Analog aquisition​, realtime properitie​s and Queue.vi
I want to shift analog sampled data from one loop to another by using Queue
Vi's to process these data parallel.
a) The ReadQueue.vi often stops reading and the programm hangs (but data
aquisition is still in process) - Why?
b) Is this, in general, a good method for parallel processing of sampled
data? The application should have realtime properties.
Thank you for ideas and proposals.
Andreas
Don't have any idea why you are hanging but to answer question b) yes, this is
quite valid. We use this technique for our DAQ applications. The DAQ actually
runs in its own top level that we call the DAQ Server. Then many other client
VIs can be running and all reading the Queue at the same time.
Jim
"A. Liedtke" wrote:
> I want to shift analog sampled data from one loop to another by using Queue
> Vi's to process these data parallel.
>
> a) The ReadQueue.vi often stops reading and the programm hangs (but data
> aquisition is still in process) - Why?
>
> b) Is this, in general, a good method for parallel processing of sampled
> data? The application should have realtime properties.
>
> Thank you for ideas and proposals.
>
> Andreas
Similar Messages
-
When do VI and queue references become invalid?
Hi all,
I have a fairly complicated problem, so please bear with me.
1) I have a reentrant SubVI (let's call it VI "Assign") that has an input cluster of (VI ref, queue ref) (let's call the cluster type "Refs"). If the VI ref is invalid (first execution), the VI ref and queue ref are assigned values and are passed on as an output cluster of same type. (The VI does other things too, but for simplicity only this is important.)
2) The VI that calls VI "Assign" (let's call it VI "Store") is not reentrant and has a local variable of type "Refs" that is wired to the input and output of VI "Assign". This VI effectively stores the references. The references returned by VI "Assign" are always valid right after the call, but after the problem condition described below, they are invalid at the start of all calls before they are passed to VI "Assign".
3) VI "Store" is called by multiple non-reentrant VIs, so the local variables of VI "Assign" retain their values (Has been tested and verified to retain their values). The VI causing the problem in this case is a template VI of which multiple copies are launched (let's call it VI "Template").
The problem is that the moment an instance of VI "Template" is closed, the queue reference becomes invalid, although the actual variant value of the reference remains the same. The VI ref can become invalid or not, depending on small changes, but is always reproducible. I assume there must be some similarity between VI and queue refs. After spending some time researching, the Labview help states for the Open VI Ref component "If you do not close this reference, it closes automatically after the top-level VI associated with this function executes." In this case I assumed it means that the moment the reentrant VI "Assign" finishes, the references will get cleared ?? So I made a non-reentrant VI (let's call it VI "NR Assign") that only assigns values to the references and VI "Assign" now calls this VI (It effectively does what I described VI "Assign" does). I keep this VI alive by using it in a VI which never terminates and since it never terminates, the references should never become invalid. Anyone still following? This didn't solve the problem though. If I reproduce the same scenario using only one instance of the template VI, it works just fine. Furthermore, the VI and queue references are never closed, to aid analysis of the problem. Can anyone shine some light on what happens when a template VI terminates? Could this be the problem?
Unfortunately I cannot include the code.
Thank you whoever is able to make sense of this.
ChristieChristie wrote:
Hi all,
I have a fairly complicated problem, so please bear with me.
1) I have a reentrant SubVI (let's call it VI "Assign") that has an input cluster of (VI ref, queue ref) (let's call the cluster type "Refs"). If the VI ref is invalid (first execution), the VI ref and queue ref are assigned values and are passed on as an output cluster of same type. (The VI does other things too, but for simplicity only this is important.)
2) The VI that calls VI "Assign" (let's call it VI "Store") is not reentrant and has a local variable of type "Refs" that is wired to the input and output of VI "Assign". This VI effectively stores the references. The references returned by VI "Assign" are always valid right after the call, but after the problem condition described below, they are invalid at the start of all calls before they are passed to VI "Assign".
3) VI "Store" is called by multiple non-reentrant VIs, so the local variables of VI "Assign" retain their values (Has been tested and verified to retain their values). The VI causing the problem in this case is a template VI of which multiple copies are launched (let's call it VI "Template").
