I thought jemalloc is used as a drop-in replacement for the standard lib heap functions / operators. So how can the freelist stuff not work with it?
On Tue, Dec 11, 2018 at 4:48 PM Bryan Call <bc...@apache.org> wrote: > There is no point in cleaning up the code if the plan is to not use it and > remove it from our codebase. Work should be done on proving that jemalloc > is valid alternative. > > If jemalloc doesn’t prove to workout, then we might look at cleaning up > the freelist. > > -Bryan > > > On Dec 10, 2018, at 5:42 PM, Walt Karas <wka...@oath.com.INVALID> wrote: > > > > As far as one can tell is a big limitation with code like: > > > > #if (defined(__i386__) || defined(__arm__) || defined(__mips__)) && > >> (SIZEOF_VOIDP == 4) > >> > >> #define FREELIST_POINTER(_x) (_x).s.pointer > >> > >> #define FREELIST_VERSION(_x) (_x).s.version > >> > >> #define SET_FREELIST_POINTER_VERSION(_x, _p, _v) \ > >> > >> (_x).s.pointer = _p; \ > >> > >> (_x).s.version = _v > >> > >> #elif TS_HAS_128BIT_CAS > >> > >> #define FREELIST_POINTER(_x) (_x).s.pointer > >> > >> #define FREELIST_VERSION(_x) (_x).s.version > >> > >> #define SET_FREELIST_POINTER_VERSION(_x, _p, _v) \ > >> > >> (_x).s.pointer = _p; \ > >> > >> (_x).s.version = _v > >> > >> #elif defined(__x86_64__) || defined(__ia64__) || defined(__powerpc64__) > >> || defined(__aarch64__) || defined(__mips64) > >> > >> #define FREELIST_POINTER(_x) \ > >> > >> ((void *)(((((intptr_t)(_x).data) << 16) >> 16) | > >> (((~((((intptr_t)(_x).data) << 16 >> 63) - 1)) >> 48) << 48))) // sign > >> extend > >> > >> #define FREELIST_VERSION(_x) (((intptr_t)(_x).data) >> 48) > >> > >> #define SET_FREELIST_POINTER_VERSION(_x, _p, _v) (_x).data = > >> ((((intptr_t)(_p)) & 0x0000FFFFFFFFFFFFULL) | (((_v)&0xFFFFULL) << 48)) > >> > >> #else > >> > >> #error "unsupported processor" > >> > >> #endif > >> > > > > > > > > > > On Mon, Dec 10, 2018 at 5:02 PM Leif Hedstrom <zw...@apache.org> wrote: > > > >> > >> > >>> On Dec 10, 2018, at 10:29 AM, SUSAN HINRICHS <shinr...@ieee.org> > wrote: > >>> > >>> Based on Fei's measurements, the ATS freelists provide no benefit over > >>> jemalloc. We are now in a position to do larger tests over our > >> production > >>> installs. > >> > >> > >> Agreed, that was generally what I noticed too, except, I could not get > ATS > >> to be stable with just jemalloc. It’d eventually get unhappy, but I > didn’t > >> investigate further. But this is my point, lets focus the efforts on > moving > >> us forward, to jemalloc, and not mess around with freelist as it is, > >> because it works fine as far as I can tell. > >> > >> — leif > >> > >> > >
