Arnold, I would love to see the numbers you get for dbench....as I have been doing exstensive testing with iozone and would like to be able to compare numbers to see that we are coming to the same conclusions. If you would like to see the basics of what I have been testing please look at http://community.gluster.com and look for the performance question. You can add your information there as well so we have it documented for easy look up by others. If there is anything I can to do help out with your testing please let me know. Bryan -----Original Message----- From: gluster-users-bounces at gluster.org [mailto:gluster-users-bounces at gluster.org] On Behalf Of Brian Candler Sent: Monday, February 13, 2012 8:13 AM To: Arnold Krille Cc: gluster-users at gluster.org Subject: Re: Performance question On Mon, Feb 13, 2012 at 03:07:53PM +0100, Arnold Krille wrote: > > If I understand it right (and I'm quite new to gluster myself), > > whenever you do a read on a replicated volume, gluster dispatches > > the operation to both nodes, waits for both results to come back, > > and checks they are the same (and if not, works out which is wrong > > and kicks off a self-heal operation) > > > > http://www.youtube.com/watch?v=AsgtE7Ph2_k > > > > And of course, writes have to be dispatched to both nodes, and won't > > complete until the slowest has finished. This may be the reason for > > your poor latency. > > I understand that writes have to happen on all (running) replicas and > only return when the last finished (like the C-protocol with drbd). > But reads can (and should) happen from the nearest only. Or from the > fastest. With two nodes you can't decide which node has the 'true' > data except to check for the attributes. The attributes say which was written most recently, and (as I understand it) that information is used to decide which is the correct one. > NFS on these nodes is limited by the Gigabit-Network-Performance and > the disk and results in min(120MBit, ~100MBit) from network and disk. > But I will run dbench on the nfs shares (without gluster) this evening. Yes, I think a useful comparison would be: * NFS * Gluster with single disk volume [or distributed-only volume] * Gluster with replicated volume [or replicated/distributed volume] Using the same dbench parameters in each case, of course. Regards, Brian. _______________________________________________ Gluster-users mailing list Gluster-users at gluster.org http://gluster.org/cgi-bin/mailman/listinfo/gluster-users NOTICE: This email and any attachments may contain confidential and proprietary information of NetSuite Inc. and is for the sole use of the intended recipient for the stated purpose. Any improper use or distribution is prohibited. If you are not the intended recipient, please notify the sender; do not review, copy or distribute; and promptly delete or destroy all transmitted information. Please note that all communications and information transmitted through this email system may be monitored by NetSuite or its agents and that all incoming email is automatically scanned by a third party spam and filtering service.
