page faults with phys. io?

From: Dirk Vleugels <>
Date: Sun, 25 Jan 1998 17:34:35 +0100


remembering a posting from Duane Wessels he mentioned that the ratio
between hitcount and page fault should be very small. ~80k pf's with
350k hits seems a bit high. This machine is running solaris 2.5.1, and
as far as i remember solaris will use the page mechanism to do all
disk writes, correct? So these numbers below aren't really a
indication that our cache get paged out? I'm certain our machine isn't
running low on ram.




Squid Object Cache: Version 1.1.17+retry
Start Time: Sat, 24 Jan 1998 18:23:22 GMT
Current Time: Sun, 25 Jan 1998 16:09:48 GMT
Connection information for squid:
        Number of TCP connections: 281721
        Number of UDP connections: 77899
        Connections per hour: 16516.1
        Select loop called: 3987673 times, 19.657 ms avg
Cache information for squid:
        Storage Swap size: 2440 MB
        Storage Mem size: 116182 KB
        Storage LRU Expiration Age: 365.00 days
        Requests given to unlinkd: 0
        Unused fileno stack count: 0
Resource usage for squid:
        CPU Time: 6089 seconds (2497 user 3592 sys)
        CPU Usage: 8%
        Maximum Resident Size: 0 KB
        Page faults with physical i/o: 78152

Dirk Vleugels
FTP- & Proxy-Services                UUnet Deutschland GmbH
Tel. +49 231 972 00                  Emil-Figge-Strasse 80
Fax. +49 231 972 1180                44227 Dortmund, Germany              URL:
Received on Sun Jan 25 1998 - 08:40:48 MST

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:38:30 MST