I’ve been doing some performance benchmarks on our exadata box specifically focusing on the performance of the smart flash cache. I found that even if I switched the CELL_FLASH_CACHE storage setting to NONE, the flash cache will still keep cached blocks in flash and would therefore give me artificially high values for “cell flash cache read hits” statistic when I set CELL_FLASH_CACHE back to DEFAULT or KEEP. What I needed was a way to flush the Exadata flash cache.
Unfortunately there doesn’t seem to be a good way to flush the flash cache – no obvious CELLCLI command. Maybe I’ve missed something, but for now I’m dropping and recreating the flash cache before each run.
Luckily the dcli command lets me drop and recreate on each cell directly from the database node and even sets up passwordless connections. Here’s how to do it.
Firstly, create a script that will drop and recreate the flash cache for a single cell:
$ cat flushcache.sh
create flashcache all;
Now, use ccli to execute that on each cell node (I have three named exa1cel01,exa1cel02,exa1cel03:
$ dcli -c exa1cel01,exa1cel02,exa1cel03 --serial -k -l userid -x flushcache.sh
The “-k” option copies the ssh key to the cell nodes which means that after the first execution you’ll be able to do this without typing in the password for each cell node. The “—serial” option makes each command happen one after another rather than all at once – you probably don’t need this…
Anyone know a better way to flush the Exadata flash cache?