{"id":2280,"date":"2024-06-01T11:20:32","date_gmt":"2024-06-01T11:20:32","guid":{"rendered":"https:\/\/mvermeulen.org\/perf\/?page_id=2280"},"modified":"2024-06-01T12:39:08","modified_gmt":"2024-06-01T12:39:08","slug":"scylladb","status":"publish","type":"page","link":"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/scylladb\/","title":{"rendered":"scylladb"},"content":{"rendered":"\n<p>ScylladDB open source NoSQL DB compatible with Apache Cassandra. Tested with three workloads. Number of runnable processes is frequently more than the number of logical cores.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1280\" height=\"960\" src=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/06\/systemtime-4.png\" alt=\"\" class=\"wp-image-2290\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/06\/systemtime-4.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/06\/systemtime-4-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/06\/systemtime-4-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>Topdown profile shows frontend stalls as dominating.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"1280\" height=\"960\" src=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/06\/amdtopdown-5.png\" alt=\"\" class=\"wp-image-2292\" srcset=\"https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/06\/amdtopdown-5.png 1280w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/06\/amdtopdown-5-1024x768.png 1024w, https:\/\/mvermeulen.org\/perf\/wp-content\/uploads\/sites\/7\/2024\/06\/amdtopdown-5-768x576.png 768w\" sizes=\"auto, (max-width: 1280px) 100vw, 1280px\" \/><\/figure>\n\n\n\n<p>AMD metrics show little floating point, with some L2 usage. Frontend stalls are latency based.<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>elapsed              1694.100\non_cpu               0.706          # 11.30 \/ 16 cores\nutime                12676.156\nstime                6465.991\nnvcsw                212212284      # 62.33%\nnivcsw               128271257      # 37.67%\ninblock              182352         # 107.64\/sec\nonblock              150337912      # 88742.03\/sec\ncpu-clock            18273317721074 # 18273.318 seconds\ntask-clock           18378211893345 # 18378.212 seconds\npage faults          3583900        # 195.008\/sec\ncontext switches     340491438      # 18526.908\/sec\ncpu migrations       50288807       # 2736.328\/sec\nmajor page faults    540            # 0.029\/sec\nminor page faults    3576715        # 194.617\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             11636616280657 # 163.317 branches per 1000 inst\nbranch misses        319551371486   # 2.75% branch miss\nconditional          6530320883898  # 91.652 conditional branches per 1000 inst\nindirect             523984592743   # 7.354 indirect branches per 1000 inst\ncpu-cycles           68408839496957 # 2.55 GHz\ninstructions         72114167774101 # 1.05 IPC\nslots                135005657739174 #\nretiring             26237637782058 # 19.4% (23.0%)\n-- ucode             129781603162   #     0.1%\n-- fastpath          26107856178896 #    19.3%\nfrontend             57564151706986 # 42.6% (50.6%) high\n-- latency           50067380633946 #    37.1%\n-- bandwidth         7496771073040  #     5.6%\nbackend              28684605264128 # 21.2% (25.2%)\n-- cpu               2703316341728  #     2.0%\n-- memory            25981288922400 #    19.2%\nspeculation          1300722224732  #  1.0% ( 1.1%)\n-- branch mispredict 1260147294137  #     0.9%\n-- pipeline restart  40574930595    #     0.0%\nsmt-contention       21172383372113 # 15.7% ( 0.0%)\ncpu-cycles           70437568065065 # 2.57 GHz\ninstructions         74202073628189 # 1.05 IPC\ninstructions         24420521971707 # 91.403 l2 access per 1000 inst\nl2 hit from l1       1540095135733  # 37.21% l2 miss\nl2 miss from l1      450108085134   #\nl2 hit from l2 pf    311577423106   #\nl3 hit from l2 pf    370326054750   #\nl3 miss from l2 pf   10105241469    #\ninstructions         24405105520058 # 9.005 float per 1000 inst\nfloat 512            150            # 0.000 AVX-512 per 1000 inst\nfloat 256            