1 /*
2 * Copyright (C) 2017, Google Inc.
3 * and other copyright owners as documented in the project's IP log.
4 *
5 * This program and the accompanying materials are made available
6 * under the terms of the Eclipse Distribution License v1.0 which
7 * accompanies this distribution, is reproduced below, and is
8 * available at http://www.eclipse.org/org/documents/edl-v10.php
9 *
10 * All rights reserved.
11 *
12 * Redistribution and use in source and binary forms, with or
13 * without modification, are permitted provided that the following
14 * conditions are met:
15 *
16 * - Redistributions of source code must retain the above copyright
17 * notice, this list of conditions and the following disclaimer.
18 *
19 * - Redistributions in binary form must reproduce the above
20 * copyright notice, this list of conditions and the following
21 * disclaimer in the documentation and/or other materials provided
22 * with the distribution.
23 *
24 * - Neither the name of the Eclipse Foundation, Inc. nor the
25 * names of its contributors may be used to endorse or promote
26 * products derived from this software without specific prior
27 * written permission.
28 *
29 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND
30 * CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
31 * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
32 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
33 * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR
34 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
35 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
36 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
37 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
38 * CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
39 * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
40 * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
41 * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
42 */
43
44 package org.eclipse.jgit.internal.storage.reftable;
45
46 import java.io.IOException;
47 import java.io.OutputStream;
48 import java.util.ArrayDeque;
49 import java.util.ArrayList;
50 import java.util.List;
51
52 import org.eclipse.jgit.internal.storage.reftable.ReftableWriter.Stats;
53 import org.eclipse.jgit.lib.PersonIdent;
54 import org.eclipse.jgit.lib.ReflogEntry;
55
56 /**
57 * Merges reftables and compacts them into a single output.
58 * <p>
59 * For a partial compaction callers should {@link #setIncludeDeletes(boolean)}
60 * to {@code true} to ensure the new reftable continues to use a delete marker
61 * to shadow any lower reftable that may have the reference present.
62 * <p>
63 * By default all log entries within the range defined by
64 * {@link #setMinUpdateIndex(long)} and {@link #setMaxUpdateIndex(long)} are
65 * copied, even if no references in the output file match the log records.
66 * Callers may truncate the log to a more recent time horizon with
67 * {@link #setOldestReflogTimeMillis(long)}, or disable the log altogether with
68 * {@code setOldestReflogTimeMillis(Long.MAX_VALUE)}.
69 */
70 public class ReftableCompactor {
71 private final ReftableWriter writer = new ReftableWriter();
72 private final ArrayDeque<Reftable> tables = new ArrayDeque<>();
73
74 private long compactBytesLimit;
75 private long bytesToCompact;
76 private boolean includeDeletes;
77 private long minUpdateIndex;
78 private long maxUpdateIndex;
79 private long oldestReflogTimeMillis;
80 private Stats stats;
81
82 /**
83 * @param cfg
84 * configuration for the reftable.
85 * @return {@code this}
86 */
87 public ReftableCompactor setConfig(ReftableConfig cfg) {
88 writer.setConfig(cfg);
89 return this;
90 }
91
92 /**
93 * @param bytes
94 * limit on number of bytes from source tables to compact.
95 * @return {@code this}
96 */
97 public ReftableCompactor setCompactBytesLimit(long bytes) {
98 compactBytesLimit = bytes;
99 return this;
100 }
101
102 /**
103 * @param deletes
104 * {@code true} to include deletions in the output, which may be
105 * necessary for partial compaction.
106 * @return {@code this}
107 */
108 public ReftableCompactor setIncludeDeletes(boolean deletes) {
109 includeDeletes = deletes;
110 return this;
111 }
112
113 /**
114 * @param min
115 * the minimum update index for log entries that appear in the
116 * compacted reftable. This should be 1 higher than the prior
117 * reftable's {@code maxUpdateIndex} if this table will be used
118 * in a stack.
119 * @return {@code this}
120 */
121 public ReftableCompactor setMinUpdateIndex(long min) {
122 minUpdateIndex = min;
123 return this;
124 }
125
126 /**
127 * @param max
128 * the maximum update index for log entries that appear in the
129 * compacted reftable. This should be at least 1 higher than the
130 * prior reftable's {@code maxUpdateIndex} if this table will be
131 * used in a stack.
132 * @return {@code this}
133 */
134 public ReftableCompactor setMaxUpdateIndex(long max) {
135 maxUpdateIndex = max;
136 return this;
137 }
138
139 /**
140 * @param timeMillis
141 * oldest log time to preserve. Entries whose timestamps are
142 * {@code >= timeMillis} will be copied into the output file. Log
143 * entries that predate {@code timeMillis} will be discarded.
