Exadata-Specific Metrics in AWR

After our ExCite review earlier in the year, I managed to borrow/steal the following metrics to determine IOPS, HCC efficiency and SmartScan efficiency.

I’m a bit wobbly on the SmartScan formula, so if anyone has any corrections, please feel free to offer them 🙂

IOPS

% of all physical reads served by the FlashCache
— physical read total IO requests / cell flash cache read hits

adjusted total read requests
– we had to double this because WE are using 16k blocks and IOPS is based on 8k blocks
— (physical read total IO requests – cell flash cache read hits) * 2

adjusted total write requests
– we had to double this because WE are using NORMAL redundancy on the ASM diskgroup
— physical write total IO requests * 2

I/O operations
– per second if we take the “Per Second” metric in AWR
— “adjusted total read requests” + “adjusted write read requests”

N.B. an X3-2 quarter-rack has an IOPS rating of 6,000 – I discovered this when the ExCite experts pointed it out (and we had exceeded it).

EHCC

average number of rows that each compression unit contains – effectiveness of what the data we do compress with EHCC
— EHCC total rows for decompression / EHCC CUs decompressed

SmartScan

total physical IO bytes saved by SmartScan
— cell physical IO bytes eligible for predicate offload – cell physical IO interconnect bytes returned by smart scan

ratio of SmartScan efficiency
— cell physical IO interconnect bytes returned by smart scan / (cell IO uncompressed bytes + cell physical IO bytes saved by storage indexes)

Advertisements
Tagged , , , , , , ,

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: