hi,
I am trying to use testlvs to test throughput and perform a "burn-in" of the
software. It seems I have succeeded (it is stable) but I can effectively
DOS the machine during the test.
director = 2.4.19-rc1 + [base redhat .config] + ipvs patch + julian's hidden
patch + heartbeat + ldirectord. 2-700mhz P3 & 512mb of ram, 7200rpm scsi
disk, etc. (valinux 2230). << I am using 2.4.19-rc1 because I have eepro
NICs >>.
real server = 2.2.x, apache, 2 proc, 512mb, requests set to reject according
to README file. specifically, srcnet is changed to 10.10.0.1 and then
make). I issue the command "route add -net 10.10.0.0 netmask 255.255.0.0
reject" to drop/reject the packets from LVS-director during test.
client/test box = 2.2.x, 2 proc, 512mb box. all three boxes are essentially
the same hardware. the command used is ./testlvs 10.0.1.10:80 -tcp -srcnum
62500 -packets 100000000
vmstat on LVS director shows sys consuming all CPU
procs memory swap io system
cpu
r b w swpd free buff cache si so bi bo in cs us sy
id
0 0 0 0 202392 103024 50160 0 0 1 2 23 6 0 1
99
0 0 0 0 202388 103024 50160 0 0 0 0 113 18 0 0
100
0 0 0 0 202372 103040 50160 0 0 0 12 122 46 0 0
100
0 0 0 0 202372 103040 50160 0 0 0 0 123 43 0 0
100
0 0 2 0 202368 103044 50160 0 0 0 45 640333 186 0
100 0
1 1 2 0 202272 103044 50160 0 0 0 51 841773 268 0
100 0
1 0 2 0 202152 103072 50160 0 0 0 78 909801 351 0
100 0
2 0 2 0 201976 103100 50160 0 0 0 76 966994 394 0
100 0
1 0 2 0 202068 103128 50160 0 0 0 76 1056957 403 0
100 0
0 0 2 0 202252 103128 50164 0 0 0 26 179219 70 0
100 0
0 0 2 0 202244 103132 50164 0 0 0 24 382777 111 0
97 3
0 0 2 0 202236 103136 50164 0 0 0 44 594000 177 0
98 2
0 0 2 0 202232 103140 50164 0 0 0 13 178590 49 0
100 0
<etc, continues for a while>
my actual question -- show_traffic.sh on the real server shows ~20-25k
packets/sec. this seems small to cause CPU to be 100% utilized. what am I
doing wrong?
|