144 * Specified in Java standard milliseconds since the epoch.
145 * @return {@code this}
146 */
147 public ReftableCompactor setOldestReflogTimeMillis(long timeMillis) {
148 oldestReflogTimeMillis = timeMillis;
149 return this;
150 }
151
152 /**
153 * Add all of the tables, in the specified order.
154 * <p>
155 * Unconditionally adds all tables, ignoring the
156 * {@link #setCompactBytesLimit(long)}.
157 *
158 * @param readers
159 * tables to compact. Tables should be ordered oldest first/most
160 * recent last so that the more recent tables can shadow the
161 * older results. Caller is responsible for closing the readers.
162 * @throws IOException
163 * update indexes of a reader cannot be accessed.
164 */
165 public void addAll(List<? extends Reftable> readers) throws IOException {
166 tables.addAll(readers);
167 for (Reftable r : readers) {
168 if (r instanceof ReftableReader) {
169 adjustUpdateIndexes((ReftableReader) r);
170 }
171 }
172 }
173
174 /**
175 * Try to add this reader at the bottom of the stack.
176 * <p>
177 * A reader may be rejected by returning {@code false} if the compactor is
178 * already rewriting its {@link #setCompactBytesLimit(long)}. When this
179 * happens the caller should stop trying to add tables, and execute the
180 * compaction.
181 *
182 * @param reader
183 * the reader to insert at the bottom of the stack. Caller is
184 * responsible for closing the reader.
185 * @return {@code true} if the compactor accepted this table; {@code false}
186 * if the compactor has reached its limit.
187 * @throws IOException
188 * if size of {@code reader}, or its update indexes cannot be read.
189 */
190 public boolean tryAddFirst(ReftableReader reader) throws IOException {
191 long sz = reader.size();
192 if (compactBytesLimit > 0 && bytesToCompact + sz > compactBytesLimit) {
193 return false;
194 }
195 bytesToCompact += sz;
196 adjustUpdateIndexes(reader);
197 tables.addFirst(reader);
198 return true;
199 }
200
201 private void adjustUpdateIndexes(ReftableReader reader) throws IOException {
202 if (minUpdateIndex == 0) {
203 minUpdateIndex = reader.minUpdateIndex();
204 } else {
205 minUpdateIndex = Math.min(minUpdateIndex, reader.minUpdateIndex());
206 }
207 maxUpdateIndex = Math.max(maxUpdateIndex, reader.maxUpdateIndex());
208 }
209
210 /**
211 * Write a compaction to {@code out}.
212 *
213 * @param out
214 * stream to write the compacted tables to. Caller is responsible
215 * for closing {@code out}.
216 * @throws IOException
217 * if tables cannot be read, or cannot be written.
218 */
219 public void compact(OutputStream out) throws IOException {
220 MergedReftable mr = new MergedReftable(new ArrayList<>(tables));
221 mr.setIncludeDeletes(includeDeletes);
222
223 writer.setMinUpdateIndex(minUpdateIndex);
224 writer.setMaxUpdateIndex(maxUpdateIndex);
225 writer.begin(out);
226 mergeRefs(mr);
227 mergeLogs(mr);
228 writer.finish();
229 stats = writer.getStats();
230 }
231
232 /** @return statistics of the last written reftable. */
233 public Stats getStats() {
234 return stats;
235 }
236
237 private void mergeRefs(MergedReftable mr) throws IOException {
238 try (RefCursor rc = mr.allRefs()) {
239 while (rc.next()) {
240 writer.writeRef(rc.getRef(), rc.getUpdateIndex());
241 }
242 }
243 }
244
245 private void mergeLogs(MergedReftable mr) throws IOException {
246 if (oldestReflogTimeMillis == Long.MAX_VALUE) {
247 return;
248 }
249
250 try (LogCursor lc = mr.allLogs()) {
251 while (lc.next()) {
252 long updateIndex = lc.getUpdateIndex();
253 if (updateIndex < minUpdateIndex
254 || updateIndex > maxUpdateIndex) {
255 // Cannot merge log records outside the header's range.
256 continue;
257 }
258
259 String refName = lc.getRefName();
260 ReflogEntry log = lc.getReflogEntry();
261 if (log == null) {
262 if (includeDeletes) {
263 writer.deleteLog(refName, updateIndex);
264 }
265 continue;
266 }
267
268 PersonIdent who = log.getWho();
269 if (who.getWhen().getTime() >= oldestReflogTimeMillis) {
270 writer.writeLog(
271 refName,
272 updateIndex,
273 who,
274 log.getOldId(),
275 log.getNewId(),
276 log.getComment());
277 }
278 }
279 }
280 }
281 }