Hi. Welcome to the club. > > Thanks, wish it filled nice to be welcomed :). Do you mean that you loose the whole file or just the content of the file? > Somehow lately the whole AFR functionality is borked for me. I tried to > reduce everything to the minimum (no performance translators or anything > other not needed) and still I am loosing data. Restarting server and client > can lead to total loss of content for some files in my case. > I don't really know, because the total difference in used space between server 1 and server 2, sometimes reaches more then 50%! Now, I noticed that this might be related to case when there is no space left on the mount point, meaning that GlusterFS is unable to write for some time. Things go downhill from there, and even if the space freed, there is a large difference between server one and server two. Running ls -lR doesn't help at all. The only way to get things back to normal, seems so far to erase all the data, and restart all the servers + client. > > > > 3) Possible memory leak > > > Could you provide valgrind dumps showing where the leaks are occurring? > Good idea - will do. Though I think it mostly related to read-ahead and io threads translators. When I removed the and only left write-behind and cache, things seems to have improved. Regards. -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://zresearch.com/pipermail/gluster-users/attachments/20090331/35463e90/attachment.htm>
