Interesting that Intel (https://newsroom.intel.de/news-releases/industr y-testing-shows-recently-released-security-updates-not-impacting- performance-real-world-deployments/) thinks that there is no performance issue.
Meassuring LFS builds looks a bit different to me (column 2+3 are build times in seconds and may not be 100% accurate but the trend is clear): Package 4.14.10 .12 Ratio -------------------------------------------- 034-binutils-pass1 97 113 1,16 035-gcc-pass1 261 296 1,13 036-linux-headers 6 17 2,83 037-glibc 149 178 1,19 038-gcc-libstdc++ 24 29 1,20 039-binutils-pass2 39 42 1,07 040-gcc-pass2 425 411 0,96 041-tcl 50 57 1,14 042-expect 4 6 1,50 043-dejagnu 2 2 1,00 044-check 6 8 1,33 045-ncurses 22 25 1,13 046-bash 21 25 1,19 047-bison 21 25 1,19 048-bzip2 1 1 1,00 049-coreutils 44 51 1,15 050-diffutils 19 23 1,21 051-file 6 6 1,00 052-findutils 29 34 1,17 053-gawk 12 14 1,16 054-gettext 49 57 1,16 055-grep 16 19 1,18 056-gzip 10 11 1,10 057-m4 15 17 1,13 058-make 5 6 1,20 059-patch 17 19 1,11 060-perl 51 58 1,13 061-sed 15 16 1,06 062-tar 27 32 1,18 063-texinfo 21 24 1,14 064-util-linux 31 36 1,16 065-xz 10 11 1,10 072-creatingdirs 1 1 1,00 073-createfiles 1 1 1,00 074-linux-headers 8 8 1,00 075-man-pages 1 1 1,00 076-glibc 197 227 1,15 077-adjusting 1 1 1,00 078-zlib 1 2 2,00 079-file 5 6 1,20 080-readline 4 5 1,25 081-m4 15 17 1,13 082-bc 3 3 1,00 083-binutils 114 121 1,06 084-gmp 25 31 1,24 085-mpfr 14 15 1,07 086-mpc 4 5 1,25 087-gcc 346 418 1,20 088-bzip2 4 2 0,50 089-pkg-config 17 21 1,23 090-ncurses 16 19 1,18 091-attr 3 3 1,00 092-acl 3 3 1,00 093-libcap 1 1 1,00 094-sed 15 19 1,26 095-shadow 10 12 1,20 096-psmisc 3 4 1,33 097-iana-etc 1 1 1,00 098-bison 20 24 1,20 099-flex 6 7 1,16 100-grep 16 19 1,18 101-bash 20 24 1,20 102-libtool 4 6 1,50 103-gdbm 5 5 1,00 104-gperf 2 3 1,50 105-expat 5 6 1,20 106-inetutils 29 35 1,20 107-perl 72 86 1,19 108-xml-parser 2 2 1,00 109-intltool 2 2 1,00 110-autoconf 2 2 1,00 111-automake 1 2 2,00 112-xz 8 10 1,25 113-kmod 4 6 1,50 114-gettext 95 109 1,14 115-libffi 3 4 1,33 116-Python 53 58 1,09 117-ninja 14 17 1,21 118-meson 1 1 1,00 119-procps-ng 8 9 1,12 120-e2fsprogs 16 18 1,12 121-coreutils 84 98 1,16 122-diffutils 20 24 1,20 123-gawk 13 16 1,23 124-findutils 30 35 1,16 125-groff 40 45 1,12 126-grub 34 42 1,23 127-less 4 4 1,00 128-gzip 10 11 1,10 129-iproute2 5 6 1,20 130-kbd 7 9 1,28 131-libpipeline 12 15 1,25 132-make 5 6 1,20 133-patch 17 20 1,17 134-sysklogd 1 1 1,00 135-sysvinit 1 1 1,00 136-eudev 10 12 1,20 137-util-linux 27 32 1,18 138-man-db 28 32 1,14 139-tar 31 36 1,16 140-texinfo 25 28 1,12 141-vim 18 11 0,61 142-cpio 21 25 1,19 143-openssl 42 47 1,11 144-lzo 9 11 1,22 145-btrfs-progs 5 6 1,20 146-mdadm 2 3 1,50 147-belfs 68 80 1,17 148-elfutils 21 25 1,19 150-strippingagain 8 10 1,25 153-bootscripts 1 1 1,00 155-symlinks 1 1 1,00 156-network 1 1 1,00 157-usage 1 1 1,00 158-profile 1 1 1,00 159-inputrc 1 1 1,00 160-etcshells 1 1 1,00 162-fstab 1 1 1,00 300-linux-kernel 4079 4654 1,14 -------------------------------------------- >> Total 7391 8424 1,13 Looks like doing a LFS build is not a "real world" thing in Intel's understanding. -- Thomas -- http://lists.linuxfromscratch.org/listinfo/lfs-support FAQ: http://www.linuxfromscratch.org/blfs/faq.html Unsubscribe: See the above information page Do not top post on this list. A: Because it messes up the order in which people normally read text. Q: Why is top-posting such a bad thing? A: Top-posting. Q: What is the most annoying thing in e-mail? http://en.wikipedia.org/wiki/Posting_style
