diff --git a/NOTICE.txt b/NOTICE.txt
index eb58716562..6c73c2eeba 100644
--- a/NOTICE.txt
+++ b/NOTICE.txt
@@ -29,3 +29,5 @@ Copyright 1995-2006 Mort Bay Consulting Pty Ltd
YAML support provided by snakeyaml (http://code.google.com/p/snakeyaml/).
Copyright (c) 2008-2010 Andrey Somov
+
+Compression support provided by snappy-java (http://code.google.com/p/snappy-java/)
diff --git a/build.xml b/build.xml
index bd00187caa..1583987663 100644
--- a/build.xml
+++ b/build.xml
@@ -988,6 +988,14 @@ url=${svn.entry.url}?pathrev=${svn.entry.commit.revision}
+
+
+
+
+
+
+
+
compaction_strategy_options,
31: optional i32 row_cache_keys_to_save,
+ 32: optional bool compression,
}
/* describes a keyspace. */
diff --git a/interface/thrift/gen-java/org/apache/cassandra/thrift/Cassandra.java b/interface/thrift/gen-java/org/apache/cassandra/thrift/Cassandra.java
index 717370c646..d8705dcdf3 100644
--- a/interface/thrift/gen-java/org/apache/cassandra/thrift/Cassandra.java
+++ b/interface/thrift/gen-java/org/apache/cassandra/thrift/Cassandra.java
@@ -9086,8 +9086,6 @@ public class Cassandra {
private void readObject(java.io.ObjectInputStream in) throws java.io.IOException, ClassNotFoundException {
try {
- // it doesn't seem like you should have to do this, but java serialization is wacky, and doesn't call the default constructor.
- __isset_bit_vector = new BitSet(1);
read(new org.apache.thrift.protocol.TCompactProtocol(new org.apache.thrift.transport.TIOStreamTransport(in)));
} catch (org.apache.thrift.TException te) {
throw new java.io.IOException(te);
diff --git a/interface/thrift/gen-java/org/apache/cassandra/thrift/CfDef.java b/interface/thrift/gen-java/org/apache/cassandra/thrift/CfDef.java
index 9ab9aa2203..3ca584c095 100644
--- a/interface/thrift/gen-java/org/apache/cassandra/thrift/CfDef.java
+++ b/interface/thrift/gen-java/org/apache/cassandra/thrift/CfDef.java
@@ -72,6 +72,7 @@ public class CfDef implements org.apache.thrift.TBase, jav
private static final org.apache.thrift.protocol.TField COMPACTION_STRATEGY_FIELD_DESC = new org.apache.thrift.protocol.TField("compaction_strategy", org.apache.thrift.protocol.TType.STRING, (short)29);
private static final org.apache.thrift.protocol.TField COMPACTION_STRATEGY_OPTIONS_FIELD_DESC = new org.apache.thrift.protocol.TField("compaction_strategy_options", org.apache.thrift.protocol.TType.MAP, (short)30);
private static final org.apache.thrift.protocol.TField ROW_CACHE_KEYS_TO_SAVE_FIELD_DESC = new org.apache.thrift.protocol.TField("row_cache_keys_to_save", org.apache.thrift.protocol.TType.I32, (short)31);
+ private static final org.apache.thrift.protocol.TField COMPRESSION_FIELD_DESC = new org.apache.thrift.protocol.TField("compression", org.apache.thrift.protocol.TType.BOOL, (short)32);
public String keyspace;
public String name;
@@ -100,6 +101,7 @@ public class CfDef implements org.apache.thrift.TBase, jav
public String compaction_strategy;
public Map compaction_strategy_options;
public int row_cache_keys_to_save;
+ public boolean compression;
/** The set of fields this struct contains, along with convenience methods for finding and manipulating them. */
public enum _Fields implements org.apache.thrift.TFieldIdEnum {
@@ -129,7 +131,8 @@ public class CfDef implements org.apache.thrift.TBase, jav
KEY_ALIAS((short)28, "key_alias"),
COMPACTION_STRATEGY((short)29, "compaction_strategy"),
COMPACTION_STRATEGY_OPTIONS((short)30, "compaction_strategy_options"),
- ROW_CACHE_KEYS_TO_SAVE((short)31, "row_cache_keys_to_save");
+ ROW_CACHE_KEYS_TO_SAVE((short)31, "row_cache_keys_to_save"),
+ COMPRESSION((short)32, "compression");
private static final Map byName = new HashMap();
@@ -198,6 +201,8 @@ public class CfDef implements org.apache.thrift.TBase, jav
return COMPACTION_STRATEGY_OPTIONS;
case 31: // ROW_CACHE_KEYS_TO_SAVE
return ROW_CACHE_KEYS_TO_SAVE;
+ case 32: // COMPRESSION
+ return COMPRESSION;
default:
return null;
}
@@ -252,7 +257,8 @@ public class CfDef implements org.apache.thrift.TBase, jav
private static final int __REPLICATE_ON_WRITE_ISSET_ID = 11;
private static final int __MERGE_SHARDS_CHANCE_ISSET_ID = 12;
private static final int __ROW_CACHE_KEYS_TO_SAVE_ISSET_ID = 13;
- private BitSet __isset_bit_vector = new BitSet(14);
+ private static final int __COMPRESSION_ISSET_ID = 14;
+ private BitSet __isset_bit_vector = new BitSet(15);
public static final Map<_Fields, org.apache.thrift.meta_data.FieldMetaData> metaDataMap;
static {
@@ -314,6 +320,8 @@ public class CfDef implements org.apache.thrift.TBase, jav
new org.apache.thrift.meta_data.FieldValueMetaData(org.apache.thrift.protocol.TType.STRING))));
tmpMap.put(_Fields.ROW_CACHE_KEYS_TO_SAVE, new org.apache.thrift.meta_data.FieldMetaData("row_cache_keys_to_save", org.apache.thrift.TFieldRequirementType.OPTIONAL,
new org.apache.thrift.meta_data.FieldValueMetaData(org.apache.thrift.protocol.TType.I32)));
+ tmpMap.put(_Fields.COMPRESSION, new org.apache.thrift.meta_data.FieldMetaData("compression", org.apache.thrift.TFieldRequirementType.OPTIONAL,
+ new org.apache.thrift.meta_data.FieldValueMetaData(org.apache.thrift.protocol.TType.BOOL)));
metaDataMap = Collections.unmodifiableMap(tmpMap);
org.apache.thrift.meta_data.FieldMetaData.addStructMetaDataMap(CfDef.class, metaDataMap);
}
@@ -418,6 +426,7 @@ public class CfDef implements org.apache.thrift.TBase, jav
this.compaction_strategy_options = __this__compaction_strategy_options;
}
this.row_cache_keys_to_save = other.row_cache_keys_to_save;
+ this.compression = other.compression;
}
public CfDef deepCopy() {
@@ -470,6 +479,8 @@ public class CfDef implements org.apache.thrift.TBase, jav
this.compaction_strategy_options = null;
setRow_cache_keys_to_saveIsSet(false);
this.row_cache_keys_to_save = 0;
+ setCompressionIsSet(false);
+ this.compression = false;
}
public String getKeyspace() {
@@ -1142,6 +1153,29 @@ public class CfDef implements org.apache.thrift.TBase, jav
__isset_bit_vector.set(__ROW_CACHE_KEYS_TO_SAVE_ISSET_ID, value);
}
+ public boolean isCompression() {
+ return this.compression;
+ }
+
+ public CfDef setCompression(boolean compression) {
+ this.compression = compression;
+ setCompressionIsSet(true);
+ return this;
+ }
+
+ public void unsetCompression() {
+ __isset_bit_vector.clear(__COMPRESSION_ISSET_ID);
+ }
+
+ /** Returns true if field compression is set (has been assigned a value) and false otherwise */
+ public boolean isSetCompression() {
+ return __isset_bit_vector.get(__COMPRESSION_ISSET_ID);
+ }
+
+ public void setCompressionIsSet(boolean value) {
+ __isset_bit_vector.set(__COMPRESSION_ISSET_ID, value);
+ }
+
public void setFieldValue(_Fields field, Object value) {
switch (field) {
case KEYSPACE:
@@ -1360,6 +1394,14 @@ public class CfDef implements org.apache.thrift.TBase, jav
}
break;
+ case COMPRESSION:
+ if (value == null) {
+ unsetCompression();
+ } else {
+ setCompression((Boolean)value);
+ }
+ break;
+
}
}
@@ -1446,6 +1488,9 @@ public class CfDef implements org.apache.thrift.TBase, jav
case ROW_CACHE_KEYS_TO_SAVE:
return new Integer(getRow_cache_keys_to_save());
+ case COMPRESSION:
+ return new Boolean(isCompression());
+
}
throw new IllegalStateException();
}
@@ -1511,6 +1556,8 @@ public class CfDef implements org.apache.thrift.TBase, jav
return isSetCompaction_strategy_options();
case ROW_CACHE_KEYS_TO_SAVE:
return isSetRow_cache_keys_to_save();
+ case COMPRESSION:
+ return isSetCompression();
}
throw new IllegalStateException();
}
@@ -1771,6 +1818,15 @@ public class CfDef implements org.apache.thrift.TBase, jav
return false;
}
+ boolean this_present_compression = true && this.isSetCompression();
+ boolean that_present_compression = true && that.isSetCompression();
+ if (this_present_compression || that_present_compression) {
+ if (!(this_present_compression && that_present_compression))
+ return false;
+ if (this.compression != that.compression)
+ return false;
+ }
+
return true;
}
@@ -1913,6 +1969,11 @@ public class CfDef implements org.apache.thrift.TBase, jav
if (present_row_cache_keys_to_save)
builder.append(row_cache_keys_to_save);
+ boolean present_compression = true && (isSetCompression());
+ builder.append(present_compression);
+ if (present_compression)
+ builder.append(compression);
+
return builder.toHashCode();
}
@@ -2194,6 +2255,16 @@ public class CfDef implements org.apache.thrift.TBase, jav
return lastComparison;
}
}
+ lastComparison = Boolean.valueOf(isSetCompression()).compareTo(typedOther.isSetCompression());
+ if (lastComparison != 0) {
+ return lastComparison;
+ }
+ if (isSetCompression()) {
+ lastComparison = org.apache.thrift.TBaseHelper.compareTo(this.compression, typedOther.compression);
+ if (lastComparison != 0) {
+ return lastComparison;
+ }
+ }
return 0;
}
@@ -2437,6 +2508,14 @@ public class CfDef implements org.apache.thrift.TBase, jav
org.apache.thrift.protocol.TProtocolUtil.skip(iprot, field.type);
}
break;
+ case 32: // COMPRESSION
+ if (field.type == org.apache.thrift.protocol.TType.BOOL) {
+ this.compression = iprot.readBool();
+ setCompressionIsSet(true);
+ } else {
+ org.apache.thrift.protocol.TProtocolUtil.skip(iprot, field.type);
+ }
+ break;
default:
org.apache.thrift.protocol.TProtocolUtil.skip(iprot, field.type);
}
@@ -2624,6 +2703,11 @@ public class CfDef implements org.apache.thrift.TBase, jav
oprot.writeI32(this.row_cache_keys_to_save);
oprot.writeFieldEnd();
}
+ if (isSetCompression()) {
+ oprot.writeFieldBegin(COMPRESSION_FIELD_DESC);
+ oprot.writeBool(this.compression);
+ oprot.writeFieldEnd();
+ }
oprot.writeFieldStop();
oprot.writeStructEnd();
}
@@ -2842,6 +2926,12 @@ public class CfDef implements org.apache.thrift.TBase, jav
sb.append(this.row_cache_keys_to_save);
first = false;
}
+ if (isSetCompression()) {
+ if (!first) sb.append(", ");
+ sb.append("compression:");
+ sb.append(this.compression);
+ first = false;
+ }
sb.append(")");
return sb.toString();
}
diff --git a/interface/thrift/gen-java/org/apache/cassandra/thrift/Constants.java b/interface/thrift/gen-java/org/apache/cassandra/thrift/Constants.java
index 6bac7b01e3..b005c0f865 100644
--- a/interface/thrift/gen-java/org/apache/cassandra/thrift/Constants.java
+++ b/interface/thrift/gen-java/org/apache/cassandra/thrift/Constants.java
@@ -44,6 +44,6 @@ import org.slf4j.LoggerFactory;
public class Constants {
- public static final String VERSION = "19.11.0";
+ public static final String VERSION = "19.12.0";
}
diff --git a/lib/licenses/snappy-java-1.0.3.txt b/lib/licenses/snappy-java-1.0.3.txt
new file mode 100644
index 0000000000..d5c4984908
--- /dev/null
+++ b/lib/licenses/snappy-java-1.0.3.txt
@@ -0,0 +1,209 @@
+
+ Apache License
+ Version 2.0, January 2004
+ http://www.apache.org/licenses/
+
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+ 1. Definitions.
