[Gluster-users] please please please I beg redhat fix file system crush issue for fluster

[yongtaofu]

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 one of the brick file system crush the whole volume collapse. Please don't say there're only few files can't be accessed. I swear to Beijing air the truth is the whole volume collapse and more files can't be accessed if don't handle it. Almost no file can be accessed. Some directory can't be accessed too which make millions of files missing and almost no fops can be performed. If you don't believe in me I have to swear to Beijing air again that I have see it happens several times. It's too expensive for us to restore this kind of failure! I admire redhat works and I hate myself that I don't have the ability to fix it. But I hope one day I can make contribute too.
I have raise this issue before and I see there're updates. But I beg you please raise it's priority! Thank you very much!

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20130202/e55fb737/attachment.html>