1660           # 0.000 AVX-256 per 1000 inst\nfloat 128            219778225999   # 9.005 AVX-128 per 1000 inst\nfloat MMX            0              # 0.000 MMX per 1000 inst\nfloat scalar         4907           # 0.000 scalar per 1000 inst\ninstructions         72112578261538 #\nopcache              13754611532886 # 190.738 opcache per 1000 inst\nopcache miss         3606490621743  # 26.2% opcache miss rate\nl1 dTLB miss         165260023029   # 2.292 L1 dTLB per 1000 inst\nl2 dTLB miss         45599207352    # 0.632 L2 dTLB per 1000 inst\ninstructions         74160692511870 #\nicache               6490741776395  # 87.523 icache per 1000 inst\nicache miss          2195763203080  # 33.8% icache miss rate\nl1 iTLB miss         71751779126    # 0.968 L1 iTLB per 1000 inst\nl2 iTLB miss         0              # 0.000 L2 iTLB per 1000 inst\ntlb flush            853851         # 0.000 TLB flush per 1000 inst<\/code><\/pre>\n\n\n\n<p>Intel metrics<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>elapsed              2007.141\non_cpu               0.754          # 12.06 \/ 16 cores\nutime                18239.201\nstime                5969.687\nnvcsw                237491138      # 65.11%\nnivcsw               127280059      # 34.89%\ninblock              24180568       # 12047.27\/sec\nonblock              172900464      # 86142.66\/sec\ncpu-clock            23542596123952 # 23542.596 seconds\ntask-clock           23623187999792 # 23623.188 seconds\npage faults          3482620        # 147.424\/sec\ncontext switches     364780670      # 15441.636\/sec\ncpu migrations       72270905       # 3059.321\/sec\nmajor page faults    2178           # 0.092\/sec\nminor page faults    3469450        # 146.866\/sec\nalignment faults     0              # 0.000\/sec\nemulation faults     0              # 0.000\/sec\nbranches             14317293488627 # 160.573 branches per 1000 inst\nbranch misses        73859936712    # 0.52% branch miss\nconditional          14317293594579 # 160.573 conditional branches per 1000 inst\nindirect             3822925888376  # 42.875 indirect branches per 1000 inst\nslots                116896604298938 #\nretiring             31377352560659 # 26.8% (26.8%)\n-- ucode             5281214510679  #     4.5%\n-- fastpath          26096138049980 #    22.3%\nfrontend             34563899421102 # 29.6% (29.6%)\n-- latency           19582310389903 #    16.8%\n-- bandwidth         14981589031199 #    12.8%\nbackend              41154609101187 # 35.2% (35.2%)\n-- cpu               17188075502098 #    14.7%\n-- memory            23966533599089 #    20.5%\nspeculation          8352463961496  #  7.1% ( 7.1%)\n-- branch mispredict 6989686313816  #     6.0%\n-- pipeline restart  1362777647680  #     1.2%\nsmt-contention       0              #  0.0% ( 0.0%)\ncpu-cycles           57186380640876 # 1.63 GHz\ninstructions         82885849354422 # 1.45 IPC\nl2 access            3327703911676  # 57.071 l2 access per 1000 inst\nl2 miss              692348158023   # 20.81% l2 miss\ncpu-cycles           38656418202945 # 26.4% memory latency\nload stalls          9404889202907  #  0.8% l1 bound\nl1 miss              9091340864219  # 15.6% l2 bound\nl2 miss              3045483126586  #  6.9% l3 bound\nl3 miss              371844966072   #  1.0% dram bound\nstore_stalls         802883916659   #  2.1% store bound\n<\/code><\/pre>\n\n\n\n<p>Process overview<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>3396 processes\n\t480 cluster1-nio-wo      97942.39 97812.78\n\t  9 reactor-1            10361.46  2457.35\n\t  9 reactor-10           10361.46  2457.35\n\t  9 reactor-11           10361.46  2457.35\n\t  9 reactor-12           10361.46  2457.35\n\t  9 reactor-13           10361.46  2457.35\n\t  9 reactor-14           10361.46  2457.35\n\t  9 reactor-15           10361.46  2457.35\n\t  9 reactor-2            10361.46  2457.35\n\t  9 reactor-3            10361.46  2457.35\n\t  9 reactor-4            10361.46  2457.35\n\t  9 reactor-5            10361.46  2457.35\n\t  9 reactor-6            10361.46  2457.35\n\t  9 reactor-7            10361.46  2457.35\n\t  9 reactor-8            10361.46  