1 # Welcome to the Leyden Prototype Repository!
2
3 The purpose of the Leyden repository is to prototype improvements to the
4 startup time, time to peak performance, and footprint of Java programs, as a part of
5 [Project Leyden](https://openjdk.org/projects/leyden). We solicit feedback from
6 the Java community, with the hope that some of these improvements can be eventually
7 incoporated in future JDK releases.
8
9 ## 0. Disclaimers
10
11 - *This repository contains experimental and unstable code. It is not intended to be used
12 in a production environment.*
13 - *This repository is intended for developers of the JDK, and advanced Java developers who
14 are familiar with building the JDK.*
15 - *The experimental features in this repository may be changed or removed without notice.
16 Command line flags and workflows will change.*
17 - *The benchmarks results reported on this page are for illustrative purposes only. Your
18 applications may get better or worse results.*
19
20 ## 1. Overview
21
22 The Leyden "[premain](https://github.com/openjdk/leyden/blob/premain/)" prototype
23 includes many optimizations that shift work from run time to earlier
24 executions of the application, which are
25 called _training runs_. In a training run, we pre-compute various kinds of information.
26 Importantly, we pre-compile
27 bytecode to native code, guided by observations of the application's actual behavior
28 during the training run.
29
30 The Leyden repository closely tracks the JDK main line. We are typically only a few weeks behind
31 the [main-line JDK repo](https://github.com/openjdk/jdk).
32
33 We have implemented the following improvements over the JDK main line:
34
35 - **[Ahead-of-Time Class Loading & Linking (JEP 483)](https://openjdk.org/jeps/483)**:
36 This gives
37 the JVM the ability to put classes in the _linked_ state as soon the application starts up. As a result,
38 we can implement many other time shifting optimizations with considerably simplified assumptions.
39 - This feature is accessed with the new VM flag `-XX:+PreloadSharedClasses`.
40
41 - **[Unified Ahead-of-Time Cache (JEP draft 8320264)](https://openjdk.org/jeps/8320264)**:
42 This enhancement to [CDS] is foundational to the features that follow.
43 - It enables [CDS] to store not only class metadata and heap objects (as before),
44 but also profiling data and compiled code.
45 - This feature is accessed with the new VM flag `-XX:CacheDataStore`.
46 - This option simplifies the creation of the CDS archive, and also the testing
47 of all the prototype features listed here.
48
49 - **[Ahead-of-Time Method Profiling (JEP draft 8325147)](https://openjdk.org/jeps/8325147)**: We store method profiles
50 from training runs in the CDS archive, thereby enabling the JIT to begin compiling earlier during warmup.
51 As a result, Java applications can reach peak performance faster.
52 - This feature is enabled by the new VM flags `-XX:+RecordTraining` and `-XX:+ReplayTraining`.
53
54 - **Ahead-of-time resolution of constant pool entries**: many
55 constant pool entries are resolved during the assembly phase. This allows the application to start up faster. Also,
56 the existence of resolved constant pool entries allows the AOT compiler to generate better code.
57 For diagnostic purposes, you can use `-XX:+UnlockDiagnosticVMOptions -XX:-AOTInvokeDynamicLinking`
58 to disable the AOT linking of constant pool entries for the `invokedynamic` bytecode.
59
60 - **[Ahead-of-Time Code Compilation (JEP draft 8335368)](https://openjdk.org/jeps/8335368)**: Methods that are frequently used during the training run can be
61 compiled and stored along with the CDS archive. As a result, as soon as the application starts up
62 in the production run, its methods can be can be natively executed.
63 - This feature is enabled by the new VM flags `-XX:+StoreCachedCode`, `-XX:+LoadCachedCode`, and `-XX:CachedCodeFile`.
64 - Currently, the native code is stored in a separate file, but our plans is to eventually store the native code
65 inside the CDS archive file.