+
+ "License" shall mean the terms and conditions for use, reproduction,
+ and distribution as defined by Sections 1 through 9 of this document.
+
+ "Licensor" shall mean the copyright owner or entity authorized by
+ the copyright owner that is granting the License.
+
+ "Legal Entity" shall mean the union of the acting entity and all
+ other entities that control, are controlled by, or are under common
+ control with that entity. For the purposes of this definition,
+ "control" means (i) the power, direct or indirect, to cause the
+ direction or management of such entity, whether by contract or
+ otherwise, or (ii) ownership of fifty percent (50%) or more of the
+ outstanding shares, or (iii) beneficial ownership of such entity.
+
+ "You" (or "Your") shall mean an individual or Legal Entity
+ exercising permissions granted by this License.
+
+ "Source" form shall mean the preferred form for making modifications,
+ including but not limited to software source code, documentation
+ source, and configuration files.
+
+ "Object" form shall mean any form resulting from mechanical
+ transformation or translation of a Source form, including but
+ not limited to compiled object code, generated documentation,
+ and conversions to other media types.
+
+ "Work" shall mean the work of authorship, whether in Source or
+ Object form, made available under the License, as indicated by a
+ copyright notice that is included in or attached to the work
+ (an example is provided in the Appendix below).
+
+ "Derivative Works" shall mean any work, whether in Source or Object
+ form, that is based on (or derived from) the Work and for which the
+ editorial revisions, annotations, elaborations, or other modifications
+ represent, as a whole, an original work of authorship. For the purposes
+ of this License, Derivative Works shall not include works that remain
+ separable from, or merely link (or bind by name) to the interfaces of,
+ the Work and Derivative Works thereof.
+
+ "Contribution" shall mean any work of authorship, including
+ the original version of the Work and any modifications or additions
+ to that Work or Derivative Works thereof, that is intentionally
+ submitted to Licensor for inclusion in the Work by the copyright owner
+ or by an individual or Legal Entity authorized to submit on behalf of
+ the copyright owner. For the purposes of this definition, "submitted"
+ means any form of electronic, verbal, or written communication sent
+ to the Licensor or its representatives, including but not limited to
+ communication on electronic mailing lists, source code control systems,
+ and issue tracking systems that are managed by, or on behalf of, the
+ Licensor for the purpose of discussing and improving the Work, but
+ excluding communication that is conspicuously marked or otherwise
+ designated in writing by the copyright owner as "Not a Contribution."
+
+ "Contributor" shall mean Licensor and any individual or Legal Entity
+ on behalf of whom a Contribution has been received by Licensor and
+ subsequently incorporated within the Work.
+
+ 2. Grant of Copyright License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ copyright license to reproduce, prepare Derivative Works of,
+ publicly display, publicly perform, sublicense, and distribute the
+ Work and such Derivative Works in Source or Object form.
+
+ 3. Grant of Patent License. Subject to the terms and conditions of
+ this License, each Contributor hereby grants to You a perpetual,
+ worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+ (except as stated in this section) patent license to make, have made,
+ use, offer to sell, sell, import, and otherwise transfer the Work,
+ where such license applies only to those patent claims licensable
+ by such Contributor that are necessarily infringed by their
+ Contribution(s) alone or by combination of their Contribution(s)
+ with the Work to which such Contribution(s) was submitted. If You
+ institute patent litigation against any entity (including a
+ cross-claim or counterclaim in a lawsuit) alleging that the Work
+ or a Contribution incorporated within the Work constitutes direct
+ or contributory patent infringement, then any patent licenses
+ granted to You under this License for that Work shall terminate
+ as of the date such litigation is filed.
+
+ 4. Redistribution. You may reproduce and distribute copies of the
+ Work or Derivative Works thereof in any medium, with or without
+ modifications, and in Source or Object form, provided that You
+ meet the following conditions:
+
+ (a) You must give any other recipients of the Work or
+ Derivative Works a copy of this License; and
+
+ (b) You must cause any modified files to carry prominent notices
+ stating that You changed the files; and
+
+ (c) You must retain, in the Source form of any Derivative Works
+ that You distribute, all copyright, patent, trademark, and
+ attribution notices from the Source form of the Work,
+ excluding those notices that do not pertain to any part of
+ the Derivative Works; and
+
+ (d) If the Work includes a "NOTICE" text file as part of its
+ distribution, then any Derivative Works that You distribute must
+ include a readable copy of the attribution notices contained
+ within such NOTICE file, excluding those notices that do not
+ pertain to any part of the Derivative Works, in at least one
+ of the following places: within a NOTICE text file distributed
+ as part of the Derivative Works; within the Source form or
+ documentation, if provided along with the Derivative Works; or,
+ within a display generated by the Derivative Works, if and
+ wherever such third-party notices normally appear. The contents
+ of the NOTICE file are for informational purposes only and
+ do not modify the License. You may add Your own attribution
+ notices within Derivative Works that You distribute, alongside
+ or as an addendum to the NOTICE text from the Work, provided
+ that such additional attribution notices cannot be construed
+ as modifying the License.
+
+ You may add Your own copyright statement to Your modifications and
+ may provide additional or different license terms and conditions
+ for use, reproduction, or distribution of Your modifications, or
+ for any such Derivative Works as a whole, provided Your use,
+ reproduction, and distribution of the Work otherwise complies with
+ the conditions stated in this License.
+
+ 5. Submission of Contributions. Unless You explicitly state otherwise,
+ any Contribution intentionally submitted for inclusion in the Work
+ by You to the Licensor shall be under the terms and conditions of
+ this License, without any additional terms or conditions.
+ Notwithstanding the above, nothing herein shall supersede or modify
+ the terms of any separate license agreement you may have executed
+ with Licensor regarding such Contributions.
+
+ 6. Trademarks. This License does not grant permission to use the trade
+ names, trademarks, service marks, or product names of the Licensor,
+ except as required for reasonable and customary use in describing the
+ origin of the Work and reproducing the content of the NOTICE file.
+
+ 7. Disclaimer of Warranty. Unless required by applicable law or
+ agreed to in writing, Licensor provides the Work (and each
+ Contributor provides its Contributions) on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+ implied, including, without limitation, any warranties or conditions
+ of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+ PARTICULAR PURPOSE. You are solely responsible for determining the
+ appropriateness of using or redistributing the Work and assume any
+ risks associated with Your exercise of permissions under this License.
+
+ 8. Limitation of Liability. In no event and under no legal theory,
+ whether in tort (including negligence), contract, or otherwise,
+ unless required by applicable law (such as deliberate and grossly
+ negligent acts) or agreed to in writing, shall any Contributor be
+ liable to You for damages, including any direct, indirect, special,
+ incidental, or consequential damages of any character arising as a
+ result of this License or out of the use or inability to use the
+ Work (including but not limited to damages for loss of goodwill,
+ work stoppage, computer failure or malfunction, or any and all
+ other commercial damages or losses), even if such Contributor
+ has been advised of the possibility of such damages.
+
+ 9. Accepting Warranty or Additional Liability. While redistributing
+ the Work or Derivative Works thereof, You may choose to offer,
+ and charge a fee for, acceptance of support, warranty, indemnity,
+ or other liability obligations and/or rights consistent with this
+ License. However, in accepting such obligations, You may act only
+ on Your own behalf and on Your sole responsibility, not on behalf
+ of any other Contributor, and only if You agree to indemnify,
+ defend, and hold each Contributor harmless for any liability
+ incurred by, or claims asserted against, such Contributor by reason
+ of your accepting any such warranty or additional liability.
