Hey Eric, On Wed, Feb 08, 2017 at 04:24:36PM -0800, Eric Biggers wrote: > On Thu, Feb 09, 2017 at 08:31:21AM +0900, Minchan Kim wrote: > > > > Today, I did zram-lz4 performance test with fio in current mmotm and > > found it makes regression about 20%. > > > > This may or may not be the cause of the specific regression you're observing, > but I just noticed that the proposed patch drops a lot of FORCEINLINE > annotations from upstream LZ4. The FORCEINLINE's are there for a reason, > especially for the main decompression and compression functions which are > basically "templates" that take in different sets of constant parameters, and > should be left in. We should #define FORCEINLINE to __always_inline somewhere, > or just do a s/FORCEINLINE/__always_inline/g. > I generally just replaced "FORCE_INLINE" by "static inline". At least I thought so. I rechecked and realised, I missed at least two of them (why did I not just use "search+replace"?). So I think it's maybe safer and easier to eventually just use "FORCE_INLINE" with the definition you suggested. Will try that. > Note that the upstream LZ4 code is very carefully optimized, so we should not, > in general, be changing things like when functions are force-inlined, what the > hash table size is, etc. > > [Also, for some reason linux-crypto is apparently still not receiving patch 1/5 > in the series. It's missing from the linux-crypto archive at > http://www.spinics.net/lists/linux-crypto/, so it's not just me.] > I don't really know what to do about this. I think the matter is the size of the E-Mail. Are there filters or something like that? Since in linux-kernel the patch seems to get delivered. I could otherwise CC you if you wish. Thanks, Sven
