Compile test cotinues

Szabo, Balazs (dlux@dlux.sch.bme.hu)
Thu, 28 Jan 1999 19:36:07 +0100 (CET)


Hello!

Here is the new results of the interactivity and kernel-compiling
test.
The evaluation in short:

I made heavy load with the kernel-compiling (make -j), and
paralelly, I started 7 other tasks like this:
------------
#!/bin/sh
while /bin/true
do
/bin/echo -n "#"
sleep $1
done
------------
The parameter was 1 2 4 8 16 32 64.
These programs echoes one symbol after every x seconds. These are
redirected to different files, and counted after finishing the
kernel-compilation has finished.
The reading of the test results:
First line: Kernel image name, user space, kernel space time, and
CPU% (like time), and the total compilation time in seconds.
Second line: The (number of #s per second * 10000 * program
parameter ) in the shell script outputs. If this number is lower, it
menas that the program had less time to put the # sign. In normal
case, every test result should be around 10000, because, the shell
script speed is 1/parameter hashmarks/sec.
ar6 means arca-6,
p7 means pre7.

The best kernel-swap code is written in the pre6 I think...

2.0.35-3 : usr: 868.77s, sys: 6.83s, cpu:74%, total: 1321s
01: 2420 02: 3646 04: 4932 08: 6112 16: 6898 32: 7746 64: 8714
2.0.35-3 : usr: 633.65s, sys: 3.75s, cpu:65%, total: 1100s
01: 2262 02: 3361 04: 4651 08: 5450 16: 5814 32: 7558 64: 8139
2.1.131-3 : usr: 862.72s, sys: 6.94s, cpu:46%, total: 2140s
01: 3928 02: 5091 04: 5549 08: 5867 16: 6053 32: 6577 64: 7473
2.1.131-3 : usr: 656.56s, sys: 4.16s, cpu:29%, total: 2623s
01: 2595 02: 3170 04: 3719 08: 4207 16: 4024 32: 5122 64: 5609
2.2.0-ac1 : usr: 845.69s, sys: 7.55s, cpu:86%, total: 1096s
01: 3173 02: 4469 04: 5983 08: 7004 16: 8026 32: 8755 64: 9339
2.2.0-ac1 : usr: 877.54s, sys: 3.64s, cpu:86%, total: 1145s
01: 3106 02: 4451 04: 6074 08: 6982 16: 7959 32: 8378 64: 8936
2.2.0-ar1 : usr: 853.10s, sys: 6.57s, cpu:89%, total: 1069s
01: 3234 02: 4711 04: 6394 08: 7105 16: 8376 32: 9273 64: 9573
2.2.0-ar1 : usr: 885.22s, sys: 0.44s, cpu:90%, total: 1102s
01: 3418 02: 4859 04: 6528 08: 7761 16: 8704 32: 9284 64: 9864
2.2.0-ar6 : usr: 842.82s, sys: 5.23s, cpu:88%, total: 1072s
01: 3236 02: 4776 04: 6380 08: 7985 16: 8805 32: 8955 64: 9552
2.2.0-ar6 : usr: 885.03s, sys: 5.90s, cpu:85%, total: 1164s
01: 3502 02: 4910 04: 6696 08: 7691 16: 8515 32: 9065 64: 9340
2.2.0-f-1 : usr: 849.33s, sys: 2.46s, cpu:89%, total: 1077s
01: 3005 02: 4285 04: 5751 08: 6976 16: 8163 32: 8905 64: 9499
2.2.0-f-1 : usr: 885.24s, sys: 7.20s, cpu:89%, total: 1103s
01: 3043 02: 4529 04: 5905 08: 7101 16: 8116 32: 8695 64: 9275