66
67 - **Ahead-of-time generation of [Dynamic Proxies](https://docs.oracle.com/en/java/javase/22/docs/api/java.base/java/lang/reflect/Proxy.html)**:
68 Dynamic proxies are frequently used by popular application frameworks. We can improve start-up time by generating these proxies ahead of time.
69 - This feature is enabled by the new VM flag `-XX:+ArchiveDynamicProxies`.
70
71 - **Ahead-of-time generation of reflection data**: Reflection data (such as instances of
72 `java.lang.reflect.Method`) are generated by the JVM to support `java.lang.reflect` operations. We can
73 generate these ahead of time to improve start-up.
74 - This feature is enabled by the new VM flag `-XX:+ArchiveReflectionData`.
75
76 - **Class Not Found Cache**: Sometimes application frameworks repeatedly try to load classes that do not exist. This optimization allows such failing lookups to be done quickly without repeatedly scanning the class path.
77 - This feature is enabled by the new VM flag `-XX:+ArchiveLoaderLookupCache`.
78
79 The flag `-XX:CacheDataStore` automatically enables the whole bundle
80 of features listed above. This simplifies testing of the whole
81 prototype. If necessary for more detailed testing, each feature can
82 be individually disabled by negating its associated flag.
83
84 The names of all of these VM flags will change in a future EA build as we transition from the old “CDS” terminology to the new “AOT” terminology, as discussed [here](https://openjdk.org/jeps/483#History).
85
86 [CDS]: <https://docs.oracle.com/en/java/javase/22/vm/class-data-sharing.html>
87
88 ## 2. Building the Leyden Repository
89
90 The Leyden Repository can be built in the same way as the main-line JDK repository.
91 Please use the "premain" branch. I.e., [https://github.com/openjdk/leyden/tree/premain](https://github.com/openjdk/leyden/tree/premain).
92
93 For build instructions please see the
94 [online documentation](https://openjdk.org/groups/build/doc/building.html),
95 or either of these files:
96
97 - [doc/building.html](doc/building.html) (html version)
98 - [doc/building.md](doc/building.md) (markdown version)
99
100 See <https://openjdk.org/> for more information about the OpenJDK
101 Community and the JDK and see <https://bugs.openjdk.org> for JDK issue
102 tracking.
103
104 ## 3. Trying out Leyden Features
105
106 The easiest way to try out the Leyden features is to build a JVM from the Leyden repository, and use it with your application with the `-XX:CacheDataStore` flag.
107
108 Here's a small benchmark that uses the JDK's built-in
109 [`JavaCompiler`](https://docs.oracle.com/en/java/javase/21/docs/api/java.compiler/javax/tools/JavaCompiler.html)
110 class to compile some Java source files. This benchmark spends a significant amount of start-up time
111 setting up the classes used by `JavaCompiler`, so it will benefit from the Leyden features.
112
113 First, download [JavacBenchApp.java](https://github.com/iklam/jdk/blob/f95f851aed3d2bf06edabab1e7c24e15f4145d0d/test/hotspot/jtreg/runtime/cds/appcds/applications/JavacBenchApp.java)
114 and compile it into a JAR file.
115
116 (Remember to use the `java` program that you built from the Leyden repository.)
117
118 ```
119 $ javac JavacBenchApp.java
120 $ jar cvf JavacBenchApp.jar JavacBenchApp*.class
121 added manifest
122 adding: JavacBenchApp$ClassFile.class(in = 1608) (out= 787)(deflated 51%)
123 adding: JavacBenchApp$FileManager.class(in = 2090) (out= 979)(deflated 53%)
124 adding: JavacBenchApp$SourceFile.class(in = 1351) (out= 671)(deflated 50%)
125 adding: JavacBenchApp.class(in = 7571) (out= 3302)(deflated 56%)
