|
|
|
* Following Perf stats were collected
|
|
-------------------------------------------
|
|
|
|
0 - Memory Reservation statistics:
|
|
|
|
CPU_COMMITTED_INST
|
|
CPU_CYCLE_COUNT
|
|
L2_LWARX_COMPLETE
|
|
L2_STWCX_SUCCESS
|
|
L2_READ_AFTER_WRITE
|
|
L2_WRITE_AFTER_WRITE
|
|
|
|
1 - L1 Cache performance
|
|
|
|
L2_MISS_I_FETCH
|
|
L2_HIT_I_FETCH
|
|
CPU_ICACHE_HIT
|
|
L2_MISS_D_FETCH
|
|
L2_MISS_STORE
|
|
L2_HIT_STORE
|
|
L2_HIT_D_FETCH
|
|
CPU_DCACHE_HIT
|
|
|
|
2 - L2 Cache performance
|
|
|
|
L2_MISS_D_FETCH
|
|
L2_MISS_I_FETCH
|
|
L2_MISS_STORE
|
|
L2_HIT_D_FETCH
|
|
L2_HIT_I_FETCH
|
|
L2_HIT_STORE
|
|
|
|
3 - Shadow TLB misses - L2 Miss Eviction
|
|
|
|
CPU_COMMITTED_INST
|
|
CPU_CYCLE_COUNT
|
|
CPU_DTLB_RELOAD
|
|
CPU_ITLB_RELOAD
|
|
L2_MISS_EVICTION
|
|
L2_MISS_D_FETCH
|
|
L2_MISS_I_FETCH
|
|
L2_MISS_STORE
|
|
|
|
4 - PLB6 Commands
|
|
|
|
PLB_MASTER_COMMAND
|
|
PLB_MASTER_READ
|
|
PLB_MASTER_RWITM
|
|
PLB_MASTER_DCLAIM
|
|
PLB_MASTER_WRITE
|
|
PLB_MASTER_INTVN_M
|
|
PLB_MASTER_INTVN_S
|
|
PLB_MASTER_MEM_DATA
|
|
|
|
=======================================================
|
|
|
|
A loop with an active tracepoint inside was executed a million times.
|
|
Time was taken before entering the loop and after exiting it. Average time
|
|
was then calculated. At very start, application sleeps 2 seconds to wait
|
|
that everything is initialized.
|
|
|
|
|
|
* LTTng 2.1.1 stats
|
|
-------------------------------------------
|
|
|
|
root@du1:~# ./rbs-perf-test -t 0 -s -c ./ltt-test-2.1.1 -l 1000000 -t 1
|
|
--- Memory Reservation statistics - exec cmd - ./ltt-test-2.1.1 ---
|
|
Benchmark test starts now...
|
|
Time it took to loop 1000000 times : 3 s 586888706 ns | [ 3586 ns per tp ]
|
|
Stats for pid 2826
|
|
Counters enabled in user and in kernel space
|
|
------------------------------------------------------------------
|
|
2735477556 Instruction count # 0.48 Instructions per Cycle
|
|
5690106496 CPU cycles # 1.596 GHz
|
|
3306491 Completed lwarx instructions
|
|
3306180 Successful stwcx instructions
|
|
2062689 L2 Read after Write
|
|
99173776 L2 Write after Write
|
|
1245 Context Switches # 0.000 M/sec
|
|
2 CPU-migrations # 0.000 M/sec
|
|
359 Page Faults # 0.000 M/sec
|
|
3566.016640 Task Clock # 0.635 CPUs utilized
|
|
5.615581770 seconds time elapsed
|
|
|
|
root@du1:~# ./rbs-perf-test -t 1 -s -c ./ltt-test-2.1.1 -l 1000000 -t 1
|
|
--- L1 Cache performance - exec cmd - ./ltt-test-2.1.1 ---
|
|
Benchmark test starts now...
