Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 02 Jul 2021 20:45:40 +0000
From:      bugzilla-noreply@freebsd.org
To:        fs@FreeBSD.org
Subject:   [Bug 256936] Buggy filesystem detected - message wrongly triggered by FUSE filesystems
Message-ID:  <bug-256936-3630-HHCrQ7O4yF@https.bugs.freebsd.org/bugzilla/>
In-Reply-To: <bug-256936-3630@https.bugs.freebsd.org/bugzilla/>
References:  <bug-256936-3630@https.bugs.freebsd.org/bugzilla/>

next in thread | previous in thread | raw e-mail | index | archive | help
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=3D256936

--- Comment #6 from Alan Somers <asomers@FreeBSD.org> ---
Ahh, well if moosefs is indeed using fusefs-libs3, then
vfs.fusefs.data_cache_mode is completely ignored.  Instead, the cache behav=
ior
is controlled by moosefs itself.  You can tell what it's requesting by look=
ing
at the FUSE_INIT response, either by dialing up the log verbosity (maybe,
depending on if moosefs displays it), or by running this (untested) dtrace
script at mount time

fusefs:fusefs:internal:init_done
{
    printf("flags=3D%s", args[1]->flags);
}

Another important thing that the server tells the kernel is the entry and a=
ttr
valid timeouts, which are returned by FUSE_LOOKUP.

Finally, there is the AUTO_INVAL_DATA feature (known as
FUSE_CAP_AUTO_INVAL_DATA in libfuse).  This would probably be very useful f=
or
MooseFS.  In fact, MooseFS may well be written assuming that the feature is
available and working.  However, it is not currently implemented in FreeBSD.

--=20
You are receiving this mail because:
You are the assignee for the bug.=



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-256936-3630-HHCrQ7O4yF>