|
Ran
|
Jobs
1
|
Files
89
|
Run time
7s
|
Badge
README BADGES
|
push
github
profilers: purge generation mechanism Since both of the profiler parsers are now processing the events in a stream-like fashion, the generation mechanism is excessive and can be purged. This results in a significant memory consumption drop, especially for the AVL-tree part. Consider this script: | jit.off() | misc.sysprof.start{mode = 'C', interval=10} | for i = 1, 1e7 do tostring(i) end | misc.sysprof.stop() After executing it with LuaJIT, you can parse it like this: | $ time -v luajit-parse-sysprof sysprof.bin So, before the patch: | Maximum resident set size (kbytes): 224928 And after the patch: | Maximum resident set size (kbytes): 32780 That is the 85% reduction in memory consumption. Follows up tarantool/tarantool#8700 Reviewed-by: Sergey Kaplun <skaplun@tarantool.org> Reviewed-by: Sergey Bronnikov <sergeyb@tarantool.org> Signed-off-by: Igor Munkin <imun@tarantool.org> (cherry picked from commit 090117d83)
5326 of 5957 branches covered (0.0%)
Branch coverage included in aggregate %.
20430 of 23231 relevant lines covered (87.94%)
690740.59 hits per line
| Lines | Coverage | ∆ | File |
|---|---|---|---|
| 1 |
92.62 |
-0.06% | src/lj_asm_x86.h |
| 2 |
88.86 |
-0.25% | src/lj_ffrecord.c |
| 2 |
93.09 |
-0.99% | src/lj_ir.c |
| 2 |
75.75 |
-0.16% | src/lj_opt_fold.c |
| 6 |
82.76 |
-2.59% | src/lj_sysprof.c |
| 7 |
94.74 |
-4.78% | src/lj_str.c |
| ID | Job ID | Ran | Files | Coverage | |
|---|---|---|---|---|---|
| 1 | 6854723694.1 | 89 |
88.24 |
GitHub Action Run |
| Coverage | ∆ | File | Lines | Relevant | Covered | Missed | Hits/Line | Branch Hits | Branch Misses |
|---|