maedhroz commented on code in PR #2267: URL: https://github.com/apache/cassandra/pull/2267#discussion_r1183030818
########## src/java/org/apache/cassandra/io/sstable/format/bti/BtiTableScrubber.java: ########## @@ -0,0 +1,304 @@ +/* + * 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.sstable.format.bti; + +import java.io.IOError; +import java.io.IOException; +import java.nio.ByteBuffer; + +import org.apache.cassandra.db.ColumnFamilyStore; +import org.apache.cassandra.db.DecoratedKey; +import org.apache.cassandra.db.TypeSizes; +import org.apache.cassandra.db.compaction.CompactionInterruptedException; +import org.apache.cassandra.db.lifecycle.LifecycleTransaction; +import org.apache.cassandra.db.rows.UnfilteredRowIterator; +import org.apache.cassandra.db.rows.UnfilteredRowIterators; +import org.apache.cassandra.io.sstable.IScrubber; +import org.apache.cassandra.io.sstable.SSTableRewriter; +import org.apache.cassandra.io.sstable.format.SortedTableScrubber; +import org.apache.cassandra.io.sstable.format.bti.BtiFormat.Components; +import org.apache.cassandra.io.util.FileUtils; +import org.apache.cassandra.utils.ByteBufferUtil; +import org.apache.cassandra.utils.FBUtilities; +import org.apache.cassandra.utils.OutputHandler; +import org.apache.cassandra.utils.Throwables; + +public class BtiTableScrubber extends SortedTableScrubber<BtiTableReader> implements IScrubber +{ + private final boolean isIndex; + private ScrubPartitionIterator indexIterator; + + public BtiTableScrubber(ColumnFamilyStore cfs, + LifecycleTransaction transaction, + OutputHandler outputHandler, + IScrubber.Options options) + { + super(cfs, transaction, outputHandler, options); + + boolean hasIndexFile = sstable.getComponents().contains(Components.PARTITION_INDEX); + this.isIndex = cfs.isIndex(); + if (!hasIndexFile) + { + // if there's any corruption in the -Data.db then partitions can't be skipped over. but it's worth a shot. + outputHandler.warn("Missing index component"); + } + + try + { + this.indexIterator = hasIndexFile + ? openIndexIterator() + : null; + } + catch (RuntimeException ex) + { + outputHandler.warn("Detected corruption in the index file - cannot open index iterator", ex); + } + } + + private ScrubPartitionIterator openIndexIterator() + { + try + { + return sstable.scrubPartitionsIterator(); + } + catch (Throwable t) + { + outputHandler.warn(t, "Index is unreadable, scrubbing will continue without index."); + } + return null; + } + + @Override + protected UnfilteredRowIterator withValidation(UnfilteredRowIterator iter, String filename) + { + return options.checkData && !isIndex ? UnfilteredRowIterators.withValidation(iter, filename) : iter; + } + + public void scrubInternal(SSTableRewriter writer) + { + assert !indexAvailable() || indexIterator.dataPosition() == 0 : indexIterator.dataPosition(); + + DecoratedKey prevKey = null; + + while (!dataFile.isEOF()) + { + if (scrubInfo.isStopRequested()) + throw new CompactionInterruptedException(scrubInfo.getCompactionInfo()); + + // position in a data file where the partition starts + long dataStart = dataFile.getFilePointer(); + outputHandler.debug("Reading row at %d", dataStart); + + DecoratedKey key = null; + Throwable keyReadError = null; + try + { + ByteBuffer raw = ByteBufferUtil.readWithShortLength(dataFile); + if (!cfs.metadata.getLocal().isIndex()) Review Comment: nit: Do we have to check this on every iteration? (i.e. Is the table going to change type in the middle of this loop?) -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
