Prepend filter like:

    #!/usr/bin/perl

    @filter=q(mawk '{print "mytag\t" $0}');

    open(STDOUT, '|-', @filter) || die ("Cannot start @filter");
    while($read=sysread(STDIN,$buf,32767)){syswrite(STDOUT,$buf);}
    close STDOUT;
    exit 8;

It gives 80 MB/s.

comment #4:

>     sed -e 's/^/abc\t/'
>
> is 4 times faster than:
>
>     perl -pe 's/^/abc\t/'
>

2x faster than parallel-20170722.

Should take < 10s

    time parallel --tag --line-buffer seq  ::: {1000000..1000029} >/dev/null

Introduce --fasttag: If --tag does not change use this.