Storage
3FS: Some Performance Tests
· β˜• 3 min read
1. Hardware Tests There are two NVMe SSDs (SAMSUNG MZQL27T6HBLA-00A07) and a 3FS cluster made up of two nodes, each with 4 IB ports. 1.1 Single Thread Disk FIO 128 K, read 1 fio -numjobs=1 -fallocate=none -iodepth=2 -ioengine=libaio -direct=1 -rw=read -bs=128K --group_reporting -size=100M -time_based -runtime=30 -name=fio-test -directory=/data/fio 1 Jobs: 1

NFS Over RDMA
· β˜• 5 min read
1. Prerequisites The storage and the nodes that use it form an RDMA network The RDMA devices are configured with IP addresses If you are using Mellanox NICs, add the -with-nfsrdma parameter when installing the driver 1 ./mlnxofedinstall --with-nfsrdma 2. Starting the Server Install dependencies 1 apt install nfs-kernel-server rdma-core -y Load the kernel module 1 modprobe svcrdma Add the port to portlist 1 echo 'rdma 20049' | tee /proc/fs/nfsd/portlist Export directory 1 mkdir /data1/nfs 1 2 3 vim /etc/exports /data1/nfs *(rw,sync,no_root_squash,no_all_squash) Start the NFS service 1 systemctl start nfs-server.

Maintaining JuiceFS Enterprise Edition under Fluid
· β˜• 7 min read
1. Setting Environment Variables 1 2 export NAMESPACE=xxx export PVC=xxx 2. The Dataset Will Not Become Ready 2.1 Fluid Component Problems 1 kubectl -n fluid-system get pod -o wide | grep -v "Running" There may be cases where something did not start up properly. 2.2 Abnormally Terminated Datasets Abnormal resources can cause Fluid resources to restart repeatedly, and manual intervention is required to delete them.

Using Fluid to Access S3 Storage and Performance Testing
· β˜• 2 min read
1. Jindo Mounting S3 Set the environment variables 1 2 3 4 export ENDPOINT=obs.ap-southeast-3.myhuaweicloud.com export BUCKET= export AK= export SK= Create the credentials 1 2 3 4 5 6 7 8 9 10 kubectl apply -f - <<EOF apiVersion: v1 kind: Secret metadata: name: mys3secret type: Opaque stringData: fs.s3.accessKeyId: ${AK} fs.

How to Enable GDS on a GPU Host
· β˜• 8 min read
1. What GDS (GPUDirectStorage) Is GDS lets an RDMA NIC access GPU memory directly, which helps increase the IO bandwidth for GPU applications reading and writing files, reduces IO latency, and lowers their CPU load. Once the client has GDS enabled, files are opened in O_DIRECT mode and the client no longer caches file data.