126 ```
127
128 We can run this benchmark without any Leyden features. It takes 893 ms:
129
130 ```
131 $ java -cp JavacBenchApp.jar JavacBenchApp 50
132 Generated source code for 51 classes and compiled them in 893 ms
133 ```
134
135 Now, we can perform a _training run_ and create the Leyden cache files.
136
137 <b>Note: Any files `JavacBenchApp.cds*` created by previous tests must
138 be deleted, before new ones are created.</b>:
139
140 ```
141 $ rm -fv JavacBenchApp.cds*
142 $ java -XX:CacheDataStore=JavacBenchApp.cds -cp JavacBenchApp.jar JavacBenchApp 50
143 $ ls -l JavacBenchApp.cds*
144 -r--r--r-- 1 iklam iklam 30900224 May 20 19:21 JavacBenchApp.cds
145 -r--r--r-- 1 iklam iklam 16895736 May 20 19:21 JavacBenchApp.cds.code
146 ```
147
148 Two files are created:
149
150 - `JavacBenchApp.cds`: This file contains classes, heap objects and profiling data harvested from the training run.
151 - `JavacBenchApp.cds.code`: This file contains AOT-compiled methods, optimized for the execution behaviors observed during the training run.
152 (Data in this file will be merged into `JavacBenchApp.cds` in a future release.)
153
154 Now, we can make a _production run_ of the program with the cache files. It finishes in 423 ms, or more than twice as fast as
155 before.
156
157 ```
158 $ java -XX:CacheDataStore=JavacBenchApp.cds -cp JavacBenchApp.jar JavacBenchApp 50
159 Generated source code for 51 classes and compiled them in 423 ms
160 ```
161
162 ### Optional VM Flags
163
164 When you create the file `JavacBenchApp.cds` with the flag `-XX:CacheDataStore`,
165 all of the other options described
166 in the [Overview](#1-overview) section above are enabled by default. This ensures that you can get all the optimizations
167 without specifying them individually.
168
169 For diagnostic purposes, you can selectively disable some of the options:
170
171 - The `-XX:+LoadCachedCode` and `-XX:+ReplayTraining` flags affect only the production run.
172 - All other options affect only the training run.
173
174 For example, you can disable the loading of the AOT code during the production run. Notice that the benchmark now
175 starts more slowly than it did when AOT code was loaded.
176
177 ```
178 $ java -XX:CacheDataStore=JavacBenchApp.cds -XX:-LoadCachedCode -cp JavacBenchApp.jar JavacBenchApp 50
179 Generated source code for 51 classes and compiled them in 647 ms
180 ```
181
182 You can also disable AOT compilation in the training run:
183
184 ```
185 $ rm -fv JavacBenchApp.cds*
186 $ java -XX:CacheDataStore=JavacBenchApp.cds -XX:-StoreCachedCode -cp JavacBenchApp.jar JavacBenchApp 50
187 $ ls -l JavacBenchApp.cds*
188 -r--r--r-- 1 iklam iklam 30277632 May 20 20:05 JavacBenchApp.cds
189 ```
190
191 Note that the file `JavacBenchApp.cds.code` is no longer created.
192
193 ## 4. Limitations of the Leyden Prototype
194
195 When trying out the Leyden, please pay attention to the following limitations.
196
197 ### The Same Garbage Collector Must be Used between Training and Production Runs
198
199 The CDS archive generated by the Leyden prototype includes machine instructions that are specific to
200 the garbage collector. We recommend that you explicitly specify the same collector during both
201 training and production runs. For example:
202
203 ```
204 # training run
205 $ rm -fv JavacBenchApp.cds*
206 $ java -XX:CacheDataStore=JavacBenchApp.cds -XX:+UseSerialGC -cp JavacBenchApp.jar JavacBenchApp 50
207
208 # production run
209 $ java -XX:CacheDataStore=JavacBenchApp.cds -XX:+UseSerialGC -cp JavacBenchApp.jar JavacBenchApp 50