|
|
Time it took to loop 1000000 times : 3 s 618456855 ns | [ 3618 ns per tp ]
|
|
Stats for pid 2846
|
|
Counters enabled in user and in kernel space
|
|
------------------------------------------------------------------
|
|
1382879363 L1-icache-loads # 387.507 M/sec
|
|
1376632814 L1-icache-load-hits # 99.55 of all L1-icache hits
|
|
838963771 L1-dcache-loads # 235.092 M/sec
|
|
705560597 L1-dcache-load-hits # 84.10 of all L1-dcache hits
|
|
1157 Context Switches # 0.000 M/sec
|
|
2 CPU-migrations # 0.000 M/sec
|
|
358 Page Faults # 0.000 M/sec
|
|
3568.655296 Task Clock # 0.632 CPUs utilized
|
|
5.645967350 seconds time elapsed
|
|
|
|
root@du1:~# ./rbs-perf-test -t 3 -s -c ./ltt-test-2.1.1 -l 1000000 -t 1
|
|
--- Shadow TLB misses - L2 Miss Eviction - exec cmd - ./ltt-test-2.1.1 ---
|
|
Benchmark test starts now...
|
|
Time it took to loop 1000000 times : 3 s 492358390 ns | [ 3492 ns per tp ]
|
|
Stats for pid 2863
|
|
Counters enabled in user and in kernel space
|
|
------------------------------------------------------------------
|
|
2733834879 Instruction count # 0.50 Instructions per Cycle
|
|
5508422280 CPU cycles # 1.595 GHz
|
|
91880488 dcache shadow TLB misses # 26.607 M/sec
|
|
37082980 icache shadow TLB misses # 10.739 M/sec
|
|
66490 L2 Miss Eviction # 56.39 of all L2 cache misses
|
|
1046 Context Switches # 0.000 M/sec
|
|
2 CPU-migrations # 0.000 M/sec
|
|
358 Page Faults # 0.000 M/sec
|
|
3453.270784 Task Clock # 0.626 CPUs utilized
|
|
5.518885690 seconds time elapsed
|
|
|
|
root@du1:~# ./rbs-perf-test -t 4 -s -c ./ltt-test-2.1.1 -l 1000000 -t 1
|
|
--- PLB6 Commands - exec cmd - ./ltt-test-2.1.1 ---
|
|
Benchmark test starts now...
|
|
Time it took to loop 1000000 times : 3 s 562387238 ns | [ 3562 ns per tp ]
|
|
Stats for pid 2877
|
|
Counters enabled in user and in kernel space
|
|
------------------------------------------------------------------
|
|
6588193 PLB6 Commands # 1.894 M/sec
|
|
106741 READ/READ-ATOMIC commands # 0.031 M/sec
|
|
11681 RWITM commands # 0.003 M/sec
|
|
90533 DCLAIM commands # 0.026 M/sec
|
|
13808 Cache line WRITE commands # 0.004 M/sec
|
|
8133 Cache line fill IntvnM # 0.002 M/sec
|
|
48460 Cache line fill IntvnS # 0.014 M/sec
|
|
59714 Cache line fill memory # 0.017 M/sec
|
|
2985 Context Switches # 0.001 M/sec
|
|
2 CPU-migrations # 0.000 M/sec
|
|
359 Page Faults # 0.000 M/sec
|
|
3477.678672 Task Clock # 0.622 CPUs utilized
|
|
5.589642530 seconds time elapsed
|
|
|
|
|
|
|
|
=======================================================
|
|
|
|
* LTTng 2.2.0-rc2 stats
|
|
-------------------------------------------
|
|
|
|
root@du1:~# ./rbs-perf-test -t 0 -s -c ./ltt-test-2.2.0 -l 1000000 -t 1
|
|
--- Memory Reservation statistics - exec cmd - ./ltt-test-2.2.0 ---
|
|
Benchmark test starts now...
|
|
Time it took to loop 1000000 times : 8 s 666169809 ns | [8666 ns per tp]
|
|
Stats for pid 2737
|
|
Counters enabled in user and in kernel space
|
|
------------------------------------------------------------------
|
|
6682138400 Instruction count # 0.50 Instructions per Cycle
|
|
13486937352 CPU cycles # 1.593 GHz
|
|
3378637 Completed lwarx instructions
|
|
3378115 Successful stwcx instructions
|
|
1116115 L2 Read after Write
|
|
419986854 L2 Write after Write
|
|
4674 Context Switches # 0.001 M/sec
|
|
8 CPU-migrations # 0.000 M/sec
|
|
375 Page Faults # 0.000 M/sec
|
|
8465.781152 Task Clock # 0.790 CPUs utilized
|
|
10.710508740 seconds time elapsed
|
|
|
|
root@du1:~# ./rbs-perf-test -t 1 -s -c ./ltt-test-2.2.0 -l 1000000 -t 1
|
|
--- L1 Cache performance - exec cmd - ./ltt-test-2.2.0 ---
|
|
Benchmark test starts now...
