2348
|
1 /*
|
3358
|
2 * Copyright (c) 2010, 2011, Oracle and/or its affiliates. All rights reserved.
|
|
3 * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
|
|
4 *
|
|
5 * This code is free software; you can redistribute it and/or modify it
|
|
6 * under the terms of the GNU General Public License version 2 only, as
|
|
7 * published by the Free Software Foundation.
|
|
8 *
|
|
9 * This code is distributed in the hope that it will be useful, but WITHOUT
|
|
10 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
11 * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
|
|
12 * version 2 for more details (a copy is included in the LICENSE file that
|
|
13 * accompanied this code).
|
|
14 *
|
|
15 * You should have received a copy of the GNU General Public License version
|
|
16 * 2 along with this work; if not, write to the Free Software Foundation,
|
|
17 * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
|
|
18 *
|
|
19 * Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
|
|
20 * or visit www.oracle.com if you need additional information or have any
|
|
21 * questions.
|
|
22 *
|
|
23 */
|
2348
|
24
|
|
25 #ifndef SHARE_VM_RUNTIME_ADVANCEDTHRESHOLDPOLICY_HPP
|
|
26 #define SHARE_VM_RUNTIME_ADVANCEDTHRESHOLDPOLICY_HPP
|
|
27
|
|
28 #include "runtime/simpleThresholdPolicy.hpp"
|
|
29
|
|
30 #ifdef TIERED
|
|
31 class CompileTask;
|
|
32 class CompileQueue;
|
|
33
|
|
34 /*
|
|
35 * The system supports 5 execution levels:
|
|
36 * * level 0 - interpreter
|
|
37 * * level 1 - C1 with full optimization (no profiling)
|
|
38 * * level 2 - C1 with invocation and backedge counters
|
|
39 * * level 3 - C1 with full profiling (level 2 + MDO)
|
|
40 * * level 4 - C2
|
|
41 *
|
|
42 * Levels 0, 2 and 3 periodically notify the runtime about the current value of the counters
|
|
43 * (invocation counters and backedge counters). The frequency of these notifications is
|
|
44 * different at each level. These notifications are used by the policy to decide what transition
|
|
45 * to make.
|
|
46 *
|
|
47 * Execution starts at level 0 (interpreter), then the policy can decide either to compile the
|
|
48 * method at level 3 or level 2. The decision is based on the following factors:
|
|
49 * 1. The length of the C2 queue determines the next level. The observation is that level 2
|
|
50 * is generally faster than level 3 by about 30%, therefore we would want to minimize the time
|
|
51 * a method spends at level 3. We should only spend the time at level 3 that is necessary to get
|
|
52 * adequate profiling. So, if the C2 queue is long enough it is more beneficial to go first to
|
|
53 * level 2, because if we transitioned to level 3 we would be stuck there until our C2 compile
|
|
54 * request makes its way through the long queue. When the load on C2 recedes we are going to
|
|
55 * recompile at level 3 and start gathering profiling information.
|
|
56 * 2. The length of C1 queue is used to dynamically adjust the thresholds, so as to introduce
|
|
57 * additional filtering if the compiler is overloaded. The rationale is that by the time a
|
|
58 * method gets compiled it can become unused, so it doesn't make sense to put too much onto the
|
|
59 * queue.
|
|
60 *
|
|
61 * After profiling is completed at level 3 the transition is made to level 4. Again, the length
|
|
62 * of the C2 queue is used as a feedback to adjust the thresholds.
|
|
63 *
|
|
64 * After the first C1 compile some basic information is determined about the code like the number
|
|
65 * of the blocks and the number of the loops. Based on that it can be decided that a method
|
|
66 * is trivial and compiling it with C1 will yield the same code. In this case the method is
|
|
67 * compiled at level 1 instead of 4.
|
|
68 *
|
|
69 * We also support profiling at level 0. If C1 is slow enough to produce the level 3 version of
|
|
70 * the code and the C2 queue is sufficiently small we can decide to start profiling in the
|
|
71 * interpreter (and continue profiling in the compiled code once the level 3 version arrives).
|
|
72 * If the profiling at level 0 is fully completed before level 3 version is produced, a level 2
|
|
73 * version is compiled instead in order to run faster waiting for a level 4 version.
|
|
74 *
|
|
75 * Compile queues are implemented as priority queues - for each method in the queue we compute
|
|
76 * the event rate (the number of invocation and backedge counter increments per unit of time).
|
|
77 * When getting an element off the queue we pick the one with the largest rate. Maintaining the
|
|
78 * rate also allows us to remove stale methods (the ones that got on the queue but stopped
|
|
79 * being used shortly after that).
