On Tue, 5 Mar 2002, Edward Millington wrote: > Hi there! > > I am do a very small review of oops 1.5.21 - 1.5.22. running on Solaris, FreeBsd & >Linux. > > Is there anyone out there that have oops running with over 18GB os cache in a high >load environment with requests over 50+ req/sec, 900+ clients & 980+ thread?
Yes, I can monitor one system with 34G raw disk storage. It handle from 400 to 1500 connections at near 100-150 req/sec (near 8-9 Mbit/sec transparent/wccp2 traffic at peak time). This is Solaris on dual pentium machine, 1G memory (from which oops really use near 400-500M). Recently they added second disk. This bring one problem: when url database (berkeley_db 2.7.7) become very large then db_sync can take long time. This can increase responce time and decrease hit rate. We try to play with db version and configuration to avoid the problem. > > I am particularly interested in linux performance at this load. > > What are the system hardware configurations? > > Thank you very much. > > Best regards, > > Edward Millington. BSc, Network+ > Systems Administrator > Cariaccess Communications Ltd. > Palm Plaza > Wildey > St. Michael > Barbados > 1-246-430-7435 > Fax : 1-246-431-0170 > [EMAIL PROTECTED] > www.cariaccess.com > Igor Khasilev | PACO Links, igor at paco dot net | ===================================================================== If you would like to unsubscribe from this list send message to [EMAIL PROTECTED] with "unsubscribe oops-eng" in message body. Archive is accessible on http://lists.paco.net/oops-eng/