The problem is that the moment an instance of VI "Template" is closed, the queue reference becomes invalid, although the actual variant value of the reference remains the same. The VI ref can become invalid or not, depending on small changes, but is always reproducible. I assume there must be some similarity between VI and queue refs. After spending some time researching, the Labview help states for the Open VI Ref component "If you do not close this reference, it closes automatically after the top-level VI associated with this function executes." In this case I assumed it means that the moment the reentrant VI "Assign" finishes, the references will get cleared ?? So I made a non-reentrant VI (let's call it VI "NR Assign") that only assigns values to the references and VI "Assign" now calls this VI (It effectively does what I described VI "Assign" does). I keep this VI alive by using it in a VI which never terminates and since it never terminates, the references should never become invalid. Anyone still following? This didn't solve the problem though. If I reproduce the same scenario using only one instance of the template VI, it works just fine. Furthermore, the VI and queue references are never closed, to aid analysis of the problem. Can anyone shine some light on what happens when a template VI terminates? Could this be the problem?
Unfortunately I cannot include the code.
Thank you whoever is able to make sense of this.
Christie
All LabVIEW refnums do get deallocated automatically when the top-level VI in whose hierarchy the refnum was created goes idle (stops executing). You will have to make sure that the creation of a refnum is done inside a VI hierarchy that stays running for the entire time you want to use that refnum.
Rolf Kalbermatter
Message Edited by rolfk on 06-27-2007 11:52 AM
Rolf Kalbermatter
CIT Engineering Netherlands
a division of Test & Measurement Solutions -
Monitoring of remote system's Transactional RFC and Queued RFC
Hello,
In our production system, in rz20- CCMS monitor templates- Communication-Transactional RFC and Queued RFc- outbound queues- Queues otherwise not monitored we can see blocked queues for each client.
System is connected to solution manager and we wish the central auto reaction is implemented in solution manager
However i am unable to find Transactional RFC and Queued RFC for the remote system, they exist only for solution manager itself
Tell me how can i do the central monitoringHello,
First you need to check with your Landscape in solman in order to monitor any kind of activities to do so pls follow these steps.
Go to SMSY in solman under Landscape components>Product systemsselect you satellite system example SAP ECC.
On the main screen you will find client for which you have generated RFC connection. Please check though connection are working fine, Go to edit mode and try to click on generate button there will be a pop-up, which gives a clear picture of RFC connection which already exists, and you can also re-generate this RFC connection by clean it up when you re-generate pls select under Actions after generation assign RFC dest for system monitoring.
But make sure there is no project impact on this RFC, like they are not using any logical components and already have some projects running on this RFC connection.
I would advise you to first you the option of assign and check RFC button which is next to generate icon.
Regards
JUDE -
What is required in the HOST and QUEUE field when ...
Hi
When setting up my printer, i fill the options identical to what follows:
PRINTER: SAMSUNG HOME
DRIVER: GENERAL
BEARER: LPR <-----------------------------( NOT SURE IF IT IS THE CORRECT OPTION TO SELECT )
The following fields appear once LPR is selected:
ACCES POINT : HOME
HOST: WHAT COMES HERE?
USER: SKY00BER
QUEUE: WHAT COMES HERE?
ORIENTATION: PORTRAIT
PAPER SIZE: A4
if it helps, my printer is SAMSUNG CLX-3175FW. It is Wifi Enable and is connected to my HOME acces point.
please do correct me if there has to be changes to the BEARER or anything else.
i could really use some help.
thanks in advanced.sky00ber wrote:
Hi,
What is required in the HOST and QUEUE field when setting a WIFI printer?
When setting up my printer, i fill the options identical to what follows:
PRINTER: SAMSUNG HOME
DRIVER: GENERAL
BEARER: LPR <-----------------------------( NOT SURE IF IT IS THE CORRECT OPTION TO SELECT )
The following fields appear once LPR is selected:
ACCES POINT : HOME
HOST: WHAT COMES HERE?
USER: SKY00BER
QUEUE: WHAT COMES HERE?
ORIENTATION: PORTRAIT
PAPER SIZE: A4
if it helps, my printer is SAMSUNG CLX-3175FW. It is Wifi Enable and is connected to my HOME acces point.
please do correct me if there has to be changes to the BEARER or anything else.
