[Bug 276002] nfscl: data corruption using both copy_file_range and mmap'd I/O

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=276002

--- Comment #29 from Alan Somers <asomers@FreeBSD.org> ---
With kib's latest patch, it's more difficult to produce a miscompare.  But
still possible.  For example, using the toml file from Comment 4 with Seed
9675272854109691020 will crash in 95 steps.

Or, without copy_file_range at all, it's possible to crash in 126 steps using
seed 8637402481540764494 and this toml file:

flen = 524288
nomsyncafterwrite = true
[opsize]
max = 131072
min = 65536
[weights]
truncate = 1
fsync = 1
fdatasync = 1
punch_hole = 0
write = 10
read = 10

-- 
You are receiving this mail because:
You are the assignee for the bug.