+
+ END OF TERMS AND CONDITIONS
+
+ APPENDIX: How to apply the Apache License to your work.
+
+ To apply the Apache License to your work, attach the following
+ boilerplate notice, with the fields enclosed by brackets "[]"
+ replaced with your own identifying information. (Don't include
+ the brackets!) The text should be enclosed in the appropriate
+ comment syntax for the file format. We also recommend that a
+ file or class name and description of purpose be included on the
+ same "printed page" as the copyright notice for easier
+ identification within third-party archives.
+
+ Copyright [yyyy] [name of copyright owner]
+
+ Licensed under the Apache License, Version 2.0 (the "License");
+ you may not use this file except in compliance with the License.
+ You may obtain a copy of the License at
+
+ http://www.apache.org/licenses/LICENSE-2.0
+
+ Unless required by applicable law or agreed to in writing, software
+ distributed under the License is distributed on an "AS IS" BASIS,
+ WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+ See the License for the specific language governing permissions and
+ limitations under the License.
+
+
+THIRD-PARTY DEPENDENCIES
+========================
+Convenience copies of some third-party dependencies are distributed with
+Apache Cassandra as Java jar files in lib/. Licensing information for
+these files can be found in the lib/licenses directory.
diff --git a/lib/snappy-java-1.0.3.jar b/lib/snappy-java-1.0.3.jar
new file mode 100644
index 0000000000..d33b0b1cfa
Binary files /dev/null and b/lib/snappy-java-1.0.3.jar differ
diff --git a/src/avro/internode.genavro b/src/avro/internode.genavro
index e9db99b9af..aa6fccc673 100644
--- a/src/avro/internode.genavro
+++ b/src/avro/internode.genavro
@@ -67,6 +67,7 @@ protocol InterNode {
union { null, bytes } key_alias = null;
union { null, string } compaction_strategy = null;
union { null, map } compaction_strategy_options = null;
+ boolean compression = false;
}
@aliases(["org.apache.cassandra.config.avro.KsDef"])
diff --git a/src/java/org/apache/cassandra/cli/CliClient.java b/src/java/org/apache/cassandra/cli/CliClient.java
index c9ace1349b..873e80ad16 100644
--- a/src/java/org/apache/cassandra/cli/CliClient.java
+++ b/src/java/org/apache/cassandra/cli/CliClient.java
@@ -134,7 +134,8 @@ public class CliClient
ROW_CACHE_PROVIDER,
KEY_VALIDATION_CLASS,
COMPACTION_STRATEGY,
- COMPACTION_STRATEGY_OPTIONS
+ COMPACTION_STRATEGY_OPTIONS,
+ COMPRESSION
}
private static final String DEFAULT_PLACEMENT_STRATEGY = "org.apache.cassandra.locator.NetworkTopologyStrategy";
@@ -1259,6 +1260,9 @@ public class CliClient
case COMPACTION_STRATEGY_OPTIONS:
cfDef.setCompaction_strategy_options(getStrategyOptionsFromTree(statement.getChild(i+1)));
break;
+ case COMPRESSION:
+ cfDef.setCompression(Boolean.parseBoolean(mValue));
+ break;
default:
//must match one of the above or we'd throw an exception at the valueOf statement above.
assert(false);
@@ -1731,6 +1735,7 @@ public class CliClient
sessionState.out.printf(" Compaction min/max thresholds: %s/%s%n", cf_def.min_compaction_threshold, cf_def.max_compaction_threshold);
sessionState.out.printf(" Read repair chance: %s%n", cf_def.read_repair_chance);
sessionState.out.printf(" Replicate on write: %s%n", cf_def.replicate_on_write);
+ sessionState.out.printf(" Compression enabled: %s%n", cf_def.compression);
// if we have connection to the cfMBean established
if (cfMBean != null)
diff --git a/src/java/org/apache/cassandra/config/CFMetaData.java b/src/java/org/apache/cassandra/config/CFMetaData.java
index b6f0a9aa5c..8a2a8c04cf 100644
--- a/src/java/org/apache/cassandra/config/CFMetaData.java
+++ b/src/java/org/apache/cassandra/config/CFMetaData.java
@@ -80,6 +80,7 @@ public final class CFMetaData
public final static String DEFAULT_ROW_CACHE_PROVIDER = "org.apache.cassandra.cache.ConcurrentLinkedHashCacheProvider";
public final static String DEFAULT_COMPACTION_STRATEGY_CLASS = "org.apache.cassandra.db.compaction.SizeTieredCompactionStrategy";
public final static ByteBuffer DEFAULT_KEY_NAME = ByteBufferUtil.bytes("KEY");
+ public final static boolean DEFAULT_COMPRESSION = false;
private static final int MIN_CF_ID = 1000;
private static final AtomicInteger idGen = new AtomicInteger(MIN_CF_ID);
@@ -171,6 +172,7 @@ public final class CFMetaData
private double mergeShardsChance; // default 0.1, chance [0.0, 1.0] of merging old shards during replication
private IRowCacheProvider rowCacheProvider;
private ByteBuffer keyAlias; // default NULL
+ private boolean compression;
private Map column_metadata;
public Class extends AbstractCompactionStrategy> compactionStrategyClass;
@@ -193,6 +195,7 @@ public final class CFMetaData
public CFMetaData memOps(double prop) {memtableOperationsInMillions = prop; return this;}
public CFMetaData mergeShardsChance(double prop) {mergeShardsChance = prop; return this;}
public CFMetaData keyAlias(ByteBuffer prop) {keyAlias = prop; return this;}
+ public CFMetaData compression(boolean prop) {compression = prop; return this; }
public CFMetaData columnMetadata(Map prop) {column_metadata = prop; return this;}
public CFMetaData rowCacheProvider(IRowCacheProvider prop) { rowCacheProvider = prop; return this;}
public CFMetaData compactionStrategyClass(Class extends AbstractCompactionStrategy> prop) {compactionStrategyClass = prop; return this;}
@@ -243,6 +246,7 @@ public final class CFMetaData
memtableThroughputInMb = DEFAULT_MEMTABLE_THROUGHPUT_IN_MB;
memtableOperationsInMillions = DEFAULT_MEMTABLE_OPERATIONS_IN_MILLIONS;
mergeShardsChance = DEFAULT_MERGE_SHARDS_CHANCE;
+ compression = DEFAULT_COMPRESSION;
try
{
rowCacheProvider = FBUtilities.newCacheProvider(DEFAULT_ROW_CACHE_PROVIDER);
@@ -328,7 +332,8 @@ public final class CFMetaData
.memOps(oldCFMD.memtableOperationsInMillions)
.columnMetadata(oldCFMD.column_metadata)
.compactionStrategyClass(oldCFMD.compactionStrategyClass)
- .compactionStrategyOptions(oldCFMD.compactionStrategyOptions);
+ .compactionStrategyOptions(oldCFMD.compactionStrategyOptions)
+ .compression(oldCFMD.compression);
}
/** used for evicting cf data out of static tracking collections. */
@@ -378,6 +383,7 @@ public final class CFMetaData
cf.memtable_operations_in_millions = memtableOperationsInMillions;
cf.merge_shards_chance = mergeShardsChance;
cf.key_alias = keyAlias;
+ cf.compression = compression;
cf.column_metadata = SerDeUtils.createArray(column_metadata.size(),
org.apache.cassandra.db.migration.avro.ColumnDef.SCHEMA$);
for (ColumnDefinition cd : column_metadata.values())
@@ -477,7 +483,8 @@ public final class CFMetaData
.gcGraceSeconds(cf.gc_grace_seconds)
.defaultValidator(validator)
.keyValidator(keyValidator)
- .columnMetadata(column_metadata);
+ .columnMetadata(column_metadata)
+ .compression(cf.compression);
}
public String getComment()
@@ -570,6 +577,16 @@ public final class CFMetaData
return keyAlias == null ? DEFAULT_KEY_NAME : keyAlias;
}
+ public boolean useCompression()
+ {
+ return compression;
+ }
+
+ public void useCompression(boolean flag)
+ {
+ compression = flag;
+ }
+
public Map getColumn_metadata()
{
return Collections.unmodifiableMap(column_metadata);
@@ -617,6 +634,7 @@ public final class CFMetaData
.append(memtableOperationsInMillions, rhs.memtableOperationsInMillions)
.append(mergeShardsChance, rhs.mergeShardsChance)
.append(keyAlias, rhs.keyAlias)
+ .append(compression, rhs.compression)
.append(compactionStrategyClass, rhs.compactionStrategyClass)
.append(compactionStrategyOptions, rhs.compactionStrategyOptions)
.isEquals();
@@ -649,6 +667,7 @@ public final class CFMetaData
.append(memtableOperationsInMillions)
.append(mergeShardsChance)
.append(keyAlias)
+ .append(compression)
.append(compactionStrategyClass)
.append(compactionStrategyOptions)
.toHashCode();
@@ -697,6 +716,8 @@ public final class CFMetaData
cf_def.compaction_strategy = DEFAULT_COMPACTION_STRATEGY_CLASS;
if (null == cf_def.compaction_strategy_options)
cf_def.compaction_strategy_options = Collections.emptyMap();
+ if (!cf_def.isSetCompression())
+ cf_def.setCompression(CFMetaData.DEFAULT_COMPRESSION);
}
public static CFMetaData fromThrift(org.apache.cassandra.thrift.CfDef cf_def) throws InvalidRequestException, ConfigurationException
@@ -748,7 +769,8 @@ public final class CFMetaData
.replicateOnWrite(cf_def.replicate_on_write)
.defaultValidator(TypeParser.parse(cf_def.default_validation_class))
.keyValidator(TypeParser.parse(cf_def.key_validation_class))
- .columnMetadata(ColumnDefinition.fromColumnDef(cf_def.column_metadata));
+ .columnMetadata(ColumnDefinition.fromColumnDef(cf_def.column_metadata))
+ .compression(cf_def.compression);
}
// merges some final fields from this CFM with modifiable fields from CfDef into a new CFMetaData.
