Re: BlueStore with v11.1.0 Kraken

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



> Op 22 december 2016 om 14:36 schreef Eugen Leitl <eugen@xxxxxxxxx>:
> 
> 
> Hi guys,
> 
> I'm building a first test cluster for homelab, and would like to start
> using BlueStore since data loss is not critical. However, there are
> obviously no official documentation for basic best usage online yet.
> 

True, so my answer here isn't 100% complete either.

> My original layout was using 2x single Xeon nodes with 24 GB RAM each
> under Proxmox VE for the test application and two metadata servers, 
> each as a VM guest. Each VM woud be about 8 GB, 16 GB max.
> 

The VM size doesn't really matter for BlueStore nor did it for XFS/FileStore.

> Ceph OSD etc. was 7x dual-core Opteron with 8 GB RAM each, and some
> 2x2 to 2x1 TB SATA drives. Current total is 24 TB SATA, 56 GB RAM.
> 
> Each node has 4x Gbit NIC, so I have two local storage networks each on a
> dedicated unmanaged switch and two NICs serving the app data, on two
> dedicated managed ones. I guess up to 0.6 GB/s worst case is more than
> enough for dual core Opterons, especially with crappy (nVidia/Broadcom) NICs.
> 
> Question is, how is Bluestore changing the picture?
> 

No, network doesn't change for BlueStore.

> E.g. looking at http://www.slideshare.net/sageweil1/bluestore-a-new-faster-storage-backend-for-ceph-63311181
> They say things like metadata is all in memory. 
> So how much GB RAM for each TB disk then? I'm assuming 4 MB object size as default.
> 
> Slide 23 has four example cases. Assuming I have only two HDDs I 
> guess my options are small partition for Linux boot/root, and the 
> rest as raw partitions for rocksdb and object data. I could boot 
> the nodes from an USB memory stick, of course. Would that work, 
> or too much I/O still on the slow USB device?
> 

As long as you disable logging you could run on USB sticks.

> Before I was limited due to 8 GB RAM to max 8 TB/node, 
> so e.g. 2x 4 TB disks. Is this still the case for Bluestore?
> 

Well, the 1GB per 1TB was mainly a PG concern. Storing more data doesn't persé use more memory. Placement Groups are the main CPU and Memory consumers.

Since BlueStore hasn't been used that much the only output comes from devs and what they have tested.

What I'd say, more memory is always better. When you have memory to spare, put it in there.

Wido

> Thanks!
> 
> Regards,
> Eugen 
> _______________________________________________
> ceph-users mailing list
> ceph-users@xxxxxxxxxxxxxx
> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com




[Index of Archives]     [Information on CEPH]     [Linux Filesystem Development]     [Ceph Development]     [Ceph Large]     [Linux USB Development]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]     [xfs]


  Powered by Linux