General

Profile

Bryan Stillwell

Issues

Activity

03/24/2020

10:03 PM RADOS Bug #44724: compressor: Set default Zstd compression level to 1
I've closed *PR:* https://github.com/ceph/ceph/pull/34133 in favor of making it a separate commit as part of:
*PR:...

03/23/2020

10:41 PM RADOS Bug #44724: compressor: Set default Zstd compression level to 1
*PR*: https://github.com/ceph/ceph/pull/34133
10:33 PM RADOS Bug #44724 (New): compressor: Set default Zstd compression level to 1
The default compression level of 5 for Zstandard is too high for the majority
of use cases since it requires too man...

03/20/2020

10:26 PM mgr Feature #43556: Improve internal python to c++ interface
Could this be backported to Nautilus? I believe this is causing the ceph-mgr on our larger clusters to get hung up i...
09:20 PM RADOS Bug #37875: osdmaps aren't being cleaned up automatically on healthy cluster
This also affects Nautilus v14.2.6. On one of our clusters it caused multiple performance problems when we were rebo...

03/06/2020

06:15 PM RADOS Feature #43377: Make Zstandard compression level a configurable option
*PR*: https://github.com/ceph/ceph/pull/33790

02/28/2020

10:48 PM bluestore Bug #44359 (New): Raw usage reported by 'ceph osd df' incorrect when using WAL/DB on another drive
While converting a nautilus (14.2.6) cluster from using FileStore to BlueStore I've noticed that the RAW USE reported...
05:59 PM Ceph Bug #40624: Ubuntu Bionic package index missing most packages for arm64
There still aren't any arm64 packages being built for Ubuntu Bionic, and the last time they were built for Ubuntu Xen...

12/18/2019

10:12 PM RADOS Feature #43377 (Resolved): Make Zstandard compression level a configurable option
I've played with using the different compression algorithms on the RGWs and the default compression level for Zstanda...
09:48 PM mgr Bug #43364: ceph-mgr's finisher queue can grow indefinitely, making python modules/commands unres...
I'm also seeing the 'mgr-fin' thread using 100% of a CPU core. However, I don't see a high queue_len, so maybe ~350 ...

Also available in: Atom