diff options
author | wangzhenhua <wangzhenhua@huawei.com> | 2017-02-24 10:24:59 -0800 |
---|---|---|
committer | Wenchen Fan <wenchen@databricks.com> | 2017-02-24 10:24:59 -0800 |
commit | 69d0da6373979ce5b2bcd52933b5a7660d893e88 (patch) | |
tree | 0604364d8facb22837c95564d6df4d05736477c7 /core/src/main | |
parent | 05954f32e9bde56dc1f9a72028900d705185f6d7 (diff) | |
download | spark-69d0da6373979ce5b2bcd52933b5a7660d893e88.tar.gz spark-69d0da6373979ce5b2bcd52933b5a7660d893e88.tar.bz2 spark-69d0da6373979ce5b2bcd52933b5a7660d893e88.zip |
[SPARK-17078][SQL] Show stats when explain
## What changes were proposed in this pull request?
Currently we can only check the estimated stats in logical plans by debugging. We need to provide an easier and more efficient way for developers/users.
In this pr, we add EXPLAIN COST command to show stats in the optimized logical plan.
E.g.
```
spark-sql> EXPLAIN COST select count(1) from store_returns;
...
== Optimized Logical Plan ==
Aggregate [count(1) AS count(1)#24L], Statistics(sizeInBytes=16.0 B, rowCount=1, isBroadcastable=false)
+- Project, Statistics(sizeInBytes=4.3 GB, rowCount=5.76E+8, isBroadcastable=false)
+- Relation[sr_returned_date_sk#3,sr_return_time_sk#4,sr_item_sk#5,sr_customer_sk#6,sr_cdemo_sk#7,sr_hdemo_sk#8,sr_addr_sk#9,sr_store_sk#10,sr_reason_sk#11,sr_ticket_number#12,sr_return_quantity#13,sr_return_amt#14,sr_return_tax#15,sr_return_amt_inc_tax#16,sr_fee#17,sr_return_ship_cost#18,sr_refunded_cash#19,sr_reversed_charge#20,sr_store_credit#21,sr_net_loss#22] parquet, Statistics(sizeInBytes=28.6 GB, rowCount=5.76E+8, isBroadcastable=false)
...
```
## How was this patch tested?
Add test cases.
Author: wangzhenhua <wangzhenhua@huawei.com>
Author: Zhenhua Wang <wzh_zju@163.com>
Closes #16594 from wzhfy/showStats.
Diffstat (limited to 'core/src/main')
-rw-r--r-- | core/src/main/scala/org/apache/spark/util/Utils.scala | 40 |
1 files changed, 27 insertions, 13 deletions
diff --git a/core/src/main/scala/org/apache/spark/util/Utils.scala b/core/src/main/scala/org/apache/spark/util/Utils.scala index 480240a93d..10e5233679 100644 --- a/core/src/main/scala/org/apache/spark/util/Utils.scala +++ b/core/src/main/scala/org/apache/spark/util/Utils.scala @@ -19,6 +19,7 @@ package org.apache.spark.util import java.io._ import java.lang.management.{LockInfo, ManagementFactory, MonitorInfo, ThreadInfo} +import java.math.{MathContext, RoundingMode} import java.net._ import java.nio.ByteBuffer import java.nio.channels.Channels @@ -1109,26 +1110,39 @@ private[spark] object Utils extends Logging { /** * Convert a quantity in bytes to a human-readable string such as "4.0 MB". */ - def bytesToString(size: Long): String = { + def bytesToString(size: Long): String = bytesToString(BigInt(size)) + + def bytesToString(size: BigInt): String = { + val EB = 1L << 60 + val PB = 1L << 50 val TB = 1L << 40 val GB = 1L << 30 val MB = 1L << 20 val KB = 1L << 10 - val (value, unit) = { - if (size >= 2*TB) { - (size.asInstanceOf[Double] / TB, "TB") - } else if (size >= 2*GB) { - (size.asInstanceOf[Double] / GB, "GB") - } else if (size >= 2*MB) { - (size.asInstanceOf[Double] / MB, "MB") - } else if (size >= 2*KB) { - (size.asInstanceOf[Double] / KB, "KB") - } else { - (size.asInstanceOf[Double], "B") + if (size >= BigInt(1L << 11) * EB) { + // The number is too large, show it in scientific notation. + BigDecimal(size, new MathContext(3, RoundingMode.HALF_UP)).toString() + " B" + } else { + val (value, unit) = { + if (size >= 2 * EB) { + (BigDecimal(size) / EB, "EB") + } else if (size >= 2 * PB) { + (BigDecimal(size) / PB, "PB") + } else if (size >= 2 * TB) { + (BigDecimal(size) / TB, "TB") + } else if (size >= 2 * GB) { + (BigDecimal(size) / GB, "GB") + } else if (size >= 2 * MB) { + (BigDecimal(size) / MB, "MB") + } else if (size >= 2 * KB) { + (BigDecimal(size) / KB, "KB") + } else { + (BigDecimal(size), "B") + } } + "%.1f %s".formatLocal(Locale.US, value, unit) } - "%.1f %s".formatLocal(Locale.US, value, unit) } /** |