@@ -800,6 +822,7 @@ public final class CFMetaData
if (cf_def.row_cache_provider != null)
rowCacheProvider = FBUtilities.newCacheProvider(cf_def.row_cache_provider.toString());
keyAlias = cf_def.key_alias;
+ compression = cf_def.compression;
// adjust column definitions. figure out who is coming and going.
Set toRemove = new HashSet();
@@ -918,6 +941,7 @@ public final class CFMetaData
def.setMemtable_operations_in_millions(cfm.memtableOperationsInMillions);
def.setMerge_shards_chance(cfm.mergeShardsChance);
def.setKey_alias(cfm.getKeyName());
+ def.setCompression(cfm.compression);
List column_meta = new ArrayList< org.apache.cassandra.thrift.ColumnDef>(cfm.column_metadata.size());
for (ColumnDefinition cd : cfm.column_metadata.values())
{
@@ -966,6 +990,7 @@ public final class CFMetaData
def.merge_shards_chance = cfm.mergeShardsChance;
def.key_validation_class = cfm.keyValidator.getClass().getName();
def.key_alias = cfm.keyAlias;
+ def.compression = cfm.compression;
List column_meta = new ArrayList(cfm.column_metadata.size());
for (ColumnDefinition cd : cfm.column_metadata.values())
{
@@ -1011,7 +1036,7 @@ public final class CFMetaData
newDef.subcomparator_type = def.getSubcomparator_type();
newDef.merge_shards_chance = def.getMerge_shards_chance();
newDef.key_alias = def.key_alias;
-
+ newDef.compression = def.compression;
List columnMeta = new ArrayList();
if (def.isSetColumn_metadata())
{
@@ -1146,6 +1171,7 @@ public final class CFMetaData
.append("memtableOperationsInMillions", memtableOperationsInMillions)
.append("mergeShardsChance", mergeShardsChance)
.append("keyAlias", keyAlias)
+ .append("compression", compression)
.append("column_metadata", column_metadata)
.append("compactionStrategyClass", compactionStrategyClass)
.append("compactionStrategyOptions", compactionStrategyOptions)
diff --git a/src/java/org/apache/cassandra/db/compaction/CompactionManager.java b/src/java/org/apache/cassandra/db/compaction/CompactionManager.java
index 0cf4929297..ee9264b00e 100644
--- a/src/java/org/apache/cassandra/db/compaction/CompactionManager.java
+++ b/src/java/org/apache/cassandra/db/compaction/CompactionManager.java
@@ -32,6 +32,7 @@ import javax.management.ObjectName;
import com.google.common.base.Predicates;
import com.google.common.collect.Iterators;
+
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@ -46,7 +47,6 @@ import org.apache.cassandra.io.util.FileUtils;
import org.apache.cassandra.io.util.RandomAccessReader;
import org.apache.cassandra.service.AntiEntropyService;
import org.apache.cassandra.service.StorageService;
-import org.apache.cassandra.streaming.OperationType;
import org.apache.cassandra.utils.*;
/**
@@ -471,7 +471,8 @@ public class CompactionManager implements CompactionManagerMBean
// we'll also loop through the index at the same time, using the position from the index to recover if the
// row header (key or data size) is corrupt. (This means our position in the index file will be one row
// "ahead" of the data file.)
- final RandomAccessReader dataFile = RandomAccessReader.open(new File(sstable.getFilename()), true);
+ final RandomAccessReader dataFile = sstable.openDataReader(true);
+
String indexFilename = sstable.descriptor.filenameFor(Component.PRIMARY_INDEX);
RandomAccessReader indexFile = RandomAccessReader.open(new File(indexFilename), true);
try
diff --git a/src/java/org/apache/cassandra/io/compress/CompressedRandomAccessReader.java b/src/java/org/apache/cassandra/io/compress/CompressedRandomAccessReader.java
new file mode 100644
index 0000000000..c3431a93d9
--- /dev/null
+++ b/src/java/org/apache/cassandra/io/compress/CompressedRandomAccessReader.java
@@ -0,0 +1,176 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.cassandra.io.compress;
+
+import java.io.*;
+import java.nio.ByteBuffer;
+import java.nio.channels.WritableByteChannel;
+
+import org.apache.cassandra.io.sstable.Component;
+import org.apache.cassandra.io.sstable.Descriptor;
+import org.apache.cassandra.io.util.FileUtils;
+import org.apache.cassandra.io.util.RandomAccessReader;
+import org.apache.cassandra.streaming.FileStreamTask;
+import org.apache.cassandra.streaming.PendingFile;
+import org.apache.cassandra.utils.Pair;
+
+import org.slf4j.Logger;
+import org.slf4j.LoggerFactory;
+import org.xerial.snappy.Snappy;
+
+public class CompressedRandomAccessReader extends RandomAccessReader
+{
+ private static final Logger logger = LoggerFactory.getLogger(CompressedRandomAccessReader.class);
+
+ /**
+ * Transfer sections of the file to the given target channel
+ * This method streams decompressed data so receiving party responsible for compression
+ *
+ * @param file The compressed file to transfer
+ * @param target Channel to transfer data into
+ *
+ * @throws IOException on any I/O error.
+ */
+ public static void transfer(PendingFile file, WritableByteChannel target) throws IOException
+ {
+ RandomAccessReader compressedFile = CompressedRandomAccessReader.open(file.getFilename(), true);
+
+ try
+ {
+ for (Pair section : file.sections)
+ {
+ long length = section.right - section.left;
+
+ compressedFile.seek(section.left);
+
+ while (length > 0)
+ {
+ int toRead = (length > FileStreamTask.CHUNK_SIZE) ? FileStreamTask.CHUNK_SIZE : (int) length;
+
+ ByteBuffer buffer = compressedFile.readBytes(toRead);
+
+ long bytesTransferred = 0;
+
+ while (bytesTransferred < toRead)
+ {
+ // we don't need to re-read a buffer, it will write starting from buffer.position()
+ long lastWrite = target.write(buffer);
+ bytesTransferred += lastWrite;
+ file.progress += lastWrite;
+ }
+
+ length -= bytesTransferred;
+
+ if (logger.isDebugEnabled())
+ logger.debug("Bytes transferred " + bytesTransferred + "/" + file.size);
+ }
+ }
+ }
+ finally
+ {
+ FileUtils.closeQuietly(compressedFile);
+ }
+ }
+
+ /**
+ * Get metadata about given compressed file including uncompressed data length, chunk size
+ * and list of the chunk offsets of the compressed data.
+ *
+ * @param dataFilePath Path to the compressed file
+ *
+ * @return metadata about given compressed file.
+ */
+ public static CompressionMetadata metadata(String dataFilePath)
+ {
+ Descriptor desc = Descriptor.fromFilename(dataFilePath);
+
+ try
+ {
+ return new CompressionMetadata(desc.filenameFor(Component.COMPRESSION_INFO), new File(dataFilePath).length());
+ }
+ catch (IOException e)
+ {
+ throw new IOError(e);
+ }
+ }
+
+ public static RandomAccessReader open(String dataFilePath, boolean skipIOCache) throws IOException
+ {
+ return open(dataFilePath, metadata(dataFilePath), skipIOCache);
+ }
+
+ public static RandomAccessReader open(String dataFilePath, CompressionMetadata metadata) throws IOException
+ {
+ return open(dataFilePath, metadata, false);
+ }
+
+ public static RandomAccessReader open(String dataFilePath, CompressionMetadata metadata, boolean skipIOCache) throws IOException
+ {
+ return new CompressedRandomAccessReader(dataFilePath, metadata, skipIOCache);
+ }
+
+ private final CompressionMetadata metadata;
+ // used by reBuffer() to escape creating lots of temporary buffers
+ private final byte[] compressed;
+
+ private final FileInputStream source;
+
+ public CompressedRandomAccessReader(String dataFilePath, CompressionMetadata metadata, boolean skipIOCache) throws IOException
+ {
+ super(new File(dataFilePath), metadata.chunkLength, skipIOCache);
+ this.metadata = metadata;
+ compressed = new byte[metadata.chunkLength];
+ // can't use super.read(...) methods
+ // that is why we are allocating special InputStream to read data from disk
+ // from already open file descriptor
+ source = new FileInputStream(getFD());
+ }
+
+ @Override
+ protected void reBuffer() throws IOException
+ {
+ decompressChunk(metadata.chunkFor(current));
+ }
+
+ private void decompressChunk(CompressionMetadata.Chunk chunk) throws IOException
+ {
+ if (source.getChannel().position() != chunk.offset)
+ source.getChannel().position(chunk.offset);
+
+ if (source.read(compressed, 0, chunk.length) != chunk.length)
+ throw new IOException(String.format("(%s) failed to read %d bytes from offset %d.", getPath(), chunk.length, chunk.offset));
+
+ validBufferBytes = Snappy.rawUncompress(compressed, 0, chunk.length, buffer, 0);
+
+ // buffer offset is always aligned
+ bufferOffset = current & ~(buffer.length - 1);
+ }
+
+ @Override
+ public long length() throws IOException
+ {
+ return metadata.dataLength;
+ }
+
+ @Override
+ public String toString()
+ {
+ return String.format("%s - chunk length %d, data length %d.", getPath(), metadata.chunkLength, metadata.dataLength);
+ }
+}
diff --git a/src/java/org/apache/cassandra/io/compress/CompressedSequentialWriter.java b/src/java/org/apache/cassandra/io/compress/CompressedSequentialWriter.java
new file mode 100644
index 0000000000..a262a25638
--- /dev/null
+++ b/src/java/org/apache/cassandra/io/compress/CompressedSequentialWriter.java
@@ -0,0 +1,186 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.cassandra.io.compress;
+
+import java.io.File;
+import java.io.IOException;
+
+import org.apache.cassandra.io.util.FileMark;
+import org.apache.cassandra.io.util.SequentialWriter;
+
+import org.xerial.snappy.Snappy;
+
+public class CompressedSequentialWriter extends SequentialWriter
+{
+ public static final int CHUNK_LENGTH = 65536;
+
+ public static SequentialWriter open(String dataFilePath, String indexFilePath, boolean skipIOCache) throws IOException
+ {
+ return new CompressedSequentialWriter(new File(dataFilePath), indexFilePath, skipIOCache);
