You have plenty of CPU left, but it is very worrying that there always
is 1 "blocked" process.
If this is Squid, then my advice is to investigate using "async-io" or
"diskd".
-- Henrik Nordstrom Squid Hacker Brad Allyn wrote: > > $ vmstat 5 12 > procs memory page disks faults cpu > r b w avm fre flt re pi po fr sr wd0 fd0 in sy cs us sy id > 0 1 0 16360 5868 2 0 0 0 2 9 0 0 263 75 11 7 1 93 > 0 1 0 16212 5856 1 0 0 0 0 0 5 0 320 134 17 1 1 98 > 0 1 0 15508 5832 1 0 0 0 0 0 3 0 329 281 32 3 1 96 > 0 1 0 15600 5816 1 0 0 0 0 0 0 0 308 278 30 2 2 96 > 0 1 0 15552 5808 1 0 0 0 0 0 2 0 252 109 12 2 1 97 > 0 1 0 18116 5792 1 0 0 0 0 0 5 0 298 33 8 2 1 97 > 0 1 0 18116 5792 1 0 0 0 0 0 0 0 235 29 7 0 0 100 > 0 1 0 17432 5792 1 0 0 0 0 0 0 0 236 12 5 0 0 100 > 0 1 0 16960 5792 1 0 0 0 0 0 1 0 252 9 4 0 0 100 > 0 1 0 14780 5792 1 0 0 0 0 0 0 0 235 16 5 0 0 100 > 0 1 0 17196 5768 1 0 0 0 0 0 6 0 356 247 35 3 3 95 > 0 1 0 18196 5760 1 0 0 0 0 0 7 0 387 277 37 2 2 95 > $ > > Brad Allyn > DAEC Systems Admin. > 319 851 7844 > bradallyn@alliant-energy.com > > >>> Henrik Nordstrom <hno@hem.passagen.se> 06/08/01 01:36AM >>> > What does vmstat report? > > vmstat 5 12 > > -- > Henrik Nordstrom > Squid Hacler > > Brad Allyn wrote: > > > > I have freed up the Memory but the Cache is still extremely slow. Any ideas. > > > > Brad Allyn > > DAEC Systems Admin. > > 319 851 7844 > > bradallyn@alliant-energy.comReceived on Sun Jun 10 2001 - 13:30:04 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:00:35 MST