terrible performance in 6.1beta4
Miguel
mmiranda at 123.com.sv
Thu Mar 30 01:05:43 UTC 2006
Hi, im loading a lot of information to a postgresql 8.1.3 database, im
using the copy command, using the same file and version of postgres in
gentoo it spend a few minutes (~4-5), in freebsd 6.1-beta4 it has
already spent 25 minutes and the server apparently is doing nothing, and
the reponse time of remote logins or running simple commands like ls -l
/etc takes a lot of time (35 secs ort so), cpu usage is very low:
napstats# top -S
last pid: 10712; load averages: 0.13, 0.09,
0.02 up
2+03:43:32 18:59:57
122 processes: 3 running, 87 sleeping, 32 waiting
CPU states: 5.3% user, 0.0% nice, 0.9% system, 0.2% interrupt, 93.6%
idle
Mem: 572M Active, 972M Inact, 266M Wired, 90M Cache, 213M Buf, 2960K Free
Swap: 4096M Total, 216K Used, 4096M Free
PID USERNAME THR PRI NICE SIZE RES STATE C TIME WCPU COMMAND
11 root 1 171 52 0K 16K CPU1 1 51.6H 93.46% idle: cpu1
12 root 1 171 52 0K 16K RUN 0 51.5H 92.92% idle: cpu0
10671 postgres 1 -8 0 538M 516M biord 1 0:46 8.98% postgres
10384 postgres 1 -8 0 538M 528M biord 0 3:23 0.00% postgres
37 root 1 -32 -151 0K 16K WAIT 0 2:51 0.00% swi4:
clock sio
55 root 1 20 0 0K 16K syncer 0 1:44 0.00% syncer
8862 postgres 1 -4 0 537M 524M ufs 1 1:10 0.00% postgres
3 root 1 -8 0 0K 16K - 0 0:42 0.00% g_up
4 root 1 -8 0 0K 16K - 0 0:38 0.00% g_down
36 root 1 -44 -163 0K 16K WAIT 0 0:25 0.00% swi1: net
29 root 1 -68 -187 0K 16K WAIT 0 0:22 0.00% irq17:
bge0
32 root 1 -64 -183 0K 16K WAIT 0 0:16 0.00% irq20:
atapci1
54 root 1 -16 0 0K 16K psleep 0 0:12 0.00% bufdaemon
39 root 1 -16 0 0K 16K - 0 0:12 0.00% yarrow
2 root 1 -8 0 0K 16K - 0 0:08 0.00% g_event
61 root 1 96 0 0K 16K - 0 0:05 0.00% schedcpu
414 root 1 96 0 7532K 1536K select 0 0:04 0.00% ntpd
53 root 1 171 52 0K 16K pgzero 0 0:03 0.00% pagezero
437 root 1 96 0 9352K 2812K select 0 0:02 0.00% sendmail
napstats# systat -vmstat 1
4 users Load 0.07 0.08 0.02 Mar 29 19:01
Mem:KB REAL VIRTUAL VN PAGER SWAP PAGER
Tot Share Tot Share Free in out in out
Act 581812 4448 633656 6804 80896 count
All 1937176 6608497246344 13788 pages
Interrupts
Proc:r p d s w Csw Trp Sys Int Sof Flt cow 4145 total
3 56 990 54 373 338 13 27 272880 wire
14: ata
585256 act 4
17: bge
0.7%Sys 0.0%Intr 1.9%User 0.0%Nice 97.4%Idl 1009296 inact 146
20: ata
| | | | | | | | | | 77936 cache
21: uhc
> 2960 free 1997
lapic0: ti
daefr 1998
lapic1: ti
Namei Name-cache Dir-cache prcfr
Calls hits % hits % react
pdwake
zfod pdpgs
Disks ad4 ad8 ofod intrn
KB/t 0.00 24.49 %slo-z 218464 buf
tps 0 146 190 tfree 1727 dirtybuf
MB/s 0.00 3.49 100000 desiredvnodes
% busy 0 104 27208 numvnodes
24992 freevnodes
i see a lot of fault when using vmstat :
napstats# vmstat 1 10
procs memory page disks faults cpu
r b w avm fre flt re pi po fr sr ad4 ad8 in sy cs us
sy id
1 3 0 633036 78428 17 0 0 0 24 17 0 0 218 103 499 0
0 100
0 3 0 633036 76952 66 0 0 0 329 0 0 188 383 843 1286
1 1 98
0 3 0 633036 75008 68 0 0 0 477 0 0 119 314 1020 1007
1 1 98
0 3 0 633036 74032 60 0 0 0 244 0 0 175 371 295 1143
2 0 98
0 3 0 633036 71900 128 0 0 0 537 0 0 163 359 719 1100
3 1 96
0 3 0 633036 68680 151 0 0 0 801 0 1 136 329 989 1145
4 2 94
0 3 0 633036 67196 48 0 0 0 371 0 2 216 404 454 1273
2 1 97
0 3 0 633036 108616 115 7 0 0 657 10933 0 128 318 890 1090
3 4 93
0 3 0 633036 105504 145 0 0 0 676 0 0 173 328 842 1128
5 3 93
0 3 0 633036 103908 76 0 0 0 387 0 0 144 293 448 890 3
0 96
What should i check for improve performance?
this is a dell poweredge sc430, intel EM64T dual core , 2 gb ram, two
250G sata disks, installed using the freebsd's amd64 port.
---
thanks
More information about the freebsd-questions
mailing list