On Sun, 12 Dec 1999, Henrik Nordstrom wrote:
> Neale Banks wrote:
>
> > Sorry, I meant to add that the cache is currently 2x4GB. As this cache is
> > currently servicing > 2GB/day, there would be little obstacle to
> > justifying more disk.
>
> What is your LRU age? (see cachemgr).
That's the "Storage LRU Expiration Age"? ....
Cache information for squid:
Request Hit Ratios: 5min: 27.1%, 60min: 30.7%
Byte Hit Ratios: 5min: -3.5%, 60min: -1.4%
Storage Swap size: 7416851 KB
Storage Mem size: 102368 KB
Storage LRU Expiration Age: 7.96 days
Mean Object Size: 11.25 KB
Requests given to unlinkd: 0
Mmmm... given that I don't have any cache-digest happening, those negative
"Byte Hit Ratios" (as discussed in separate thread just now) are a bit of
concern. Maybe something like the quick-abort needs tweaking? It's
currently:
quick_abort_min 16 KB
quick_abort_max 16 KB
quick_abort_pct 95
FWIW, I am seeing in the cache.log:
aio_queue_request: WARNING - Running out of I/O theads
aio_queue_request: Perhaps you should increase NUMTHREADS
aio_queue_request: Or install more disks to share the load
But that _is_ a separate (performance) issue, right?
Thanks,
Neale.
Received on Sun Dec 12 1999 - 18:54:08 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:49:51 MST