|
|
80 */
|
|
81
|
|
82 /* Command line options:
|
|
83 * - Tier?InvokeNotifyFreqLog and Tier?BackedgeNotifyFreqLog control the frequency of method
|
|
84 * invocation and backedge notifications. Basically every n-th invocation or backedge a mutator thread
|
|
85 * makes a call into the runtime.
|
|
86 *
|
|
87 * - Tier?CompileThreshold, Tier?BackEdgeThreshold, Tier?MinInvocationThreshold control
|
|
88 * compilation thresholds.
|
|
89 * Level 2 thresholds are not used and are provided for option-compatibility and potential future use.
|
|
90 * Other thresholds work as follows:
|
|
91 *
|
|
92 * Transition from interpreter (level 0) to C1 with full profiling (level 3) happens when
|
|
93 * the following predicate is true (X is the level):
|
|
94 *
|
|
95 * i > TierXInvocationThreshold * s || (i > TierXMinInvocationThreshold * s && i + b > TierXCompileThreshold * s),
|
|
96 *
|
|
97 * where $i$ is the number of method invocations, $b$ number of backedges and $s$ is the scaling
|
|
98 * coefficient that will be discussed further.
|
|
99 * The intuition is to equalize the time that is spend profiling each method.
|
|
100 * The same predicate is used to control the transition from level 3 to level 4 (C2). It should be
|
|
101 * noted though that the thresholds are relative. Moreover i and b for the 0->3 transition come
|
|
102 * from methodOop and for 3->4 transition they come from MDO (since profiled invocations are
|
|
103 * counted separately).
|
|
104 *
|
|
105 * OSR transitions are controlled simply with b > TierXBackEdgeThreshold * s predicates.
|
|
106 *
|
|
107 * - Tier?LoadFeedback options are used to automatically scale the predicates described above depending
|
|
108 * on the compiler load. The scaling coefficients are computed as follows:
|
|
109 *
|
|
110 * s = queue_size_X / (TierXLoadFeedback * compiler_count_X) + 1,
|
|
111 *
|
|
112 * where queue_size_X is the current size of the compiler queue of level X, and compiler_count_X
|
|
113 * is the number of level X compiler threads.
|
|
114 *
|
|
115 * Basically these parameters describe how many methods should be in the compile queue
|
|
116 * per compiler thread before the scaling coefficient increases by one.
|
|
117 *
|
|
118 * This feedback provides the mechanism to automatically control the flow of compilation requests
|
|
119 * depending on the machine speed, mutator load and other external factors.
|
|
120 *
|
|
121 * - Tier3DelayOn and Tier3DelayOff parameters control another important feedback loop.
|
|
122 * Consider the following observation: a method compiled with full profiling (level 3)
|
|
123 * is about 30% slower than a method at level 2 (just invocation and backedge counters, no MDO).
|
|
124 * Normally, the following transitions will occur: 0->3->4. The problem arises when the C2 queue
|
|
125 * gets congested and the 3->4 transition is delayed. While the method is the C2 queue it continues
|
|
126 * executing at level 3 for much longer time than is required by the predicate and at suboptimal speed.
|
|
127 * The idea is to dynamically change the behavior of the system in such a way that if a substantial
|
|
128 * load on C2 is detected we would first do the 0->2 transition allowing a method to run faster.
|
|
129 * And then when the load decreases to allow 2->3 transitions.
|
|
130 *
|
|
131 * Tier3Delay* parameters control this switching mechanism.
|
|
132 * Tier3DelayOn is the number of methods in the C2 queue per compiler thread after which the policy
|
|
133 * no longer does 0->3 transitions but does 0->2 transitions instead.
|
|
134 * Tier3DelayOff switches the original behavior back when the number of methods in the C2 queue
|
|
135 * per compiler thread falls below the specified amount.
|
|
136 * The hysteresis is necessary to avoid jitter.
|
|
137 *
|
|
138 * - TieredCompileTaskTimeout is the amount of time an idle method can spend in the compile queue.
|
|
139 * Basically, since we use the event rate d(i + b)/dt as a value of priority when selecting a method to
|
|
140 * compile from the compile queue, we also can detect stale methods for which the rate has been
|
|
141 * 0 for some time in the same iteration. Stale methods can appear in the queue when an application
|
|
142 * abruptly changes its behavior.
|
|
143 *
|
|
144 * - TieredStopAtLevel, is used mostly for testing. It allows to bypass the policy logic and stick
|
|
145 * to a given level. For example it's useful to set TieredStopAtLevel = 1 in order to compile everything
|
|
146 * with pure c1.
|
|
147 *
|
|
148 * - Tier0ProfilingStartPercentage allows the interpreter to start profiling when the inequalities in the
|
|
149 * 0->3 predicate are already exceeded by the given percentage but the level 3 version of the
|
|
150 * method is still not ready. We can even go directly from level 0 to 4 if c1 doesn't produce a compiled
|
|
151 * version in time. This reduces the overall transition to level 4 and decreases the startup time.
