Bellow you can find the top-down tree of cpu usage that made us raise this issue. Please notice the 16.7% line, which we're optimizing on this PR.
We should investigate faster options than strtod, like https://github.com/lemire/fast_double_parser
Top-Down tree of hotspots by CPU utilization for TS.MADD....
| Function Stack |
CPU Time: Total |
CPU Time: Self |
Function (Full) |
Source File |
| add |
96.10% |
0.122s |
add |
module.c |
| RM_OpenKey |
27.70% |
0.066s |
RM_OpenKey |
module.c |
| internalAdd |
24.80% |
0.404s |
internalAdd |
module.c |
| RM_StringToDouble |
16.70% |
0.038s |
RM_StringToDouble |
module.c |
| RM_CloseKey |
8.30% |
0.114s |
RM_CloseKey |
module.c |
| RM_StringToLongLong |
6.80% |
0.082s |
RM_StringToLongLong |
module.c |
| zfree |
4.20% |
0.262s |
zfree |
zmalloc.c |
| ParseDuplicatePolicy |
2.40% |
0.184s |
ParseDuplicatePolicy |
query_language.c |
| RM_ModuleTypeGetType |
1.90% |
0.236s |
RM_ModuleTypeGetType |
module.c |
| _GI |
1.50% |
0.212s |
float _GI(long, int, bool, char) |
malloc.c |
Bellow you can find the top-down tree of cpu usage that made us raise this issue. Please notice the 16.7% line, which we're optimizing on this PR.
We should investigate faster options than strtod, like https://github.com/lemire/fast_double_parser
Top-Down tree of hotspots by CPU utilization for TS.MADD....