Is Parallel Programming Hard, And, If So, What Can You Do About It?

More documents

Recommendations

Info

$TeX op Mac OS X, met teTeX en TeXShop - Nluug$

220 APPENDIX D. READ-COPY UPDATE IMPLEMENTATIONS1 void rcu_qsctr_inc(int cpu)2 {3 struct rcu_data *rdp = &per_cpu(rcu_data, cpu);4 rdp->passed_quiesc = 1;5 rdp->passed_quiesc_completed = rdp->completed;6 }78 void rcu_bh_qsctr_inc(int cpu)9 {10 struct rcu_data *rdp = &per_cpu(rcu_bh_data, cpu);11 rdp->passed_quiesc = 1;12 rdp->passed_quiesc_completed = rdp->completed;13 }1 static void2 rcu_check_quiescent_state(struct rcu_state *rsp,3 struct rcu_data *rdp)4 {5 if (check_for_new_grace_period(rsp, rdp))6 return;7 if (!rdp->qs_pending)8 return;9 if (!rdp->passed_quiesc)10 return;11 cpu_quiet(rdp->cpu, rsp, rdp,12 rdp->passed_quiesc_completed);13 }Figure D.38: Code for Recording Quiescent Statesquiescent state for “rcu” and “rcu bh”, respectively.Note that the dynticks-idle and CPUofflinequiescent states are handled specially,due to the fact that such a CPU is not executing,and thus is unable to report itself as beingin a quiescent state.2. rcu_check_quiescent_state()checkstoseeifthecurrentCPUhaspassedthroughaquiescentstate, invoking cpu_quiet() if so.3. cpu_quiet() reports the specified CPU as havingpassedthroughaquiescentstatebyinvokingcpu_quiet_msk(). The specified CPU must eitherbe the current CPU or an offline CPU.4. cpu_quiet_msk() reports the specified vectorof CPUs as having passed through a quiescentstate. The CPUs in the vector need not be thecurrent CPU, nor must they be offline.Each of these functions is described below.Figure D.38 shows the code for rcu_qsctr_inc()and rcu_bh_qsctr_inc(), which note the currentCPU’s passage through a quiescent state.Line 3 of rcu_qsctr_inc() obtains a pointer tothe specified CPU’s rcu_data structure (which correspondsto “rcu” as opposed to “rcu bh”). Line 4sets the ->passed_quiesc field, recording the quiescentstate. Line 5 sets the ->passed_quiesc_completed field to the number of the last completedgraceperiodthatthisCPUknowsof(whichisstoredinthe->completedfieldofthercu_datastructure).The rcu_bh_qsctr_inc() function operates inthe same manner, the only difference being thatline 10 obtains the rcu_data pointer from the rcu_bh_data per-CPU variable rather than the rcu_data per-CPU variable.Figure D.39 shows the code for rcu_check_quiescent_state(), which is invoked fromrcu_process_callbacks() (described in SectionD.3.2.4) in order to determine when otherFigure D.39: Code forrcu check quiescent state()CPUs have started a new grace period and toinform RCU of recent quiescent states for this CPU.Line 5 invokes check_for_new_grace_period()to check for a new grace period having been startedby some other CPU, and also updating this CPU’slocal state to account for that new grace period.If a new grace period has just started, line 6 returns.Line 7 checks to see if RCU is still expectinga quiescent state from the current CPU, andline 8 returns if not. Line 9 checks to see if thisCPU has passed through a quiescent state since thestart of the current grace period (in other words,if rcu_qsctr_inc() or rcu_bh_qsctr_inc() havebeen invoked for “rcu” and “rcu bh”, respectively),and line 10 returns if not.Therefore, execution reaches line 11 only if a previouslynoted grace period is still in effect, if thisCPU needs to pass through a quiescent state in orderto allow this grace period to