On 30/03/04 19:27 +0530, Suresh Ramasubramanian wrote: > [3/30/2004 7:17 PM] Devdas Bhagat : > > > I would leave swap off on boxes which do a lot of disk IO. > > iostat/vmstat data here would be really useful. > > > > $ vmstat 5 > > procs memory page disks faults cpu > > r b w avm fre flt re pi po fr sr ad4 ad6 in sy cs us sy id > > 18 2 0 1046816 133216 648 2 1 1 552 1203 0 0 1517 8249 3369 14 72 15 > > 42 3 0 1047360 121764 1311 0 1 0 399 0 53 0 1518 33221 30699 13 87 0 > > 31 20 0 1056896 112968 1190 0 0 0 395 0 91 0 1607 31584 28209 11 82 7 > > 47 2 0 1081120 96084 2032 0 0 0 707 0 118 0 1198 27977 32636 11 89 0 > > 43 1 0 1088992 92208 1153 0 1 0 582 0 45 0 1674 42155 25758 16 84 0 > > 44 1 0 1100428 83808 1340 0 1 0 569 0 35 0 1422 32733 33175 12 88 0 > > 38 1 0 1107396 78320 1056 0 0 0 512 0 61 0 1598 34317 30187 14 86 0 > > 30 1 0 1133068 68104 1272 0 0 0 389 0 30 0 1470 33400 32184 12 88 0 A mailserver which is choked on CPU rather than disk? Highly tuned system, or too much content filtering. Methinks you need to start with a SPEWS++ like effort locally.
Devdas Bhagat ------------------------------------------------------- This SF.Net email is sponsored by: IBM Linux Tutorials Free Linux tutorial presented by Daniel Robbins, President and CEO of GenToo technologies. Learn everything from fundamentals to system administration.http://ads.osdn.com/?ad_id=1470&alloc_id=3638&op=click _______________________________________________ linux-india-help mailing list [EMAIL PROTECTED] https://lists.sourceforge.net/lists/listinfo/linux-india-help
