Hi guys, I'm testing rbd with fio. I have test it for more than 3 hours, and then it happened to see that fio showing instant iops is 0. then I catch the trace of rbd with blktrace, and found that the kernel worker thread "kworker" is busy with writing meta data to rbd with the flag "WM". I think this may be the cause of fio showing 0 iops. can anyone help me to analyse what the kworker thread is doing now, and how can we avoid or reduce the happening of this situation? I have attach the blktrace file after parsing in the attachment. Hope to get your suggestions. Best Regards -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.ceph.com/pipermail/ceph-users-ceph.com/attachments/20140801/31b20f90/attachment.htm> -------------- next part -------------- A non-text attachment was scrubbed... Name: myrbddata1 Type: application/octet-stream Size: 908859 bytes Desc: not available URL: <http://lists.ceph.com/pipermail/ceph-users-ceph.com/attachments/20140801/31b20f90/attachment.obj>
 |