2457.35\n\t  9 reactor-9            10361.46  2457.35\n\t  9 scylla               10361.46  2457.35\n\t  9 syscall-0            10361.46  2457.35\n\t  9 syscall-1            10361.46  2457.35\n\t  9 syscall-10           10361.46  2457.35\n\t  9 syscall-11           10361.46  2457.35\n\t  9 syscall-12           10361.46  2457.35\n\t  9 syscall-13           10361.46  2457.35\n\t  9 syscall-14           10361.46  2457.35\n\t  9 syscall-15           10361.46  2457.35\n\t  9 syscall-2            10361.46  2457.35\n\t  9 syscall-3            10361.46  2457.35\n\t  9 syscall-4            10361.46  2457.35\n\t  9 syscall-5            10361.46  2457.35\n\t  9 syscall-6            10361.46  2457.35\n\t  9 syscall-7            10361.46  2457.35\n\t  9 syscall-8            10361.46  2457.35\n\t  9 syscall-9            10361.46  2457.35\n\t 33 globalEventExec       6736.66  6723.54\n\t 62 java                  6122.36  6113.90\n\t 75 cluster1-worker       5624.21  5170.37\n\t 36 StressMetrics         3315.12  3109.88\n\t 31 Finalizer             3061.18  3056.95\n\t 15 Common-Cleaner        3060.77  3056.72\n\t 15 ObjectCleanerTh       3060.77  3056.72\n\t 15 Logging-Cleaner       3060.76  3056.70\n\t 15 Thread-0              3060.76  3056.68\n\t 15 Shutdown-checke       3060.74  3056.67\n\t 15 cluster1-connec       3060.74  3056.67\n\t 15 cluster1-timeou       3060.74  3056.67\n\t 15 cluster1-schedu       3058.97  3056.34\n\t 15 Thread-20             1576.59  1517.87\n\t 15 Thread-21             1576.59  1517.87\n\t 15 Thread-23             1576.59  1517.87\n\t 15 Thread-24             1576.59  1517.87\n\t 15 Thread-25             1576.59  1517.87\n\t 15 Thread-26             1576.59  1517.87\n\t 15 Thread-27             1576.59  1517.87\n\t 15 Thread-28             1576.59  1517.87\n\t 15 Thread-30             1576.59  1517.87\n\t 15 Thread-22             1576.58  1517.87\n\t 15 Thread-29             1576.58  1517.87\n\t 15 Thread-31             1576.58  1517.87\n\t 15 Thread-32             1576.58  1517.87\n\t 15 Thread-33             1576.58  1517.87\n\t 15 Thread-34             1576.57  1517.87\n\t 15 Thread-35             1576.56  1517.87\n\t  6 Thread-37             1569.14  1560.13\n\t  6 Thread-38             1569.14  1560.13\n\t  6 Thread-39             1569.14  1560.13\n\t  6 Thread-40             1569.14  1560.13\n\t  6 Thread-41             1569.14  1560.13\n\t  6 Thread-42             1569.14  1560.13\n\t  6 Thread-43             1569.14  1560.13\n\t  6 Thread-44             1569.14  1560.13\n\t  6 Thread-45             1569.14  1560.13\n\t  6 Thread-46             1569.14  1560.13\n\t  6 Thread-47             1569.14  1560.13\n\t  6 Thread-48             1569.14  1560.13\n\t  6 Thread-50             1569.14  1560.13\n\t  6 Thread-51             1569.14  1560.13\n\t  6 Thread-52             1569.14  1560.13\n\t  6 Thread-49             1569.14  1560.12\n\t 15 Thread-6               168.99    31.82\n\t 15 Thread-3               168.99    31.81\n\t 15 Thread-4               168.99    31.81\n\t 15 Thread-5               168.99    31.81\n\t 15 Thread-12              168.98    31.82\n\t 15 Thread-10              168.98    31.81\n\t 15 Thread-13              168.98    31.81\n\t 15 Thread-14              168.98    31.81\n\t 15 Thread-18              168.98    31.81\n\t 15 Thread-7               168.98    31.81\n\t 15 Thread-8               168.98    31.81\n\t 15 Thread-9               168.98    31.81\n\t 15 Thread-15              168.98    31.80\n\t 15 Thread-16              168.98    31.80\n\t 15 Thread-17              168.98    31.80\n\t 15 Thread-11              168.97    31.81\n\t 68 clinfo                  20.18     5.99\n\t 38 vulkaninfo               1.33     1.71\n\t  6 glxinfo:gdrv0            0.16     0.06\n\t  6 glxinfo:gl0              0.16     0.06\n\t  4 vulkani:disk$0           0.14     0.18\n\t  6 php                      0.08     0.34\n\t  2 glxinfo                  0.08     0.02\n\t  2 glxinfo:cs0              0.08     0.02\n\t  2 glxinfo:disk$0           0.08     0.02\n\t  2 glxinfo:sh0              0.08     0.02\n\t  2 glxinfo:shlo0            0.08     