[Bug 223786] Remounting a UFS filesystem read-only takes very long time

[bugzilla-noreply at freebsd.org]

https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=223786

--- Comment #7 from Mikhail Teterin <mi at FreeBSD.org> ---
(In reply to Kirk McKusick from comment #3)
> include the -o noatime option

No obvious difference:

root at narawntapu:/etc/mail (1024) mount -orw,noatime /
root at narawntapu:/etc/mail (1025) touch q
root at narawntapu:/etc/mail (1026) rm q
root at narawntapu:/etc/mail (1027) mount -oro -u /
load: 0.71  cmd: mount 27675 [biowr] 7.92r 0.00u 0.72s 4% 2224k
load: 0.52  cmd: mount 27675 [biowr] 54.83r 0.00u 2.64s 2% 2224k
load: 0.47  cmd: mount 27675 [biowr] 68.05r 0.00u 3.12s 2% 2224k
load: 0.58  cmd: mount 27675 [biowr] 121.83r 0.00u 5.08s 3% 2224k
load: 0.36  cmd: mount 27675 [biowr] 254.59r 0.00u 9.97s 2% 2224k
...

> time -l

root at narawntapu:/etc/mail (1034) /usr/bin/time -l mount -oro /
      330,18 real         0,00 user        13,01 sys
      2212  maximum resident set size
        22  average shared memory size
         7  average unshared data size
       121  average unshared stack size
       112  page reclaims
         0  page faults
         0  swaps
         0  block input operations
    344120  block output operations
         0  messages sent
         0  messages received
         0  signals received
    344178  voluntary context switches
      1014  involuntary context switches

The entire FS is:

Filesystem   1M-blocks  Used Avail Capacity  Mounted on
/dev/ada0s1a     22808 16268  4715    78%    /

*what* 344120 "block output operations"?!

-- 
You are receiving this mail because:
You are the assignee for the bug.