avoid regex 'parsing' format strings every time #2164
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
before:
after:
|
fbs
commented
Mar 10, 2022
| void split(); | ||
|
|
||
| public: | ||
| FormatString() = default; |
There was a problem hiding this comment.
shouldn't need this but got some confusing template errors. Will try to remove it
There was a problem hiding this comment.
Don't see a way to avoid this, unless we change the vector<tuple<FormatString, vector<Fields>> into something with a custom serializer that does it correctly. Unless I'm doing something wrong.
Having this also keeps the serializer for this class easy.
fbs
force-pushed
the
optimize_fmtstr
branch
2 times, most recently
from
02bc547 to
5a662e9
Compare
viktormalik
reviewed
Mar 28, 2022
| @@ -6,70 +6,6 @@ | |||
|
|
|||
| namespace bpftrace { | |||
|
|
|||
| std::string verify_format_string(const std::string &fmt, std::vector<Field> args) | |||
There was a problem hiding this comment.
Should be also removed from src/printf.h.
fbs
force-pushed
the
optimize_fmtstr
branch
2 times, most recently
from
ac29327 to
4b62cc3
Compare
viktormalik
approved these changes
Apr 8, 2022
bpftrace::format spends about 60% of its time in the regex_iterator we use to split the string. The FormatString type avoids this by splitting the string on first use and storing the result for re-use. I've kept the code mostly as is, just moving and minor modifications. The whole output code can do with a refactoring but this should be a nice performance gain. Test case is running opensnoop.bt while running `find /` in another terminal: original: bpftrace::perf_event_printer spent 75% of the time in format new: bpftrace::perf_event_printer spent 15% of the time in format
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
bpftrace::format spends about 60% of its time in the regex_iterator we
use to split the string.
The FormatString type avoids this by splitting the string on first use
and storing the result for re-use.
I've kept the code mostly as is, just moving and minor modifications.
The whole output code can do with a refactoring but this should be a
nice performance gain.
Test case is running opensnoop.bt while running
find /in anotherterminal:
original: bpftrace::perf_event_printer spent 75% of the time in format
new: bpftrace::perf_event_printer spent 15% of the time in format
Checklist
man/adoc/bpftrace.adocand if needed indocs/reference_guide.mdCHANGELOG.md