[Gluster-users] gluster performance

[Bartosz Zięba]

Hi,
Try iperf in TCP mode, because GlusterFS use TCP not UDP.

Best,
Bart

> On 25 Oct 2018, at 09:52, Krishna Verma <kverma at cadence.com> wrote:
> 
> Hi All,
>  
> I have checked the network speed bandwidth from my Gluster Master node to Slave node that I found  957 Mbits/sec. But syncing over the geo replication is too much slow as it took 1.28hrs to sync a 9.8GB of file from master to slave.
>  
> Anyone having any clue to improve the sync speed over geo replication?
>  
> [root at XXXXXX]# iperf -c sj-gluster01 -u -b 1500m
> ------------------------------------------------------------
> Client connecting to sj-gluster01, UDP port 5001
> Sending 1470 byte datagrams, IPG target: 7.84 us (kalman adjust)
> UDP buffer size:  208 KByte (default)
> ------------------------------------------------------------
> [  3] local 172.23.16.38 port 39104 connected with 172.18.33.52 port 5001
> [ ID] Interval       Transfer     Bandwidth
> [  3]  0.0-10.0 sec  1.11 GBytes   957 Mbits/sec
> [  3] Sent 813830 datagrams
> [  3] Server Report:
> [  3]  0.0-10.2 sec   230 MBytes   188 Mbits/sec  12.987 ms 649728/813829 (80%)
> [root at XXXXXX]#
>  
> /Krishna
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> https://lists.gluster.org/mailman/listinfo/gluster-users
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20181025/5415671c/attachment.html>