f2f4c8072f
Summary: The pupose of this diff is to expose per user-call level precise timing of block read, so that we can answer questions like: a Get() costs me 100ms, is that somehow related to loading blocks from file system, or sth else? We will answer that with EXACTLY how many blocks have been read, how much time was spent on transfering the bytes from os, how much time was spent on checksum verification and how much time was spent on block decompression, just for that one Get. A nano second stopwatch was introduced to track time with higher precision. The cost/precision of the stopwatch is also measured in unit-test. On my dev box, retrieving one time instance costs about 30ns, on average. The deviation of timing results is good enough to track 100ns-1us level events. And the overhead could be safely ignored for 100us level events (10000 instances/s), for example, a viewstate thrift call. Test Plan: perf_context_test, also testing with viewstate shadow traffic. Reviewers: dhruba Reviewed By: dhruba CC: leveldb, xjin Differential Revision: https://reviews.facebook.net/D12351
34 lines
677 B
C++
34 lines
677 B
C++
#ifndef PERF_CONTEXT_IMP_H
|
|
#define PERF_CONTEXT_IMP_H
|
|
|
|
#include "rocksdb/perf_context.h"
|
|
#include "util/stop_watch.h"
|
|
|
|
namespace leveldb {
|
|
|
|
extern enum PerfLevel perf_level;
|
|
|
|
inline void StartPerfTimer(StopWatchNano* timer) {
|
|
if (perf_level >= PerfLevel::kEnableTime) {
|
|
timer->Start();
|
|
}
|
|
}
|
|
|
|
inline void BumpPerfCount(uint64_t* count, uint64_t delta = 1) {
|
|
if (perf_level >= PerfLevel::kEnableCount) {
|
|
*count += delta;
|
|
}
|
|
}
|
|
|
|
inline void BumpPerfTime(uint64_t* time,
|
|
StopWatchNano* timer,
|
|
bool reset = true) {
|
|
if (perf_level >= PerfLevel::kEnableTime) {
|
|
*time += timer->ElapsedNanos(reset);
|
|
}
|
|
}
|
|
|
|
}
|
|
|
|
#endif
|