https://github.com/apache/spark
Revision 6b4ec22e3551f930f988c44e161d1987866607a2 authored by Kazuaki Ishizaki on 10 November 2017, 20:17:49 UTC, committed by Wenchen Fan on 10 November 2017, 20:18:14 UTC
## What changes were proposed in this pull request? This PR avoids to generate a huge method for calculating a murmur3 hash for nested structs. This PR splits a huge method (e.g. `apply_4`) into multiple smaller methods. Sample program ``` val structOfString = new StructType().add("str", StringType) var inner = new StructType() for (_ <- 0 until 800) { inner = inner1.add("structOfString", structOfString) } var schema = new StructType() for (_ <- 0 until 50) { schema = schema.add("structOfStructOfStrings", inner) } GenerateMutableProjection.generate(Seq(Murmur3Hash(exprs, 42))) ``` Without this PR ``` /* 005 */ class SpecificMutableProjection extends org.apache.spark.sql.catalyst.expressions.codegen.BaseMutableProjection { /* 006 */ /* 007 */ private Object[] references; /* 008 */ private InternalRow mutableRow; /* 009 */ private int value; /* 010 */ private int value_0; ... /* 034 */ public java.lang.Object apply(java.lang.Object _i) { /* 035 */ InternalRow i = (InternalRow) _i; /* 036 */ /* 037 */ /* 038 */ /* 039 */ value = 42; /* 040 */ apply_0(i); /* 041 */ apply_1(i); /* 042 */ apply_2(i); /* 043 */ apply_3(i); /* 044 */ apply_4(i); /* 045 */ nestedClassInstance.apply_5(i); ... /* 089 */ nestedClassInstance8.apply_49(i); /* 090 */ value_0 = value; /* 091 */ /* 092 */ // copy all the results into MutableRow /* 093 */ mutableRow.setInt(0, value_0); /* 094 */ return mutableRow; /* 095 */ } /* 096 */ /* 097 */ /* 098 */ private void apply_4(InternalRow i) { /* 099 */ /* 100 */ boolean isNull5 = i.isNullAt(4); /* 101 */ InternalRow value5 = isNull5 ? null : (i.getStruct(4, 800)); /* 102 */ if (!isNull5) { /* 103 */ /* 104 */ if (!value5.isNullAt(0)) { /* 105 */ /* 106 */ final InternalRow element6400 = value5.getStruct(0, 1); /* 107 */ /* 108 */ if (!element6400.isNullAt(0)) { /* 109 */ /* 110 */ final UTF8String element6401 = element6400.getUTF8String(0); /* 111 */ value = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashUnsafeBytes(element6401.getBaseObject(), element6401.getBaseOffset(), element6401.numBytes(), value); /* 112 */ /* 113 */ } /* 114 */ /* 115 */ /* 116 */ } /* 117 */ /* 118 */ /* 119 */ if (!value5.isNullAt(1)) { /* 120 */ /* 121 */ final InternalRow element6402 = value5.getStruct(1, 1); /* 122 */ /* 123 */ if (!element6402.isNullAt(0)) { /* 124 */ /* 125 */ final UTF8String element6403 = element6402.getUTF8String(0); /* 126 */ value = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashUnsafeBytes(element6403.getBaseObject(), element6403.getBaseOffset(), element6403.numBytes(), value); /* 127 */ /* 128 */ } /* 128 */ } /* 129 */ /* 130 */ /* 131 */ } /* 132 */ /* 133 */ /* 134 */ if (!value5.isNullAt(2)) { /* 135 */ /* 136 */ final InternalRow element6404 = value5.getStruct(2, 1); /* 137 */ /* 138 */ if (!element6404.isNullAt(0)) { /* 139 */ /* 140 */ final UTF8String element6405 = element6404.getUTF8String(0); /* 141 */ value = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashUnsafeBytes(element6405.getBaseObject(), element6405.getBaseOffset(), element6405.numBytes(), value); /* 142 */ /* 143 */ } /* 144 */ /* 145 */ /* 146 */ } /* 147 */ ... /* 12074 */ if (!value5.isNullAt(798)) { /* 12075 */ /* 12076 */ final InternalRow element7996 = value5.getStruct(798, 1); /* 12077 */ /* 12078 */ if (!element7996.isNullAt(0)) { /* 12079 */ /* 12080 */ final UTF8String element7997 = element7996.getUTF8String(0); /* 12083 */ } /* 12084 */ /* 12085 */ /* 12086 */ } /* 12087 */ /* 12088 */ /* 12089 */ if (!value5.isNullAt(799)) { /* 12090 */ /* 12091 */ final InternalRow element7998 = value5.getStruct(799, 1); /* 12092 */ /* 12093 */ if (!element7998.isNullAt(0)) { /* 12094 */ /* 12095 */ final UTF8String element7999 = element7998.getUTF8String(0); /* 12096 */ value = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashUnsafeBytes(element7999.getBaseObject(), element7999.getBaseOffset(), element7999.numBytes(), value); /* 12097 */ /* 12098 */ } /* 12099 */ /* 12100 */ /* 12101 */ } /* 12102 */ /* 12103 */ } /* 12104 */ /* 12105 */ } /* 12106 */ /* 12106 */ /* 12107 */ /* 12108 */ private void