Search results

Hi Maximiliano, thank you for your advice. i have tested this on our testing cluster (very old hardware, no ssd's...) and... the cluster is gone :( the only thing i changed was the Target Ratio to "1.0" he struggled hard with IO and after 4 days i turned all nodes off. it was not the best...

hi, sorry for my late answer - long work day. at the moment my pool have this config: what will be happen with my ceph storage after change the target ratio to 1? some performance impact?

hi there, thanks for your hint - i changed my post with ceph osd tree and added the code tags - nice feature :) the pool with the small hdds is for testing ONLY and i know about 2/1 and data loss on crash. and here are the output form pveceph pool ls root@pve-hp-01:~# pveceph pool ls...

hi wigor, thanks for your answer. at next time i will be think on code-tags :) at the moment the SSD Pool have 1024 PGs and PVE says it also in "Optimal PGs" the thing is every time i decrease one osd's weight i have more space in this pool - but a few hours later the "new" space is gone...

the hdd osd's are in an separate class-pool. here are the output of "ceph osd df tree" root@pve-hp-01:~# ceph osd df tree ID CLASS WEIGHT REWEIGHT SIZE RAW USE DATA OMAP META AVAIL %USE VAR PGS STATUS TYPE NAME -1 51.27962 - 51 TiB 34...

Hello, maybe often diskussed but also question from me too: since we have our ceph cluster we can see an unweighted usage of all osd's. 4 nodes with 7x1TB SSDs (1HE, no space left) 3 nodes with 8X1TB SSDs (2HE, some space left) = 52 SSDs pve 7.2-11 all ceph-nodes showing us the same like...

hat alles nicht geholfen - wir haben 4 incomplete PGs und bekommen die nicht weg. zudem ist immer noch das "Slow OPS" und keine VM will mehr wirklich arbeiten. wir sind gerade hart am verzweifeln. also - falls hier jemand mit echt guten CEPH Kenntnissen ist - bitte asap melden, gerne dann auch...

Hi, danke für deine schnelle Antwort :) hier dachten wir, dass wir per reweight die OSD's eben vor den 90% retten können. Dennoch sind OSDs mit reweight auf 80 oder 85% nun wieder bei fast 90% - andere dagegen bei 70-80... Hiermit für eine OSD (osd.79) auf 85% ceph osd reweight 79 0.85...

Hi zusammen, wir haben einen PVE Cluster mit 7 Nodes mit CEPH - je Node 8-9 SSDs. Bei einem Node hat der Raid-Controller (ceph läuft nativ, ohne Raid) heute Nacht ein Problem gehabt, dann waren alle OSDs auf einmal weg. Nach neustart der Node ist der RaidController wieder OK und die OSDs sind...

haha - we found it: # pveceph pool destroy cons_level_3 -remove_storages --force and instantly the old pool is gone and all is fine... omg regards Ronny

Hello anybody, today we want to destroy our old CEPH Pool with old SSDs. At first we set all SSDs on this Pool (cons_level_3) to OUT, then STOP, then DESTROY All this SSDs on this Pool have an own replication rule! After that we destroyed the CEPH-Pool - and now the Task stays for about...

wow, cool. do you have any examples for me? What should I pay attention if i will mix it? regards Ronny

Hello, it is possible to use different size and/ or different count of OSDs (Disks) per CEPH Node? example ceph config, every disk have 1TB size Node 1, 1HE hight, all 8 Slots full for CEPH Node 2, 1HE hight, all 8 Slots full for CEPH Node 3, 1HE hight, all 8 Slots full for CEPH Node 4, 2HE...

hi Boris, i'm sorry - we didnt resolve it. we recovered the data from older backups or remote-files. there was an nextcloud storage. we suspect that the issue was the remote backup storage (hetzner storage box) and large files on it. our recommendation is - don't use it on this way. regards...

we had the same problems with server 2012R2 and some old pfsenses. - on pfsenses only move to virtio was needed - on server 2012R2: it is not enough to only re-install the driver and/or move to virtio-card our solution was to remove all network-drivers and network-cards (via proxmox-gui) from...

ah, ok, it runs - but i have to chose "host" as cpu type. thanks a lot :)

thanks for your answer, but in dont know what i have todo.. like that? args: -cpu Nehalem,+pcid,+spec-ctrl,+ssbd,+kvm_pv_unhalt,+kvm_pv_eoi,+nonstop_tsc,enforce,vendor=GenuineIntel

Hello, because of an Performance issue in SAP HANA System we need to add this CPU Flag to our VM: nonstop_tsc i've added this in my vm.conf file but after that the VM had 64kvm CPU without any flags :( OLD cpu: Nehalem,flags=+md-clear;+pcid;+spec-ctrl;+ssbd NEW cpu...

thanks for your answer yes, i think so too - no block storage on it. we had this SSDs on a OpenFiler NAS an with ISCSI connected to PRX-Cluster. Performance bad and high io-delay also... so how can i use it for my cluster? build an OpenNAS and share NFS?

Hi there, we have 15 Consumer Samsung 1TB SSDs (850 and 860 Pro) and dont know how we can use it as well. I tested these SSDs on our 7-Node Cluster in CEPH (3 Nodes got 5 SSDs) and on all 3 nodes the io-delay runs high. my test was to move some VM-Harddisks to this Customer_SSD_Pool, start 3...