Nils Goroll
Nils Goroll
extra bugwash: after release, add vcl control over all esi feature flags
I am not against, but my question is: Do we really want to continue adding functions piecemeal or should we try to get something like libm covered as a whole?
I can not provide a list of "most valuable" functions. You need a function when you need it. Standard libraries provide functions which were deemed valuable before we knew they...
bugwash is asking for examples of use cases
Interesting. Without any information on the background at all, I did wildly guess during bugwash: > (15:45:26) slink: predictive rate limiting comes to my mind at least Some library functions...
> I found something interesting about this: [43af86c](https://github.com/varnishcache/varnish-cache/commit/43af86cc40ed78a4b41be60fa3542e45ad644285) Should we maybe wrap the assertion and make acceptance of `EINTR` conditional like `#if HAVE_SANITIZER_ASAN_INTERFACE_H` or `#if ENABLE_ASAN`? Note: I am an...
bugwash: @Dridi will present something in this area
So, I overlooked that it was me who initially added tolerance of `EINTR` in 0895d2e61f61c2942e6bc4db3347adec7966d6c2, which is embarrassing and I will go back to the elementary school of `git`. The...
👍🏽 but could not look in detail yet
The usual suspect is jemalloc in combination with Linux transparent huge pages (THP). You might want to have a look at [this stackoverflow question](https://stackoverflow.com/questions/65450044/varnish-6-lts-w-centos-8-not-respecting-memory-limits/76850685#76850685).