210 ```
211
212 Otherwise, the CDS archive may not be loaded for the production run, leading to suboptimal performance.
213 For example, sometimes you may perform the training run on a large development host, and then use
214 a container to run the application in a small production node. In the following scenario, as the collector
215 is not explicitly specified, the VM will automatically pick G1 for the training run, and SerialGC for the
216 production run (due to its limited amount of memory):
217
218 ```
219 # training run (uses G1 by default)
220 $ rm -fv JavacBenchApp.cds*
221 $ java -XX:CacheDataStore=JavacBenchApp.cds -cp JavacBenchApp.jar JavacBenchApp 50
222
223 # production run (uses SerialGC)
224 $ docker run --rm -v /repos/leyden/build/linux-x64/images/jdk:/jdk -v $(pwd):/test \
225 --memory=1024m \
226 container-registry.oracle.com/java/openjdk \
227 bash -c 'cd /test; /jdk/bin/java -XX:CacheDataStore=JavacBenchApp.cds -cp JavacBenchApp.jar JavacBenchApp 50'
228 [0.001s][error][cds] CDS archive has preloaded classes. It cannot be used because GC used during dump time (G1)
229 is not the same as runtime (Serial)
230 [0.001s][error][cds] An error has occurred while processing the shared archive file.
231 [0.001s][error][cds] Unable to map shared spaces
232 Error occurred during initialization of VM
233 Unable to use shared archive.
234 ```
235 ### Only G1GC, SerialGC, ParallelGC, EpsilonGC, ShenandoahGC are Supported
236 =======
237
238 Currently, if you use any other garbage collector in combination with `-XX:CacheDataStore`, the VM will
239 exit with an error.
240
241 ```
242 $ java -XX:+UseZGC -XX:CacheDataStore=foo --version
243 Error occurred during initialization of VM
244 Cannot create the CacheDataStore: UseCompressedClassPointers must be enabled, and collector
245 must be G1, Parallel, Serial, Epsilon, or Shenandoah
246 ```
247
248
249 ### -Xshare:on is Enabled by default
250
251 As seen in the example immediately above, in the production run, if the CDS archive cannot be
252 used for any reason, the JVM will report an error and exit. This happens as if `-Xshare:on` was
253 specified in the command-line.
254
255 In the standard JDK, when the CDS archive cannot be used for any reason (for example, the
256 archive was created for a different version of the JDK), the application will
257 continue to run without using CDS.
258 This fall-back strategy ensures that the application will function correctly, though at a lower level of performance.
259
260 With the Leyden prototype, we have changed this fall-back behavior to make it easier to diagnose
261 performance issues. For example, when the start-up time is not as good as one would expect, we
262 want know whether it's caused by a misconfiguration that prevents the CDS archive
263 from being used, or it's caused by a deficiency in the implementation of the Leyden optimizations.
264
265 To revert to the behavior of the standard JDK, you can explicitly add `-Xshare:auto` to the command-line.
266
267 ```
268 $ docker run --rm -v /repos/leyden/build/linux-x64/images/jdk:/jdk -v $(pwd):/test \
269 --memory=1024m \
270 container-registry.oracle.com/java/openjdk \
271 bash -c 'cd /test; /jdk/bin/java -Xshare:auto -XX:CacheDataStore=JavacBenchApp.cds -cp JavacBenchApp.jar JavacBenchApp 50'
272 [0.001s][error][cds] CDS archive has preloaded classes. It cannot be used because GC used during dump time (G1)
273 is not the same as runtime (Serial)
274 Generated source code for 51 classes and compiled them in 831 ms
275 ```
276
277 See [here](https://docs.oracle.com/en/java/javase/21/vm/class-data-sharing.html) for a discussion of `-Xshare:on` vs `-Xshare:auto`.
