Database Administration (MOSC)

MOSC Banner

OS Thread Startup and aioserver issues

edited Jul 9, 2014 5:00AM in Database Administration (MOSC) 6 commentsAnswered
Before I get too deep into this issue, I want to see if anyone has come across anything like this.

System - Upgrading from Power 5 to an IBM Power 6. Main Lpar = 32 CPUs. 376GB memory. 16 HBAs. EMC Vmax dasd. AIX using CIO.

Database = 40 TB datawarehouse. 1.4 billion queries/ month. Limit parallelism to 24 (or 48) threads per query.

Issue (1): When executing parallel queries, the queries will hang with Latch 'query server process' and OS Thread Startup waits. only a single thread is running so it is obiviously slow spawning the parallel threads. However, this could take 5-10 minutes to spawn 20 or so slaves!

Read the os thread caused by DNS config. Does not appear to be the issue. Workaround was to reduce some memory setting. But we are now only using about 25% of the memory (pga and sga combined) . But, things cleared up and parallel slaves spawn now almost immediately and hardly any time is spent of latches. Oracle having issues with big memory?? Thoughts?

Howdy, Stranger!

Log In

To view full details, sign in to My Oracle Support Community.

Register

Don't have a My Oracle Support Community account? Click here to get started.

Category Leaderboard

Top contributors this month

Instructions for posting

×

1. Select a discussion category from the picklist.


2. Enter a title that clearly identifies the subject of your question.


3. In the body, insert detailed information, including Oracle product and version.


Please abide by the Oracle Community guidelines and refrain from posting any customer or personally identifiable information (PI/CI).


Cloud / Fusion customers - Our Cloud community has moved! Please go to Cloud Customer Connect .


New to My Oracle Support Community? Visit our Welcome Center

MOSC Help Center