https://bugzilla.kernel.org/show_bug.cgi?id=202441 --- Comment #24 from Roger (rogan6710@xxxxxxxxx) --- A few moments ago, a piece of the puzzle fell into place. The problem persists. All this revert did, was to make the issue granularity dependent from what I gather. While redoing the test with all those source trees I used to compile the kernels, the same exact problem came back. The earlier tests were done using mostly multi GB files. After some more testing I found out that rc4 is completely problem free in this regard, but rc5 is definately not, so the real culprit was probably introduced in rc5. After applying our inode.c revert on 4.19.18, it shows the same behaviour as rc5. I can test on intermediate versions as well if necessary, as I still have them all compiled and ready. -- You are receiving this mail because: You are watching the assignee of the bug.
