Archive for the ‘Performance Monitoring’ Category

Crash Dump Analysis Patterns (Part 250)

Monday, April 3rd, 2017

For completeness, we add Aggregated Frames analysis pattern implemented as “aggregated stack trace” in various software performance profiling tools. Such tools periodically record CPU Stack Trace Collection. Other tools profile memory allocations and their stack traces. By aggregation we mean summing up occurrences of modules and functions from all collected stack traces similar to this table:

ModuleA         88%
   +0x234          42%
   +0x123           8%
   !foo            38%
      +0xd            30%
      +0x56            2%
   !bar             6%
      +0x18            6%
ModuleB         12%
   !export         12%
      +0x2380          1%
      +0x1224          6%
      +0x3812          5%

Related to memory dump analysis we can either use Stack Trace Collection to detect Ubiquitous Component in user and kernel spaces, or database Stack Traces, for example, used in detection of process heap, handle, and reference Memory Leaks.

We do not include “stack” in the name of this pattern because frames are not sorted by the execution direction compared to Unified Stack Trace analysis pattern where we have some notion of aggregation depicted as multiplicities.

We can also name it as Frame Usage Signature similar to Stack Trace Signature.

- Dmitry Vostokov @ + -

Trace Analysis Patterns (Part 102)

Tuesday, March 3rd, 2015

When we do tracing and logging much of computational activity is not visible. For live tracing and debugging this can be alleviated by adding Watch Threads. These are selected memory locations that may or may not be formatted according to specific data structures and are inspected at each main trace message occurrence or after specific intervals or events:

This analysis pattern is different from State Dump which is about intrinsic tracing where the developer of logging statements already incorporated variable watch in source code. Watch Threads are completely independent from original tracing and may be added independently. Counter Value is the simplest example of Watch Thread if done externally because the former usually doesn’t require source code and often means some OS or module variable independent of product internals. Watch Thread is also similar to Data Flow pattern where specific data we are interested in is a part of every trace message.

- Dmitry Vostokov @ + -

Trace Analysis Patterns (Part 52)

Wednesday, September 26th, 2012

The modern software trace recording, visualization and analysis tools such as Process Monitor, Xperf, WPR and WPA provide stack traces associated with trace messages. Consider stack traces as software traces we have, in a more general case, traces (fibers) bundled together on (attached to) a base software trace. For example, a trace message, that mentions an IRP can have its I/O stack attached together with thread stack trace with function calls leading to a function that emitted the trace message. Another example is association of different types of traces with trace messages such as managed and unmanaged ones. This general trace analysis pattern needs a name so we opted for Fiber Bundle as analogy with a fiber bundle from mathematics. Here’s a graphical representation of stack traces recorded for each trace message where one message also has an associated I/O stack trace:

- Dmitry Vostokov @ + -

Webinar: Introduction to Philosophy of Software Diagnostics

Sunday, September 23rd, 2012

Learn from this Webinar about phenomenological, hermeneutical and analytical approaches to software diagnostics and its knowledge, foundations, norms, theories, logic, methodology, language, ontology, nature and truth. This seminar is hosted by Software Diagnostics Services.

 Introduction to Philosophy of Software Diagnostics Logo

Title: Introduction to Philosophy of Software Diagnostics
Date: 17th of December, 2012
Time: 19:00 GMT
Duration: 60 minutes

Space is limited.
Reserve your Webinar seat now at:

- Dmitry Vostokov @ + -

Software Diagnostics Services

Friday, July 13th, 2012

For some time I was struggling with finding a good name for memory dump and software trace analysis activities. The name Memoretics I use for the science of memory dump analysis (that also incorporates software traces) seems not so good to describe the whole practical activity that should be transparent to everyone in IT. Fortunately, I timely understood that all these activities constitute the essence of software diagnostics that previously lacked any solid foundation. Thus, Software Diagnostics Institute was reborn from the previous Crash Dump Analysis Portal. This institute does pure and applied research and scientific activities and in recent years was funded mainly from OpenTask publisher and recently from Memory Dump Analysis Services. The latter company also recognized that the broadening of its commercial activities requires a new name. So, Software Diagnostics Services was reborn:

The First Comprehensive Software Diagnostics Service

- Dmitry Vostokov @ + -

Trace Analysis Patterns (Part 51)

Saturday, June 23rd, 2012

Counter Value pattern covers performance monitoring and its logs. A counter value is some variable in memory, for example, a module variable, that is updated periodically to reflect some aspect of state or it can be calculated from different such variables and presented in trace messages. Such messages can also be organized in a similar format as ETW based traces we usually consider as examples for our trace patterns:

Source  PID TID   Function         Value
System    0   0   Committed Memory 12,002,234,654
Process 844   0   Private Bytes    345,206,456
System    0   0   Committed Memory 12,002,236,654
Process 844   0   Working Set      122,160,068

Therefore, all other trace patterns such as adjoint thread (can be visualized via different colors on a graph), focus of tracing, characteristic message block (for graphs), activity regionsignificant event, and others can be applicable here. There are also some specific patterns such as global monotonicity and constant value that we discuss with examples in subsequent parts.

- Dmitry Vostokov @ + -