Analyse system boot up performance by ‘systemd’ or ‘systemd-analyse:’ in fedora

systemd-analyse binary has different options to list this: 2 of the interesting options are ‘time’ and ‘blame’

   ‘systemd-analyze time’ prints the time spent in the kernel before userspace has been reached, the time spent in the initial RAM disk (initrd)
before normal system userspace has been reached and the time normal system userspace took to initialize. Note that these measurements
simply measure the time passed up to the point where all system services have been spawned, but not necessarily until they fully finished
initialization or the disk is idle.

$ systemd-analyze time
Startup finished in 3.371s (kernel) + 4.063s (initrd) + 30.260s (userspace) = 37.694s
$

     systemd-analyze blame prints a list of all running units, ordered by the time they took to initialize. This information may be used to
optimize boot-up times. Note that the output might be misleading as the initialization of one service might be slow simply because it waits
for the initialization of another service to complete.

# systemd-analyze blame

17.154s systemd-fsck@dev-disk-by\x2duuid-20ad6689\x2db5a3\x2d4ec3\x2da9f4\x2de81d6360ca58.service
11.544s NetworkManager-wait-online.service
11.176s systemd-udev-settle.service
6.052s fedora-loadmodules.service
5.986s systemd-vconsole-setup.service
4.079s fedora-storage-init-late.service
3.922s fedora-storage-init.service
3.862s plymouth-start.service
3.759s systemd-fsck@dev-disk-by\x2duuid-3ba53f9b\x2df44b\x2d4c3f\x2daaa2\x2d0dfbbb75b1e5.service
2.702s initrd-switch-root.service
2.374s lvm2-monitor.service
2.310s systemd-modules-load.service
1.946s rtkit-daemon.service
1.910s plymouth-quit-wait.service
1.881s fedora-readonly.service
1.807s firewalld.service
1.789s iscsid.service
1.607s systemd-sysctl.service
1.558s systemd-remount-fs.service
968ms systemd-tmpfiles-clean.service
859ms systemd-user-sessions.service
818ms chronyd.service
731ms NetworkManager.service
700ms systemd-udev-trigger.service
567ms gdm.service
513ms boot.mount
489ms systemd-readahead-collect.service
476ms systemd-readahead-replay.service
431ms boot-efi.mount
416ms bluetooth.service
412ms dev-mqueue.mount
397ms sys-kernel-debug.mount
387ms dev-hugepages.mount
341ms systemd-tmpfiles-setup.service
334ms colord.service
325ms dev-disk-by\x2duuid-d080a09a\x2d3b45\x2d48d7\x2d9410\x2dba3b07443388.swap
316ms sm-client.service
316ms alsa-restore.service
312ms sendmail.service
285ms wpa_supplicant.service
256ms plymouth-read-write.service
250ms restorecond.service
236ms irqbalance.service
227ms ksm.service
225ms mcelog.service
206ms accounts-daemon.service
200ms abrt-ccpp.service
200ms abrt-vmcore.service
197ms home.mount
159ms avahi-daemon.service
133ms iscsi.service
111ms udisks2.service
110ms sshd.service
76ms rpcbind.service
70ms systemd-logind.service
61ms plymouth-switch-root.service
36ms upower.service
33ms tmp.mount
32ms systemd-journal-flush.service
25ms systemd-udevd.service
24ms systemd-readahead-done.service
23ms systemd-update-utmp-runlevel.service
20ms ksmtuned.service
15ms auditd.service
10ms polkit.service
6ms sys-fs-fuse-connections.mount
2ms systemd-random-seed-load.service
1ms sys-kernel-config.mount

2 thoughts on “Analyse system boot up performance by ‘systemd’ or ‘systemd-analyse:’ in fedora”

  1. “systemd-analyze critical-chain” is more useful than “blame”.

    Enabling systemd-readahead can also help with stat up time.

    • Zoidberg, Thanks for pointers on ‘crtical-chain’ and ‘readahead’.. I will try those and get back!

Comments are closed.