278
279
280 ## 5. Benchmarking
281
282 We use a small set of benchmarks to demonstrate the performance of the optimizations in the Leyden repo.
283
284 | Benchmark | Source |
285 | ------------- | ------------- |
286 |[helidon-quickstart-se](test/hotspot/jtreg/premain/helidon-quickstart-se) | https://helidon.io/docs/v4/se/guides/quickstart|
287 |[micronaut-first-app](test/hotspot/jtreg/premain/micronaut-first-app) | https://guides.micronaut.io/latest/creating-your-first-micronaut-app-maven-java.html|
288 |[quarkus-getting-started](test/hotspot/jtreg/premain/quarkus-getting-started) | https://quarkus.io/guides/getting-started|
289 |[spring-boot-getting-started](test/hotspot/jtreg/premain/spring-boot-getting-started) | https://spring.io/guides/gs/spring-boot|
290 |[spring-petclinic](test/hotspot/jtreg/premain/spring-petclinic) | https://github.com/spring-projects/spring-petclinic|
291
292 *(FIXME: add a benchmark for javac)*
293
294 ### Benchmarking Against JDK Main-line
295
296 To can compare the performance of Leyden vs the main-line JDK, you need:
297
298 - An official build of JDK 21
299 - An up-to-date build of the JDK main-line
300 - The latest Leyden build
301 - Maven (ideally 3.8 or later, as required by some of the demos). Note: if you are behind
302 a firewall, you may need to [set up proxies for Maven](https://maven.apache.org/guides/mini/guide-proxies.html)
303
304 The same steps are used for benchmarking all of the above demos. For example:
305
306 ```
307 $ cd helidon-quickstart-se
308 $ make PREMAIN_HOME=/repos/leyden/build/linux-x64/images/jdk \
309 MAINLINE_HOME=/repos/jdk/build/linux-x64/images/jdk \
310 BLDJDK_HOME=/usr/local/jdk21 \
311 bench
312 run,mainline default,mainline custom static CDS,premain custom static CDS only,premain CDS + AOT
313 1,398,244,144,107
314 2,387,247,142,108
315 3,428,238,143,107
316 4,391,252,142,111
317 5,417,247,141,107
318 6,390,239,139,127
319 7,387,247,145,111
320 8,387,240,147,110
321 9,388,242,147,108
322 10,400,242,167,108
323 Geomean,397.08,243.76,145.52,110.26
324 Stdev,13.55,4.19,7.50,5.73
325 Markdown snippets in mainline_vs_premain.md
326 ```
327
328 The above command runs each configuration 10 times, in an interleaving order. This way
329 the noise of the system (background processes, thermo throttling, etc) is more likely to
330 be spread across the different runs.
331
332 As is typical for benchmarking start-up performance, the numbers are not very steady.
333 It is best to plot
334 the results (as saved in the file `mainline_vs_premain.csv`) in a spreadsheet to check for
335 noise and other artifacts.
336
337 The "make bench" target also generates GitHub markdown snippets (in the file `mainline_vs_premain.md`) for creating the
338 graphs below.
339
340 ### Benchmarking Between Two Leyden Builds
341
342 This is useful for Leyden developers to measure the benefits of a particular optimization.
343 The steps are similar to above, but we use the "make compare_premain_builds" target:
344
345 ```
346 $ cd helidon-quickstart-se
347 $ make PM_OLD=/repos/leyden_old/build/linux-x64/images/jdk \
348 PM_NEW=/repos/leyden_new/build/linux-x64/images/jdk \
349 BLDJDK_HOME=/usr/local/jdk21 \
350 compare_premain_builds
351 Old build = /repos/leyden_old/build/linux-x64/images/jdk with options
352 New build = /repos/leyden_new/build/linux-x64/images/jdk with options
353 Run,Old CDS + AOT,New CDS + AOT
354 1,110,109
355 2,131,111
356 3,118,115
357 4,110,108
358 5,117,110
359 6,114,109
360 7,110,109
361 8,118,110
362 9,110,110
363 10,113,114
364 Geomean,114.94,110.48
365 Stdev,6.19,2.16
366 Markdown snippets in compare_premain_builds.md
367 ```
368
369 Please see [test/hotspot/jtreg/premain/lib/Bench.gmk](test/hotspot/jtreg/premain/lib/Bench.gmk) for more details.
370
371 Note: due to the variability of start-up time, the benefit of minor improvements may
372 be difficult to measure.
