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