end, and if thisCPU has passed through such a quiescent state. Inthis case, lines 11-12 invoke cpu_quiet() in orderto report this quiescent state to RCU.Quick Quiz D.46: What prevents lines 11-12 ofFigure D.39 from reporting a quiescent state from aprior grace period against the current grace period?Figure D.40 shows cpu_quiet, which is used toreport a quiescent state for the specified CPU. Asnoted earlier, this must either be the currently runningCPU or a CPU that is guaranteed to remainoffline throughout.Line 9 picks up a pointer to the leaf rcu_nodestructure responsible for this CPU. Line 10 acquiresthis leaf rcu_node structure’s lock and disables interrupts.Line 11 checks to make sure that the specifiedgrace period is still in effect, and, if not, line 11clears the indication that this CPU passed througha quiescent state (since it belongs to a defunct graceperiod), line 13 releases the lock and re-enables interrupts,and line 14 returns to the caller.
D.3. HIERARCHICAL RCU CODE WALKTHROUGH 2211 static void2 cpu_quiet(int cpu, struct rcu_state *rsp,3 struct rcu_data *rdp, long lastcomp)4 {5 unsigned long flags;6 unsigned long mask;7 struct rcu_node *rnp;89 rnp = rdp->mynode;10 spin_lock_irqsave(&rnp->lock, flags);11 if (lastcomp != ACCESS_ONCE(rsp->completed)) {12 rdp->passed_quiesc = 0;13 spin_unlock_irqrestore(&rnp->lock, flags);14 return;15 }16 mask = rdp->grpmask;17 if ((rnp->qsmask & mask) == 0) {18 spin_unlock_irqrestore(&rnp->lock, flags);19 } else {20 rdp->qs_pending = 0;21 rdp = rsp->rda[smp_processor_id()];22 rdp->nxttail[RCU_NEXT_READY_TAIL] =23 rdp->nxttail[RCU_NEXT_TAIL];24 cpu_quiet_msk(mask, rsp, rnp, flags);25 }26 }Figure D.40: Code for cpu quiet()Otherwise, line 16 forms a mask with the specifiedCPU’s bit set. Line 17 checks to see if this bit is stillsetintheleafrcu_nodestructure, and, ifnot, line18releases the lock and re-enables interrupts.On the other hand, if the CPU’s bit is still set,line 20 clears ->qs_pending, reflecting that thisCPU has passed through its quiescent state forthis grace period. Line 21 then overwrites localvariable rdp with a pointer to the running CPU’srcu_datastructure,andlines22-23updatestherunningCPU’s RCU callbacks so that all those not yetassociatedwithaspecificgraceperiodbeservicedbythe next grace period. Finally, line 24 clears bits upthercu_nodehierarchy, endingthecurrentgraceperiodif appropriate and perhaps even starting a newone. Note that cpu_quiet() releases the lock andre-enables interrupts.Quick Quiz D.47: How do lines 22-23 of FigureD.40 know that it is safe to promote the runningCPU’s RCU callbacks?Figure D.41 shows cpu_quiet_msk(), which updatesthe rcu_node hierarchy to reflect the passageof the CPUs indicated by argument mask throughtheir respective quiescent states. Note that argumentrnp is the leaf rcu_node structure correspondingto the specified CPUs.Quick Quiz D.48: Given that argument maskon line 2 of Figure D.41 is an unsigned long, howcan it possibly deal with systems with more than 64CPUs?Line 4 is annotation for the sparse utility, indicatingthat cpu_quiet_msk() releases the leaf1 static void2 cpu_quiet_msk(unsigned long mask, struct rcu_state *rsp,3 struct rcu_node *rnp, unsigned long flags)4 __releases(rnp->lock)5 {6 for (;;) {7 if (!