Comments (4)
It doesn't filter. It will ignore invalid lines, and print that count as a warning. Sounds like your problem needs to be debugged!
from flamegraph.
Brendan, believe me, it does filter them. In order to reproduce here you are - two files:
https://drive.google.com/open?id=0B3DMXMfcPWF3T1ZSczdEM1U0N3c
the difference between sortedx.txt and sortedy.txt is in a dozen of lines: I filtered sortedx.txt and got sortedy.txt. Just run winmerge on these two files - and you will see that some lines are missing in sortedty.txt
So, if we run
./flamegraph.pl sortedy.txt > sortedy.svg
it must produce A LITTLE BIT LESS file than if we run
./flamegraph.pl sortedx.txt > sortedx.svg
right?
But in fact, I get sortedy.svg about 10MB in size, while sortedx.svg is 300 kb.
It should NOT be like this.
Note: I removed lines with these strings:
EPollArrayWrapper
org.apache.hadoop.net.unix.DomainSocketWatcher
java.lang.UNIXProcess.waitForProcessExit
org.apache.hadoop.util.Shell$1.run:509;java.io.BufferedReader.readLine:382;java.io.BufferedReader.readLine:317;java.io.BufferedReader.fill:154;java.io.InputStreamReader.read:184;sun.nio.cs.StreamDecoder.read:177;sun.nio.cs.StreamDecoder.implRead:325;sun.nio.cs.StreamDecoder.readBytes:283;java.io.BufferedInputStream.read:334;java.io.BufferedInputStream.read1:273;java.io.FileInputStream.read:272;java.io.FileInputStream.readBytes
org.apache.hadoop.util.Shell$1.run:509;java.io.BufferedReader.readLine:382;java.io.BufferedReader.readLine:317;java.io.BufferedReader.fill:154;java.io.InputStreamReader.read:184;sun.nio.cs.StreamDecoder.read:177;sun.nio.cs.StreamDecoder.implRead:325;sun.nio.cs.StreamDecoder.readBytes:283;java.io.BufferedInputStream.read:334;java.io.BufferedInputStream.read1:273;java.io.FileInputStream.read:272;java.io.FileInputStream.readBytes.:2
java.lang.Thread.run:745;java.util.concurrent.ThreadPoolExecutor$Worker.run:615;java.util.concurrent.ThreadPoolExecutor.runWorker:1145;java.util.concurrent.FutureTask.run:262;org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call:81;org.apache.hadoop.yarn.server.nodemanager.containermanager.launcher.ContainerLaunch.call:299;org.apache.hadoop.yarn.server.nodemanager.DefaultContainerExecutor.launchContainer:197;org.apache.hadoop.util.Shell$ShellCommandExecutor.execute:702;org.apache.hadoop.util.Shell.run:455;org.apache.hadoop.util.Shell.runCommand:524;org.apache.hadoop.util.Shell$ShellCommandExecutor.parseExecResult:715;java.io.BufferedReader.read:279;java.io.BufferedReader.read1:205;java.io.BufferedReader.fill:154;java.io.InputStreamReader.read:184;sun.nio.cs.StreamDecoder.read:177;sun.nio.cs.StreamDecoder.implRead:325;sun.nio.cs.StreamDecoder.readBytes:283;java.io.BufferedInputStream.read:334;java.io.BufferedInputStream.read1:273;java.io.FileInputStream.read:272;java.io.FileInputStream.readBytes.:2
These strings have too big quantity of calls (in comparison to the others). I think this is the reason of a bug.
from flamegraph.
It has minwidth for eliding data:
./flamegraph.pl --help
USAGE: ./flamegraph.pl [options] infile > outfile.svg
--title # change title text
--width # width of image (default 1200)
--height # height of each frame (default 16)
--minwidth # omit smaller functions (default 0.1 pixels)
from flamegraph.
so, if I want everything to be included, I need to specify --minwidth 0 and I will get everything.
THANK YOU VERY MUCH!
from flamegraph.
Related Issues (20)
- Failure on `Hello, world!` with `ERROR No stack counts found` HOT 2
- Error while using stack collapse for pmc on freebsd
- bjdump: /tmp/perf-$pid.map: File format not recognized ▒
- Capturing stacks on Amazon Linux 2 kernel 4.14 and 5.10 HOT 1
- Segment Fault and report errors when I using perf script -F ...,trace HOT 3
- Trace file recreated and new file has a 'n' added to the end of the name after running
- Adjust --minwidth options HOT 1
- Warn for low sample counts HOT 1
- How can it get some time internal flamegraph HOT 2
- Producing proper Flame Charts
- flamegraph hierarchical disorder HOT 1
- Supporting real number for samples data
- CPU flamegraphs using perf show wrong sample counts HOT 1
- show layer usage percent locally in zoom
- hot/cold FlameGraph 目前可以使用进行性能测试分析么?
- Is gprof currently supported?
- Suggestion: ./flamegraph.pl start with no parameters
- Add option to exclude 'search' functionality
- Unable to obtain the complete function call stack of `__memset_avx2_erms`.
- Not aggregating stacks for threads HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from flamegraph.