> While investigating this, we came up with a test scenario that > consistantly reproduced this behavior. The behavior is that if you > have a system with 4gb of memory, and create a 1gb file in /tmp, and a > 1gb file in /var/tmp, and then you start 2 processes each with an rss > of about 1gb, your reads from /tmp get very... very..... slow. The > file in /tmp was maxing out at about 6mb/sec read, with a typical read > speed of about 2.5mb/sec as measured by iostat. The file from /var/tmp > reads about 50mb/sec.
Do your swap device and /var/tmp share the same physical disk? Your description of the problem reminds me of: 5014737 UFS can flood underlying device with writes, delaying service If both the swap device and /var/tmp are sharing the same disk, it's possible that your reads of the file on /tmp are getting stuck in line behind the I/Os to swap out other dirty pages. How do you have your swap device configured? -j _______________________________________________ perf-discuss mailing list perf-discuss@opensolaris.org