(rnp->qsmask & mask)) {8 spin_unlock_irqrestore(&rnp->lock, flags);9 return;10 }11 rnp->qsmask &= ~mask;12 if (rnp->qsmask != 0) {13 spin_unlock_irqrestore(&rnp->lock, flags);14 return;15 }16 mask = rnp->grpmask;17 if (rnp->parent == NULL) {18 break;19 }20 spin_unlock_irqrestore(&rnp->lock, flags);21 rnp = rnp->parent;22 spin_lock_irqsave(&rnp->lock, flags);23 }24 rsp->completed = rsp->gpnum;25 rcu_process_gp_end(rsp, rsp->rda[smp_processor_id()]);26 rcu_start_gp(rsp, flags);27 }Figure D.41: Code for cpu quiet msk()rcu_node structure’s lock.Each pass through the loop spanning lines 6-23does the required processing for one level of thercu_node hierarchy, traversing the data structuresas shown by the blue arrow in Figure D.42.Line 7 checks to see if all of the bits in mask havealready been cleared in the current rcu_node structure’s->qsmask field, and, if so, line 8 releases thelock and re-enables interrupts, and line 9 returns tothe caller. If not, line 11 clears the bits specified bymask from the current rcu_node structure’s qsmaskfield. Line 12 then checks to see if there are morebits remaining in ->qsmask, and, if so, line 13 releasesthe lock and re-enables interrupts, and line 14returns to the caller.Otherwise, it is necessary to advance up to thenext level of the rcu_node hierarchy. In preparationfor this next level, line 16 places a maskwith the single bit set corresponding to the currentrcu_node structure within its parent. Line 17checks to see if there in fact is a parent for the currentrcu_node structure, and, if not, line 18 breaksfrom the loop. On the other hand, if there is a parentrcu_node structure, line 20 releases the currentrcu_node structure’s lock, line 21 advances the rnplocal variable to the parent, and line 22 acquires theparent’s lock. Execution then continues at the beginningof the loop on line 7.If line 18 breaks from the loop, we know that thecurrent grace period has ended, as the only way thatall bits can be cleared in the root rcu_node structureis if all CPUs have passed through quiescent
Page 1 and 2:
Is Parallel Programming Hard, And,
Page 3 and 4:
Contents1 Introduction 11.1 Histori
Page 5 and 6:
CONTENTSv6 Locking 676.1 Staying Al
Page 7 and 8:
CONTENTSviiB Synchronization Primit
Page 9 and 10:
CONTENTSixE.7.1 Introduction to Pre
Page 11 and 12:
PrefaceThe purpose of this book is
Page 13 and 14:
Chapter 1IntroductionParallel progr
Page 15 and 16:
1.2. PARALLEL PROGRAMMING GOALS 3CP
Page 17 and 18:
1.3. ALTERNATIVES TO PARALLEL PROGR
Page 19 and 20:
1.4. WHAT MAKES PARALLEL PROGRAMMIN
Page 21 and 22:
1.5. GUIDE TO THIS BOOK 9other hand
Page 23 and 24:
Chapter 2Hardware and its HabitsMos
Page 25:
2.1. OVERVIEW 13Therefore, as shown
Page 28 and 29:
16 CHAPTER 2. HARDWARE AND ITS HABI
Page 30 and 31:
18 CHAPTER 2. HARDWARE AND ITS HABI
Page 32 and 33:
20 CHAPTER 3. TOOLS OF THE TRADE1 p
Page 34 and 35:
22 CHAPTER 3. TOOLS OF THE TRADE1 p
Page 36 and 37:
24 CHAPTER 3. TOOLS OF THE TRADE1.1
Page 38 and 39:
26 CHAPTER 3. TOOLS OF THE TRADEQui
Page 40 and 41:
28 CHAPTER 3. TOOLS OF THE TRADE
Page 42 and 43:
30 CHAPTER 4. COUNTING1 atomic_t co
Page 44 and 45:
32 CHAPTER 4. COUNTING4.2.3 Eventua
Page 46 and 47:
34 CHAPTER 4. COUNTINGvanish when t
Page 48 and 49:
36 CHAPTER 4. COUNTINGper-thread va
Page 50 and 51:
38 CHAPTER 4. COUNTING1 unsigned lo
Page 52 and 53:
Page 54 and 55:
42 CHAPTER 4. COUNTING1 #define THE
Page 56 and 57:
Page 58 and 59:
46 CHAPTER 4. COUNTINGReadsAlgorith
Page 60 and 61:
48 CHAPTER 5. PARTITIONING AND SYNC
Page 62 and 63:
Page 64 and 65:
Page 66 and 67:
Page 68 and 69:
