[Bug 253968] 13.0-BETA4: UFS with journaled soft-updates is three times SLOWER than before
bugzilla-noreply at freebsd.org
bugzilla-noreply at freebsd.org
Wed Mar 3 09:08:32 UTC 2021
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=253968
--- Comment #7 from Mark Millard <marklmi26-fbsd at yahoo.com> ---
(In reply to Mark Millard from comment #6)
[I use -noatime mounts, by the way.]
Given the reports I got a surprise booting the OverDrive 1000
via 13.0-BETA4 and trying the operations on the SSD (not
the boot media this time), evidence of definite changes from
the main (14) vintage that I have things at for normal booting:
# time -l make extract
===> firefox-85.0.2,2 depends on file: /usr/local/sbin/pkg - found
===> Fetching all distfiles required by firefox-85.0.2,2 for building
===> Extracting for firefox-85.0.2,2
=> SHA256 Checksum OK for firefox-85.0.2.source.tar.xz.
93.39 real 55.46 user 34.47 sys
76576 maximum resident set size
30 average shared memory size
4 average unshared data size
128 average unshared stack size
26460 page reclaims
0 page faults
0 swaps
15569 block input operations
994 block output operations
16 messages sent
14 messages received
0 signals received
16752 voluntary context switches
1192 involuntary context switches
Vastly fewer block output operations (and less time).
# time -l rm -fr work
12.74 real 0.29 user 7.80 sys
3920 maximum resident set size
8 average shared memory size
4 average unshared data size
128 average unshared stack size
588 page reclaims
0 page faults
0 swaps
644 block input operations
360 block output operations
0 messages sent
0 messages received
0 signals received
1093 voluntary context switches
337 involuntary context switches
So even if there are issues still, apparently some have
been taken care of.
For reference:
# uname -apKU
FreeBSD generic 13.0-BETA4 FreeBSD 13.0-BETA4 #0
releng/13.0-n244592-e32bc253629: Fri Feb 26 08:02:53 UTC 2021
root at releng1.nyi.freebsd.org:/usr/obj/usr/src/arm64.aarch64/sys/GENERIC arm64
aarch64 1300139 1300139
--
You are receiving this mail because:
You are the assignee for the bug.
More information about the freebsd-bugs
mailing list