Hi, we are using fio to generate interleaved I/O, by making several job read from the whole /dev/sda and we are using zoneskip to create the interleave among jobs. But we have bumped into the following issue, shown for just one job. The following command: $ sudo fio --name=reader0 -rw=read --filename=/dev/sda --zonesize=16384 --zonemode=zbd --zoneskip=16384 smalloc: OOM. Consider using --alloc-size to increase the shared memory available. In contrast, if we invoke, sudo fio --name=reader0 -rw=read --filename=/dev/sda --zonesize=16384 --zonemode=strided --zoneskip=16384 (which is ok for our goal at the moment), then we everything seems to work fine. Could you please example me why --zonemode=zbd fails by apparently trying to allocate memory for the whole size of the special file /dev/sda? Is it (strictly) necessary for doing random I/O among zones? Thanks, Paolo
