Using io_uring to make a high-performance finger server

I tried to use finger in Ubuntu, and it doesn&#x27;t display UTF-8 correctly. It seems that a patch would fix this but it&#x27;s been untouched for 6 years <a href="https:&#x2F;&#x2F;bugs.launchpad.net&#x2F;ubuntu&#x2F;+source&#x2F;bsd-finger&#x2F;+bug&#x2F;461354" rel="nofollow">https:&#x2F;&#x2F;bugs.launchpad.net&#x2F;ubuntu&#x2F;+source&#x2F;bsd-finger&#x2F;+bug&#x2F;46...</a>

I&#x27;m missing some &quot;high level&quot; context about io_uring, I might as well ask here:<p>- If I want to write a multithreaded program, is it best to have one io_uring per thread?<p>- Per CPU core?<p>- Per device or PCIe lane to the device? (It might make sense ...)<p>- Or one for the whole program? (Will Linux distribute requests across cores and run them in parallel for me?)<p>- If I&#x27;m writing a library that uses io_uring, should I create my own io_uring or offer an interface to add requests to one which the main program creates? (Or perhaps both?)

<p><pre><code> const grent = match (passwd::getgroup(group)) { void =&gt; fmt::fatal(&quot;No &#x27;{}&#x27; group available&quot;, group), gr: passwd::grent =&gt; gr, }; </code></pre> Interesting, is void being used as the &quot;None&quot; of an option type here? At least that&#x27;s what it looks like to me.

For confused people: it&#x27;s written in author&#x27;s language Hare. The language uses QBE as backend [2]. I wonder what author has against Zig (probably at least current dependence on LLVM). It reminds me of Myrddin [3], which AFAIR is connected to Suckless folks.<p>[1] <a href="https:&#x2F;&#x2F;harelang.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;harelang.org&#x2F;</a><p>[2] <a href="https:&#x2F;&#x2F;c9x.me&#x2F;compile&#x2F;" rel="nofollow">https:&#x2F;&#x2F;c9x.me&#x2F;compile&#x2F;</a><p>[3] <a href="https:&#x2F;&#x2F;myrlang.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;myrlang.org&#x2F;</a><p>[4] <a href="https:&#x2F;&#x2F;suckless.org&#x2F;" rel="nofollow">https:&#x2F;&#x2F;suckless.org&#x2F;</a>