+ }
+
+ // holds offset in the file where current chunk should be written
+ // changed only by flush() method where data buffer gets compressed and stored to the file
+ private long chunkOffset = 0;
+
+ // index file writer (random I/O)
+ private final CompressionMetadata.Writer metadataWriter;
+
+ // used to store compressed data
+ private final byte[] compressed;
+
+ // holds a number of already written chunks
+ private int chunkCount = 0;
+
+ public CompressedSequentialWriter(File file, String indexFilePath, boolean skipIOCache) throws IOException
+ {
+ super(file, CHUNK_LENGTH, skipIOCache);
+
+ // buffer for compression should be the same size as buffer itself
+ compressed = new byte[buffer.length];
+
+ /* Index File (-CompressionInfo.db component) and it's header */
+ metadataWriter = new CompressionMetadata.Writer(indexFilePath);
+ metadataWriter.writeHeader(Snappy.class.getSimpleName(), CHUNK_LENGTH);
+ }
+
+ @Override
+ public void sync() throws IOException
+ {
+ throw new UnsupportedOperationException();
+ }
+
+ @Override
+ public void flush() throws IOException
+ {
+ throw new UnsupportedOperationException();
+ }
+
+ @Override
+ protected void flushData() throws IOException
+ {
+ seekToChunkStart();
+
+ // compressing data with buffer re-use
+ int compressedLength = Snappy.rawCompress(buffer, 0, validBufferBytes, compressed, 0);
+
+ // write an offset of the newly written chunk to the index file
+ metadataWriter.writeLong(chunkOffset);
+ chunkCount++;
+
+ // write data itself
+ out.write(compressed, 0, compressedLength);
+
+ // next chunk should be written right after current
+ chunkOffset += compressedLength;
+ }
+
+ @Override
+ public FileMark mark()
+ {
+ return new CompressedFileWriterMark(chunkOffset, current, validBufferBytes, chunkCount + 1);
+ }
+
+ @Override
+ public synchronized void resetAndTruncate(FileMark mark) throws IOException
+ {
+ assert mark instanceof CompressedFileWriterMark;
+
+ CompressedFileWriterMark realMark = ((CompressedFileWriterMark) mark);
+
+ // reset position
+ current = realMark.uncDataOffset;
+
+ if (realMark.chunkOffset == chunkOffset) // current buffer
+ {
+ // just reset a buffer offset and return
+ validBufferBytes = realMark.bufferOffset;
+ return;
+ }
+
+ // synchronize current buffer with disk
+ // because we don't want any data loss
+ syncInternal();
+
+ // setting marker as a current offset
+ chunkOffset = realMark.chunkOffset;
+
+ // compressed chunk size
+ int chunkSize = (int) (metadataWriter.chunkOffsetBy(realMark.nextChunkIndex) - chunkOffset);
+
+ out.seek(chunkOffset);
+ out.read(compressed, 0, chunkSize);
+
+ Snappy.rawUncompress(compressed, 0, chunkSize, buffer, 0);
+
+ // reset buffer
+ validBufferBytes = realMark.bufferOffset;
+ bufferOffset = current - validBufferBytes;
+ chunkCount = realMark.nextChunkIndex - 1;
+
+ // truncate data and index file
+ truncate(chunkOffset);
+ metadataWriter.resetAndTruncate(realMark.nextChunkIndex);
+ }
+
+ /**
+ * Seek to the offset where next compressed data chunk should be stored.
+ *
+ * @throws IOException on any I/O error.
+ */
+ private void seekToChunkStart() throws IOException
+ {
+ if (out.getFilePointer() != chunkOffset)
+ out.seek(chunkOffset);
+ }
+
+ @Override
+ public void close() throws IOException
+ {
+ if (buffer == null)
+ return; // already closed
+
+ super.close();
+
+ metadataWriter.finalizeHeader(current, chunkCount);
+ metadataWriter.close();
+ }
+
+ /**
+ * Class to hold a mark to the position of the file
+ */
+ protected static class CompressedFileWriterMark implements FileMark
+ {
+ // chunk offset in the compressed file
+ long chunkOffset;
+ // uncompressed data offset (real data offset)
+ long uncDataOffset;
+
+ int bufferOffset;
+ int nextChunkIndex;
+
+ public CompressedFileWriterMark(long chunkOffset, long uncDataOffset, int bufferOffset, int nextChunkIndex)
+ {
+ this.chunkOffset = chunkOffset;
+ this.uncDataOffset = uncDataOffset;
+ this.bufferOffset = bufferOffset;
+ this.nextChunkIndex = nextChunkIndex;
+ }
+ }
+}
diff --git a/src/java/org/apache/cassandra/io/compress/CompressionMetadata.java b/src/java/org/apache/cassandra/io/compress/CompressionMetadata.java
new file mode 100644
index 0000000000..85fe165e49
--- /dev/null
+++ b/src/java/org/apache/cassandra/io/compress/CompressionMetadata.java
@@ -0,0 +1,209 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.cassandra.io.compress;
+
+import java.io.*;
+
+import org.apache.cassandra.io.util.FileUtils;
+
+/**
+ * Holds metadata about compressed file
+ */
+public class CompressionMetadata
+{
+
+ public final int chunkLength;
+ public final long dataLength;
+ public final long compressedFileLength;
+ public final long[] chunkOffsets;
+ public final String indexFilePath;
+ public final String algorithm;
+
+ public CompressionMetadata(String indexFilePath, long compressedLength) throws IOException
+ {
+ this.indexFilePath = indexFilePath;
+
+ DataInputStream stream = new DataInputStream(new FileInputStream(indexFilePath));
+
+ algorithm = stream.readUTF();
+ chunkLength = stream.readInt();
+ dataLength = stream.readLong();
+ compressedFileLength = compressedLength;
+ chunkOffsets = readChunkOffsets(stream);
+
+ FileUtils.closeQuietly(stream);
+ }
+
+ /**
+ * Read offsets of the individual chunks from the given input.
+ *
+ * @param input Source of the data.
+ *
+ * @return collection of the chunk offsets.
+ *
+ * @throws java.io.IOException on any I/O error (except EOF).
+ */
+ private long[] readChunkOffsets(DataInput input) throws IOException
+ {
+ int chunkCount = input.readInt();
+ long[] offsets = new long[chunkCount];
+
+ for (int i = 0; i < offsets.length; i++)
+ {
+ try
+ {
+ offsets[i] = input.readLong();
+ }
+ catch (EOFException e)
+ {
+ throw new EOFException(String.format("Corrupted Index File %s: read %d but expected %d chunks.",
+ indexFilePath,
+ i,
+ chunkCount));
+ }
+ }
+
+ return offsets;
+ }
+
+ /**
+ * Get a chunk of compressed data (offset, length) corresponding to given position
+ *
+ * @param position Position in the file.
+ * @return pair of chunk offset and length.
+ * @throws java.io.IOException on any I/O error.
+ */
+ public Chunk chunkFor(long position) throws IOException
+ {
+ // position of the chunk
+ int idx = (int) (position / chunkLength);
+
+ if (idx >= chunkOffsets.length)
+ throw new EOFException();
+
+ long chunkOffset = chunkOffsets[idx];
+ long nextChunkOffset = (idx + 1 == chunkOffsets.length)
+ ? compressedFileLength
+ : chunkOffsets[idx + 1];
+
+ return new Chunk(chunkOffset, (int) (nextChunkOffset - chunkOffset));
+ }
+
+ public static class Writer extends RandomAccessFile
+ {
+ // place for uncompressed data length in the index file
+ private long dataLengthOffset = -1;
+
+ public Writer(String path) throws IOException
+ {
+ super(path, "rw");
+ }
+
+ public void writeHeader(String algorithm, int chunkLength) throws IOException
+ {
+ // algorithm
+ writeUTF(algorithm);
+
+ // store the length of the chunk
+ writeInt(chunkLength);
+ // store position and reserve a place for uncompressed data length and chunks count
+ dataLengthOffset = getFilePointer();
+ writeLong(-1);
+ writeInt(-1);
+ }
+
+ public void finalizeHeader(long dataLength, int chunks) throws IOException
+ {
+ assert dataLengthOffset != -1 : "writeHeader wasn't called";
+
+ long currentPosition = getFilePointer();
+
+ // seek back to the data length position
+ seek(dataLengthOffset);
+
+ // write uncompressed data length and chunks count
+ writeLong(dataLength);
+ writeInt(chunks);
+
+ // seek forward to the previous position
+ seek(currentPosition);
+ }
+
+ /**
+ * Get a chunk offset by it's index.
+ *
+ * @param chunkIndex Index of the chunk.
+ *
+ * @return offset of the chunk in the compressed file.
+ *
+ * @throws IOException any I/O error.
+ */
+ public long chunkOffsetBy(int chunkIndex) throws IOException
+ {
+ if (dataLengthOffset == -1)
+ throw new IllegalStateException("writeHeader wasn't called");
+
+ long position = getFilePointer();
+
+ // seek to the position of the given chunk
+ seek(dataLengthOffset
+ + 8 // size reserved for uncompressed data length
+ + 4 // size reserved for chunk count
+ + (chunkIndex * 8));
+
+ try
+ {
+ return readLong();
+ }
+ finally
+ {
+ // back to the original position
+ seek(position);
+ }
+ }
+
+ /**
+ * Reset the writer so that the next chunk offset written will be the
+ * one of {@code chunkIndex}.
+ */
+ public void resetAndTruncate(int chunkIndex) throws IOException
+ {
+ seek(dataLengthOffset
+ + 8 // size reserved for uncompressed data length
+ + 4 // size reserved for chunk count
+ + (chunkIndex * 8));
+ getChannel().truncate(getFilePointer());
+ }
+ }
+
+ /**
+ * Holds offset and length of the file chunk
+ */
+ public class Chunk
+ {
+ public final long offset;
+ public final int length;
+
+ public Chunk(long offset, int length)
+ {
+ this.offset = offset;
+ this.length = length;
+ }
+ }
+}
diff --git a/src/java/org/apache/cassandra/io/sstable/Component.java b/src/java/org/apache/cassandra/io/sstable/Component.java
index c527c612ee..1d0cfc87ce 100644
--- a/src/java/org/apache/cassandra/io/sstable/Component.java
+++ b/src/java/org/apache/cassandra/io/sstable/Component.java
@@ -47,6 +47,8 @@ public class Component
FILTER("Filter.db"),
// 0-length file that is created when an sstable is ready to be deleted
COMPACTED_MARKER("Compacted"),
+ // file to hold information about uncompressed data length, chunk offsets etc.
