List of Contributions

v3700 is just a compact SVC cluster. If you join the node to an existing cluster, the code should be copied from the live/pre-existing node(s). You can also use the /service GUI to load specific code levels, reload code from the live node, eject and join nodes to the cluster, etc. Each node's own ...

The mappings are not automatically rebalanced between controllers. You can manually change the primary node, and the i/o groups which can access the vdisks. Switching these automatically typically causes an interruption or a pause in I/O which is undesirable. Switching between nodes in the same I/O ...

85Y6052 is a 24x2.5" SAS 6Gbit expansion drawer that belonged to a V7000 Gen 1. It has SAS expanders inside, and does not have a controller. 69Y2921 is an X-Series 24x2.5" SAS 6Gbit expansion drawer that is sold for direct system attachment. It has SAS expanders inside, and does not have a controller. ...

SPP is basically keeping a full copy on-site. It has to do with how the deduplication database is managed. You would get similar space needs in SPE if you used a container pool for landing, and then cloud tiering. Please also note that your bucket/blob storage will have substantial overhead. This ...

TSM/SP is beholden to the latency of the individual sequence of IOs. While you can get 100,000 IOPS, that is in a highly parallel process. An individual IO on NVMe is still going to have a latency somewhere in the 80us range, plus whatever I/O latency there is for reconstruction of the raw data. For ...

Deduplication ratio is similar; however, it is post-processing. So, you ingest, then the data is read, deduplicated, and written out to new volumes. File volume RECLAIM STGPOOL will happen. Compression is an issue though. Either you use client side compression, and give up some of your deduplication ...