|
|
Time it took to loop 1000000 times : 8 s 750318129 ns | [8750 ns per tp]
|
|
Stats for pid 2752
|
|
Counters enabled in user and in kernel space
|
|
------------------------------------------------------------------
|
|
3076810638 L1-icache-loads # 361.077 M/sec
|
|
3042256266 L1-icache-load-hits # 98.88 of all L1-icache hits
|
|
2320374878 L1-dcache-loads # 272.306 M/sec
|
|
1913574867 L1-dcache-load-hits # 82.47 of all L1-dcache hits
|
|
5575 Context Switches # 0.001 M/sec
|
|
15 CPU-migrations # 0.000 M/sec
|
|
373 Page Faults # 0.000 M/sec
|
|
8521.200256 Task Clock # 0.790 CPUs utilized
|
|
10.788846760 seconds time elapsed
|
|
|
|
root@du1:~# ./rbs-perf-test -t 2 -s -c ./ltt-test-2.2.0 -l 1000000 -t 1
|
|
--- L2 Cache performance - exec cmd - ./ltt-test-2.2.0 ---
|
|
Benchmark test starts now...
|
|
Time it took to loop 1000000 times : 8 s 769646969 ns | [8769 ns per tp]
|
|
Stats for pid 2767
|
|
Counters enabled in user and in kernel space
|
|
------------------------------------------------------------------
|
|
422920080 L2-loads # 49.870 M/sec
|
|
422522434 L2-load-hits # 99.91 of all L2 cache hits
|
|
6906 Context Switches # 0.001 M/sec
|
|
15 CPU-migrations # 0.000 M/sec
|
|
372 Page Faults # 0.000 M/sec
|
|
8480.512512 Task Clock # 0.784 CPUs utilized
|
|
10.812143770 seconds time elapsed
|
|
|
|
root@du1:~# ./rbs-perf-test -t 3 -s -c ./ltt-test-2.2.0 -l 1000000 -t 1
|
|
--- Shadow TLB misses - L2 Miss Eviction - exec cmd - ./ltt-test-2.2.0 ---
|
|
Benchmark test starts now...
|
|
Time it took to loop 1000000 times : 8 s 621587970 ns | [8621 ns per tp]
|
|
Stats for pid 2782
|
|
Counters enabled in user and in kernel space
|
|
------------------------------------------------------------------
|
|
6682376594 Instruction count # 0.50 Instructions per Cycle
|
|
13404210872 CPU cycles # 1.593 GHz
|
|
117040641 dcache shadow TLB misses # 13.906 M/sec
|
|
60244653 icache shadow TLB misses # 7.158 M/sec
|
|
222672 L2 Miss Eviction # 58.50 of all L2 cache misses
|
|
3934 Context Switches # 0.000 M/sec
|
|
12 CPU-migrations # 0.000 M/sec
|
|
370 Page Faults # 0.000 M/sec
|
|
8416.596896 Task Clock # 0.789 CPUs utilized
|
|
10.661324180 seconds time elapsed
|
|
|
|
root@du1:~# ./rbs-perf-test -t 4 -s -c ./ltt-test-2.2.0 -l 1000000 -t 1
|
|
--- PLB6 Commands - exec cmd - ./ltt-test-2.2.0 ---
|
|
Benchmark test starts now...
|
|
Time it took to loop 1000000 times : 8 s 768384390 ns | [8768 ns per tp]
|
|
Stats for pid 2797
|
|
Counters enabled in user and in kernel space
|
|
------------------------------------------------------------------
|
|
11252534 PLB6 Commands # 1.335 M/sec
|
|
363519 READ/READ-ATOMIC commands # 0.043 M/sec
|
|
30251 RWITM commands # 0.004 M/sec
|
|
248485 DCLAIM commands # 0.029 M/sec
|
|
32418 Cache line WRITE commands # 0.004 M/sec
|
|
30128 Cache line fill IntvnM # 0.004 M/sec
|
|
159751 Cache line fill IntvnS # 0.019 M/sec
|
|
191845 Cache line fill memory # 0.023 M/sec
|
|
8081 Context Switches # 0.001 M/sec
|
|
6 CPU-migrations # 0.000 M/sec
|
|
372 Page Faults # 0.000 M/sec
|
|
8427.167536 Task Clock # 0.639 CPUs utilized
|
|
13.190474860 seconds time elapsed
|