From 9481fe4541a4f0abab6a4e76931a3d6bd9a5b8b0 Mon Sep 17 00:00:00 2001 From: "Suren A. Chilingaryan" Date: Fri, 2 Aug 2019 02:11:00 +0200 Subject: New WAVe project --- docs/consistency.txt | 6 ++++++ docs/problems.txt | 4 +++- docs/troubleshooting.txt | 2 +- setup/configs/openshift.yml | 6 ++++-- setup/configs/security.yml | 1 + setup/configs/volumes.yml | 2 ++ setup/projects/wave/templates/40-kaas-manager.yml.j2 | 1 + setup/projects/wave/vars/volumes.yml | 11 +++++++++++ setup/users/htpasswd | 2 +- 9 files changed, 30 insertions(+), 5 deletions(-) create mode 120000 setup/projects/wave/templates/40-kaas-manager.yml.j2 create mode 100644 setup/projects/wave/vars/volumes.yml diff --git a/docs/consistency.txt b/docs/consistency.txt index 082a734..91a0ee7 100644 --- a/docs/consistency.txt +++ b/docs/consistency.txt @@ -10,6 +10,12 @@ General overview - API health check curl -k https://apiserver.kube-service-catalog.svc/healthz +Nodes +===== + - All systemd services are running + * Communication with docker daemon is actually working + - Replicas of mandatory pods (GlusterFS, Router) are running on all nodes + Storage ======= - Heketi status diff --git a/docs/problems.txt b/docs/problems.txt index fa88afe..1d729cd 100644 --- a/docs/problems.txt +++ b/docs/problems.txt @@ -20,6 +20,7 @@ Rogue network interfaces on OpenVSwitch bridge * With time, the new rogue interfaces are created faster and faster. At some point, it really slow downs system and causes pod failures (if many pods are re-scheduled in paralllel) even if not so many rogue interfaces still present + * Even if not failed, it takes several minutes to schedule the pod on the affected nodes. Cause: * Unclear, but it seems periodic ADEI cron jobs causes the issue. @@ -28,7 +29,8 @@ Rogue network interfaces on OpenVSwitch bridge Solutions: - * According to RedHat the temporal solution is to reboot affected node (not helping in my case). The problem + * According to RedHat the temporal solution is to reboot affected node (just temporarily reduces the rate how + often the new spurious interfaces appear, but not preventing the problem completely in my case). The problem should go away, but may re-apper after a while. * The simplest work-around is to just remove rogue interface. They will be re-created, but performance problems only starts after hundreds accumulate. diff --git a/docs/troubleshooting.txt b/docs/troubleshooting.txt index 9fa6f91..ea987b5 100644 --- a/docs/troubleshooting.txt +++ b/docs/troubleshooting.txt @@ -14,7 +14,7 @@ The services has to be running Required Services: - lvm2-lvmetad.socket - lvm2-lvmetad.service - - docker + - docker - it may happen that service is alive according to systemd, but does not respond ('docker ps' timeouts) - NetworkManager - firewalld - dnsmasq diff --git a/setup/configs/openshift.yml b/setup/configs/openshift.yml index 569e554..95ade9f 100644 --- a/setup/configs/openshift.yml +++ b/setup/configs/openshift.yml @@ -5,6 +5,7 @@ ands_openshift_projects: adei: ADEI adai: ADAI bora: Build Once Run Always + wave: Web-based Analysis of Volumes web: Web Sites mon: OpenShift monitoring test: Namespace for testing and prototyping @@ -24,8 +25,9 @@ ands_openshift_roles: adei/admin: csa adei/view: pdv, kopmann adei/kaas-maintain: pdv, kopmann - adai/admin: csa - bora/admin: ntj, katrin + adai/admin: csa, kopmann + bora/admin: csa, ntj, katrin, kopmann + wave/admin: csa, ntj web/admin: kopmann, jonasteufel mon/admin: csa test/admin: csa, ntj, kopmann, katrin diff --git a/setup/configs/security.yml b/setup/configs/security.yml index 8e418f9..2c29c49 100644 --- a/setup/configs/security.yml +++ b/setup/configs/security.yml @@ -25,6 +25,7 @@ ands_openshift_gid_ranges: web: "6200/10" mon: "7000/10" test: "7100/10" + wave: "8000/10" # The default user and group mentioned in some projects ands_openshift_uids: diff --git a/setup/configs/volumes.yml b/setup/configs/volumes.yml index e03002c..cfb838f 100644 --- a/setup/configs/volumes.yml +++ b/setup/configs/volumes.yml @@ -7,6 +7,7 @@ ands_paths: databases: /mnt/databases datastore: /mnt/datastore katrin_data: /mnt/katrin + wave_data: /mnt/wave ands_heketi_domain: servers: "storage_nodes" @@ -30,6 +31,7 @@ ands_storage_domains: temporary: { type: "tmp", mount: "{{ ands_paths.temporary }}", nfs_clients: "{{ ands_nfs_clients }}" } datastore: { type: "data", mount: "{{ ands_paths.datastore }}", nfs_clients: "{{ ands_nfs_clients }}" } katrin_data: { type: "data", mount: "{{ ands_paths.katrin_data }}", nfs_clients: "{{ ands_nfs_clients }}" } + wave_data: { type: "data", mount: "{{ ands_paths.wave_data }}", nfs_clients: "{{ ands_nfs_clients }}" } - servers: "ands_storage_servers" volumes: block: { type: "db", transport: "{{ ands_rdma_support | ternary('rdma', 'tcp') }}" } diff --git a/setup/projects/wave/templates/40-kaas-manager.yml.j2 b/setup/projects/wave/templates/40-kaas-manager.yml.j2 new file mode 120000 index 0000000..b7233ad --- /dev/null +++ b/setup/projects/wave/templates/40-kaas-manager.yml.j2 @@ -0,0 +1 @@ +../../kaas/templates/40-kaas-manager.yml.j2 \ No newline at end of file diff --git a/setup/projects/wave/vars/volumes.yml b/setup/projects/wave/vars/volumes.yml new file mode 100644 index 0000000..3600d29 --- /dev/null +++ b/setup/projects/wave/vars/volumes.yml @@ -0,0 +1,11 @@ +gids: + wave: { id: 8000 } + +extra_volumes: + wave: { volume: "wave_data", path: "/", capacity: "10Ti", write: true } + +files: + - { osv: "wave", path: "/", state: "directory", group: "wave", mode: "02775" } + +#resync: true +#sync_set_gid: katrin diff --git a/setup/users/htpasswd b/setup/users/htpasswd index b7165a4..f211ac8 100644 --- a/setup/users/htpasswd +++ b/setup/users/htpasswd @@ -2,5 +2,5 @@ pdv:$apr1$ACvj6uUa$Nm1Vq8hZq3RzTtaYpAHv01 csa:$apr1$IqEwdnzy$UAdd8ZSFnXommBbj29w3c0 katrin:$apr1$AQIm74Ae$CJWEzUK6jEYSsk28DQ9du0 ntj:$apr1$G5/ThWdp$kFLsj/hO9jIYYP.Zab9kC/ -kopmann:CZFk3ASLX0Vq6 +kopmann:$apr1$jU8jCdPh$u7ZUBiT3gzxlf1xPJl6FI. jonasteufel:$apr1$2dsiiZ1p$Us/5i8DEt9fxeliGy7L6h/ -- cgit v1.2.1