HELP URGENTLY NEEDED!
I'm not sure but I give it a try.Turn your security(WPA/WEP) and Firewall temporarely off. HOST is the IP address of the printer. QUEUE can be YES or a specific amount of prints, like 1,2,3......
If I look at the manual of your printer I see that you can find the IP and MAC addresses in the Network Configuration Report.I don't know what the USER is doing there because if there is a user then there must be a password.
‡Thank you for hitting the Blue/Green Star button‡
N8-00 RM 596 V:111.030.0609; E71-1(05) RM 346 V: 500.21.009 -
Can JMS topics and queues be clustered in a WLS 7.0 Cluster?
We are installing a weblogic 7.0 cluster with 1 admin server and 2 managed
node servers. Two nodes have been clustered. We are at the point where we
need to configure JMS. Has any one implemented JMS in WLS 7 clustered
environment? What are the things to watch out when clustering JMS? Can JMS
topics and queues be clustered?
TIA for any helpful hints and comments.
Regards
"Karim Ali" <[email protected]> wrote:
>> Has any one implemented JMS in WLS 7 clustered
>> environment?
I'm currently working on a project with WLS 7 here at work, involving
the implementation of BEA's JMS Cluster. So far, I really haven't had
many hiccups.
"Karim Ali" <[email protected]> wrote:
>> What are the things to watch out when clustering JMS?
At least in WLS 7, the biggest thing that stands out is the lack of
automatic failover. Also, Message Paging -- make sure you configure
paging high/low thresholds. Or, if you don't wish for it to occur but
can't stop the server (very common these days with SLAs), set that
byte/message high threshold to a very large number (correct me if I'm
wrong, but I believe BEA recommends 2^63 -1).
"Karim Ali" <[email protected]> wrote:
>> Can JMS topics and queues be clustered?
Well, since Topics and Queues are extensions of the
javax.jms.Destination interface, the answer is: Yes!
(SIDE NOTE: most people usually refer to them as a [JMS] "destination"
-- it avoids a lot of conceptual baggage and plus, less typing!)
You'll probably want to see this section of BEA's e-docs:
http://edocs.bea.com/wls/docs70/adminguide/jms.html#config_distributed_destinations
later,
Brian J. Mitchell
BEA Systems Administrator
TRX
Atlanta, GA
email: [email protected]
office: 404-327-7238
mobile: 678-283-6530
-
Message Tracking and Queue Viewer access is denied - Exchange 2010
Hello,
I am experiencing Message Tracking and Queue viewer problems on my exchange server.
Message Tracking problem
When i run message tracking via EMC or powershell, i receive the following error;
Failed to connect to the Microsoft Exchange Transport Log Search server on computer "myserver.mydomain.com.br". Verify that a valid computer name was used and the Microsoft Exchange Transport Log Search service is started on the target computer. The
error message is: "Access is denied".
Exchange Transport Log Search service is confirmed running and have tried by restarting the service
Logon user is a member of Domain Admins, Enterprise Admins and Exchange Organization Administrators
Message Tracking Logs are generated properly
Queue Viewer problem
When i run Queue viewer, i receive the following error;
The Queue Viewer operation on computer "myserver.mydomain.com.br" has failed with exception. The error message is: Access is denied. It was running command.............................................................
My server information are as follow;
4 Exchange Server 2010 sp3
2 Mailbox Server and 2 Hub/CAS
Mail-flow is working fine
What should I grant permission for a group of users can have access to the Message Tracking ?
Regards,Hi!
The group rule was created as described below. The error persists!
