For the sake of compliance with the classical OSD where the type
of the listening address is being reflected in the address type
of an accepted connection:
```
int PosixServerSocketImpl::accept(ConnectedSocket *sock, const SocketOptions &opt, entity_addr_t *out, Worker *w) {
// ...
sockaddr_storage ss;
// ...
int sd = accept_cloexec(_fd, (sockaddr*)&ss, &slen);
if (sd < 0) {
return -ceph_sock_errno();
}
// ...
out->set_type(addr_type);
out->set_sockaddr((sockaddr*)&ss);
handler.set_priority(sd, opt.priority, out->get_family());
}
```
In Rook crimson binds explicitly to v2 address:
```
INFO 2021-10-26 17:55:08,116 [shard 0] osd - picked address v2:0.0.0.0:0/0
ERROR 2021-10-26 17:55:08,116 [shard 0] none - Falling back to public interface
INFO 2021-10-26 17:55:08,116 [shard 0] osd - picked address v2:0.0.0.0:0/0
```
Signed-off-by: Radoslaw Zarzynski <rzarzyns@redhat.com>
mgr/dashboard: Proper error handling in module status guard
Reviewed-by: Alfonso Martínez <almartin@redhat.com>
Reviewed-by: Avan Thakkar <athakkar@redhat.com>
Reviewed-by: Nizamudeen A <nia@redhat.com>
Reviewed-by: Pere Diaz Bou <pdiazbou@redhat.com>
mgr/dashboard: Fix for form inside form closing issue
Reviewed-by: Alfonso Martínez <almartin@redhat.com>
Reviewed-by: Avan Thakkar <athakkar@redhat.com>
Reviewed-by: Nizamudeen A <nia@redhat.com>
crimson/net: don't enforce peer-perceived-myaddr matches myaddr if haven't learned it yet.
Reviewed-by: Chunmei Liu <chunmei.liu@intel.com>
Reviewed-by: Samuel Just <sjust@redhat.com>
Reducing the size of split_merge_multi has an interesting side effect of
causing removes to happen on some leaf nodes immediately after split.
After split, child nodes would have size 72 or 73. At size 72, the node
would be at_min_size() and a remove would put it below causing the
at_min_size() condition to fail and hande_merge to misbehave.
Replace at_min_capacity() with below_min_capacity().
below_min_capacity() will not be true for any child of a split, and
asserts that the child is below capacity by no more than 1.
Signed-off-by: Samuel Just <sjust@redhat.com>
Clarify that lookup_depth_range may return an iterator at_boundary() and
audity users.
Fix LBABtree::lookup to correctly handle at_boundary() after the call to
lookup_depth_range.
Fixes: https://tracker.ceph.com/issues/52805
Signed-off-by: Samuel Just <sjust@redhat.com>
From an external caller, the condition is identical. However, internally
iterators may be at a leaf boundary without being at end(). For those
checks, use at_boundary() instead.
Signed-off-by: Samuel Just <sjust@redhat.com>
After the angular 11 upgrade the form in form behaviour got broken when
one tries to close that "embedded" form. This commit is to fix that
behaviour.
Fixes: https://tracker.ceph.com/issues/53020
Signed-off-by: Nizamudeen A <nia@redhat.com>
mgr/dashboard: pin a version for autopep8 and pyfakefs
Reviewed-by: Aashish Sharma <aasharma@redhat.com>
Reviewed-by: Avan Thakkar <athakkar@redhat.com>
Reviewed-by: Ernesto Puerta <epuertat@redhat.com>
Reviewed-by: Pere Diaz Bou <pdiazbou@redhat.com>
I've recently introduced a check that verifies if the orch_backend we need for a feature matches the orch_backend of the cluster. But to verify this I need to call configOpt API and some user's don't have the permission to access it. So it'll show this Access Denied page.
Fixes: https://tracker.ceph.com/issues/53021
Signed-off-by: Nizamudeen A <nia@redhat.com>
Persistent writeback cache messes with pool quota enforcement on the
OSD side and we don't always break out of the write zeroes loop:
src/test/librbd/test_librbd.cc:2165: Failure
Value of: off >= quota && off < size
Actual: false
Expected: true
Unfortunately persistent writeback cache doesn't honor FUA [1] so the
workaround for volatile caches from the previous patch doesn't apply.
[1] https://tracker.ceph.com/issues/49715
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
Work around write-back or write-around cache getting enabled (e.g. if
one runs the tests with rbd_cache_writethrough_until_flush disabled).
Fixes: https://tracker.ceph.com/issues/52883
Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
This commit makes rbm_alloc_delta_t to use std::pair based on
paddr_t in order that other modules such as cache, which does not
know about RBM, can add free information.
Signed-off-by: Myoungwon Oh <myoungwon.oh@samsung.com>
crimson/tools/store_nbd/fs_driver: fix mount and mkfs to handle new mkfs signature
Reviewed-by: Yingxin Cheng <yingxin.cheng@intel.com>
Reviewed-by: Chunmei Liu <chunmei.liu@intel.com>
