Netapps vs EMC -- db file scattered read

From: <jmourik_at_yahoo.com>
Date: 20 Jan 2005 01:41:10 -0800
Message-ID: <1106214070.081684.277660@z14g2000cwz.googlegroups.com>

Don't know if anybody here has seen this happening on NetApps storage.

I ran query "select count(*) from jvmo_test;" on three of our databases, ids9i, nyisos (both on NetApp) and gmps (on EMC). The tables are all the same, build from the sam base table and then rows copied until there are 1,600,000...
I don't understand why the wait times for NetApps are so much higher than for EMC. Take a look at these results:

IDS9I - NetApps

table info, blocksize = 8K:

BYTES            BLOCKS        EXTENTS
351010816        42848           2678

call     count       cpu    elapsed       disk      query    current

rows
------- ------ -------- ---------- ---------- ---------- ----------

---

Parse 1 0.00 0.00 0 0 0 0
Execute 1 0.00 0.00 0 0 0 0
Fetch 2 6.08 53.41 42842 43115 0 1
------- ------ -------- ---------- ---------- ---------- ----------

---

total 4 6.08 53.41 42842 43115 0 1

Elapsed times include waiting on following events:

Event waited on                   Times   Max. Wait  Total Waited


------------------------------   Waited  ----------  ------------

SQL*Net message to client             2        0.00          0.00
db file scattered read             2678        0.10         50.00

NYISOS - NetApps
table info, blocksize = 16K:

BYTES            BLOCKS        EXTENTS
345112576        21064           2633


call     count       cpu    elapsed       disk      query    current

rows
------- ------ -------- ---------- ---------- ---------- ----------

---

Parse 1 0.00 0.00 0 0 0 0
Execute 1 0.00 0.00 0 0 0 0
Fetch 2 6.15 61.62 17628 21329 0 1
------- ------ -------- ---------- ---------- ---------- ----------

---

total 4 6.15 61.62 17628 21329 0 1

Elapsed times include waiting on following events:

Event waited on                  Times   Max. Wait  Total Waited


------------------------------  Waited  ----------  ------------

db file sequential read           1142        0.06          7.31
db file scattered read            2286        0.09         52.29

GMSP - EMC
table info, blocksize = 8K:

BYTES            BLOCKS        EXTENTS
348913664        42592           2662

call     count       cpu    elapsed       disk      query    current

rows
------- ------ -------- ---------- ---------- ---------- ----------

---

Parse 1 0.00 0.01 0 0 0 0
Execute 1 0.00 0.00 0 0 0 0
Fetch 2 6.77 6.95 42574 42587 273 1
------- ------ -------- ---------- ---------- ---------- ----------

---

total 4 6.77 6.96 42574 42587 273 1

Elapsed times include waiting on following events:

Event waited on                    Times   Max. Wait  Total Waited


-------------------------------   Waited  ----------  ------------

SQL*Net message to client              2        0.00          0.00
db file scattered read              2663        0.02          3.57

EMC is more than 7 times faster than NetApps! db file scattered read is way too high for Netapps....

Any ideas?

Thanks for any info, jan Received on Thu Jan 20 2005 - 03:41:10 CST