373
374 ### Preliminary Benchmark Results
375
376 The following charts show the relative start-up performance of the Leyden/Premain branch vs
377 the JDK main-line.
378
379 For example, a number of "premain CDS + AOT : 291" indicates that if the application takes
380 1000 ms to start-up with the JDK main-line, it takes only 291 ms to start up when all the
381 current set of Leyden optimizations for CDS and AOT are enabled.
382
383 The benchmark results are collected with `make bench` in the following directories:
384
385 - `helidon-quickstart-se`
386 - `micronaut-first-app`
387 - `quarkus-getting-started`
388 - `spring-petclinic`
389
390 These JDK versions were used in the comparisons:
391
392 - JDK main-line: https://github.com/openjdk/jdk/commit/70944ca54ad0090c734bb5b3082beb33450c4877
393 - Leyden: https://github.com/openjdk/leyden/commit/9fa972214934d30f67db5fd4d1b8007636ac1428
394
395 The benchmarks were executed on an 8-core Intel i7-10700 CPU @ 2.90GHz with 32GB RAM running Ubuntu 22.04.3 LTS.
396
397 ### Helidon Quick Start (SE) Demo (3.44x improvement)
398
399 ```mermaid
400 ---
401 config:
402 xyChart:
403 chartOrientation: horizontal
404 height: 300
405 ---
406 xychart-beta
407 x-axis "variant" ["mainline default", "mainline custom static CDS", "premain custom static CDS only", "premain CDS + AOT"]
408 y-axis "Elapsed time (normalized, smaller is better)" 0 --> 1000
409 bar [1000, 632, 376, 291]
410 ```
411
412 ### Micronaut First App Demo (2.83x improvement)
413
414 ```mermaid
415 ---
416 config:
417 xyChart:
418 chartOrientation: horizontal
419 height: 300
420 ---
421 xychart-beta
422 x-axis "variant" ["mainline default", "mainline custom static CDS", "premain custom static CDS only", "premain CDS + AOT"]
423 y-axis "Elapsed time (normalized, smaller is better)" 0 --> 1000
424 bar [1000, 558, 410, 353]
425 ```
426
427 ### Quarkus Getting Started Demo (3.15x improvement)
428
429 ```mermaid
430 ---
431 config:
432 xyChart:
433 chartOrientation: horizontal
434 height: 300
435 ---
436 xychart-beta
437 x-axis "variant" ["mainline default", "mainline custom static CDS", "premain custom static CDS only", "premain CDS + AOT"]
438 y-axis "Elapsed time (normalized, smaller is better)" 0 --> 1000
439 bar [1000, 568, 395, 317]
440 ```
441
442 ### Spring-boot Getting Started Demo (3.53x improvement)
443
444 ```mermaid
445 ---
446 config:
447 xyChart:
448 chartOrientation: horizontal
449 height: 300
450 ---
451 xychart-beta
452 x-axis "variant" ["mainline default", "mainline custom static CDS", "premain custom static CDS only", "premain CDS + AOT"]
453 y-axis "Elapsed time (normalized, smaller is better)" 0 --> 1000
454 bar [1000, 560, 394, 283]
455 ```
456
457 ### Spring PetClinic Demo (2.72x improvement)
458
459 ```mermaid
460 ---
461 config:
462 xyChart:
463 chartOrientation: horizontal
464 height: 300
465 ---
466 xychart-beta
467 x-axis "variant" ["mainline default", "mainline custom static CDS", "premain custom static CDS only", "premain CDS + AOT"]
468 y-axis "Elapsed time (normalized, smaller is better)" 0 --> 1000
469 bar [1000, 695, 563, 368]
470 ```
471
472 ## 6. More Documentation
473
474 Please see [test/hotspot/jtreg/premain/](test/hotspot/jtreg/premain) for more information.