--- name: "pj_dump" section: "1" platform: "linux" package: "pajeng" version: "1.3.7-1" release: "Debian 13 (Trixie)" platforms: ["linux"] url: "https://new.carta.tech/pj_dump" --- # pj\_dump(1) dumps a paje trace file in a CSV-like textual format ## NAME pj\_dump - dumps a paje trace file in a CSV-like textual format ## SYNOPSIS **pj\_dump** \[*OPTIONS*\] \[*FILE*\] ## DESCRIPTION The [pj\_dump(1)](/pj_dump/1.md) command translates the paje trace file *FILE* to a CSV-like textual format (described below). It is a useful program to analyze the behavior of parallel and distributed applications that were traced using some library that generates trace files in the Paje file format. Once you dump the contents of the Paje trace file in a CSV-like manner, you are free to analyze the contents of the trace the way you want. You can use R for example to draw scatter plots and gantt charts. If *FILE* is not provided, then the standard input is used. By default, **pj\_dump** will read the trace file from the beginning until the end of file is found. During this process, **pj\_dump** relies on the Paje library to recreate in memory the behavior that is registered in the trace files. This means that **pj\_dump** will put in memory all the contents of the trace file, even if the input is very large. Once all the contents of the trace file are simulated, **pj\_dump** dumps the information in the CSV-like textual format described below in the OUTPUT DESCRIPTION section. You can change the default behavior of **pj\_dump** by providing the parameters **--start=START** and **--end=END** where START and END are valid timestamps of the input trace. If provided, it dumps only the contents of the trace between START and END. Note that even if used, **pj\_dump** will simulate the whole trace file to keep the same semantic of behavior. Another way to change the default behavior is through the **--stop-at=TIME** parameter. If provided, **pj\_dump** will read the trace file up to timestamp TIME (considering that the trace file is completely time ordered) and dumps what has been simulated until then. The **--no-strict** switch should be avoided and can be used only with old Paje trace files with old field names in event definitions. The **--ignore-incomplete-links** switch make **pj\_dump** ignore incomplete links silently. More details on this switch below, in the OUTPUT DESCRIPTION section. ## OPTIONS **pj\_dump** accepts the following options: - **-a, --stop-at**=*TIME* Stop the trace simulation at TIME. - **-s, --start**=START Dump starts at timestamp START (instead of timestamp 0). - **-e, --end**=*END* Dump ends timestamp END (instead of End Of File). - **-n, --no-strict** Support old field names in event definitions. - **-z, --ignore-incomplete-links** Ignore incomplete links without warnings. - **-u, --user-defined** Dump user-defined fields. See USER-DEFINED FIELDS section below. - **--type-hierarchy**=*FILE* Dump the type hierarchy in CSV format to FILE. - **--entity-hierarchy**=*FILE* Dump the entity hierarchy in CSV format to FILE. - **-f, --flex** Use alternative file reader based on flex/bison (experimental). - **-?, --help** Show all the available options. - **--usage** Give a short usage message. ## INPUT DESCRIPTION The [pj\_dump(1)](/pj_dump/1.md) command expects an input that follows the Paje file format (as described in the PDF document listed in the RESOURCES section of this page). If FILE is not provided, [pj\_dump(1)](/pj_dump/1.md) will try to read from the standard input. ## OUTPUT DESCRIPTION It’s easier to understand what is written here if you are acquainted to the Paje terminology (Container, State, Variable, Link, Event and the information attached to each of these). Take a look to the description of the Paje File Format (link below in the RESOURCES section) for further details. The contents of the lines generated by the [pj\_dump(1)](/pj_dump/1.md) command are separated by commas, defining the columns. So, a line like this: ``` Container, 0, LINK, 0, 4.48514, 4.48514, 9 ``` has seven columns. The first column is always one of: Container, State, Variable, Event or Link. The remaining columns of the line have specific information depending on the first column. Here’s a synthetic description of the five different types of lines you’ll find as output of [pj\_dump(1)](/pj_dump/1.md): ``` Container, parentContainer, containerType, startTime, endTime, duration, name State, container, stateType, startTime, endTime, duration, imbrication, value Variable, container, variableType, startTime, endTime, duration, value Event, container, eventType, time, value Link, container, linkType, startTime, endTime, duration, value, startContainer, endContainer ``` See below a detailed