Date: Mon, 8 Dec 2025 13:32:56 +0100 From: Mateusz Guzik <mjguzik@gmail.com> To: Rozhuk Ivan <rozhuk.im@gmail.com> Cc: Konstantin Belousov <kib@freebsd.org>, FreeBSD Current <freebsd-current@freebsd.org>, emaste@freebsd.org Subject: Re: performance regressions in 15.0 Message-ID: <CAGudoHGSVsaX31fRepzj4bSp%2Bh04XfUM_rYxQHc%2B1kubLp7dvQ@mail.gmail.com> In-Reply-To: <20251207203109.6d58b901@rimwks.local> References: <CAGudoHFUJ23yUWPq7_VS2ek0zoGQOS42HB00n-hWspA3Cb4-XQ@mail.gmail.com> <aTRm0WW7xaKsOKx1@kib.kiev.ua> <20251206222638.44edcd5c@rimwks.local> <CAGudoHF5kNmyeRu0pbmUvQCWwfazC4nzRgXHkbJeFsDer94dOA@mail.gmail.com> <20251207203109.6d58b901@rimwks.local>
index | next in thread | previous in thread | raw e-mail
On Sun, Dec 7, 2025 at 7:31 PM Rozhuk Ivan <rozhuk.im@gmail.com> wrote: > > On Sun, 7 Dec 2025 11:07:48 +0100 > Mateusz Guzik <mjguzik@gmail.com> wrote: > > That is to say, if you have time, can you please benchmark a > > statically linked clang vs clang which merely reverting the libprivate > > change? Should be a small speed up on top. > > NO_SHARED - it was static link with libc and probably other system libs. > Now clang splitted into set of libs, it is a bit different thing. > It is indeed a different thing and I am saying it also likely reduces performance compared to what it can be without the recent libprivat problem. It very much warrants benchmarking.help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?CAGudoHGSVsaX31fRepzj4bSp%2Bh04XfUM_rYxQHc%2B1kubLp7dvQ>