No, is real speed. From any computer linux or esxi if I write via NFS with dd utility I have this speed. But if I try to write to one raw file like esxi does in vmdk, than the speed drops to 20-40mb/s. So my issue is low speed when I write into raw image file (using losetup and DD on linux , or esxi vmdk - vm guest)
On Friday, October 16, 2015 8:31 PM, Alastair Neil <ajneil.tech@xxxxxxxxx> wrote:
is that a typo 120mb/s? Is this volume replica 2 or distributed or both?
On 16 October 2015 at 08:05, Kandalf ® <tinuro@xxxxxxxxx> wrote:
Hi,I have 2 server with centos 7 and I want to make a replicate storage cluster for the esxi.In both server I have 4 disk in raid 5 mdadm. The write speed on that device is ~250-300MB/s all the time.I create xfs file system on the mdadm and I exported that gluster volume via native fuse nfs v3 to the esxi.Read seed is great but when I try to write to the guest vms I see 20-40MB/s only. I try the test also with gluster distributed with only one brick to one server. If I take one dd write from esxi to the cluster I receive 120mb/s the full ethernet link speed. I also try to mount to linux that volumes and try dd write and the write speed is 120mb/s.But if I try to mount an raw file image with losetup, or use vmdk files, and if I write to them, the speed is 20-40MB/s and I see 12 load on linux.Can someone help me?Thanks!
_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://www.gluster.org/mailman/listinfo/gluster-users
_______________________________________________ Gluster-users mailing list Gluster-users@xxxxxxxxxxx http://www.gluster.org/mailman/listinfo/gluster-users
