Unexpected SU+J inconsistency AGAIN -- please, don't shift topic to ZFS!

[Lev Serebryakov]

Hello, Ivan.
You wrote 28 февраля 2013 г., 18:56:47:

LS>   There was commit r246876, but I don't understand exactly what it
LS>  means, as no real FS or driver's code was touched.
 And,  yes,  barriers  are  much  stronger than "sync writes", as they
 should flush all previous writes, even that is not related to journal
 or metadata and could wait more (simple file data could be fixed on
 plates out of order without destroying filesystem structure).

-- 
// Black Lion AKA Lev Serebryakov <lev at FreeBSD.org>