Re: [PATCH 1/3] lib/min_heap: Introduce non-inline versions of min heap API functions
Kent Overstreet <[email protected]>
| Newsgroups | org.kernel.vger.linux-bcache,dev.linux.lists.dm-devel,org.kernel.vger.linux-bcachefs,org.kernel.vger.linux-doc,org.kernel.vger.linux-kernel,org.kernel.vger.linux-perf-users |
|---|---|
| Message-ID | <zne3invtehte3ym34ufnydtggigxazdb2ltfa26ca4tykvprls@rcawukx5hhcn> |
On Thu, Oct 17, 2024 at 11:55:20AM +0200, Peter Zijlstra wrote: > On Wed, Oct 16, 2024 at 11:26:30PM -0400, Kent Overstreet wrote: > > > yeah, I think we would prefer smaller codesize, by default. > > > > it'd be well worth checking the code size difference on inlined vs. not, > > and then the really think to do would be to provide optional _inlined() > > helpers that we can switch to if/when a particular codepath shows up in > > a profile > > Make sure to build with kCFI and IBT enabled when you do this and enjoy > seeing ec_stripes_heap_cmp turn into this: I wouldn't worry too much about the stripes heap, I'm going to replace that with a persistent LRU. After that it looks like the only heap left in bcachefs will be in the clock code. Shame, they're one of my favorite data structures...