CARAT: a testbed for the performance evaluation of distributed database systems
ACM '86 Proceedings of 1986 ACM Fall joint computer conference
| Hi-index | 0.00 |
A QUEUEING NETWORK MODEL TO ANALYZE THE PERFORMANCE OF A DISTRIBUTED DATABASE TESTBED SYSTEM WITH A TRANSACTION WORKLOAD IS DEVELOPED AND VAL- IDATED AGAINST EMPIRICAL MEASUREMENTS. THE MODEL INCLUDES THE EFFECTS OF THE CONCURRENCY CONTROL PROTOCOL (TWO-PHASE LOCKING WITH DISTRIBUTED DEAD- LOCK DETECTION), THE TRANSACTION RECOVERY PROTOCOL (WRITE-AHEAD-LOGGING OF BEFORE-IMAGES), AND THE COMMIT PROTOCOL (CENTRALIZED TWO-PHASE COMMIT) USED IN THE TESTBED SYSTEM. THE QUEUEING MODEL DIFFERS FROM THE PREVIOUS ANALYTICAL MODELS IN THREE MAJOR ASPECTS. FIRST, IT IS A MODEL FOR A DISTRIBUTED TRANSACTION PROCESS- ING SYSTEM. SECOND, IT IS MORE GENERAL AND INTEGRATED THAN PREVIOUS ANALY- TICAL MODELS. FINALLY, IT REFLECTS A FUNCTIONING DISTRIBUTED DATABASE TESTBED SYSTEM AND IS VALIDATED AGAINST PERFORMANCE MEASUREMENTS. INDEX TERMS - QUEUEING NETWORK MODEL, PERFORMANCE EVALUATION, DISTRIBUTED TRANSACTION PROCESSING, CONCURRENCY CONTROL, WRITE-AHEAD-LOGGING, TWO- PHASE COMMIT, MODEL VALIDATION.