apply_1(InternalRow i) { ... ``` With this PR ``` /* 005 */ class SpecificMutableProjection extends org.apache.spark.sql.catalyst.expressions.codegen.BaseMutableProjection { /* 006 */ /* 007 */ private Object[] references; /* 008 */ private InternalRow mutableRow; /* 009 */ private int value; /* 010 */ private int value_0; /* 011 */ ... /* 034 */ public java.lang.Object apply(java.lang.Object _i) { /* 035 */ InternalRow i = (InternalRow) _i; /* 036 */ /* 037 */ /* 038 */ /* 039 */ value = 42; /* 040 */ nestedClassInstance11.apply50_0(i); /* 041 */ nestedClassInstance11.apply50_1(i); ... /* 088 */ nestedClassInstance11.apply50_48(i); /* 089 */ nestedClassInstance11.apply50_49(i); /* 090 */ value_0 = value; /* 091 */ /* 092 */ // copy all the results into MutableRow /* 093 */ mutableRow.setInt(0, value_0); /* 094 */ return mutableRow; /* 095 */ } /* 096 */ ... /* 37717 */ private void apply4_0(InternalRow value5, InternalRow i) { /* 37718 */ /* 37719 */ if (!value5.isNullAt(0)) { /* 37720 */ /* 37721 */ final InternalRow element6400 = value5.getStruct(0, 1); /* 37722 */ /* 37723 */ if (!element6400.isNullAt(0)) { /* 37724 */ /* 37725 */ final UTF8String element6401 = element6400.getUTF8String(0); /* 37726 */ value = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashUnsafeBytes(element6401.getBaseObject(), element6401.getBaseOffset(), element6401.numBytes(), value); /* 37727 */ /* 37728 */ } /* 37729 */ /* 37730 */ /* 37731 */ } /* 37732 */ /* 37733 */ if (!value5.isNullAt(1)) { /* 37734 */ /* 37735 */ final InternalRow element6402 = value5.getStruct(1, 1); /* 37736 */ /* 37737 */ if (!element6402.isNullAt(0)) { /* 37738 */ /* 37739 */ final UTF8String element6403 = element6402.getUTF8String(0); /* 37740 */ value = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashUnsafeBytes(element6403.getBaseObject(), element6403.getBaseOffset(), element6403.numBytes(), value); /* 37741 */ /* 37742 */ } /* 37743 */ /* 37744 */ /* 37745 */ } /* 37746 */ /* 37747 */ if (!value5.isNullAt(2)) { /* 37748 */ /* 37749 */ final InternalRow element6404 = value5.getStruct(2, 1); /* 37750 */ /* 37751 */ if (!element6404.isNullAt(0)) { /* 37752 */ /* 37753 */ final UTF8String element6405 = element6404.getUTF8String(0); /* 37754 */ value = org.apache.spark.unsafe.hash.Murmur3_x86_32.hashUnsafeBytes(element6405.getBaseObject(), element6405.getBaseOffset(), element6405.numBytes(), value); /* 37755 */ /* 37756 */ } /* 37757 */ /* 37758 */ /* 37759 */ } /* 37760 */ /* 37761 */ } ... /* 218470 */ /* 218471 */ private void apply50_4(InternalRow i) { /* 218472 */ /* 218473 */ boolean isNull5 = i.isNullAt(4); /* 218474 */ InternalRow value5 = isNull5 ? null : (i.getStruct(4, 800)); /* 218475 */ if (!isNull5) { /* 218476 */ apply4_0(value5, i); /* 218477 */ apply4_1(value5, i); /* 218478 */ apply4_2(value5, i); ... /* 218742 */ nestedClassInstance.apply4_266(value5, i); /* 218743 */ } /* 218744 */ /* 218745 */ } ``` ## How was this patch tested? Added new test to `HashExpressionsSuite` Author: Kazuaki Ishizaki <ishizaki@jp.ibm.com> Closes #19563 from kiszk/SPARK-22284. (cherry picked from commit f2da738c76810131045e6c32533a2d13526cdaf6) Signed-off-by: Wenchen Fan <wenchen@databricks.com>
1 parent 371be22
Tip revision: 6b4ec22e3551f930f988c44e161d1987866607a2 authored by Kazuaki Ishizaki on 10 November 2017, 20:17:49 UTC
[SPARK-22284][SQL] Fix 64KB JVM bytecode limit problem in calculating hash for nested structs
[SPARK-22284][SQL] Fix 64KB JVM bytecode limit problem in calculating hash for nested structs
Tip revision: 6b4ec22
File | Mode | Size |
---|---|---|
.github | ||
R | ||
assembly | ||
bin | ||
build | ||
common | ||
conf | ||
core | ||
data | ||
dev | ||
docs | ||
examples | ||
external | ||
graphx | ||
launcher | ||
licenses | ||
mllib | ||
mllib-local | ||
project | ||
python | ||
repl | ||
resource-managers | ||
sbin | ||
sql | ||
streaming | ||
tools | ||
.gitattributes | -rw-r--r-- | 40 bytes |
.gitignore | -rw-r--r-- | 1.2 KB |
.travis.yml | -rw-r--r-- | 1.7 KB |
CONTRIBUTING.md | -rw-r--r-- | 995 bytes |
LICENSE | -rw-r--r-- | 17.5 KB |
NOTICE | -rw-r--r-- | 24.1 KB |
README.md | -rw-r--r-- | 3.7 KB |
appveyor.yml | -rw-r--r-- | 1.9 KB |
pom.xml | -rw-r--r-- | 94.8 KB |
scalastyle-config.xml | -rw-r--r-- | 17.4 KB |
Computing file changes ...