[PS] C:\Windows\system32>Get-RoleGroup "Exchange Access Message Tracking" | fl
RunspaceId : 4229f35d-90f1-4c4e-822d-387979921052
ManagedBy : {bancobmg.com.br/Users/Raphael Henrique Duarte Campos}
RoleAssignments : {Message Tracking-Exchange Access Message Tracking}
Roles : {Message Tracking}
DisplayName :
ExternalDirectoryObjectId :
Members : {bancobmg.com.br/Users/Raphael Henrique Duarte Campos}
SamAccountName : Exchange Access Message Tracking
Description :
RoleGroupType : Standard
LinkedGroup :
Capabilities : {}
LinkedPartnerGroupId :
LinkedPartnerOrganizationId :
IsValid : True
ExchangeVersion : 0.10 (14.0.100.0)
Name : Exchange Access Message Tracking
DistinguishedName : CN=Exchange Access Message Tracking,OU=Microsoft Exchange Security Groups,OU=Global,DC=ba
ncobmg,DC=com,DC=br
Identity : bancobmg.com.br/Global/Microsoft Exchange Security Groups/Exchange Access Message Trackin
g
Guid : 0957152d-2073-4f75-b40e-63f45eb20f67
ObjectCategory : bancobmg.com.br/Configuration/Schema/Group
ObjectClass : {top, group}
WhenChanged : 06/02/2014 16:25:26
WhenCreated : 06/02/2014 16:25:26
WhenChangedUTC : 06/02/2014 18:25:26
WhenCreatedUTC : 06/02/2014 18:25:26
OrganizationId :
OriginatingServer : bmg190.bancobmg.com.br
[PS] C:\Windows\system32>Get-ManagementRoleAssignment "Message Tracking-Exchange Access Message Tracking" | fl
RunspaceId : 4229f35d-90f1-4c4e-822d-387979921052
User : bancobmg.com.br/Global/Microsoft Exchange Security Groups/Exchange Access Message Tracki
ng
AssignmentMethod : Direct
Identity : Message Tracking-Exchange Access Message Tracking
EffectiveUserName : All Group Members
AssignmentChain :
RoleAssigneeType : RoleGroup
RoleAssignee : bancobmg.com.br/Global/Microsoft Exchange Security Groups/Exchange Access Message Tracki
ng
Role : Message Tracking
RoleAssignmentDelegationType : Regular
CustomRecipientWriteScope :
CustomConfigWriteScope :
RecipientReadScope : Organization
ConfigReadScope : OrganizationConfig
RecipientWriteScope : Organization
ConfigWriteScope : OrganizationConfig
Enabled : True
RoleAssigneeName : Exchange Access Message Tracking
IsValid : True
ExchangeVersion : 0.11 (14.0.550.0)
Name : Message Tracking-Exchange Access Message Tracking
DistinguishedName : CN=Message Tracking-Exchange Access Message Tracking,CN=Role Assignments,CN=RBAC,CN=BANC
O BMG SA,CN=Microsoft Exchange,CN=Services,CN=Configuration,DC=bancobmg,DC=com,DC=br
Guid : c3768a00-3f36-4532-b586-a06842a85e24
ObjectCategory : bancobmg.com.br/Configuration/Schema/ms-Exch-Role-Assignment
ObjectClass : {top, msExchRoleAssignment}
WhenChanged : 06/02/2014 16:25:26
WhenCreated : 06/02/2014 16:25:26
WhenChangedUTC : 06/02/2014 18:25:26
WhenCreatedUTC : 06/02/2014 18:25:26
OrganizationId :
OriginatingServer : bmg190.bancobmg.com.br
How can I identify if there is any setting to be done?
Thank you! -
I have a working program right now..But it lacks some things to be done..It already does the stacks and queues..But still it doesnt print the info on the desired output file outTwo.dat..Both the stacks and queues should be printed on it..Also it has to compute the total commission on categories 1 and 2...and put it again on the outTwo.dat..Any kind hearted people would want to help me here?Here's the assignment detail...Thank YOU!!!!
Q2. Linked List
a. create a compile AStack class, and a AQueue class similar to the text
b. provide an application that will:
� instantiate an AStack object and an AQueue object
� create a property object for each data line read from the input file assign4.dat
� push it ti the stack if its is category 1 property; queue if its is category 2; ignore all others
� print a title called category 1 to an output file called outTwo.dat
� after printing a few blank lines to outTwo.dat, print a title called category 2 to outTwo.dat
� traverse the queue and print it to the same output file outTwo.dat
� print the total commission earned on this category of property to outTwo.dat
Note that for this question you should also print out and submit outTwo.dat. Have Fun!