description with examples for each of them. ### Container All lines starting with *Container* look like this: ``` Container, 0, HOST, 0, 4.48514, 4.48514, Tremblay ``` 1\. "Container" 2\. "0" - The name of the parent container 3\. "HOST" - The type of this container 4\. "0" - The starting time 5\. "4.48514" - The finish time 6\. "4.48514" -The duration 7\. "Tremblay" - The name of this container ### State All lines starting with *State* look like this: ``` State, node48, SERVICE, 691, 692, 1, 0, booked ``` 1\. "State" 2\. "node48" - The name of the container 3\. "SERVICE" - The type of this state 4\. "691" - The starting time 5\. "692" - The finish time 6\. "1" - The duration 7\. "0" - The imbrication level 8\. "booked" - The value of the state ### Variable All lines starting with *Variable* look like this: ``` Variable, Tremblay, pcompute, 2.15357, 2.17013, 0.016554, 9.8095e+07 ``` 1\. "Variable" 2\. "Tremblay" - The name of the container 3\. "pcompute" - The name of the variable 4\. "2.15357" - The starting time 5\. "2.17013" - The ending time 6\. "0.016554" - The duration 7\. "9.8095e+07" - The value of the variable ### Event All lines starting with *Event* look like this: ``` Event, Tremblay, msmark, 3.4286, finish_send_tasks ``` 1\. "Event" 2\. "Tremblay" - The name of the container 3\. "msmark" - The name of the event 4\. "3.4286" - The instant in time when this event took place 5\. "finish\_send\_tasks" - The value of the event ### Link All lines starting with *Link* look like this: ``` Link, 0, 0-HOST1-LINK4, 0, 0, 0, G, Tremblay, 9, mpi_123 ``` 1\. "Link" 2\. "0" - The name of the container 3\. "0-HOST1-LINK4" - The type of this link 4\. "0" - The starting time 5\. "0" - The ending time 6\. "0" - The duration 7\. "G" - The value of this link 8\. "Tremblay" - The starting container 9\. "9" - The ending container 10\. "mpi\_123" - The unique key **Incomplete Links** According to the description of the Paje File Format, a link is formed by two events: PajeStartLink and PajeEndLink. These events are matched by the Paje Simulator using a key that is provided in the trace file. If one of these two events are missing for some arbitrary reason and the trace file ends (or the container is destroyed), you’ll have a simulation with **incomplete links**. Generally, the Paje Simulator, and by consequence **pj\_dump**, consider these links as errors, and list them in the following manner: ``` $ pj_dump ~/tracefile.paje List of incomplete links in container '0': Link, 0, MSG_PROCESS_TASK_LINK, 0, -1, 0, SR, broadcaster-12, NULL Link, 0, MSG_PROCESS_TASK_LINK, 0.00013, -1, 0, SR, broadcaster-13, NULL Link, 0, MSG_PROCESS_TASK_LINK, 0.002868, -1, 0, SR, broadcaster-13, NULL (...) PajeLinkException: Incomplete links at the end of container with name '0' ``` The best action when this happens is to fix the tracer or the converter that generated the trace, since it indicates probably some error during the execution. If you think that this error is acceptable, you can provide the **-z** switch to **pj\_dump** to tell the Paje Simulator to ignore incomplete links. All the trace file will be dumped and all errors concerning incomplete links will be silently ignored. Use with caution. ## USER-DEFINED FIELDS User-defined fields is a feature of the Paje trace file format to add additional information in the trace that does not belong to the traditional fields of each event definition. An event definition with four user-defined fields (Size, Params, Footprint and Tag) looks like this: ``` %EventDef PajeSetState 20 % Time date % Container string % Type string % Value string % Size string % Params string % Footprint string % Tag string %EndEventDef ``` The dump of user-defined fields are disable by default in pj\_dump. The user can activate them by passing **-u** (or **--user-defined**) as argument. When doing so, the CSV-like output of pj\_dump will be altered from the definition above (see OUTPUT DESCRIPTION). Besides dumping the default fields for each entity and container of the trace, the CSV will have additional fields that correspond to user-defined fields. The order in which they appear in the output obeys the order of the corresponding event definition. So a **State** defined with the event definition 20 above will have four additional fields in the CSV-like output. ## RESOURCES Description of the Paje trace file: https://github.com/schnorr/pajeng/blob/master/doc/lang-paje/lang-paje.pdf Main web site: http://github.com/schnorr/pajeng/ ## REPORTING BUGS ``` Report pj_dump bugs to ``` ## COPYRIGHT Copyright (C) 2012-2014 Lucas M. Schnorr. Free use of this software is granted under the terms of the GNU General Public License (GPL). ## SEE ALSO **[pj\_validate(1)](/pj_validate/1.md)**