|
|
152 * Note that this behavior is also guarded by the Tier3Delay mechanism: when the c2 queue is too long
|
|
153 * these is not reason to start profiling prematurely.
|
|
154 *
|
|
155 * - TieredRateUpdateMinTime and TieredRateUpdateMaxTime are parameters of the rate computation.
|
|
156 * Basically, the rate is not computed more frequently than TieredRateUpdateMinTime and is considered
|
|
157 * to be zero if no events occurred in TieredRateUpdateMaxTime.
|
|
158 */
|
|
159
|
|
160
|
|
161 class AdvancedThresholdPolicy : public SimpleThresholdPolicy {
|
|
162 jlong _start_time;
|
|
163
|
|
164 // Call and loop predicates determine whether a transition to a higher compilation
|
|
165 // level should be performed (pointers to predicate functions are passed to common().
|
|
166 // Predicates also take compiler load into account.
|
|
167 typedef bool (AdvancedThresholdPolicy::*Predicate)(int i, int b, CompLevel cur_level);
|
|
168 bool call_predicate(int i, int b, CompLevel cur_level);
|
|
169 bool loop_predicate(int i, int b, CompLevel cur_level);
|
|
170 // Common transition function. Given a predicate determines if a method should transition to another level.
|
|
171 CompLevel common(Predicate p, methodOop method, CompLevel cur_level);
|
|
172 // Transition functions.
|
|
173 // call_event determines if a method should be compiled at a different
|
|
174 // level with a regular invocation entry.
|
|
175 CompLevel call_event(methodOop method, CompLevel cur_level);
|
|
176 // loop_event checks if a method should be OSR compiled at a different
|
|
177 // level.
|
|
178 CompLevel loop_event(methodOop method, CompLevel cur_level);
|
|
179 // Has a method been long around?
|
|
180 // We don't remove old methods from the compile queue even if they have
|
|
181 // very low activity (see select_task()).
|
|
182 inline bool is_old(methodOop method);
|
|
183 // Was a given method inactive for a given number of milliseconds.
|
|
184 // If it is, we would remove it from the queue (see select_task()).
|
|
185 inline bool is_stale(jlong t, jlong timeout, methodOop m);
|
|
186 // Compute the weight of the method for the compilation scheduling
|
|
187 inline double weight(methodOop method);
|
|
188 // Apply heuristics and return true if x should be compiled before y
|
|
189 inline bool compare_methods(methodOop x, methodOop y);
|
|
190 // Compute event rate for a given method. The rate is the number of event (invocations + backedges)
|
|
191 // per millisecond.
|
|
192 inline void update_rate(jlong t, methodOop m);
|
|
193 // Compute threshold scaling coefficient
|
|
194 inline double threshold_scale(CompLevel level, int feedback_k);
|
|
195 // If a method is old enough and is still in the interpreter we would want to
|
|
196 // start profiling without waiting for the compiled method to arrive. This function
|
|
197 // determines whether we should do that.
|
|
198 inline bool should_create_mdo(methodOop method, CompLevel cur_level);
|
|
199 // Create MDO if necessary.
|
|
200 void create_mdo(methodHandle mh, TRAPS);
|
|
201 // Is method profiled enough?
|
|
202 bool is_method_profiled(methodOop method);
|
|
203
|
|
204 protected:
|
|
205 void print_specific(EventType type, methodHandle mh, methodHandle imh, int bci, CompLevel level);
|
|
206
|
|
207 void set_start_time(jlong t) { _start_time = t; }
|
|
208 jlong start_time() const { return _start_time; }
|
|
209
|
|
210 // Submit a given method for compilation (and update the rate).
|
|
211 virtual void submit_compile(methodHandle mh, int bci, CompLevel level, TRAPS);
|
|
212 // event() from SimpleThresholdPolicy would call these.
|
|
213 virtual void method_invocation_event(methodHandle method, methodHandle inlinee,
|
|
214 CompLevel level, TRAPS);
|
|
215 virtual void method_back_branch_event(methodHandle method, methodHandle inlinee,
|
|
216 int bci, CompLevel level, TRAPS);
|
|
217 public:
|
|
218 AdvancedThresholdPolicy() : _start_time(0) { }
|
|
219 // Select task is called by CompileBroker. We should return a task or NULL.
|
|
220 virtual CompileTask* select_task(CompileQueue* compile_queue);
|
|
221 virtual void initialize();
|
|
222 };
|
|
223
|
|
224 #endif // TIERED
|
|
225
|
|
226 #endif // SHARE_VM_RUNTIME_ADVANCEDTHRESHOLDPOLICY_HPP
|