05-09-2008
Hi,
yeah seems pretty similar to what we are always getting from engineering ... so after having tuned a couple of 100 lpars - most of them DB boxes - I would go for following values I think ...
vmo -p -o minperm%=5
vmo -p -o maxperm%=90
vmo -p -o maxclient%=90
vmo -p -o maxperm%=80
vmo -p -o minfree=960
vmo -p -o maxfree=1088
vmo -p -o lru_file_repage=0
vmo -p -o lru_poll_interval=10
ioo -p -o j2_nBufferPerPagerDevice=1024 (if not sufficient you can go upwards 256-wise - but carefully)
ioo -p -o hd_pbuf_cnt=1024 - you can go upwards 256-wise
ioo -p -o numfsbufs=1536 (can be raised up to 2048 if needed)
ioo -p -o pv_min_pbuf=1024 (you can play here up to 1536 but carefully)
ioo -p -o j2_maxRandomWrite=32 - needs monitoring but you can go up to 128 in particular cases
ioo -p -o maxrandwrt=32
ioo -p -o j2_maxPageReadAhead=128
ioo -p -o maxpgahead=16
no -p -o tcp_sendspace=262144
no -p -o tcp_recvspace=262144
no -p -o udp_sendspace=65536
no -p -o udp_recvspace=655360
if you are running cio you can even amend
ioo -p -o lvm_bufcnt=16
But please be aware - all these values are 'best practices' but every system is different, every workload, every query. What can be really great on one system can cause a huge performance impact on another one ... so keep on monitoring.
What you have to avoid are the real problems :
fi fo pi po fr sr in sy cs us sy id wa
41 196 8 0 0 0 1110 29968 10573 17 10 70 3
75 213 11 0 0 0 1043 32556 13921 16 14 62 7
22 74 85 0 0 0 740 57171 6965 21 5 68 6
60 151 99 0 0 0 434 46722 7054 31 11 47 11
96 230 88 0 0 0 1351 32595 11736 19 10 63 8
that means your box is paging out computational pages - so you should fix this at the earliest
vmo -p -o lru_file_repage=0
72.5 numperm percentage
vmo -p -o minperm%=5
vmo -p -o maxperm%=90
vmo -p -o maxclient%=90
vmo -p -o maxperm%=80
4018 pending disk I/Os blocked with no pbuf
48890 paging space I/Os blocked with no psbuf
2740 filesystem I/Os blocked with no fsbuf
110 client filesystem I/Os blocked with no fsbuf
89345 external pager filesystem I/Os blocked with no fsbuf
with
ioo -p -o j2_nBufferPerPagerDevice=1024
ioo -p -o hd_pbuf_cnt=1024
ioo -p -o numfsbufs=1536
ioo -p -o pv_min_pbuf=1024
and afterwards you might even see a few memory pools instead of
0 memory pools
and the rest of the suggested values should at least be beneficial for performance ... and please dont make the mistake to think if a box is running cio there is no filecaching needed. There is ... depending on the amount of processes connecting on the database from any given application this can be immense. And do yourself a favour - put redo-logs into a separate filesystem with (smaller) blocksize of 512 ...
Rgds
zx
10 More Discussions You Might Find Interesting
1. AIX
Hi,
how can I find out how many memory (physical and virtual) a thread uses at the moment? I know how to find out the Thread-ID, but not how to monitor it...
We use AIX 4.3.3 at th emoment.
Please help, I am stuck :confused: !! (0 Replies)
Discussion started by: Fong
0 Replies
2. HP-UX
I want to check the memory usuage on the HP-UX box.
print_manifest : gave me the information of the system configuration
and came to know that we have 8GB of ram.
But on runtime I want to know what is the memory left.
Iam new to HP-UX and I would appreciate if some one can assist me on... (2 Replies)
Discussion started by: siebeladmin
2 Replies
3. Solaris
hi
pmap, prstat and ps gives the RSS which is shared memory.
I need to know the consumption of real memory. how to do that?
thx (4 Replies)
Discussion started by: melanie_pfefer
4 Replies
4. Programming
Hi,
my C++ program does some memory consuming tasks and runs several minutes.
