now that 067681b701
has been merged upstream, and our src/seastar submodule includes
this commit. there is no need to worry that the seastar's lockless
allocator does not work with seastar::alien anymore.
Signed-off-by: Kefu Chai <tchaikov@gmail.com>
Add Release Notes and remove any `profile`
related stuff in the autoscaler documentation
and replace it with `bulk` flag.
Signed-off-by: Kamoltat <ksirivad@redhat.com>
Creating the pool with `--bulk` will allow
the pg_autoscaler to use the `scale-down`
mode on.
Creating pool:
`ceph osd pool create <pool-name> --bulk`
Get var:
`ceph osd pool get <pool-name> bulk`
Set var:
`ceph osd pool set <pool-name> bulk=true/false/1/0`
Removed `autoscale_profile` and incorporate bulk flag
into calculating `final_pg_target` for each pool.
bin/ceph osd pool autoscale-status no longer has
`PROFILE` column but has `BULK` instead.
Signed-off-by: Kamoltat <ksirivad@redhat.com>
* refs/pull/44315/head:
doc/cephfs: mds default cache memory limit is now 4GB
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
mgr/cephadm: store contianer registry credentials in config-key
Reviewed-by: Sage Weil <sage@newdream.net>
Reviewed-by: Sebastian Wagner <sewagner@redhat.com>
Updated docs to show snmp-gateway usage. docs provide
guidance on SNMP versions supported and show CLI and
yaml deployment examples.
Signed-off-by: Paul Cuzner <pcuzner@redhat.com>
Update the ceph version used in the example upgrade command to match the one mentioned in the text above it.
Signed-off-by: Foad Lind <foad.lind@citynetwork.eu>
The new resource returns an array of informational data, which
currently consists of the RADOS cluster fsid as "cluster_fsid."
Fixes: https://tracker.ceph.com/issues/51432
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
This PR removes mentions of journaling from the hardware
recommendations.
Journaling was a FileStore-related practice. BlueStore is
the default backend for Ceph OSDs and has been since
Luminous. The documentation should reflect that.
Signed-off-by: Zac Dover <zac.dover@gmail.com>
This PR updates the content on documenting-ceph,
which is, as of December 2021, in need of an
update.
This is the first of what I estimate to be three
to five PRs against this .rst file.
Signed-off-by: Zac Dover <zac.dover@gmail.com>
Up until this point, we included aggregated and separated data for
testing purposes. Now that we've done our testing, the aggregated
metrics are no longer relevant.
Aggregated metrics can still be achieved on the server side by
summing separated metrics.
Signed-off-by: Laura Flores <lflores@redhat.com>
- Remove npm-force-resolutions: no resolution needed anymore and this is modifying package-lock.json every time it is run (striping last empty line).
- Add .npmrc: save exact version by default; do not launch audit report when installing.
Fixes: https://tracker.ceph.com/issues/48005
Signed-off-by: Alfonso Martínez <almartin@redhat.com>
Advise operators on how to benchmark devices for BlueStore, and how to
tune the volatile write cache for optimal OSD performance.
Fixes: https://tracker.ceph.com/issues/53161
Signed-off-by: Dan van der Ster <daniel.vanderster@cern.ch>
Looks up the shard index of the corresponding bucket, and only
buckets in the corresponding shard are considered for processing.
This has a side effect of matching buckets by id, and also adds
support for --tenant.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
