Operating System - HP-UX
1748255 Members
4021 Online
108760 Solutions
New Discussion юеВ

Re: Degraded backup and Oracle dump performance after 11.23 to 11.31 upgrade

 

Re: Degraded backup and Oracle dump performance after 11.23 to 11.31 upgrade

So /exp is presumably the FS you are writing to... what about the FS you are reading _from_? How do you know that is still performing?

From what I can see here:

-first point is you are still using legacy DSFs in /dev/[r]/dsk - if you are migrated to 11.31, you should really start using the new agile DSFs in /dev/[r]disk/ - I don't think will have any impact on performance but is good practice

- its also not good practice to have VGs with only one LUN, as this absolutely guarantees you will only ever hit one controller on the EVA - you should always have at least 2 LUNs in a VG and then strip across those so you get the benefit of both controllers - but again, if that's how things were setup before its not the source of your problem

So as I said at the start of my post - checkout the config of the filesystems you are reading data off...

I am an HPE Employee
Accept or Kudo
Martin Roende
Advisor

Re: Degraded backup and Oracle dump performance after 11.23 to 11.31 upgrade

The database we are reading from :
They are the same FS setup, but having 3 volume groups and several Luns..

Do you want to see the specifics ..

Yes I know about the DSF names...

But as you say, no impact, and therefore no focus right now.

regards Martin ..
TwoProc
Honored Contributor

Re: Degraded backup and Oracle dump performance after 11.23 to 11.31 upgrade

Is one of the servers set to use ILM and maybe the other a percentage of memory as SLM ? Testing has shown that it does make a difference. A small SGA that would fit into the memory of a single cell board in your server would be fine as configured SLM, but only if you're OK with just using the CPUs in a single cell. Meaning; most times you'll want to use ILM at 100% for an Oracle Database server of any signifigant size, and by that, I mean one that is to primarily set up to use most of the server that you've stood up.

So, my point is to make sure you've reviewed this setting on both servers.

Look for the paper from HP titled
"Running Oracle Database 10g or 11g on an HP-UX ccNUMA-based server", subtitled "Updated for Oracle 11gR2 and HPUX 11i v3.

The bottom of the documents id info:
4AA2-4194ENW, Created January 2009; Updated September 2010, Rev. #1




We are the people our parents warned us about --Jimmy Buffett
Martin Roende
Advisor

Re: Degraded backup and Oracle dump performance after 11.23 to 11.31 upgrade

Thanks , for your answers so far ....
suggestions are still welcome.
STATUS.:
We still have the same problem.

The latest action, was to follow the advice on the EVA side, for the /exp mount point, without any improvement in dump / backup time.

Right now I will start a formal HPUX case at the call logging facility, and eventually post any results here.

The customer is still suffering backup time into produktion time in the morning (up until 11:00AM)

Regards Martin R├Г┬╕nde Andersen
chris huys_4
Honored Contributor

Re: Degraded backup and Oracle dump performance after 11.23 to 11.31 upgrade

Hi Martin,

Did you setup, both the "hp-ux 11.23" rx6600 and the new "hp-ux 11.31" rx6600 ?

Anyway, show us a sar -d 1 100 of the "before 24h00 backup" on both systems i.e of both the "RMAN backup BEFORE:" and the "RMAN backup AFTER:" and this taken at the same time, i.e. f.e. when the backup was allready running for 30 minutes.

Greetz,
Chris
Martin Roende
Advisor

Re: Degraded backup and Oracle dump performance after 11.23 to 11.31 upgrade

Update ..

I have testet the mount options for /exp.
mincache=direct,convosync=dir
ect with no change in the behaviour described above.

I have opened a HPUX sw call at HP

Regards Martin R├Г┬╕nde Andersen
Martin Roende
Advisor

Re: Degraded backup and Oracle dump performance after 11.23 to 11.31 upgrade

Support suggestion is to add patches:

PHKL_40627 11.31 Buffer cache cumulative patch
PHKL_39594 11.31 vfs_bio QoS patch

PHKL_39594 was added when we upgraded to 11.31 Sep09.

PHKL_40627 , requires reboot, and I have requested a service window at customer. Presumeably, I will get one the 15-oct--2010.

I'll be back with results then.

Regards Martin R├Г┬╕nde Andersen

PS, in the meantime I will change all volume groups to "Persistant DSF" (/dev/disk/disk###), and no pvlinks (Alternate Link ) in vg definitions.
Martin Roende
Advisor

Re: Degraded backup and Oracle dump performance after 11.23 to 11.31 upgrade

To Chris ..
I can dig out 1 minute interval glance outputs, from BEFORE (11.23) and AFTER (11.31) , will that satify your request. ?

rgds Martin R. A.
chris huys_4
Honored Contributor

Re: Degraded backup and Oracle dump performance after 11.23 to 11.31 upgrade

Hi Martin,

> I can dig out 1 minute interval glance
> outputs, from BEFORE (11.23) and AFTER
> (11.31) , will that satify your request. ?
No. ;)

Greetz,
Chris
Martin Roende
Advisor

Re: Degraded backup and Oracle dump performance after 11.23 to 11.31 upgrade

Chris ..
I will make a "sar -d 1 100" for you on 11.31, tonight.

Martin