During execution time, I want to print information on the current memory consumption and peak memory consumption of my program into a logfile.
How can I retrieve this information, i.e. which functions are available... (0 Replies)
Discussion started by: DarthVader77
0 Replies
5. AIX
Hi,
monitor memory usage on AIX machine on any day of the week from 3:00 PM ET to 5:00 PM ET -
Povide min and max memory consumption.
Determine if all of the available memory is visible to the operating system. If it is not, determine the amount of memory which may be allocated to the... (3 Replies)
Discussion started by: Rookie_newbie
3 Replies
6. UNIX Desktop Questions & Answers
Hi All
I am new to UNIX ,can any one please help in finding MEMORY CONSUMPTION of VLC when i use it as Streaming Server.
I need to log the memory consumption for atleast 10 hours.
Can any one help me in finding this Please (1 Reply)
Discussion started by: ravikanth17
1 Replies
7. UNIX for Advanced & Expert Users
Hello,
we are using AIX 6.1
On our AIX 6.1 server there are two instance of Oracle, a Websphear, a Java application and informatica are running. Can I find out how much memory each of these are consuming?
Thanks, (1 Reply)
Discussion started by: AIX_DBA
1 Replies
8. HP-UX
Hi,
Can some one please tell me how do I generate a report of the Memory Consumption over a time period:
HP-UX B.11.31 U ia64 0440531406 unlimited-user license
I normally use glance to monitor memory in run time.
Note: I do not have root privileges.
Thanks
Danish
... (5 Replies)
Discussion started by: danish0909
5 Replies
9. HP-UX
Dear All,
I want to find out top 15 memory consumption processes in HP UX. Can anyone give me any idea about it?
Kauser (2 Replies)
Discussion started by: makauser
2 Replies
10. HP-UX
I want to obtain memory consumption history on a HPUX machine.
I know I can access data from the last week with sar
sar -f /var/adm/sa/sa14
I do not know how to get memory usage with sar.
Are there any other ways?
thank you (3 Replies)
Discussion started by: black_fender
3 Replies
LEARN ABOUT DEBIAN
xfs_estimate
xfs_estimate(8) System Manager's Manual xfs_estimate(8)
NAME
xfs_estimate - estimate the space that an XFS filesystem will take
SYNOPSIS
xfs_estimate [ -h? ] [ -b blocksize ] [ -i logsize ]
[ -e logsize ] [ -v ] directory ...
DESCRIPTION
For each directory argument, xfs_estimate estimates the space that directory would take if it were copied to an XFS filesystem. xfs_esti-
mate does not cross mount points. The following definitions are used:
KB = *1024
MB = *1024*1024
GB = *1024*1024*1024
The xfs_estimate options are:
-b blocksize
Use blocksize instead of the default blocksize of 4096 bytes. The modifier k can be used after the number to indicate multiplica-
tion by 1024. For example,
xfs_estimate -b 64k /
requests an estimate of the space required by the directory / on an XFS filesystem using a blocksize of 64K (65536) bytes.
-v Display more information, formatted.
-h Display usage message.
-? Display usage message.
-i, -e logsize
Use logsize instead of the default log size of 1000 blocks. -i refers to an internal log, while -e refers to an external log. The
modifiers k or m can be used after the number to indicate multiplication by 1024 or 1048576, respectively.
For example,
xfs_estimate -i 1m /
requests an estimate of the space required by the directory / on an XFS filesystem using an internal log of 1 megabyte.
EXAMPLES
% xfs_estimate -e 10m /var/tmp
/var/tmp will take about 4.2 megabytes
with the external log using 2560 blocks or about 10.0 megabytes
% xfs_estimate -v -e 10m /var/tmp
directory bsize blocks megabytes logsize
/var/tmp 4096 792 4.0MB 10485760
% xfs_estimate -v /var/tmp
directory bsize blocks megabytes logsize
/var/tmp 4096 3352 14.0MB 10485760
% xfs_estimate /var/tmp
/var/tmp will take about 14.0 megabytes
xfs_estimate(8)