https://jira.akraino.org This file is an XML representation of an issue en-us 9.4.5 940005 11-04-2023 https://jira.akraino.org/browse/REC-40 Radio Edge Cloud <p>Sequential read/write IOPS</p> <p>Random read/write IOPS</p> <p>Throughput for storage read/write operations</p> <p>Latency for storage read/write operations</p> <p>Consider using Ceph Benchmark Tool (CBT). CBT is a Python tool for building a Ceph cluster and running benchmarks against the cluster. It also provides the test harness for automating various load test utilities such as RADOS bench, FIO, COSBench and MySQL sysbench.</p> <p>FIO can be used to measure sequential and random throughput performance and latency</p> REC-40

Storage rpm test

Sub-task REC-31 Medium To Do Unresolved Indumathi Buddi Deepak Kataria Mon, 26 Aug 2019 18:20:16 +0000 Fri, 4 Oct 2019 14:22:56 +0000 0 2 <p>Here is what we plan to use:</p> <ul> <li><font color="#000000">Kubernetes Pod</font></li> <li><font color="#000000">Persistent Volume (PV) backed by a Ceph RBD image</font></li> <li><font color="#000000">FIO (a block testing tool) on the mounted location of the above PV</font></li> <li><font color="#000000">The parameters of the FIO tests (e.g. block size, threads, etc) would be inputs to the test.   Alternatively, we could set up few sample parameter </font></li> <li><font color="#000000">sets to mimic a few traffic profiles and run those.</font></li> <li><font color="#000000">The FIO results could then be compared baseline numbers to determine whether it is passes.</font></li> <li><font color="#000000">FIO will be used to measure sequential and random throughput performance and latency</font></li> </ul> <p><font color="#000000"> </font></p> <p>Elasticsearch uses the host path /var/log/elasticsearch to store its data.</p> <p> </p> <p>About E2 Termination, I believe that's out of REC scope.</p> <p><font color="#000000"><b>Logging:</b> Each component writes log files (<b>sequential write</b>) and REC has a fluentd configured to send the data to Elastic Search. How does Elastic Search uses storage internally (sequential/random)?</font></p> <p><font color="#000000"><b>Redis DB</b>: in memory only, does not use disk at all</font></p> <p><font color="#000000"><b>Message archiving</b>: There is a plan that the E2 Termination writes all the messages that pass through it to disk (<b>sequential write</b>) and periodically these files would be copied either to another local server or send to Research Data Lake using Data Router.</font></p> <p><font color="#000000">So, except for whatever Elastic Search does internally, all the writes and reads would be sequential and each data item would be written and read one time (50/50).</font></p> <p><font color="#000000">As far as throughput versus latency, throughput would be more important. We can test IOPS for 4KB average size. Throughput in MB/s=Average IO size x IOPS. Each IO request will take time to complete, this is the average latency, measured in milliseconds (ms).</font></p> <ol> <li><font color="#000000">One IOPS test case can be: 4KB block size, sequential read/write (50/50)</font></li> <li><font color="#000000">Second IOPS test case can be: 4KB block size, random read/write (70/30)</font></li> </ol> <p>This seems like a pure performance test case. Are there any targets for the measured properties?</p> Development Rank 0|i001gf: