Re: [ceph-users] Ceph OSDs advice

Dear John, Thank for your respone. My cluster have 4616 pgs and 13 pools show as below: in which default.rgw.buckets.data is erasure pool with config: + pg_num=pgp_num=1792 + size=12 + erause-code-profile: directory=/usr/lib64/ceph/erasure-code k=9 m=3 plugin=isa

Re: [ceph-users] Ceph OSDs advice

You should subtract buffers and cache from the used memory to get a more accurate representation of how much memory is actually available to processes. In this case that puts you around 22G of used - or a better term might be unavailable memory. Buffers and cache can be reallocated when needed -

Re: [ceph-users] Ceph OSDs advice

Hi Sam, Thank for your reply. I use BTRFS file system on OSDs. Here is result of "*free -hw*": total used freeshared buffers cache available Mem: 125G 58G 31G1.2M3.7M 36G 60G and "*ceph df*":

Re: [ceph-users] Ceph OSDs advice

Hi Khang, What file system do you use in OSD node? XFS always use Memory for caching data before writing to disk. So, don't worry, it always holds memory in your system as much as possible. 2017-02-15 10:35 GMT+07:00 Khang Nguyễn Nhật : > Hi all, > My ceph

[ceph-users] Ceph OSDs advice

Hi all, My ceph OSDs is running on Fedora-server24 with config are: 128GB RAM DDR3, CPU Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz, 72 OSDs (8TB per OSD). My cluster was use ceph object gateway with S3 API. Now, it had contained 500GB data but it was used > 50GB RAM. I'm worry my OSD will dead if i