+ COMPRESSION_INFO("CompressionInfo.db"),
// statistical metadata about the content of the sstable
STATS("Statistics.db"),
// a bitmap secondary index: many of these may exist per sstable
@@ -72,6 +74,7 @@ public class Component
public final static Component PRIMARY_INDEX = new Component(Type.PRIMARY_INDEX, -1);
public final static Component FILTER = new Component(Type.FILTER, -1);
public final static Component COMPACTED_MARKER = new Component(Type.COMPACTED_MARKER, -1);
+ public final static Component COMPRESSION_INFO = new Component(Type.COMPRESSION_INFO, -1);
public final static Component STATS = new Component(Type.STATS, -1);
public final Type type;
@@ -101,6 +104,7 @@ public class Component
case PRIMARY_INDEX:
case FILTER:
case COMPACTED_MARKER:
+ case COMPRESSION_INFO:
case STATS:
return type.repr;
case BITMAP_INDEX:
@@ -137,6 +141,7 @@ public class Component
case PRIMARY_INDEX: component = Component.PRIMARY_INDEX; break;
case FILTER: component = Component.FILTER; break;
case COMPACTED_MARKER: component = Component.COMPACTED_MARKER; break;
+ case COMPRESSION_INFO: component = Component.COMPRESSION_INFO; break;
case STATS: component = Component.STATS; break;
case BITMAP_INDEX:
component = new Component(type, id);
diff --git a/src/java/org/apache/cassandra/io/sstable/SSTable.java b/src/java/org/apache/cassandra/io/sstable/SSTable.java
index 84027649de..dfdd535ed9 100644
--- a/src/java/org/apache/cassandra/io/sstable/SSTable.java
+++ b/src/java/org/apache/cassandra/io/sstable/SSTable.java
@@ -64,6 +64,7 @@ public abstract class SSTable
protected final Set components;
public final CFMetaData metadata;
public final IPartitioner partitioner;
+ public final boolean compression;
protected SSTable(Descriptor descriptor, CFMetaData metadata, IPartitioner partitioner)
{
@@ -82,6 +83,8 @@ public abstract class SSTable
Set dataComponents = new HashSet(components);
for (Component component : components)
assert component.type != Component.Type.COMPACTED_MARKER;
+
+ this.compression = dataComponents.contains(Component.COMPRESSION_INFO);
this.components = Collections.unmodifiableSet(dataComponents);
this.metadata = metadata;
this.partitioner = partitioner;
@@ -107,6 +110,7 @@ public abstract class SSTable
{
if (component.equals(Component.DATA) || component.equals(Component.COMPACTED_MARKER))
continue;
+
FileUtils.deleteWithConfirm(desc.filenameFor(component));
}
// remove the COMPACTED_MARKER component last if it exists
diff --git a/src/java/org/apache/cassandra/io/sstable/SSTableReader.java b/src/java/org/apache/cassandra/io/sstable/SSTableReader.java
index 88b95f6fc0..f40f94a264 100644
--- a/src/java/org/apache/cassandra/io/sstable/SSTableReader.java
+++ b/src/java/org/apache/cassandra/io/sstable/SSTableReader.java
@@ -27,6 +27,7 @@ import java.util.concurrent.atomic.AtomicBoolean;
import com.google.common.base.Function;
import com.google.common.collect.Collections2;
+import org.apache.cassandra.io.compress.CompressedRandomAccessReader;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@ -249,7 +250,9 @@ public class SSTableReader extends SSTable
{
boolean cacheLoading = keyCache != null && !keysToLoadInCache.isEmpty();
SegmentedFile.Builder ibuilder = SegmentedFile.getBuilder(DatabaseDescriptor.getIndexAccessMode());
- SegmentedFile.Builder dbuilder = SegmentedFile.getBuilder(DatabaseDescriptor.getDiskAccessMode());
+ SegmentedFile.Builder dbuilder = (components.contains(Component.COMPRESSION_INFO))
+ ? SegmentedFile.getCompressedBuilder()
+ : SegmentedFile.getBuilder(DatabaseDescriptor.getDiskAccessMode());
// we read the positions in a BRAF so we don't have to worry about an entry spanning a mmap boundary.
RandomAccessReader input = RandomAccessReader.open(new File(descriptor.filenameFor(Component.PRIMARY_INDEX)), true);
@@ -800,6 +803,18 @@ public class SSTableReader extends SSTable
return sstableMetadata.getMaxTimestamp();
}
+ public RandomAccessReader openDataReader(boolean skipIOCache) throws IOException
+ {
+ return openDataReader(RandomAccessReader.DEFAULT_BUFFER_SIZE, skipIOCache);
+ }
+
+ public RandomAccessReader openDataReader(int bufferSize, boolean skipIOCache) throws IOException
+ {
+ return compression
+ ? CompressedRandomAccessReader.open(getFilename(), skipIOCache)
+ : RandomAccessReader.open(new File(getFilename()), bufferSize, skipIOCache);
+ }
+
public static void acquireReferences(Iterable sstables)
{
for (SSTableReader sstable : sstables)
diff --git a/src/java/org/apache/cassandra/io/sstable/SSTableScanner.java b/src/java/org/apache/cassandra/io/sstable/SSTableScanner.java
index b78e68e39c..dd2b04442c 100644
--- a/src/java/org/apache/cassandra/io/sstable/SSTableScanner.java
+++ b/src/java/org/apache/cassandra/io/sstable/SSTableScanner.java
@@ -19,7 +19,6 @@
package org.apache.cassandra.io.sstable;
-import java.io.File;
import java.io.IOError;
import java.io.IOException;
import java.util.Arrays;
@@ -53,7 +52,7 @@ public class SSTableScanner implements CloseableIterator
{
try
{
- this.file = RandomAccessReader.open(new File(sstable.getFilename()), skipCache);
+ this.file = sstable.openDataReader(bufferSize, skipCache);
}
catch (IOException e)
{
@@ -70,7 +69,7 @@ public class SSTableScanner implements CloseableIterator
{
try
{
- this.file = RandomAccessReader.open(new File(sstable.getFilename()), bufferSize);
+ this.file = sstable.openDataReader(bufferSize, false);
}
catch (IOException e)
{
diff --git a/src/java/org/apache/cassandra/io/sstable/SSTableWriter.java b/src/java/org/apache/cassandra/io/sstable/SSTableWriter.java
index 7714af3e0a..bf0f708864 100644
--- a/src/java/org/apache/cassandra/io/sstable/SSTableWriter.java
+++ b/src/java/org/apache/cassandra/io/sstable/SSTableWriter.java
@@ -21,10 +21,7 @@ package org.apache.cassandra.io.sstable;
import java.io.*;
import java.nio.ByteBuffer;
-import java.util.Arrays;
-import java.util.Collections;
-import java.util.HashSet;
-import java.util.Set;
+import java.util.*;
import com.google.common.collect.Sets;
@@ -36,11 +33,10 @@ import org.apache.cassandra.config.DatabaseDescriptor;
import org.apache.cassandra.db.*;
import org.apache.cassandra.db.compaction.*;
import org.apache.cassandra.dht.IPartitioner;
+import org.apache.cassandra.io.compress.CompressedSequentialWriter;
import org.apache.cassandra.io.util.*;
-import org.apache.cassandra.io.util.RandomAccessReader;
import org.apache.cassandra.io.util.SequentialWriter;
import org.apache.cassandra.service.StorageService;
-import org.apache.cassandra.streaming.OperationType;
import org.apache.cassandra.utils.BloomFilter;
import org.apache.cassandra.utils.ByteBufferUtil;
import org.apache.cassandra.utils.FBUtilities;
@@ -65,6 +61,14 @@ public class SSTableWriter extends SSTable
SSTableMetadata.createCollector());
}
+ private static Set components(CFMetaData metadata)
+ {
+ Set components = new HashSet(Arrays.asList(Component.DATA, Component.FILTER, Component.PRIMARY_INDEX, Component.STATS));
+ if (metadata.useCompression())
+ components.add(Component.COMPRESSION_INFO);
+ return components;
+ }
+
public SSTableWriter(String filename,
long keyCount,
CFMetaData metadata,
@@ -72,12 +76,24 @@ public class SSTableWriter extends SSTable
SSTableMetadata.Collector sstableMetadataCollector) throws IOException
{
super(Descriptor.fromFilename(filename),
- new HashSet(Arrays.asList(Component.DATA, Component.FILTER, Component.PRIMARY_INDEX, Component.STATS)),
+ components(metadata),
metadata,
partitioner);
iwriter = new IndexWriter(descriptor, partitioner, keyCount);
- dbuilder = SegmentedFile.getBuilder(DatabaseDescriptor.getDiskAccessMode());
- dataFile = SequentialWriter.open(new File(getFilename()), true);
+
+ if (compression)
+ {
+ dbuilder = SegmentedFile.getCompressedBuilder();
+ dataFile = CompressedSequentialWriter.open(getFilename(),
+ descriptor.filenameFor(Component.COMPRESSION_INFO),
+ true);
+ }
+ else
+ {
+ dbuilder = SegmentedFile.getBuilder(DatabaseDescriptor.getDiskAccessMode());
+ dataFile = SequentialWriter.open(new File(getFilename()), true);
+ }
+
this.sstableMetadataCollector = sstableMetadataCollector;
}
@@ -205,10 +221,8 @@ public class SSTableWriter extends SSTable
// index and filter
iwriter.close();
- // main data
- long position = dataFile.getFilePointer();
- dataFile.close(); // calls force
- FileUtils.truncate(dataFile.getPath(), position);
+ // main data, close will truncate if necessary
+ dataFile.close();
// write sstable statistics
SSTableMetadata sstableMetadata = sstableMetadataCollector.finalizeMetadata();
diff --git a/src/java/org/apache/cassandra/io/util/CompressedSegmentedFile.java b/src/java/org/apache/cassandra/io/util/CompressedSegmentedFile.java
new file mode 100644
index 0000000000..144d64f21b
--- /dev/null
+++ b/src/java/org/apache/cassandra/io/util/CompressedSegmentedFile.java
@@ -0,0 +1,77 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.cassandra.io.util;
+
+import java.io.IOError;
+import java.io.IOException;
+
+import org.apache.cassandra.io.compress.CompressedRandomAccessReader;
+import org.apache.cassandra.io.compress.CompressionMetadata;
+
+public class CompressedSegmentedFile extends SegmentedFile
+{
+ private final CompressionMetadata metadata;
+
+ public CompressedSegmentedFile(String path, CompressionMetadata metadata)
+ {
+ super(path, metadata.dataLength);
+ this.metadata = metadata;
+ }
+
+ public static class Builder extends SegmentedFile.Builder
+ {
+ /**
+ * Adds a position that would be a safe place for a segment boundary in the file. For a block/row based file
+ * format, safe boundaries are block/row edges.
