search for: nrfiles

...I am running two fio processes (one per file, so only 2 out of 8 files are involved) with 8 threads each like this: fio --thread --directory=/btrfs/subvol1 --rw=randwrite --randrepeat=1 --fadvise_hint=0 --fallocate=posix --size=1000m --filesize=10737418240 --bsrange=512b-64k --scramble_buffers=1 --nrfiles=1 --overwrite=1 --ioengine=sync --filename=file-1 --name=job0 --name=job1 --name=job2 --name=job3 --name=job4 --name=job5 --name=job6 --name=job7 The files are preallocated with fallocate before the fio run. Mount options: noatime,nodatasum,nodatacow,nospace_cache Can somebody please advise on how...

I generally run TestDFSIO for Hadoop running on HDFS as shown: hadoop jar hadoop-*test*.jar TestDFSIO -write -nrFiles 10 -fileSize 1000 How to run it on lustre filesystem? -------------- next part -------------- An HTML attachment was scrubbed... URL: http://lists.lustre.org/pipermail/lustre-discuss/attachments/20130509/821dc4bb/attachment.html

Hi Rob & Mihai, I wrote vhost-nvme patches on top of Christoph's NVMe target. vhost-nvme still uses mmio. So the guest OS can run unmodified NVMe driver. But the tests I have done didn't show competitive performance compared to virtio-blk/virtio-scsi. The bottleneck is in mmio. Your nvme vendor extension patches reduces greatly the number of MMIO writes. So I'd like to push it

Hi Rob & Mihai, I wrote vhost-nvme patches on top of Christoph's NVMe target. vhost-nvme still uses mmio. So the guest OS can run unmodified NVMe driver. But the tests I have done didn't show competitive performance compared to virtio-blk/virtio-scsi. The bottleneck is in mmio. Your nvme vendor extension patches reduces greatly the number of MMIO writes. So I'd like to push it

...o,file=debian.raw,cache=none \ -drive file=nvme.raw,if=none,id=nvme-dev \ -device nvme,drive=nvme-dev,serial=nvme-serial Using "fio": vm # fio -time_based --name=benchmark --ioengine=libaio --iodepth=32 \ --numjobs=1 --runtime=30 --blocksize=4k --filename=/dev/nvme0n1 \ --nrfiles=1 --invalidate=1 --verify=0 --direct=1 --rw=randread I get about 20k IOPs with the original code and about 85k IOPs with the vendor extension changes applied (and running a vendor extension supporting 3.14 based guest kernel). Signed-off-by: Mihai Rusu <dizzy at google.com> [fixed for a mer...