stress test deadlock involving vm and/or geom
phk at phk.freebsd.dk
Thu Sep 29 00:34:10 PDT 2005
In message <200509290731.j8T7V2OR007019 at gw.catspoiler.org>, Don Lewis writes:
>(kgdb) print runningbufspace
>$3 = 1585152
>(kgdb) print lorunningspace
>$4 = 524288
>$5 = 1048576
>so runningbufspace >> hirunningspace
>The bufdaemon and the syncer both ignore the runningbufspace limit.
>Maybe they should obey the limit, but each be guaranteed a minimum
I'm not quite sure what a/the sensible solution is, but the
lemming-syncer certainly is my prime suspect.
Poul-Henning Kamp | UNIX since Zilog Zeus 3.20
phk at FreeBSD.ORG | TCP/IP since RFC 956
FreeBSD committer | BSD since 4.3-tahoe
Never attribute to malice what can adequately be explained by incompetence.
More information about the freebsd-current