On Sat, Jun 27, 2020, at 1:34 AM, Chun-Yu Shei wrote:
> According to cProfile, catpkgsplit is called up to 1-5.5 million times
> during "emerge -uDvpU --with-bdeps=y @world". Adding a dict to cache its
> results reduces the time for this command from 43.53 -> 41.53 seconds --
> a 4.8% speedup.
> ---
> lib/portage/versions.py | 7 +++++++
> 1 file changed, 7 insertions(+)
>
> diff --git a/lib/portage/versions.py b/lib/portage/versions.py
> index 0c21373cc..ffec316ce 100644
> --- a/lib/portage/versions.py
> +++ b/lib/portage/versions.py
> @@ -312,6 +312,7 @@ def _pkgsplit(mypkg, eapi=None):
>
> _cat_re = re.compile('^%s$' % _cat, re.UNICODE)
> _missing_cat = 'null'
> +_catpkgsplit_cache = {}
>
> def catpkgsplit(mydata, silent=1, eapi=None):
> """
> @@ -331,6 +332,11 @@ def catpkgsplit(mydata, silent=1, eapi=None):
> return mydata.cpv_split
> except AttributeError:
> pass
> +
> + cache_entry = _catpkgsplit_cache.get(mydata)
> + if cache_entry is not None:
> + return cache_entry
> +
> mysplit = mydata.split('/', 1)
> p_split = None
> if len(mysplit) == 1:
> @@ -343,6 +349,7 @@ def catpkgsplit(mydata, silent=1, eapi=None):
> if not p_split:
> return None
> retval = (cat, p_split[0], p_split[1], p_split[2])
> + _catpkgsplit_cache[mydata] = retval
> return retval
>
> class _pkg_str(_unicode):
> --
> 2.27.0.212.ge8ba1cc988-goog
>
There are libraries that provide decorators, etc, for caching and memoization.
Have you evaluated any of those? One is available in the standard library:
https://docs.python.org/dev/library/functools.html#functools.lru_cache
I comment as this would increase code clarity.
