> FWIW, I'd be for trying to take periodic samples of actual IO happening > on the drive during operation. Thumbs up for this. Using actual user-IO in a proper way will provide real-life information not polluted by the artificial nature of workloads of generic benchmark procedures. As far as I know OSDs already collect a lot of counters and only little might be needed to track certain characteristic averages/rates over time. Best regards. ================= Frank Schilder AIT Risø Campus Bygning 109, rum S14 _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |