From: Ricardo J. B. <ric...@do...> - 2017-02-06 18:38:32
|
El Lunes 06/02/2017, Jakub Kruszona-Zawadzki escribió: > On 2 Feb, 2017, at 19:28, WK <wk...@bn...> wrote: > > We have a project where we have a machine that is talking to a MFS3 > > cluster for two purposes > > > > The main purpose is a very busy file repo, we are also copying off large > > archives in to a backup folder 2-3 times a day. > > > > We want to reduce latency on the files as the client is somewhat picky > > and want to avoid the archive dump slowing things down. > > > > What is the best way to handle that > > > > A) one mfsmount to /mfs3mnt > > > > with subdirectory /mfs3mnt/backup & /mfs3mnt/files > > > > > > b) Two seperate mfsmounts on the client > > > > /mfs3backup > > > > and > > > > /mfs3files > > > > Security isolation is not a concern. > > > > So what would provide the best performance? or does it really matter? > > > > The connection would be 1GB ethernet with jumbo frames. > > > > > > Note we are considering that with two mounts we could use seperate > > ethernet cards, however its not an option immediately as the host has > > used up all the ports with other needs. > > > > If you feel strongly that would make a difference then I can push a host > > migration on the client. > > > > And of course 10G is getting reasonable, but still not a default on our > > somewhat older kit. > > > > -wk > > The main difference will be cache. In case of one mount you will have one > cache shared between users ('files' folder) and your backup ('backup' > folder). In case of two mounts you will have two independent caches. I do > not expect big difference but still it may improve a little bit. Also, copying/moving files between mountpoints is going to be slower than if you have files and backup on the same mountpoint. PS: Jakub, is this your signature or something went wrong?: "Segmentation fault (core dumped)" Cheers, -- Ricardo J. Barberis Senior SysAdmin / IT Architect DonWeb La Actitud Es Todo www.DonWeb.com _____ |