+ * @param boundary The absolute position of the potential boundary in the file.
+ */
+ public void addPotentialBoundary(long boundary)
+ {
+ // only one segment in a standard-io file
+ }
+
+ /**
+ * Called after all potential boundaries have been added to apply this Builder to a concrete file on disk.
+ * @param path The file on disk.
+ */
+ public SegmentedFile complete(String path)
+ {
+ return new CompressedSegmentedFile(path, CompressedRandomAccessReader.metadata(path));
+ }
+ }
+
+ public FileDataInput getSegment(long position, int bufferSize)
+ {
+ try
+ {
+ RandomAccessReader file = CompressedRandomAccessReader.open(path, metadata);
+ file.seek(position);
+ return file;
+ }
+ catch (IOException e)
+ {
+ throw new IOError(e);
+ }
+ }
+
+ public void cleanup()
+ {
+ // nothing to do
+ }
+}
diff --git a/src/java/org/apache/cassandra/io/util/RandomAccessReader.java b/src/java/org/apache/cassandra/io/util/RandomAccessReader.java
index 4f9f3de446..336cce8f13 100644
--- a/src/java/org/apache/cassandra/io/util/RandomAccessReader.java
+++ b/src/java/org/apache/cassandra/io/util/RandomAccessReader.java
@@ -1,3 +1,21 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
package org.apache.cassandra.io.util;
import java.io.EOFException;
@@ -32,7 +50,7 @@ public class RandomAccessReader extends RandomAccessFile implements FileDataInpu
protected int validBufferBytes = 0;
// channel liked with the file, used to retrieve data and force updates.
- private final FileChannel channel;
+ protected final FileChannel channel;
private final boolean skipIOCache;
diff --git a/src/java/org/apache/cassandra/io/util/SegmentedFile.java b/src/java/org/apache/cassandra/io/util/SegmentedFile.java
index 7058db3d67..709e662bdb 100644
--- a/src/java/org/apache/cassandra/io/util/SegmentedFile.java
+++ b/src/java/org/apache/cassandra/io/util/SegmentedFile.java
@@ -61,6 +61,11 @@ public abstract class SegmentedFile
: new BufferedSegmentedFile.Builder();
}
+ public static Builder getCompressedBuilder()
+ {
+ return new CompressedSegmentedFile.Builder();
+ }
+
public abstract FileDataInput getSegment(long position, int bufferSize);
/**
diff --git a/src/java/org/apache/cassandra/io/util/SequentialWriter.java b/src/java/org/apache/cassandra/io/util/SequentialWriter.java
index 4f2c9da437..02f0924c5a 100644
--- a/src/java/org/apache/cassandra/io/util/SequentialWriter.java
+++ b/src/java/org/apache/cassandra/io/util/SequentialWriter.java
@@ -26,7 +26,7 @@ import org.apache.cassandra.utils.CLibrary;
public class SequentialWriter extends OutputStream
{
// isDirty - true if this.buffer contains any un-synced bytes
- private boolean isDirty = false, syncNeeded = false;
+ protected boolean isDirty = false, syncNeeded = false;
// absolute path to the given file
private final String filePath;
@@ -34,14 +34,14 @@ public class SequentialWriter extends OutputStream
// so we can use the write(int) path w/o tons of new byte[] allocations
private final byte[] singleByteBuffer = new byte[1];
- private byte[] buffer;
+ protected byte[] buffer;
private final boolean skipIOCache;
private final int fd;
- private long current = 0, bufferOffset;
- private int validBufferBytes;
+ protected long current = 0, bufferOffset;
+ protected int validBufferBytes;
- private final RandomAccessFile out;
+ protected final RandomAccessFile out;
// used if skip I/O cache was enabled
private long ioCacheStartOffset = 0, bytesSinceCacheFlush = 0;
@@ -139,10 +139,15 @@ public class SequentialWriter extends OutputStream
* @throws java.io.IOException on any I/O error.
*/
public void sync() throws IOException
+ {
+ syncInternal();
+ }
+
+ protected void syncInternal() throws IOException
{
if (syncNeeded)
{
- flush();
+ flushInternal();
out.getFD().sync();
syncNeeded = false;
@@ -158,10 +163,15 @@ public class SequentialWriter extends OutputStream
*/
@Override
public void flush() throws IOException
+ {
+ flushInternal();
+ }
+
+ protected void flushInternal() throws IOException
{
if (isDirty)
{
- out.write(buffer, 0, validBufferBytes);
+ flushData();
if (skipIOCache)
{
@@ -187,6 +197,15 @@ public class SequentialWriter extends OutputStream
}
}
+ /**
+ * Override this method instead of overriding flush()
+ * @throws IOException on any I/O error.
+ */
+ protected void flushData() throws IOException
+ {
+ out.write(buffer, 0, validBufferBytes);
+ }
+
public long getFilePointer()
{
return current;
@@ -202,14 +221,13 @@ public class SequentialWriter extends OutputStream
return filePath;
}
-
- private void reBuffer() throws IOException
+ protected void reBuffer() throws IOException
{
- flush();
+ flushInternal();
resetBuffer();
}
- private void resetBuffer()
+ protected void resetBuffer()
{
bufferOffset = current;
validBufferBytes = 0;
@@ -229,12 +247,18 @@ public class SequentialWriter extends OutputStream
{
assert mark instanceof BufferedFileWriterMark;
+ long previous = current;
+ current = ((BufferedFileWriterMark) mark).pointer;
+
+ if (previous - current <= validBufferBytes) // current buffer
+ {
+ validBufferBytes = validBufferBytes - ((int) (previous - current));
+ return;
+ }
+
// synchronize current buffer with disk
// because we don't want any data loss
- sync();
-
- // setting marker as a current offset
- current = ((BufferedFileWriterMark) mark).pointer;
+ syncInternal();
// truncate file to given position
truncate(current);
@@ -253,14 +277,17 @@ public class SequentialWriter extends OutputStream
@Override
public void close() throws IOException
{
- sync();
+ if (buffer == null)
+ return; // already closed
+
+ syncInternal();
buffer = null;
if (skipIOCache && bytesSinceCacheFlush > 0)
CLibrary.trySkipCache(fd, 0, 0);
- out.close(); // this will also close channel for us
+ out.close();
}
/**
diff --git a/src/java/org/apache/cassandra/streaming/FileStreamTask.java b/src/java/org/apache/cassandra/streaming/FileStreamTask.java
index 7fe120af17..c6e79a76f1 100644
--- a/src/java/org/apache/cassandra/streaming/FileStreamTask.java
+++ b/src/java/org/apache/cassandra/streaming/FileStreamTask.java
@@ -28,6 +28,7 @@ import java.nio.channels.FileChannel;
import java.nio.channels.SocketChannel;
import org.apache.cassandra.gms.Gossiper;
+import org.apache.cassandra.io.compress.CompressedRandomAccessReader;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
@@ -91,6 +92,12 @@ public class FileStreamTask extends WrappedRunnable
if (header.file == null)
return;
+ if (header.file.sstable.compression)
+ {
+ CompressedRandomAccessReader.transfer(header.file, channel);
+ return;
+ }
+
RandomAccessFile raf = new RandomAccessFile(new File(header.file.getFilename()), "r");
try
{
diff --git a/src/java/org/apache/cassandra/streaming/IncomingStreamReader.java b/src/java/org/apache/cassandra/streaming/IncomingStreamReader.java
index b45e6d607d..1a7ee95dd6 100644
--- a/src/java/org/apache/cassandra/streaming/IncomingStreamReader.java
+++ b/src/java/org/apache/cassandra/streaming/IncomingStreamReader.java
@@ -21,7 +21,6 @@ package org.apache.cassandra.streaming;
import java.io.*;
import java.net.InetSocketAddress;
import java.net.Socket;
-import java.nio.channels.SocketChannel;
import java.util.Collections;
import org.slf4j.Logger;
@@ -35,10 +34,7 @@ import org.apache.cassandra.db.Table;
import org.apache.cassandra.db.compaction.AbstractCompactedRow;
import org.apache.cassandra.db.compaction.CompactionController;
import org.apache.cassandra.db.compaction.PrecompactedRow;
-import org.apache.cassandra.io.sstable.IndexHelper;
-import org.apache.cassandra.io.sstable.SSTableIdentityIterator;
-import org.apache.cassandra.io.sstable.SSTableReader;
-import org.apache.cassandra.io.sstable.SSTableWriter;
+import org.apache.cassandra.io.sstable.*;
import org.apache.cassandra.io.util.FileUtils;
import org.apache.cassandra.service.StorageService;
import org.apache.cassandra.utils.ByteBufferUtil;
diff --git a/src/resources/org/apache/cassandra/cli/CliHelp.yaml b/src/resources/org/apache/cassandra/cli/CliHelp.yaml
index 882e469160..c7ed23b0d8 100644
--- a/src/resources/org/apache/cassandra/cli/CliHelp.yaml
+++ b/src/resources/org/apache/cassandra/cli/CliHelp.yaml
@@ -531,6 +531,8 @@ commands:
NOTE: Thsi provider requires JNA.jar to be in the class path to
enable native methods.
+ - compression: Use compression for SSTable data files. Accepts the values true and false.
+
Examples:
create column family Super4
with column_type = 'Super'
@@ -772,6 +774,8 @@ commands:
NOTE: Thsi provider requires JNA.jar to be in the class path to
enable native methods.