//This is the program I have done so far....
import java.io.*;
import java.util.StringTokenizer;
public class TestSQ {
public static void readFileSQ(AStack s, AQueue q)
try {
FileReader inStream=new FileReader("assign4.dat");
BufferedReader ins= new BufferedReader(inStream);
FileWriter outStream=new FileWriter("outTwo.dat");
PrintWriter outs= new PrintWriter(outStream);
String line;
int category;
double price;
String categoryString;
String priceString;
StringTokenizer st;
while((line=ins.readLine())!=null) {
st=new StringTokenizer(line," ");
if(st.countTokens()==2){
categoryString = st.nextToken();
priceString = st.nextToken();
try{
category = Integer.parseInt(categoryString);
price = Double.parseDouble(priceString);
Property myProperty = new Property(category, price);
myProperty.setCommissionRate();
myProperty.getCommission();
if(category==1)
s.push(myProperty);
outs.println(s.toString());
if(category==2)
q.insert(myProperty);
outs.println(q.toString());
}catch(NumberFormatException nfe){
System.out.println("error while parsing Integer: "+categoryString+"/"+priceString);
else
System.out.println("invalid number of elements in line: " +st.countTokens());
catch (IOException e) {
System.out.println("i/o error:"+e.getMessage());
e.printStackTrace();
public static void showStack(AStack s){
while(!s.isEmpty()){
Object line=s.pop();
System.out.println(line);
public static void main(String args[])
AStack stackOfProperty=new AStack();
AQueue queueOfProperty=new AQueue();
readFileSQ(stackOfProperty,queueOfProperty);
showStack(stackOfProperty);
System.out.println();
System.out.println(queueOfProperty.toString());
}import java.io.*;
import java.util.StringTokenizer;
public class TestSQ {
public static void readFileSQ(AStack s, AQueue q)
try {
FileReader inStream=new FileReader("assign4.dat");
BufferedReader ins= new BufferedReader(inStream);
FileWriter outStream=new FileWriter("outTwo.dat");
PrintWriter outs= new PrintWriter(outStream);
String line;
int category;
double price;
String categoryString;
String priceString;
StringTokenizer st;
while((line=ins.readLine())!=null) {
st=new StringTokenizer(line," ");
if(st.countTokens()==2){
categoryString = st.nextToken();
priceString = st.nextToken();
try{
category = Integer.parseInt(categoryString);
price = Double.parseDouble(priceString);
Property myProperty = new Property(category, price);
myProperty.setCommissionRate();
myProperty.getCommission();
if(category==1)
s.push(myProperty);
// outs.println(s.toString());
else if(category==2)
q.insert(myProperty);
outs.println(q.toString());
}catch(NumberFormatException nfe){
System.out.println("error while parsing Integer: "+categoryString+"/"+priceString);
else
System.out.println("invalid number of elements in line: " +st.countTokens());
outs.close();
ins.close();
catch (IOException e) {
System.out.println("i/o error:"+e.getMessage());
e.printStackTrace();
public static void showStack(AStack s){
while(!s.isEmpty()){
Object line=s.pop();
System.out.println(line);
public static void main(String args[])
AStack stackOfProperty=new AStack();
AQueue queueOfProperty=new AQueue();
readFileSQ(stackOfProperty,queueOfProperty);
showStack(stackOfProperty);
System.out.println();
System.out.println(queueOfProperty.toString());
}//This is the updated version of my program..Now the ouput file works now, but then it shows different ouput..Thats only for the queue.I dont know about the stack..Tnx for looking... -
Oracle Streams 'ORA-25215: user_data type and queue type do not match'
I am trying replication between two databases (10.2.0.3) using Oracle Streams.
I have followed the instructions at http://www.oracle.com/technology/oramag/oracle/04-nov/o64streams.html
The main steps are:
1. Set up ARCHIVELOG mode.
2. Set up the Streams administrator.
3. Set initialization parameters.
4. Create a database link.
5. Set up source and destination queues.
6. Set up supplemental logging at the source database.
7. Configure the capture process at the source database.
8. Configure the propagation process.
9. Create the destination table.
10. Grant object privileges.
11. Set the instantiation system change number (SCN).
12. Configure the apply process at the destination database.
13. Start the capture and apply processes.
For step 5, I have used the 'set_up_queue' in the 'dbms_strems_adm package'. This procedure creates a queue table and an associated queue.
