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