Page 70 and 71:
Page 72 and 73:
Page 74 and 75:
Page 76 and 77:
Page 78 and 79:
Page 80 and 81:
68 CHAPTER 6. LOCKING1 int delete(i
Page 82 and 83:
70 CHAPTER 7. DATA OWNERSHIP
Page 84 and 85:
72 CHAPTER 8. DEFERRED PROCESSINGfo
Page 86 and 87:
74 CHAPTER 8. DEFERRED PROCESSINGth
Page 88 and 89:
76 CHAPTER 8. DEFERRED PROCESSING
Page 90 and 91:
78 CHAPTER 8. DEFERRED PROCESSINGfi
Page 92 and 93:
80 CHAPTER 8. DEFERRED PROCESSINGti
Page 94 and 95:
82 CHAPTER 8. DEFERRED PROCESSINGNo
Page 96 and 97:
84 CHAPTER 8. DEFERRED PROCESSING12
Page 98 and 99:
Page 100 and 101:
88 CHAPTER 8. DEFERRED PROCESSINGvo
Page 102 and 103:
90 CHAPTER 8. DEFERRED PROCESSINGLi
Page 104 and 105:
92 CHAPTER 8. DEFERRED PROCESSINGpe
Page 106 and 107:
94 CHAPTER 8. DEFERRED PROCESSINGCa
Page 108 and 109:
96 CHAPTER 8. DEFERRED PROCESSINGTh
Page 110 and 111:
Page 112 and 113:
Page 114 and 115:
Page 116 and 117:
104 CHAPTER 8. DEFERRED PROCESSINGs
Page 118 and 119:
106 CHAPTER 8. DEFERRED PROCESSINGo
Page 120 and 121:
108 CHAPTER 8. DEFERRED PROCESSING
Page 122 and 123:
110 CHAPTER 9. APPLYING RCU1 struct
Page 124 and 125:
112 CHAPTER 9. APPLYING RCU
Page 126 and 127:
114 CHAPTER 10. VALIDATION: DEBUGGI
Page 128 and 129:
116 CHAPTER 11. DATA STRUCTURES
Page 130 and 131:
118 CHAPTER 12. ADVANCED SYNCHRONIZ
Page 132 and 133:
Page 134 and 135:
Page 136 and 137:
Page 138 and 139:
Page 140 and 141:
Page 142 and 143:
Page 144 and 145:
Page 146 and 147:
Page 148 and 149:
Page 150 and 151:
138 CHAPTER 13. EASE OF USEFigure 1
Page 152 and 153:
140 CHAPTER 13. EASE OF USE
Page 154 and 155:
142 CHAPTER 14. TIME MANAGEMENT
Page 156 and 157:
144 CHAPTER 15. CONFLICTING VISIONS
Page 158 and 159:
Page 160 and 161:
Page 162 and 163:
Page 164 and 165:
Page 166 and 167:
154 APPENDIX A. IMPORTANT QUESTIONS
Page 168 and 169:
156 APPENDIX A. IMPORTANT QUESTIONS
Page 170 and 171:
158 APPENDIX B. SYNCHRONIZATION PRI
Page 172 and 173:
160 APPENDIX B. SYNCHRONIZATION PRI
Page 174 and 175:
162 APPENDIX C. WHY MEMORY BARRIERS
Page 176 and 177:
Page 178 and 179:
Page 180 and 181:
Page 182 and 183: 170 APPENDIX C. WHY MEMORY BARRIERS
Page 196 and 197: 184 APPENDIX D. READ-COPY UPDATE IM
Page 256 and 257: 244 APPENDIX E. FORMAL VERIFICATION
Page 282 and 283:
270 APPENDIX E. FORMAL VERIFICATION
Page 284 and 285:
272 APPENDIX F. ANSWERS TO QUICK QU
Page 286 and 287:
Page 288 and 289:
Page 290 and 291:
Page 292 and 293:
Page 294 and 295:
Page 296 and 297:
Page 298 and 299:
Page 300 and 301:
Page 302 and 303:
Page 304 and 305:
Page 306 and 307:
Page 308 and 309:
Page 310 and 311:
Page 312 and 313:
Page 314 and 315:
Page 316 and 317:
Page 318 and 319:
Page 320 and 321:
Page 322 and 323:
Page 324 and 325:
Page 326 and 327:
Page 328 and 329:
Page 330 and 331:
Page 332 and 333:
Page 334 and 335:
Page 336 and 337:
Page 338 and 339:
Page 340 and 341:
Page 342 and 343:
330 APPENDIX G. GLOSSARY(2) A physi
Page 344 and 345:
332 APPENDIX G. GLOSSARYnear by. Th
Page 346 and 347:
334 APPENDIX G. GLOSSARY
Page 348 and 349:
336 BIBLIOGRAPHY[But97]USA, March 2
Page 350 and 351:
338 BIBLIOGRAPHY[HMB06][Hol03][HP95
Page 352 and 353:
340 BIBLIOGRAPHY[McK06] Paul E. McK
Page 354 and 355:
342 BIBLIOGRAPHYtor. Software - Pra
Page 356 and 357:
344 BIBLIOGRAPHY[UoC08][VGS08]Berke
Page 358:
346 APPENDIX H. CREDITSH.4 Original
show all

Is Parallel Programming Hard, And, If So, What Can You Do About It?

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?