In the extended SQL trace data, you can see exactly which block (file ID
and block ID) each read manipulates. You also can see the ID of the object
being manipulated.
So, you can know exactly which blocks of which objects are being read. All
of them.
Cary Millsap
Method R Corporation
Author of *Optimizing Oracle Performance <http://amzn.to/OM0q75>* and *The
Method R Guide to Mastering Oracle Trace Data, 2nd edition
<http://amzn.to/1U7q8X1>*
On Sun, Mar 11, 2018 at 11:10 AM, Tim Gorman <tim.evdbt@xxxxxxxxx> wrote:
The "db file sequential read" is an index read.
The event "db file sequential read" indicates a single-block random-access
synchronous read operation on a datafile. Even during indexed scans, db
file sequential reads alternate between index blocks, table blocks, and
undo blocks, and during full table-scans they can start off the operation
by reading segment headers, for example.
On 3/10/18 20:01, Mladen Gogala wrote:
Well, when you have updates, your index block may need to be rebuilt. The
"db file sequential read" is an index read. If the block has been updated,
not only does the block need to be rebuilt, the index block also needs to
be rebuilt. It takes time, even if both are cached in memory. However, the
precise answer to your question is not possible. For the precise answer,
one would need to profile the running code and see exactly where the time
is spent. Only Oracle developers can do that. You may try with strace, to
see whether there is another IO that somehow creeps in.
Regards
On 03/08/2018 09:54 AM, Hameed, Amir wrote:
I am running SLOB to gauge latency of the storage array. When I configure
my test for SELECT only run (no updates), I see average latency of *db
file sequential read* consistently around 3ms. However, as I start to add
UPDATE activity to the run, I see average latency of *db file sequential
read* go up in the vicinity of 5ms. Is the cause of this increase in
latency due to the *commit cleanouts* phenomena? The database version is
12.1.0.2. My DB_CACHE size is set to 128M to drive physical IOs and I am
running my tests with 64 concurrent users.
Thanks,
Amir
--
Mladen Gogala
Database Consultant
Tel: (347) 321-1217