+ - compression: Use compression for SSTable data files. Accepts the values true and false.
+
Examples:
update column family Super4
with column_type = 'Super'
diff --git a/test/unit/org/apache/cassandra/SchemaLoader.java b/test/unit/org/apache/cassandra/SchemaLoader.java
index d6bfb680ad..57c2f89d78 100644
--- a/test/unit/org/apache/cassandra/SchemaLoader.java
+++ b/test/unit/org/apache/cassandra/SchemaLoader.java
@@ -239,10 +239,24 @@ public class SchemaLoader
false,
standardCFMD(ks_nocommit, "Standard1")));
+
+ if (Boolean.parseBoolean(System.getProperty("cassandra.test.compression", "false")))
+ useCompression(schema);
return schema;
}
+ private static void useCompression(List schema)
+ {
+ for (KSMetaData ksm : schema)
+ {
+ for (CFMetaData cfm : ksm.cfMetaData().values())
+ {
+ cfm.compression(true);
+ }
+ }
+ }
+
private static CFMetaData standardCFMD(String ksName, String cfName)
{
return new CFMetaData(ksName, cfName, ColumnFamilyType.Standard, BytesType.instance, null).keyCacheSize(0);
diff --git a/test/unit/org/apache/cassandra/db/TableTest.java b/test/unit/org/apache/cassandra/db/TableTest.java
index 54523a5320..da199c7a27 100644
--- a/test/unit/org/apache/cassandra/db/TableTest.java
+++ b/test/unit/org/apache/cassandra/db/TableTest.java
@@ -18,7 +18,6 @@
package org.apache.cassandra.db;
-import java.io.File;
import java.nio.ByteBuffer;
import java.nio.charset.CharacterCodingException;
import java.text.DecimalFormat;
@@ -406,7 +405,7 @@ public class TableTest extends CleanupHelper
// verify that we do indeed have multiple index entries
SSTableReader sstable = cfStore.getSSTables().iterator().next();
long position = sstable.getPosition(key, SSTableReader.Operator.EQ);
- RandomAccessReader file = RandomAccessReader.open(new File(sstable.getFilename()));
+ RandomAccessReader file = sstable.openDataReader(false);
file.seek(position);
assert ByteBufferUtil.readWithShortLength(file).equals(key.key);
SSTableReader.readRowSize(file, sstable.descriptor);
diff --git a/test/unit/org/apache/cassandra/io/compress/CompressedRandomAccessReaderTest.java b/test/unit/org/apache/cassandra/io/compress/CompressedRandomAccessReaderTest.java
new file mode 100644
index 0000000000..bc4a8492d7
--- /dev/null
+++ b/test/unit/org/apache/cassandra/io/compress/CompressedRandomAccessReaderTest.java
@@ -0,0 +1,90 @@
+/**
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+package org.apache.cassandra.io.compress;
+
+import java.io.*;
+
+import org.junit.Test;
+
+import org.apache.cassandra.io.util.*;
+
+public class CompressedRandomAccessReaderTest
+{
+ @Test
+ public void testResetAndTruncate() throws IOException
+ {
+ // test reset in current buffer or previous one
+ testResetAndTruncate(false, 10);
+ testResetAndTruncate(false, CompressedSequentialWriter.CHUNK_LENGTH);
+ }
+
+ @Test
+ public void testResetAndTruncateCompressed() throws IOException
+ {
+ // test reset in current buffer or previous one
+ testResetAndTruncate(true, 10);
+ testResetAndTruncate(true, CompressedSequentialWriter.CHUNK_LENGTH);
+ }
+
+ private void testResetAndTruncate(boolean compressed, int junkSize) throws IOException
+ {
+ String filename = "corruptFile";
+ File f = new File(filename);
+
+ try
+ {
+ SequentialWriter writer = compressed
+ ? new CompressedSequentialWriter(f, filename + ".metadata", false)
+ : new SequentialWriter(f, CompressedSequentialWriter.CHUNK_LENGTH, false);
+
+ writer.write("The quick ".getBytes());
+ FileMark mark = writer.mark();
+ writer.write("blue fox jumps over the lazy dog".getBytes());
+
+ // write enough to be sure to change chunk
+ for (int i = 0; i < junkSize; ++i)
+ {
+ writer.write((byte)1);
+ }
+
+ writer.resetAndTruncate(mark);
+ writer.write("brown fox jumps over the lazy dog".getBytes());
+ writer.close();
+
+ assert f.exists();
+ RandomAccessReader reader = compressed
+ ? new CompressedRandomAccessReader(filename, new CompressionMetadata(filename + ".metadata", f.length()), false)
+ : new RandomAccessReader(f, CompressedSequentialWriter.CHUNK_LENGTH, false);
+ String expected = "The quick brown fox jumps over the lazy dog";
+ assert reader.length() == expected.length();
+ byte[] b = new byte[expected.length()];
+ reader.readFully(b);
+ assert new String(b).equals(expected) : "Expecting '" + expected + "', got '" + new String(b) + "'";
+ }
+ finally
+ {
+ // cleanup
+ if (f.exists())
+ f.delete();
+ File metadata = new File(filename + ".metadata");
+ if (compressed && metadata.exists())
+ metadata.delete();
+ }
+ }
+}
diff --git a/test/unit/org/apache/cassandra/io/sstable/SSTableTest.java b/test/unit/org/apache/cassandra/io/sstable/SSTableTest.java
index d4590bc525..4836da7694 100644
--- a/test/unit/org/apache/cassandra/io/sstable/SSTableTest.java
+++ b/test/unit/org/apache/cassandra/io/sstable/SSTableTest.java
@@ -19,7 +19,6 @@
package org.apache.cassandra.io.sstable;
-import java.io.File;
import java.io.IOException;
import java.nio.ByteBuffer;
import java.util.*;
@@ -51,7 +50,7 @@ public class SSTableTest extends CleanupHelper
private void verifySingle(SSTableReader sstable, ByteBuffer bytes, ByteBuffer key) throws IOException
{
- RandomAccessReader file = RandomAccessReader.open(new File(sstable.getFilename()));
+ RandomAccessReader file = sstable.openDataReader(false);
file.seek(sstable.getPosition(sstable.partitioner.decorateKey(key), SSTableReader.Operator.EQ));
assert key.equals(ByteBufferUtil.readWithShortLength(file));
int size = (int)SSTableReader.readRowSize(file, sstable.descriptor);
@@ -88,7 +87,7 @@ public class SSTableTest extends CleanupHelper
{
List keys = new ArrayList(map.keySet());
Collections.shuffle(keys);
- RandomAccessReader file = RandomAccessReader.open(new File(sstable.getFilename()));
+ RandomAccessReader file = sstable.openDataReader(false);
for (ByteBuffer key : keys)
{
file.seek(sstable.getPosition(sstable.partitioner.decorateKey(key), SSTableReader.Operator.EQ));
diff --git a/tools/stress/src/org/apache/cassandra/stress/Session.java b/tools/stress/src/org/apache/cassandra/stress/Session.java
index e0765f8581..1508379b25 100644
--- a/tools/stress/src/org/apache/cassandra/stress/Session.java
+++ b/tools/stress/src/org/apache/cassandra/stress/Session.java
@@ -77,6 +77,7 @@ public class Session implements Serializable
availableOptions.addOption("W", "no-replicate-on-write",false, "Set replicate_on_write to false for counters. Only counter add with CL=ONE will work");
availableOptions.addOption("V", "average-size-values", false, "Generate column values of average rather than specific size");
availableOptions.addOption("T", "send-to", true, "Send this as a request to the stress daemon at specified address.");
+ availableOptions.addOption("I", "compression", false, "Use sstable compression when creating schema");
}
private int numKeys = 1000 * 1000;
@@ -92,6 +93,7 @@ public class Session implements Serializable
private int retryTimes = 10;
private int port = 9160;
private int superColumns = 1;
+ private boolean compression = false;
private int progressInterval = 10;
private int keysPerCall = 1000;
@@ -258,6 +260,9 @@ public class Session implements Serializable
if (cmd.hasOption("W"))
replicateOnWrite = false;
+ if (cmd.hasOption("I"))
+ compression = true;
+
averageSizeValues = cmd.hasOption("V");
try
@@ -412,7 +417,8 @@ public class Session implements Serializable
// column family for standard columns
CfDef standardCfDef = new CfDef("Keyspace1", "Standard1");
- standardCfDef.setComparator_type("AsciiType").setDefault_validation_class("BytesType");
+ System.out.println("Compression = " + compression);
+ standardCfDef.setComparator_type("AsciiType").setDefault_validation_class("BytesType").setCompression(compression);
if (indexType != null)
{
ColumnDef standardColumn = new ColumnDef(ByteBufferUtil.bytes("C1"), "BytesType");
@@ -422,13 +428,13 @@ public class Session implements Serializable
// column family with super columns
CfDef superCfDef = new CfDef("Keyspace1", "Super1").setColumn_type("Super");
- superCfDef.setComparator_type("AsciiType").setSubcomparator_type("AsciiType").setDefault_validation_class("BytesType");
+ superCfDef.setComparator_type("AsciiType").setSubcomparator_type("AsciiType").setDefault_validation_class("BytesType").setCompression(compression);
// column family for standard counters
- CfDef counterCfDef = new CfDef("Keyspace1", "Counter1").setDefault_validation_class("CounterColumnType").setReplicate_on_write(replicateOnWrite);
+ CfDef counterCfDef = new CfDef("Keyspace1", "Counter1").setDefault_validation_class("CounterColumnType").setReplicate_on_write(replicateOnWrite).setCompression(compression);
// column family with counter super columns
- CfDef counterSuperCfDef = new CfDef("Keyspace1", "SuperCounter1").setDefault_validation_class("CounterColumnType").setReplicate_on_write(replicateOnWrite).setColumn_type("Super");
+ CfDef counterSuperCfDef = new CfDef("Keyspace1", "SuperCounter1").setDefault_validation_class("CounterColumnType").setReplicate_on_write(replicateOnWrite).setColumn_type("Super").setCompression(compression);
keyspace.setName("Keyspace1");
keyspace.setStrategy_class(replicationStrategy);