|To:||Steve Lord <lord@xxxxxxx>|
|Subject:||Re: Shared Devices with XFS|
|From:||Frank Hellmann <frank@xxxxxxxxxxxxx>|
|Date:||Thu, 27 May 2004 14:56:52 +0200|
|Cc:||XFS List <linux-xfs@xxxxxxxxxxx>|
|Organization:||Optical Art Film- und Special-Effects GmbH|
|User-agent:||Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.2.1) Gecko/20030225|
Steve Lord wrote:
Frank Hellmann wrote:
There is a good chance what will happen here is your read-only nodes will crash at some point, or at least decide the fs is corrupted and needs to be shutdown. The read only nodes will have a lot of metadata in cache, and will not know that it is stale and should be refreshed from disk. Once they get a mix of inconsistent metadata all bets are off. You will tend to see stale data as well, and things which the read/write node has put into the filesystem may not show up for a while.
So, there is no way of striktly working read-only of disk without caching/relying on the meta-data locally.
Actually, this is fine for our application. We aquire a lot of hires 50MB sized images that are not changed after that. The clients work on proxy images that they generate locally of these hires images. So during aquisition I can unmount all clients and do the r/w operations and after that mount it on all clients as read-only.
That is still better then putting the arrays directly on the single clients...
Finally, if two nodes both need to read the same data at the same time, they issue scsi commands to the device, and one gets to wait for the other to complete - but at least the second one gets to use cache on the device.
|<Prev in Thread]||Current Thread||[Next in Thread>|