* [9fans] entire cache is busy, 999 dirty
@ 2010-01-31 5:04 Kenji Arisawa
2010-01-31 17:22 ` erik quanstrom
0 siblings, 1 reply; 3+ messages in thread
From: Kenji Arisawa @ 2010-01-31 5:04 UTC (permalink / raw)
To: Fans of the OS Plan 9 from Bell Labs
Hello 9fans,
Latterly my file server speaks annoying kernel message such as:
entire cache is busy, 999 dirty -- waking flush thread
cache is okay again
entire cache is busy, 999 dirty -- waking flush thread
cache is okay again
...
My question is:
(a) where these messages come from? venti?
(b) what is the problem?
(c) how to fix?
My plan9 partitions are:
hera% disk/prep -p /dev/sdC0/plan9
part 9fat 63 41027
part fossil 41027 21021587
part arenas 21021587 104943827
part isect0 104943827 109139939
part isect1 109139939 113336051
part nvram 113336051 113336052
part cache 113336052 115434108
part swap 115434108 117532164
part bloom 117532164 117597700
part vac 152100272 152100273
part fs 152100273 160826715
hera%
# don't mined "vac", that is my own use.
Kenji Arisawa
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [9fans] entire cache is busy, 999 dirty
2010-01-31 5:04 [9fans] entire cache is busy, 999 dirty Kenji Arisawa
@ 2010-01-31 17:22 ` erik quanstrom
2010-02-01 4:39 ` Kenji Arisawa
0 siblings, 1 reply; 3+ messages in thread
From: erik quanstrom @ 2010-01-31 17:22 UTC (permalink / raw)
To: 9fans
> My question is:
> (a) where these messages come from? venti?
fossil. (cache.c)
> (b) what is the problem?
> (c) how to fix?
good question. are you running the latest
version of fossil? if not, this could be caused by slow
disk writes which could in turn be caused by the
periodic bug that cinap_lenrek reported.
the 999 number is also curious. one would
expect that there are more than 999 blocks
in the cache.
- erik
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: [9fans] entire cache is busy, 999 dirty
2010-01-31 17:22 ` erik quanstrom
@ 2010-02-01 4:39 ` Kenji Arisawa
0 siblings, 0 replies; 3+ messages in thread
From: Kenji Arisawa @ 2010-02-01 4:39 UTC (permalink / raw)
To: Fans of the OS Plan 9 from Bell Labs
Hello erik,
> are you running the latest version of fossil?
probably not.
I will refresh my file server.
Thanks
Kenji Arisawa
On 2010/02/01, at 2:22, erik quanstrom wrote:
>> My question is:
>> (a) where these messages come from? venti?
>
> fossil. (cache.c)
>
>> (b) what is the problem?
>> (c) how to fix?
>
> good question. are you running the latest
> version of fossil? if not, this could be caused by slow
> disk writes which could in turn be caused by the
> periodic bug that cinap_lenrek reported.
>
> the 999 number is also curious. one would
> expect that there are more than 999 blocks
> in the cache.
>
> - erik
>
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2010-02-01 4:39 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2010-01-31 5:04 [9fans] entire cache is busy, 999 dirty Kenji Arisawa
2010-01-31 17:22 ` erik quanstrom
2010-02-01 4:39 ` Kenji Arisawa
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).