From 56d410572e0648b4664b1277e7a7f5ef50886dbc Mon Sep 17 00:00:00 2001 From: Patrick Donnelly Date: Fri, 7 Jul 2023 08:42:58 -0400 Subject: [PATCH] doc/cephfs: add note to isolate metadata pool osds Signed-off-by: Patrick Donnelly (cherry picked from commit 4e2e61f16438dcd5eb35854091114d18b6fe9a9e) --- doc/cephfs/createfs.rst | 15 +++++++++++---- doc/rados/operations/crush-map.rst | 2 ++ 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/doc/cephfs/createfs.rst b/doc/cephfs/createfs.rst index 537a46b25d507..c5a87293a66fb 100644 --- a/doc/cephfs/createfs.rst +++ b/doc/cephfs/createfs.rst @@ -8,10 +8,17 @@ Creating pools A Ceph file system requires at least two RADOS pools, one for data and one for metadata. When configuring these pools, you might consider: -- Using a higher replication level for the metadata pool, as any data loss in - this pool can render the whole file system inaccessible. -- Using lower-latency storage such as SSDs for the metadata pool, as this will - directly affect the observed latency of file system operations on clients. +- We recommend configuring *at least* 3 replicas for the metadata pool, + as data loss in this pool can render the entire file system inaccessible. + Configuring 4 would not be extreme, especially since the metadata pool's + capacity requirements are quite modest. +- We recommend the fastest feasible low-latency storage devices (NVMe, Optane, + or at the very least SAS/SATA SSD) for the metadata pool, as this will + directly affect the latency of client file system operations. +- We strongly suggest that the CephFS metadata pool be provisioned on dedicated + SSD / NVMe OSDs. This ensures that high client workload does not adversely + impact metadata operations. See :ref:`device_classes` to configure pools this + way. - The data pool used to create the file system is the "default" data pool and the location for storing all inode backtrace information, used for hard link management and disaster recovery. For this reason, all inodes created in diff --git a/doc/rados/operations/crush-map.rst b/doc/rados/operations/crush-map.rst index a27640ab197f9..1a6b1216f1d7b 100644 --- a/doc/rados/operations/crush-map.rst +++ b/doc/rados/operations/crush-map.rst @@ -221,6 +221,8 @@ To view the contents of the rules, run the following command: ceph osd crush rule dump +.. _device_classes: + Device classes -------------- -- 2.39.5