| Commit message (Collapse) | Author | Age | Files | Lines |
|\
| |
| |
| |
| | |
vespa-engine/balder/gc-unused-bucketdb-feature-flag
bucketdb-stripe-bits flag is no longer needed.
|
| | |
|
| | |
|
|\ \
| | |
| | |
| | |
| | | |
vespa-engine/hakonhall/support-delegating-content-node-suspension-to-cluster-controller
Support delegating content node suspension to cluster controller
|
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | |
| | | |
This PR introduces a new flag group-suspension, which if true, enables:
- Instead of allowing at most one storagenode to suspend at any given time, it
will now ignore storagenode, searchnode, and distributor service clusters,
and rely on the cluster controller to allow or deny the request to suspend.
This will increase the load on the cluster controllers.
Combined with earlier changes to the cluster controller, this new flag
effectively guard the feature of allowing all nodes within a hierarchical group
to suspend concurrently.
I also took the opportunity to tune related policies:
- Allow at most one config server and controller to be down at any given time.
This is actually a no-op, since it was effectivelly equal to the older
policy of 10% down.
- Allows 20% of all host-admins to be down, not just tenant host-admins. This
is effectively equal to the old policy of 10% except that it may allow 2
proxy host-admins to go down at the same time. Should be fine.
|
|/ / |
|
|\ \
| | |
| | |
| | |
| | | |
vespa-engine/hmusum/use-zookeeper-server-3.6.2-as-default-version
Use version 3.6.2 as default version for ZooKeeper server
|
| |/ |
|
|\ \
| |/
|/| |
Wait for resources in prepare
|
| | |
|
|/
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* remove support for old formats and introduce EndpointCertificateMaintainer
* record certificate refresh time, run maintainer every 12 hours
* retrigger prod deployments if refreshed certificate not deployed after one week
* only re-trigger production jobs
* unit test EndpointCertificateMaintainer
* take application lock to avoid concurrent modifications when managing endpoint certs
* only trigger deployment jobs
Co-authored-by: Jon Marius Venstad <jonmv@users.noreply.github.com>
|
| |
|
| |
|
|\
| |
| |
| |
| | |
vespa-engine/hakonhall/noop-update-default-of-reboot-interval-in-days-to-15
Noop update default of reboot-interval-in-days to 15
|
| | |
|
|/ |
|
|\
| |
| | |
Remove host-hardening flag
|
| | |
|
| |
| |
| | |
Co-authored-by: andreer <andreer@verizonmedia.com>
|
|/ |
|
|\
| |
| |
| |
| | |
vespa-engine/hmusum/use-flag-to-choose-vespa-zookeeper-server-implementation
Use feature flag to decide how to run ZooKeeper server
|
| |
| |
| |
| |
| | |
Add flag to choose between reconfigurable ZooKeeper server or not for
the ZooKeeper server used by cluster controller
|
|/ |
|
| |
|
| |
|
|\
| |
| |
| |
| | |
vespa-engine/geirst/remove-use-fast-value-tensor-implementation
Remove "use-fast-value-tensor-implementation" flag.
|
| |
| |
| |
| | |
Has been default on since 7.319.17 (25-Nov-2020).
|
|/ |
|
| |
|
|\
| |
| |
| |
| |
| |
| | |
Conflicts:
controller-server/src/main/java/com/yahoo/vespa/hosted/controller/restapi/user/UserApiHandler.java
controller-server/src/main/java/com/yahoo/vespa/hosted/controller/security/CloudAccessControl.java
flags/src/main/java/com/yahoo/vespa/flags/Flags.java
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| | |
|
| |\
| | |
| | | |
Bjorncs/feature flags
|
| | | |
|
| | |
| | |
| | |
| | | |
Actual owners will be specified in upcoming PR
|
| |/ |
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Adds a 'minCount' field to the shared host jackson flag, denoting the minimum
number of "shared hosts" that must exist, otherwise the deficit will be
provisioned by DynamicProvisioningMaintainer.
A "shared host" is one that is considered for allocation if current tenant node
allocations were removed: It must be a tenant host, cannot be an exclusiveTo
host, etc.
minCount requires the setting of (at least one) shared host.
|
| | |
|
|/
|
|
|
|
| |
Create a feature flag that has the max nr. of tenants with the trial
plan. If the number is exceeded we fail creation of new tenants (who
are implicitly in the trial plan).
|
|\
| |
| |
| |
| | |
vespa-engine/hakonhall/allow-preprovision-capacity-on-partially-filled-hosts
Allow preprovision capacity on partially filled hosts
|
| | |
|
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| | |
Adds new functionality that can be disabled by setting the
compact-preprovision-capacity flag to false.
preprovision-capacity can be satisfied by hosts with spare resources. The
DynamicProvisioningMaintainer does this as follows:
1. For each cluster in preprovision-capacity, try to
a. allocate the cluster using NodePrioritizer
b. If there is a deficit, provision the deficit with HostProvisioner, which
may provision larger shared hosts depending on shared-hosts, and retry
(1) from the first cluster again.
c. Otherwise, pretend the nodes are allocated and go to next cluster.
2. All of preprovision-capacity was successfully allocated, and empty hosts
are therefore excess that can be deprovisioned.
|
| |
| |
| |
| | |
Flag will be used in code in zookeeper-server modules
|
| | |
|
|/ |
|
| |
|