The problem is that, in the propagation process, I get this error:
'ORA-25215: user_data type and queue type do not match'
I have checked it, and the queue table and its associated queue are created as shown:
sys.dbms_aqadm.create_queue_table (
queue_table => 'CAPTURE_SFQTAB'
, queue_payload_type => 'SYS.ANYDATA'
, sort_list => ''
, COMMENT => ''
, multiple_consumers => TRUE
, message_grouping => DBMS_AQADM.TRANSACTIONAL
, storage_clause => 'TABLESPACE STREAMSTS LOGGING'
, compatible => '8.1'
, primary_instance => '0'
, secondary_instance => '0');
sys.dbms_aqadm.create_queue(
queue_name => 'CAPTURE_SFQ'
, queue_table => 'CAPTURE_SFQTAB'
, queue_type => sys.dbms_aqadm.NORMAL_QUEUE
, max_retries => '5'
, retry_delay => '0'
, retention_time => '0'
, COMMENT => '');
The capture process is 'capturing changes' but it seems that these changes cannot be enqueued into the capture queue because the data type is not correct.
As far as I know, 'sys.anydata' payload type and 'normal_queue' type are the right parameters to get a successful configuration.
I would be really grateful for any idea!Hi
You need to run a VERIFY to make sure that the queues are compatible. At least on my 10.2.0.3/4 I need to do it.
DECLARE
rc BINARY_INTEGER;
BEGIN
DBMS_AQADM.VERIFY_QUEUE_TYPES(
src_queue_name => 'np_out_onlinex',
dest_queue_name => 'np_out_onlinex',
rc => rc, , destination => 'scnp.pfa.dk',
transformation => 'TransformDim2JMS_001x');
DBMS_OUTPUT.PUT_LINE('Compatible: '||rc);
If you dont have transformations and/or a remote destination - then delete those params.
Check the table: SYS.AQ$_MESSAGE_TYPES there you can see what are verified or not
regards
Mette -
Can any one tell me how to write the properites files and how to acces
can any one tell me how to write the properites files and how to acces thoose files
plz let me no
thanks in advancehttp://www.exampledepot.com/egs/java.util/Props.html
-
Message Status as "Scheduled" and Queue Status "Queue Stopped".
Hi friends,
My scenario is from Peoplesoft -> XI -> BI
Message has reached BI, but in SXMB_MONI, its showing Message Status as "Scheduled" and Queue Status "Queue Stopped".
How to proceed further ? How can I start that queue ?
Thanks ain advance,
Neena JohnHi Neena,
Go to SXMB_ADM -> Manage Queues -> Register Queues
More on queues
XI : How to Re-Process failed XI Messages Automatically
Run the report RSXMB_REGISTER_QUEUES and register the queues
Run the report RSXMB_RESTART_MESSAGES for restarting ur messages
Refer this:
https://www.sdn.sap.com/irj/sdn/go/portal/prtroot/docs/library/uuid/20bb9649-e86e-2910-7aa9-88ed4972a5f6
Regards,
Vinod. -
CCMS qRFC Monitoring: Missing Transactional and Queued RFC Monitoring Nodes
Hi ,
We are trying to create a Queued RFC monitoring for VERTEX Queued , but we are missing CCMS Monitor Templates,in monitor Communications -->Transactional RFC and Queued RFC in Dev and PROD ,but its present in QA System .
I have checked all system are at same level for support packs , kernel version .
I have refered following Notes - 441269,437187,455431, 485826
Can we create manually new one , but we are missing MTE class also ?
Can we create new monitoring template ?
We are running 4.6c with basis support pack level :
SAP_BASIS 46C 0054 SAPKB46C54
SAP_ABA 46C 0054 SAPKA46C54
Thanks
HamendraHamendra,
Please make sure background dispatching is activated in your system. Go to tcode RZ21 and menu Technical Infrastructure --> Method execution --> Active background dispatching.
This should schedule a job called SAP_CCMS_MONI_BATCH_DP. This is the job that will run the function for building the ALE/EDI monitoring segment.
