It's mid night in china about 2:00 and I can't sleep. I have a glusterfs 3.3
cluster in production and there're several
hundreds of clients on it. The io load is extremely high 24 hours. So the file
system crush happens frequently in the cluster. About several times a year(I
use xfs
)
When
Hi brian
Thank you very much for your info.
I have already tried io-cache it helps a little but it can't compete with page
cache.
BTW what's the effort if I want to back port fopen keep cache to 3.3?
发自我的 iPhone
在 2013-1-8，23:21，Brian Foster bfos...@redhat.com 写道：
On 01/08/2013 09:49 AM, 符永涛
