.\" -*- nroff -*- .TH STAP\-MERGE 1 .SH NAME stap\-merge \- systemtap per-cpu binary merger .\" macros .\" do not nest SAMPLEs .de SAMPLE .br .nr oldin \\n(.i .RS .nf .nh .. .de ESAMPLE .hy .fi .RE .in \\n[oldin]u .. .SH SYNOPSIS .br .B stap\-merge [ .I OPTIONS ] [ .I INPUT FILENAMES ] .SH DESCRIPTION The stap\-merge executable applies when the \-b option has been used while running a .IR stap script. The \-b option will generate files per\-cpu, based on the timestamp field. Then stap\-merge will merge and sort through the per-cpu files based on the timestamp field. .SH OPTIONS The systemtap merge executable supports the following options. .TP .B \-v Verbose mode, displays three extra fields per set of collected data. .SAMPLE .BR [cpu number, sequence number of data, the length of the data set] .ESAMPLE .TP .BI \-o " OUTPUT_FILENAME" Specify the name of the file you would like the output to be redirected into. If this option is not specified than the output will be pushed to standard out. .SH EXAMPLES .SAMPLE $ stap \-v \-b \-e 'probe syscall.open { printf("%s(%d) open\\n", execname(), pid()) }' .ESAMPLE This should result in several .I stpd_cpu files (each labled with a number representing which cpu the file was produced from). .SAMPLE $ stap\-merge \-v stpd_cpu0 stpd_cpu1 .ESAMPLE Running the stap\-merge program in the same directory as the stap script earlier in the example, will produce an ordered sequence of packets with the three part label for each set of data. This result will be pushed through the standard output. An output file could have been specified using the "\-o" option. .SH FILES .TP Important files and their corresponding paths can be located in the stappaths (7) manual page. .SH SEE ALSO .nh .nf .IR stapprobes (3stap), .IR stappaths (7), .IR staprun (8), .IR stapvars (3stap), .IR stapex (3stap), .IR stap\-server (8), .IR gdb (1) .SH BUGS Use the Bugzilla link of the project web page or our mailing list. .nh .BR http://sourceware.org/systemtap/ , . .hy