Hi,
The autoscale settings of some pools seem to be disabled in some of my clusters.
This problem seems to be caused by overlapping root. My cluster is for RGW
and there are two shadow trees, one is for index (SSD), and the other
is for data (HDD).
This overlapping is caused by the existence of
`c
crash info:
{
"backtrace": [
"/lib64/libpthread.so.0(+0x12ce0) [0x7f82e87cece0]",
"(BlueStore::Onode::put()+0x1a3) [0x55bd21a422e3]",
"(std::_Hashtable >,
mempool::pool_allocator<(mempool::pool_index_t)4, std::pair > >,
std::__detail::_Select1st, std::equal_to,
std::has
On Sun, Oct 23, 2022 at 11:04 PM can zhu wrote:
>
> crash info:
>
> {
> "backtrace": [
> "/lib64/libpthread.so.0(+0x12ce0) [0x7f82e87cece0]",
> "(BlueStore::Onode::put()+0x1a3) [0x55bd21a422e3]",
> "(std::_Hashtable boost::intrusive_ptr >,
> mempool::pool_allocator<(mem
Hi,
We deployed Quincy 17.2.3 with rook on top of k8s. After bringing up rook
as orchestrator,we got dashboard page hung and active manager daemon with
the following log:
---
kubectl logs rook-ceph-mgr-a-6df8788cd9-wnpn9 mgr -n rook-ceph
debug 2022-10-21T09:07:21.760+ 7f