2.2.0-p5-1 : usr: 883.34s, sys: 7.23s, cpu:86%, total: 1158s
01: 2959 02: 4262 04: 5556 08: 6764 16: 7592 32: 8559 64: 8835
2.2.0-p5-1 : usr: 849.86s, sys: 2.57s, cpu:87%, total: 1096s
01: 2899 02: 4267 04: 5690 08: 6565 16: 7586 32: 8170 64: 8754
2.2.0-p5-am : usr: 875.72s, sys: 2.28s, cpu:87%, total: 1128s
01: 3190 02: 4395 04: 5919 08: 7018 16: 7797 32: 8506 64: 9073
2.2.0-p5-am : usr: 851.36s, sys: 8.46s, cpu:84%, total: 1152s
01: 3219 02: 4425 04: 5692 08: 6873 16: 7636 32: 8331 64: 8886
2.2.0-p6-1 : usr: 874.55s, sys: 9.75s, cpu:88%, total: 1113s
01: 3881 02: 5552 04: 6971 08: 8193 16: 9199 32: 9487 64: 9774
2.2.0-p6-1 : usr: 858.25s, sys: 1.39s, cpu:89%, total: 1077s
01: 3572 02: 5047 04: 6977 08: 7571 16: 8759 32: 9204 64: 9501
2.2.0-p7-1 : usr: 884.57s, sys: 4.16s, cpu:62%, total: 1602s
01: 2970 02: 4218 04: 4542 08: 5391 16: 7088 32: 7188 64: 8386
2.2.0-p7-1 : usr: 720.24s, sys: 1.28s, cpu:41%, total: 2019s
01: 2188 02: 2782 04: 3425 08: 3960 16: 4356 32: 5544 64: 5069
2.2.0-p7ac191: usr: 891.44s, sys: 2.35s, cpu:87%, total: 1151s
01: 3116 02: 4444 04: 5903 08: 6875 16: 8055 32: 8889 64: 9444
2.2.0-p7ac191: usr: 866.36s, sys: 6.66s, cpu:85%, total: 1145s
01: 3054 02: 4381 04: 5794 08: 6772 16: 7959 32: 8657 64: 8936
2.2.0-p7ac20: usr: 902.98s, sys: 6.30s, cpu:59%, total: 2013s
01: 1907 02: 2672 04: 3397 08: 4291 16: 5563 32: 6675 64: 7629
2.2.0-p7ac20: usr: 742.73s, sys: 3.36s, cpu:63%, total: 1659s
01: 1669 02: 2446 04: 3446 08: 4290 16: 5110 32: 5977 64: 6556
2.2.0-p8 : usr: 891.57s, sys: 5.12s, cpu:87%, total: 1150s
01: 3111 02: 4502 04: 5910 08: 6953 16: 7926 32: 8621 64: 9456
2.2.0-p8 : usr: 852.79s, sys: 5.58s, cpu:87%, total: 1113s
01: 2946 02: 4258 04: 5570 08: 6684 16: 7762 32: 8337 64: 9200
2.2.0-p8a109: usr: 879.36s, sys: 2.18s, cpu:56%, total: 2555s
01: 1275 02: 1878 04: 2519 08: 3099 16: 3819 32: 4883 64: 6010
2.2.0-p8a109: usr: 893.35s, sys: 2.14s, cpu:85%, total: 1220s
01: 2728 02: 3883 04: 5210 08: 6160 16: 6947 32: 7864 64: 8389
2.2.0-p8a25 : usr: 891.11s, sys: 5.35s, cpu:91%, total: 1418s
01: 2277 02: 3370 04: 4455 08: 5245 16: 6542 32: 7445 64: 8121
2.2.0-p8a25 : usr: 870.12s, sys: 1.90s, cpu:89%, total: 1371s
01: 2281 02: 3309 04: 4402 08: 5248 16: 6181 32: 7230 64: 7930
2.2.0-p8a26 : usr: 876.76s, sys: 1.73s, cpu:91%, total: 1381s
01: 2294 02: 3358 04: 4604 08: 5443 16: 6254 32: 6949 64: 7876
2.2.0-p8a26 : usr: 891.10s, sys: 2.66s, cpu:90%, total: 1454s
01: 2309 02: 3244 04: 4426 08: 5333 16: 5938 32: 7038 64: 7918

dLux

--
== Whip me. Beat me. Make me maintain AIX ==

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/