After scheduling the job check back in a few hours, if the ALE/EDI monitor is still not there try the following.
1. Go to tcode RZ21
2. In the topology section choose radio button "Segment overview" and click display
3. Go into change mode and delete the monitoring segments
This will force the system to recreate all the monitoring contexts.
Check back in a few hours and see if the monitor is working.
Tarkesh -
Tuxedo - Ave. Len and #Queued in psadmin for PeopleSoft
Hi,
We set LDBAL = Y in psapsrv.ubx file and since then we started noticing queuing at Ave. Len and #Queued (see below).
>
pq
Prog Name Queue Name # Serve Wk Queued # Queued Ave. Len Machine
PSSAMSRV SAMQ 1 0 0 0.0 uqa031
JSL 00095.00200 1 0 0 0.0 uqa031
BBL 58048 1 0 0 0.0 uqa031
PSMONITORSRV MONITOR 1 0 0 0.0 uqa031
PSAPPSRV APPQ 15 350 7 4.1 uqa031
PSWATCHSRV WATCH 1 0 0 0.0 uqa031
JREPSVR 00094.00250 1 0 0 0.0 uqa031
PSQCKSRV QCKQ 1 0 0 0.0 uqa031
If we set LDBAL to 'N', we would n't see any queqing at both Ave. Len and #Queued.
we had a look at PeopleSoft servrices using 'psr' and there are number of application server processes which are in 'IDLE' status and this confirms that there is n't actually any queing.
The following Oracle PeopleSoft support document (831594.1) does not recommend enabling LDBAL in PeopleSoft domains as it is not supported.
The reason that we enabled LDBAL is that to monitor queqing at Ave. Len and #Queued as we have reduced number of application server processes from 20 to 15, as at any given time only around 10 PSAPPSRV processes are actively being used (from psr). Hence we reduced number of processes to free up some system resources (memory and swap) as the additonal resouces that we freed up can be used by the remaining 15 PSAPPSRV processes.
The #Queued and Ave. Len does not show up any values if we do not set LDBAL to 'Y. FYI, we are PeopleTools 8.50.07.
Any ideas and clarification would be appreciated.
Cheers
RajCan't tell much about the PeopleSoft configuration without the UBBCONFIG file. The tmunloadcf command should give one. What operating system is this for?
With reguards to queueing, the "ipcs -qa" command should give you an excellent snapshot of all of the IPC message queues and whether there are any messages on the queues. I prefer to use this approach with scripts to monitoring queueing.
With LDBAL=N, the "psr" command will show how many messages each server in the MSSQ set processed. The number of messages processes for each server in the MSSQ set is not equal but rather significantly unequal. The server with the fewest number of messages processed should have a significantly fewer number of messages processed than the other servers in the MSSQ set.
This URL may be useful: http://www.aurorainfo.com/wp1/index.htm
Harvey -
Hi,
Iam not clear with the concept of message and queue in XI, can anybody please tell how the message and queue are related and what are the inbound and outbound queues?
Thanks.Hi Lou,
A queue in XI, is very similar to your real-life one, where messages are in the status, for inbound( coming into XI) or outbound( leaving XI) processing. The queues in XI can be seen in ur transaction smq1 and smq2. Please go through these documents to understand better.
<a href="/people/siva.maranani/blog/2005/05/25/understanding-message-flow-in-xi message flow in XI</a>
<a href="/people/sap.india5/blog/2006/01/03/xi-asynchronous-message-processing-understanding-xi-queues-part-i XI queues</a>
<a href="http://help.sap.com/saphelp_nw2004s/helpdata/en/96/8412417301ee6fe10000000a1550b0/frameset.htm">Registering queues</a>
http://help.sap.com/saphelp_nw2004s/helpdata/en/f7/2c4b3f53275003e10000000a114084/frameset.htm
http://help.sap.com/saphelp_nw2004s/helpdata/en/c3/eab140cbe49d2ae10000000a155106/frameset.htm
Hope these answer your question
cheers,
Prashanth
P.S Please mark helpful answers -
Difference between notifiers and queues
Hi, I have a question about notifiers and queues. I try to do a moving average for 6 min, having data with a sampling rate of 25 us. I use a producer/ consumer architecture. The producer loop reads 3 DMA Fifos from my FPGA vi and writes them in three diferent queues. Each queue is beeing read again in three consumer loop, one for each queue. I thought this might be faster??!! If I limit my queue to a certain size than after some minutes I get a timeout error, if I say 0 ms for timeout. I wanted to make sure that nothing will get lost. If I don't limit my queue size ( -1) after 10 minutes I get a message that I don't have enough memory to operate. I also can see that that in Task manager the page file is getting bigger and bigger until 2 gb. So from this poit of view I would assume that my average calculation is to slow and data has to be stored inbetween. So my consumer loop is to slow. Well I don't have any idea how to make my code faster. I also do a cascade for the averaging and the average is beeig calculated adding the new value and subtract the oldest value in the array.
