Ceph Quarterly October 2023 Summary of Developments in Q3 ----------------------------- CephFS: A non-blocking I/O API for libcephfs has been added to Ceph: https://github.com/ceph/ceph/pull/48038 A cause of potential deadlock in Python libcephfs has been fixed, which also affected the mgr modules using it: https://github.com/ceph/ceph/pull/52290 MDS: acquisition throttles have been adjusted to more sensible defaults: https://github.com/ceph/ceph/pull/52577 MDS: Buggy clients are now evicted in order to keep MDS available: https://github.com/ceph/ceph/pull/52944 Cephadm: Support for init containers has been added. Init containers allow custom actions to run before the daemon container starts: https://github.com/ceph/ceph/pull/52178 We announce the deployment of the NVMe-oF gateway: https://github.com/ceph/ceph/pull/50423, https://github.com/ceph/ceph/pull/52691 LV devices are now reported by ceph-volume in the inventory list, and can be prepared as OSDs: https://github.com/ceph/ceph/pull/52877 cephadm is now split into multiple files in order to make it easier for humans to read and understand. A new procedure has been added to the documentation that describes how to acquire this new version of cephadm: https://github.com/ceph/ceph/pull/53052 https://docs.ceph.com/en/latest/cephadm/install/#install-cephadm Crimson: Support for multicore has been added to Crimson: https://github.com/ceph/ceph/pull/51147, https://github.com/ceph/ceph/pull/51770, https://github.com/ceph/ceph/pull/51916, https://github.com/ceph/ceph/pull/52306 Infrastructure to support erasure coding has been added to Crimson: https://github.com/ceph/ceph/pull/52211 We announce the introduction of a performance test suite for Crimson: https://github.com/ceph/ceph/pull/50458 Dashboard: RGW multisite configuration can now be imported from a secondary cluster or exported to a secondary cluster: https://github.com/ceph/ceph/pull/50706 We accounce several upgrades to the Cluster User Interface and the Cluster API: https://github.com/ceph/ceph/pull/52351, https://github.com/ceph/ceph/pull/52395, https://github.com/ceph/ceph/pull/52903, https://github.com/ceph/ceph/pull/52919, https://github.com/ceph/ceph/pull/52222, https://github.com/ceph/ceph/pull/53022 More detail has been added to the RGW overview. This includes more granular information about daemons, zoning, buckets, sers, used capacity (the capacity used by all the pools in the cluster). Cards detailing these assets have been added to the rgw overview dashboard.: https://github.com/ceph/ceph/pull/52317, https://github.com/ceph/ceph/pull/52405, https://github.com/ceph/ceph/pull/52915 It is now possible to manage CephFS subvolumes from the dashboard. This includes creating subvolumes, editing subvolumes, removing subvolumes, creating subvolume groups, editing subvolume groups, removing subvolume groups, removing subvolume groups with snapshots, and displaying subvolume groups in the CephFS subvolume tab: https://github.com/ceph/ceph/pull/52786, https://github.com/ceph/ceph/pull/52861, https://github.com/ceph/ceph/pull/52869, https://github.com/ceph/ceph/pull/52886, https://github.com/ceph/ceph/pull/52898, https://github.com/ceph/ceph/pull/53018, https://github.com/ceph/ceph/pull/53182, https://github.com/ceph/ceph/pull/53246 RADOS: Improved robustness against disk corruption of key data structures - OSD superblock data is now replicated in an onode's OMAP, which makes recovery possible even when onode data is corrupted: https://github.com/ceph/ceph/pull/50326 We introduce a disk-fragmentation histogram for bluestore, accessible through an admin socket: https://github.com/ceph/ceph/pull/51820 The amount of metadata necessary to create a snapshot has been significantly reduced, making snapshot creation and deletion more efficient: https://github.com/ceph/ceph/pull/53178 ceph-mgr is now more resilient to blocklisting - cluster connections between MGRs and RADOS clients are now reopened when this occurs: https://github.com/ceph/ceph/pull/50291 LZ4 compression can now be enabled for Bluestore RocksDB: https://github.com/ceph/ceph/pull/53343 RBD: Windows driver now runs RBD functional tests in CI: https://github.com/ceph/ceph/pull/50141 The handling of blocklisting in rbd-mirror and krbd has been improved: https://github.com/ceph/ceph/pull/52990, Linux kernel 6.5-rc5 Various rbd-mirror bug fixes: https://github.com/ceph/ceph/pull/52057, https://github.com/ceph/ceph/pull/52086, https://github.com/ceph/ceph/pull/53251 RGW: Support for versioned objects has been added to emergency bucket repair tools, and rgw-restore-bucket-index can now recognize versioned buckets and RGW objects that have names beginning with underscores: https://github.com/ceph/ceph/pull/51071 Multisite sync load is now distributed farily across gateways: https://github.com/ceph/ceph/pull/51493 Several issues have been fixed, and Trino/TPCDS benchmark now runs with s3select: https://github.com/ceph/ceph/pull/52651, https://github.com/ceph/s3select/pull/132 An initial version of a posix-fs backend for RGW has been developed: https://github.com/ceph/ceph/pull/52933 Telemetry: Over the past two months, Telemetry reports a storage capacity of 27PB from ~170 Reef clusters. Approximately 2,800 clusters report ~1.2EB, including the 27PB from the Reef clusters. See telemetry-public.ceph.com User+Dev Meeting Relaunched: Neha Ojha and Laura Flores organized the relaunch of the User+Dev meeting, which was held on 21 Sep 2023. Two members of the Ceph upstream community gave presentations at this meeting. These were: Cory Snyder of 11:11 Systems's "What To Do When Ceph isn't Cephing" (https://ceph.io/assets/pdfs/user_dev_meeting_2023_09_21_cory_snyder.pdf) and Jonas Sterr of Thomas Krenn AG's "Ceph Usability Improvements" (https://ceph.io/assets/pdfs/user_dev_meeting_2023_09_21_jonas_sterr.pdf). The minutes of this meeting are available here: https://pad.ceph.com/p/ceph-user-dev-monthly-minutes. The User+Dev Meeting is held at 14:00 UTC on the third Thursday of every month. https://meet.jit.si/ceph-user-dev-monthly is where the meeting is held. CQ is a production of the Ceph Foundation. To support or join the Ceph Foundation, contact membership@linuxfoundation.org.