mirror of https://github.com/postgres/postgres
If sizeof(Pointer) is 4 then sizeof(SortItem) will be 12, so that if data->numrows is odd then we placed the values array at a location that's not a multiple of 8. That was fine when sizeof(Datum) was also 4, but in the wake of commitmaster2a600a93c
it makes some alignment-picky machines unhappy. (You need a 32-bit machine that nonetheless expects 8-byte alignment of 8-byte quantities, which is an odd-seeming combination but it does exist outside the Intel universe.) To fix, MAXALIGN the space allocated to the SortItem array. In passing, let's make the "len" variable be Size not int, just for paranoia's sake. This code was arguably not too safe even before2a600a93c
, but at present I don't see a strong argument for back-patching. Reported-by: Tomas Vondra <tomas@vondra.me> Author: Tom Lane <tgl@sss.pgh.pa.us> Discussion: https://postgr.es/m/87036018-8d70-40ad-a0ac-192b07bd7b04@vondra.me
parent
bdc6cfcd12
commit
09036dc71c
Loading…
Reference in new issue