Memory management policies:** the policies for dividing available memory between execution and storage are the same for both on- and off-heap memory. For off-heap memory, the total amount of memory available for use by Spark is controlled by `spark.memory.offHeap.size`, which is an absolute size. Off-heap storage memory obeys `spark.memory.storageFraction` in order to control the amount of unevictable storage memory. For example, if `spark.memory.offHeap.size` is 1 gigabyte and Spark uses the default `storageFraction` of 0.5, then up to 500 megabytes of off-heap cached blocks will be protected from eviction due to execution memory pressure. If necessary, we can split `spark.memory.storageFraction` into separate on- and off-heap configurations, but this doesn't seem necessary now and can be done later without any breaking changes.

**Use of off-heap memory does not imply use of off-heap execution (or vice-versa)**: for now, the settings controlling the use of off-heap execution memory (`spark.memory.offHeap.enabled`) and off-heap caching are completely independent, so Spark SQL can be configured to use off-heap memory for execution while continuing to cache blocks on-heap. If desired, we can change this in a followup patch so that `spark.memory.offHeap.enabled` affect the default storage level for cached SQL tables.

## Internal changes

- Rename `ByteArrayChunkOutputStream` to `ChunkedByteBufferOutputStream`
  - It now returns a `ChunkedByteBuffer` instead of an array of byte arrays.
  - Its constructor now accept an `allocator` function which is called to allocate `ByteBuffer`s. This allows us to control whether it allocates regular ByteBuffers or off-heap DirectByteBuffers.
  - Because block serialization is now performed during the unroll process, a `ChunkedByteBufferOutputStream` which is configured with a `DirectByteBuffer` allocator will use off-heap memory for both unroll and storage memory.
- The `MemoryStore`'s MemoryEntries now tracks whether blocks are stored on- or off-heap.
  - `evictBlocksToFreeSpace()` now accepts a `MemoryMode` parameter so that we don't try to evict off-heap blocks in response to on-heap memory pressure (or vice-versa).
- Make sure that off-heap buffers are properly de-allocated during MemoryStore eviction.
- The JVM limits the total size of allocated direct byte buffers using the `-XX:MaxDirectMemorySize` flag and the default tends to be fairly low (< 512 megabytes in some JVMs). To work around this limitation, this patch adds a custom DirectByteBuffer allocator which ignores this memory limit.

Author: Josh Rosen <joshrosen@databricks.com>

Closes #11805 from JoshRosen/off-heap-caching.

## What changes were proposed in this pull request?
In this patch, we set the initial `maxNumComponents` to `Integer.MAX_VALUE` instead of the default size ( which is 16) when allocating `compositeBuffer` in `TransportFrameDecoder` because `compositeBuffer` will introduce too many memory copies underlying if `compositeBuffer` is with default `maxNumComponents` when the frame size is large (which result in many transport messages). For details, please refer to [SPARK-14242](https://issues.apache.org/jira/browse/SPARK-14242).

## How was this patch tested?
spark unit tests and manual tests.
For manual tests, we can reproduce the performance issue with following code:
`sc.parallelize(Array(1,2,3),3).mapPartitions(a=>Array(new Array[Double](1024 * 1024 * 50)).iterator).reduce((a,b)=> a).length`
It's easy to see the performance gain, both from the running time and CPU usage.

Author: Zhang, Liye <liye.zhang@intel.com>

Closes #12038 from liyezhang556520/spark-14242.

## What changes were proposed in this pull request?

It would be very helpful for network performance investigation if we log the time spent on connecting and resolving host.

## How was this patch tested?

Jenkins unit tests.

Author: Shixiong Zhu <shixiong@databricks.com>

Closes #12046 from zsxwing/connection-time.