DBCollect/Usage: Difference between revisions

From Dirty Cache Wiki
Jump to navigation Jump to search
← Older editNewer edit →
VisualWikitext
No edit summary
No edit summary
Line 45: Line 45:


</syntaxhighlight>
</syntaxhighlight>
= Explanation of all options =
== help ==
<code>--help</code> or <code>-h</code>
Shows usage (list of all arguments)
== version ==
<code>-V | --version</code>
Shows detailed version, build and copyright details
== debug ==
<code>-D | --debug</code>
enables debugging. This will result in more logging (sometimes dumping unhandled Python exceptions and traces.
Even without this option, debug info is written to the {{dbcollect}} logfile for troubleshooting purposes.
== quiet ==
<code>-q | --quiet</code>
Hides most normal terminal output (except errors). Useful for scripted runs (such as with [[DBCollect/Ansible]])
== overwrite ==
<code>-o | --overwrite</code>
Overwrites the previous dbcollect ZIP file if it exsts.
== update ==
<code>--update</code>
Downloads new version of {{dbcollect}} from github and replaces the old version.
Requires https access to github.com
== sudoers ==
<code>--sudoers</code>
Writes sudoers settings to <code>/etc/sudoers.d/dbcollect</code>. This allows {{dbcollect}} to run some commands as root, that otherwise would fail.
This retrieves some extra, optional information. Not required, but on HP-UX highly recommended, as otherwise disk devices cannot be properly detected.
== filename ==
<code>--filename FILENAME</code>
Write to the given FILENAME instead of /tmp/dbcollect-<hostname>.zip.
If FILENAME is only an identifier, the new name will be /tmp/<filename>.zip.
If FILENAME is a full path, dbcollect will use it as new location (.zip extension will be added if needed)
== tempdir ==
<code>--tempdir TEMPDIR</code>
Use TEMPDIR as alternative temporary folder (for example <code>/var/tmp</code>.
Useful if <code>/tmp</code> freespace is insufficient. {{dbcollect}} will always create a subdirectory such as <code>/tmp/dbcollect_uwfb4li0</code> so it will never overwrite existing files or directories.
== user ==
<code>-u USER | --user USER</code>
Normally, {{dbcollect}} will use the owner of the first detected Oracle instance (i.e., running <code>ora_pmon_<instance></code>. Use this option to force using another user.
To work properly, it has to be a user with SYSDBA privileges.
== days ==
<code>-d DAYS | --days DAYS</code>
The number of days for which to generate AWR or Statspack reports. The default is 10 days, so with an AWR interval of 1 hour and long enough AWR retention, about 240 AWR reports will be generated per instance.
Increasing this value will only work if the retention in Oracle is also high enough (and AWR data is actually available).
Note that the Linux SAR/Sysstat reports will always be the entire period of 30 or 31 days (where available).
== end_days ==
<code>--end_days END_DAYS</code>
Number of days ago to stop AWR report generation. For example, you want to pick up reports from 20 days ago to 10 days ago:
<code>dbcollect --days 20 --end_days 10</code>
This can be used if you want to pick up a very specific period of time only.
== force-awr ==
<code>--force-awr</code>
This causes {{dbcollect}} to ignore prior AWR report detection and always create AWR reports. You need to have Diagnostics Pack if you use this to avoid licensing violations.
== statspack ==
<code>--statspack</code>
Force usage of Statspack even if AWR usage is detected.
== ignore-awr ==
<code>--ignore-awr</code>
Ignores AWR reporting for databases that have no prior AWR usage.
== strip ==
<code>--strip</code>
AWR reports usually contain (parts of) SQL code. This is sometimes considered a security issue. This option removes all SQL code sections from the AWR reports. It only works for AWR, not Statspack.
Note that it works on best-effort basis, if the AWR report cannot be parsed, the report will be saved in its original form.
== no-rac ==
<code>--no-rac</code>
To make {{dbcollect}} as robust as possible, by default if running RAC, it generates AWR reports for all database instances which significantly increases runtime and ZIP file size.
If {{dbcollect}} is executed on all RAC nodes (recommended), this is not necessary and the double generation of AWR can be disabled using this option.
== no-stby ==
<code>--no-stby</code>
By default, AWR reports cannot be created for Data Guard Standby databases. This is typically not a big problem as standby databases do not usually generate much workload. However, if real-time queries are running against the standby database (requiring Active Data Guard license), we are also interested in the workload on those instances.
Since Oracle 12, Remote Management Framework (RMF) allows AWR reports to be generated for standby databases (but it has to be configured by the DBA first). {{dbcollect}} will pick up AWR reports from RMF managed standby databases (through the primary instance).
Use this option to disable this feature.
== no-awr ==
<code>--no-awr</code>
Skip AWR/Statspack reports completely. Note that the {{dbinfo}} reports are still created.
== no-sar ==
<code>--no-sar</code>
Skips collection of SAR reports (Linux/UNIX).
== no-ora ==
<code>--no-ora</code>
Skips entire collection of Oracle related information. Only OS info will be collected.
== no-sys ==
<code>--no-sys</code>
Skips entire collection of OS related information. Only Oracle info will be collected.
== no-orainv ==
<code>--no-orainv</code>
Skip using Oracle Inventory for ORACLE_HOME and instances detection. Only instances in <code>oratab</code> will be detected.
This can be useful for troubleshooting Oracle Instances detection.
== no-oratab ==
<code>--no-oratab</code>
Skip using Oracle <code>oratab</code> for ORACLE_HOME and instances detection. Only instances in Oracle Inventory will be detected.
This can be useful for troubleshooting Oracle Instances detection.
== splunk ==
<code>--splunk</code>
Generate additional reports for usage with [https://dell.com Dell's] internal SPLUNK toolset (for Dell Presales Engineers) or [https://www.liveoptics.com/ Dell LiveOptics]. These reports contain extra info such as database size.
== include ==
<code>--include INSTANCE_LIST</code>
Include only the given instances (comma separated). Without this option, all detected instances are included.
== exclude ==
<code>--exclude INSTANCE_LIST</code>
Exclude only the given instances (comma separated).
Note that excluded instances are prioritized over included.
== tasks ==
<code>-t TASKS | --tasks TASKS</code>
Set the maximum number of workers (for AWR generation) to TASKS (default = 50% of available CPUs).
== timeout ==
<code>--timeout TIMEOUT</code>
Change the timeout for long running SQL scripts. The default is 10 minutes.
Useful for troubleshooting timeout errors.

Revision as of 12:17, 10 October 2024


Usage

Short summary

If dbcollect is installed correctly: 

# Simply run dbcollect
dbcollect

# Error: Zipfile already exists
# Overwrite previous zipfile
dbcollect --overwrite

# Error: No AWR or Statspack detected
# If you are sure the system is licensed with Diagnostics Pack
dbcollect --overwrite --force-awr

# If you want to retrieve more than 10 days worth of AWR files:
dbcollect --days 20

# Limit dbcollect to use only 2 tasks (CPUs) for AWR generation (default = 50% of CPUs, with a maximum of 8)
dbcollect --tasks 2


Resolve AWR reporting issues

dbcollect checks for prior AWR usage to make sure it will not trigger Oracle license violations ( More info)

If you get Error [DBC-E021] No AWR or Statspack detected: 

# If you are sure you have Diagnostics Pack license:
dbcollect --force-awr

# If you want to ignore databases without AWR usage:
dbcollect --ignore-awr

# If the problem databases are not important, try excluding them:
dbcollect --exclude inst1,inst2
Retrieved from "https://wiki.dirty-cache.com/index.php?title=DBCollect/Usage&oldid=389"