* What are the semantics of BLKIF_OP_WRITE_BARRIER?
@ 2010-07-22 20:41 Jeremy Fitzhardinge
0 siblings, 0 replies; only message in thread
From: Jeremy Fitzhardinge @ 2010-07-22 20:41 UTC (permalink / raw)
To: Daniel Stodden; +Cc: Xen-devel@lists.xensource.com, Jake Wires
What does BLKIF_OP_WRITE_BARRIER mean precisely? Presumably it prevents
writes from being reordered past it. But does it also imply a flush, in
that all previous writes are on stable storage? If not, is there
another operation which does guarantee that? If the backend doesn't
support barriers, is there any other way for a guest to force writes to
stable storage?
How does blktap(2) deal with devices with volatile write caches? Does
it generate its own barriers/flushes/FUA requests to push things out to
stable storage?
Thanks,
J
^ permalink raw reply [flat|nested] only message in thread
only message in thread, other threads:[~2010-07-22 20:41 UTC | newest]
Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-07-22 20:41 What are the semantics of BLKIF_OP_WRITE_BARRIER? Jeremy Fitzhardinge
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.