[tom@qemu]$time ./qemu-img co_bench -c 40000
real	0m1.325s
user	0m1.020s
sys	0m0.303s
[tom@qemu]$time ./qemu-img co_bench -c 40000 -b
real	0m0.903s
user	0m0.900s
sys	0m0.003s

[tom@qemu]$~/bin/perf stat -e L1-dcache-loads,L1-dcache-load-misses,cpu-cycles,instructions,branch-instructions,branch-misses,branch-loads,branch-load-misses,dTLB-loads,dTLB-load-misses ./qemu-img co_bench -c 40000 -b

 Performance counter stats for './qemu-img co_bench -c 40000 -b':

       512,790,342      L1-dcache-loads                                              [39.94%]
       187,363,176      L1-dcache-load-misses     #   36.54% of all L1-dcache hits   [40.01%]
     3,209,062,143      cpu-cycles                [50.02%]
     5,219,287,984      instructions              #    1.63  insns per cycle         [60.03%]
       348,201,358      branch-instructions                                          [60.05%]
           821,621      branch-misses             #    0.24% of all branches         [60.07%]
       349,613,600      branch-loads                                                 [60.18%]
        24,381,506      branch-load-misses                                           [60.05%]
       517,471,894      dTLB-loads                                                   [39.96%]
            83,661      dTLB-load-misses          #    0.02% of all dTLB cache hits  [39.95%]

       1.110885646 seconds time elapsed

[tom@qemu]$
[tom@qemu]$
[tom@qemu]$~/bin/perf stat -e L1-dcache-loads,L1-dcache-load-misses,cpu-cycles,instructions,branch-instructions,branch-misses,branch-loads,branch-load-misses,dTLB-loads,dTLB-load-misses ./qemu-img co_bench -c 40000

 Performance counter stats for './qemu-img co_bench -c 40000':

       693,552,491      L1-dcache-loads                                              [40.00%]
       214,062,328      L1-dcache-load-misses     #   30.86% of all L1-dcache hits   [40.00%]
     4,353,866,093      cpu-cycles                [49.90%]
     5,867,354,897      instructions              #    1.35  insns per cycle         [59.92%]
       475,022,290      branch-instructions                                          [59.96%]
         2,163,935      branch-misses             #    0.46% of all branches         [60.11%]
       473,943,061      branch-loads                                                 [60.07%]
       131,389,175      branch-load-misses                                           [60.04%]
       692,140,040      dTLB-loads                                                   [40.08%]
           562,117      dTLB-load-misses          #    0.08% of all dTLB cache hits  [40.01%]

       1.509369485 seconds time elapsed