[GitHub] [spark] alkis commented on a diff in pull request #40301: [SPARK-42685][CORE] Optimize Utils.bytesToString routines

["alkis (via GitHub)" <gi...@apache.org>]

alkis commented on code in PR #40301:
URL: https://github.com/apache/spark/pull/40301#discussion_r1130795171


##########
core/src/main/scala/org/apache/spark/util/Utils.scala:
##########
@@ -1305,41 +1305,30 @@ private[spark] object Utils extends Logging {
     (JavaUtils.byteStringAsBytes(str) / 1024 / 1024).toInt
   }
 
+  private[this] val siByteSizes =
+    Array(1L << 60, 1L << 50, 1L << 40, 1L << 30, 1L << 20, 1L << 10, 1)
+  private[this] val siByteSuffixes =
+    Array("EiB", "PiB", "TiB", "GiB", "MiB", "KiB", "B")
   /**
    * Convert a quantity in bytes to a human-readable string such as "4.0 MiB".
    */
-  def bytesToString(size: Long): String = bytesToString(BigInt(size))
+  def bytesToString(size: Long): String = {
+    var i = 0
+    while (i < siByteSizes.length - 1 && size < 2 * siByteSizes(i)) i += 1
+    "%.1f %s".formatLocal(Locale.US, size.toDouble / siByteSizes(i), siByteSuffixes(i))
+  }
 
   def bytesToString(size: BigInt): String = {
     val EiB = 1L << 60
-    val PiB = 1L << 50
-    val TiB = 1L << 40
-    val GiB = 1L << 30
-    val MiB = 1L << 20
-    val KiB = 1L << 10
-
-    if (size >= BigInt(1L << 11) * EiB) {
+    if (size.isValidLong) {
+      // Common case, most sizes fit in 64 bits and all ops on BigInt are order(s) of magnitude
+      // slower than Long/Double.
+      bytesToString(size.toLong)
+    } else if (size < BigInt(2000) * EiB) {

Review Comment:
   Changed it back to match.



-- 
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: reviews-unsubscribe@spark.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org


---------------------------------------------------------------------
To unsubscribe, e-mail: reviews-unsubscribe@spark.apache.org
For additional commands, e-mail: reviews-help@spark.apache.org