Than I tryed using the notifiers. As I read you can not size a notifier. But what happens if the consumer loop is slower than the producer loop? Do I loose data? When using notifiers I don't get any error messages, like don't have enough memory . So what is the diference between notifiers and queues?
Has also someone any idea how to make the code faster ?
Thanks
Attachments:
mittel_Fifo1+2+3_gra_notif.vi 274 KBCheck the number of elements in the queue when running your vi, so you can see if your queue is running full.
Furthermore, your code looks a bit 'dirty'. From that I guess, there is still a lot of improvements that can be made to get the performance you need.
Take a look at the 'ptbypt Mean.vi' (I don't remember the exact name).
Felix
www.aescusoft.de
My latest community nugget on producer/consumer design
My current blog: A journey through uml -
Hello, I am new to Java and am working out an assignment. I need to manipulate some stacks and queues in various ways.
I need to reverse a stack in three different ways:
1. using two additional stacks.
2. using one additional queue.
3. using one additional stack and some additional non-array variables.
I think I have ways to do 1 and 2 but I'm a bit confused about 3.
For 1, I would pop the the elements off of the full stack A, and push them onto B. Then pop them from B and push them to C. Then pop them from C and push them to A, thus reversing the order.
For 2, simply pop the elements from the stack and enqueue them in the queue. Then dequeue them and push them back to the stack.
For 3, not really sure where to start or how? I could think of how to do it with an array but I'm drawing a blank on this. I don't want anyone to write the code for me just maybe point me in the right direction?
The assignment then carries on to sorting in ascending order using a stack and then just using non-array variables. I feel like if I can figure out number 3 above the rest will be along similar lines.
Any help is greatly appreciated.The restrictions might be nudging towards a constant-storage algorithm. In which case, try the following.
You can move any element to the top of the stack using a stack and non-array variables. Take the 4th element for example:
Pop 3 elements from the stack and push onto the other.
Pop the next element and store in a variable.
Pop the 3 elements from the second stack and push back on the first.
Push the value from the variable onto the first stack.
This can be used for reversing and sorting the stack.
Maybe you are looking for
-
Incorrect Apple ID in App Store / How to do a fresh Lion install
I'm trying to redownload the OSX Lion Install App. I held the Option key when clicking purchases and instead of saying "Installed", it now says "Download". However, even though I'm signed into the App Store with my personal Apple ID, it asks me to
-
Hello all, im working in hr schema i need sql statement to answer my question i need all employees information where average salary = average salary department 50 sorry i can't speak english very well thank's all
-
Recoloring a halftone pattern in Illustrator
Hello, I have a question regarding changing the color of a halftone pattern created in Illustrator. Here is what I do step by step: 1) fill the expanded text with a black and white gradient 2) apply Effects>Pixelate>Color Halftone 3) expand the halft
-
Why won't iphoto send pictures
When I try to send multiple pictures using the fun templates included with iphoto, an error message comes up every time saying "username and password not recognized by e-mail server." this cannot be correct since I've since deleted and added both of
-
CSCue57694 - netflow on 7.4 will not support 3rd party NMS e.g. solarwind
Having netflow support on 7.4 was a great news....but is not usable. Is there any way to define a record template which corresponds to a v5 flow. Doing so, it would be possible to get flow information on existing flow collector such as Fluke NPM.