squid.1.NOVM.20+retry memory usage report bug

Hello,

I'm using squid.NOVM+retry under Linux 2.0.30.

Since I upgraded from NOVM.17+retry to NOVM.20+retry, I noticed that the
amount
of memory reported by cachemgr.cgi for 'Pool for disk I/O' started to grow. It
was usually under 200/300KB with NOVM.17 but now it is over 20 MB.
I suspected that the real amount of memory used was nearly the same between 17
and 20 because the process's size was around 32-35 MB for both versions. Now
I'm pretty sure it is the case because the amount of memory reported by
cachemgr.cgi is greater than the size of the process. And the difference keeps
growing...

cachemgr.cgi reports this:
        StoreEntry 110244 x 52 bytes = 5598 KB
        URL strings = 5415 KB
        IPCacheEntry 737 x 40 bytes = 28 KB
        FQDNCacheEntry 195 x 56 bytes = 10 KB
        Hash link 0 x 12 bytes = 0 KB
        Pool MemObject structures 11 x 80 bytes = 0 KB ( 0
free)
        Pool for Request structur 11 x 4408 bytes = 47 KB ( 0
free)
        Pool for in-memory object 0 x 4096 bytes = 0 KB ( 0
free)
        Pool for disk I/O 2975 x 8192 bytes = 23800 KB ( 0
free)
        NetDB Address Entries 0 x 76 bytes = 0 KB
        NetDB Host Entries 0 x 8 bytes = 0 KB
        NetDB Peer Entries 0 x 24 bytes = 0 KB
        ClientDB Entries 72 x 292 bytes = 20 KB
        Miscellaneous = 229 KB
        Total Accounted = 35198 KB

ps ux reports this:
squid 923 1.0 75.9 34596 23432 ? S Feb 24 26:04 /var/squid/bin/squid
-sYDFb -f /var/squid/conf/squid.conf

Hum, looks like a '--' disappeared somewhere in the code :)

Lionel Bouton.
Received on Wed Feb 25 1998 - 10:14:22 MST