class HashPartitioner(partitions: Int) extends Partitioner {
require(partitions >= 0, s"Number of partitions ($partitions) cannot be
negative.")
def numPartitions: Int = partitions
def getPartition(key: Any): Int = key match {
case null => 0
case _ => Utils.nonNegativeMod(key.hashCode, numPartitions)
}
override def equals(other: Any): Boolean = other match {
case h: HashPartitioner =>
h.numPartitions == numPartitions
case _ =>
false
}
override def hashCode: Int = numPartitions
}
2. Range分区
说明
将一定范围内的数据映射到一个分区中,尽量保证每个分区数据均匀,而且分区间有序。
源码
class RangePartitioner[K : Ordering : ClassTag, V](
partitions: Int,
rdd: RDD[_ <: Product2[K, V]],
private var ascending: Boolean = true)
extends Partitioner {
// We allow partitions = 0, which happens when sorting an empty RDD under the
default settings.
require(partitions >= 0, s"Number of partitions cannot be negative but found
$partitions.")
private var ordering = implicitly[Ordering[K]]
// An array of upper bounds for the first (partitions - 1) partitions
private var rangeBounds: Array[K] = {
…
}
def numPartitions: Int = rangeBounds.length + 1
private var binarySearch: ((Array[K], K) => Int) =
CollectionsUtils.makeBinarySearch[K]
def getPartition(key: Any): Int = {
val k = key.asInstanceOf[K]
var partition = 0
if (rangeBounds.length <= 128) {
// If we have less than 128 partitions naive search
while (partition < rangeBounds.length && ordering.gt(k,
rangeBounds(partition))) {
partition += 1
}
} else {
// Determine which binary search method to use only once.
partition = binarySearch(rangeBounds, k)
// binarySearch either returns the match location or -[insertion point]-1
if (partition < 0) {
partition = -partition-1
}
if (partition > rangeBounds.length) {
partition = rangeBounds.length
}
}
if (ascending) {
partition
} else {
rangeBounds.length - partition
}
}
override def equals(other: Any): Boolean = other match {
…
}
override def hashCode(): Int = {
…
}
@throws(classOf[IOException])
private def writeObject(out: ObjectOutputStream): Unit =
Utils.tryOrIOException {
…
}
@throws(classOf[IOException])
private def readObject(in: ObjectInputStream): Unit = Utils.tryOrIOException
{
…
}
}
3. 用户自定义分区
说明
用户可以根据自己的需要,自定义分区个数。
案例实操
最后
小编利用空余时间整理了一份《MySQL性能调优手册》,初衷也很简单,就是希望能够帮助到大家,减轻大家的负担和节省时间。
关于这个,给大家看一份学习大纲(PDF)文件,每一个分支里面会有详细的介绍。
这里都是以图片形式展示介绍,如要下载原文件以及更多的性能调优笔记(MySQL+Tomcat+JVM)!
案例实操
最后
小编利用空余时间整理了一份《MySQL性能调优手册》,初衷也很简单,就是希望能够帮助到大家,减轻大家的负担和节省时间。
关于这个,给大家看一份学习大纲(PDF)文件,每一个分支里面会有详细的介绍。
[外链图片转存中…(img-pHSH35Zu-1714447238451)]
这里都是以图片形式展示介绍,如要下载原文件以及更多的性能调优笔记(MySQL+Tomcat+JVM)!