On 07/07/2015 06:24 PM, James Page wrote: > On 06/07/15 18:23, James Page wrote: >>> The ceph Debian package git repository only contains very little >>>> reasoning about the change. James can you please expand on this >>>> a bit? In general I would prefer to have changes like this in >>>> their own commit and not mixed with unrelated changelog >>>> updates. Did the Hammer release not build with the jerasure in >>>> Debian or are you just afraid of unexpected results if the >>>> Debian package is built with another version of jerasure than >>>> what they ship in their source code? These would IMO be valid >>>> reasons to (temporarily) remove the patch. >> Re-basing the patch - which was turning out to be non-trivial - >> pushed me over the time I had todo this update; as the upload was >> to experimental only, I intended to revisit when time permitted. > > I dug into this in a bit more detail today; the Ceph package builds a > number of difference loadable erasure coding plugins, enabling > different cpu feature sets (generic, neon, sse3, sse4); each time > Jerasure and gf-complete are statically linked into the module, built > with the required flags to enable the right CPU instruction codes > (build time, not runtime enablement).
I really wish gf-complete & jerasure had runtime checks for the CPU type, because I had to disable all SSE stuff, since it isn't available on all Intel CPUs. :( > Unless I'm reading the packaging wrong, the jerasure and gf-complete > packages current disable any CPU specific extensions in order to have > a completely generic library that works on any CPU. Correct. > So using the > system libraries effectively cripples any CPU optimization that might > be achievable at runtime in Ceph. Yes. The way it should be fixed is by fixing upstream code to do runtime checks, or just rebuilding the libraries without the SSE disable patches. The fact that SSE is disabled in Debian & Ubuntu is certainly not a valid reason to hack and embed the libs in Ceph. IMO we shall talk to upstream about this issue and get it solved there, probably by a contribution to gf-complete & jerasure. If shere was such patch available, I'd include it in the Debian package, even if it wasn't available in a new upstream release. Cheers, Thomas Goirand (zigo) -- To UNSUBSCRIBE, email to debian-bugs-rc-requ...@lists.debian.org with a subject of "unsubscribe". Trouble? Contact listmas...@lists.debian.org