0.02\n\t  2 llvmpipe-0               0.07     0.09\n\t  2 llvmpipe-1               0.07     0.09\n\t  2 llvmpipe-10              0.07     0.09\n\t  2 llvmpipe-11              0.07     0.09\n\t  2 llvmpipe-12              0.07     0.09\n\t  2 llvmpipe-13              0.07     0.09\n\t  2 llvmpipe-14              0.07     0.09\n\t  2 llvmpipe-15              0.07     0.09\n\t  2 llvmpipe-2               0.07     0.09\n\t  2 llvmpipe-3               0.07     0.09\n\t  2 llvmpipe-4               0.07     0.09\n\t  2 llvmpipe-5               0.07     0.09\n\t  2 llvmpipe-6               0.07     0.09\n\t  2 llvmpipe-7               0.07     0.09\n\t  2 llvmpipe-8               0.07     0.09\n\t  2 llvmpipe-9               0.07     0.09\n\t  6 clang                    0.07     0.05\n\t  3 rocminfo                 0.03     0.00\n\t269 C2 CompilerThre          0.00 14607.40\n\t131 C1 CompilerThre          0.00  3985.10\n\t 31 G1 Conc#0                0.00  3061.18\n\t 31 GC Thread#0              0.00  3061.18\n\t 31 Reference Handl          0.00  3061.18\n\t 31 Service Thread           0.00  3061.18\n\t 31 Signal Dispatch          0.00  3061.18\n\t 31 Sweeper thread           0.00  3061.18\n\t 31 VM Thread                0.00  3061.18\n\t 31 G1 Refine#0              0.00  3061.17\n\t 15 G1 Conc#1                0.00  3060.77\n\t 15 G1 Conc#2                0.00  3060.77\n\t 15 GC Thread#1              0.00  3060.77\n\t 15 GC Thread#10             0.00  3060.77\n\t 15 GC Thread#2              0.00  3060.77\n\t 15 GC Thread#3              0.00  3060.77\n\t 15 GC Thread#4              0.00  3060.77\n\t 15 GC Thread#5              0.00  3060.77\n\t 15 GC Thread#6              0.00  3060.77\n\t 15 GC Thread#7              0.00  3060.77\n\t 15 GC Thread#8              0.00  3060.77\n\t 15 GC Thread#9              0.00  3060.77\n\t 15 GC Thread#11             0.00  3060.76\n\t 15 GC Thread#12             0.00  3060.76\n\t 14 G1 Refine#1              0.00  2977.78\n\t 10 G1 Refine#2              0.00  2139.52\n\t 18 rm                       0.00     0.09\n\t  1 lspci                    0.00     0.03\n\t  1 ps                       0.00     0.01\n\t120 cassandra-stres          0.00     0.00\n\t 88 sh                       0.00     0.00\n\t 70 grep                     0.00     0.00\n\t 45 awk                      0.00     0.00\n\t 42 sleep                    0.00     0.00\n\t 31 G1 Main Marker           0.00     0.00\n\t 31 G1 Young RemSet          0.00     0.00\n\t 31 VM Periodic Tas          0.00     0.00\n\t 31 dirname                  0.00     0.00\n\t 18 scylladb                 0.00     0.00\n\t 15 cut                      0.00     0.00\n\t 13 gsettings                0.00     0.00\n\t 12 gcc                      0.00     0.00\n\t  9 tail                     0.00     0.00\n\t  8 stat                     0.00     0.00\n\t  8 systemd-detect-          0.00     0.00\n\t  6 llvm-link                0.00     0.00\n\t  5 phoronix-test-s          0.00     0.00\n\t  2 gmain                    0.00     0.00\n\t  2 lscpu                    0.00     0.00\n\t  2 uname                    0.00     0.00\n\t  2 which                    0.00     0.00\n\t  2 xset                     0.00     0.00\n\t  1 cc                       0.00     0.00\n\t  1 date                     0.00     0.00\n\t  1 dconf worker             0.00     0.00\n\t  1 dmesg                    0.00     0.00\n\t  1 dmidecode                0.00     0.00\n\t  1 ifconfig                 0.00     0.00\n\t  1 ip                       0.00     0.00\n\t  1 lsmod                    0.00     0.00\n\t  1 mktemp                   0.00     0.00\n\t  1 python                   0.00     0.00\n\t  1 python3                  0.00     0.00\n\t  1 qdbus                    0.00     0.00\n\t  1 readlink                 0.00     0.00\n\t  1 realpath                 0.00     0.00\n\t  1 sed                      0.00     0.00\n\t  1 sort                     0.00     0.00\n\t  1 stty                     0.00     0.00\n\t  1 systemctl                0.00     0.00\n\t  1 template.sh              0.00     0.00\n\t  1 wc                       0.00     0.00\n\t  1 xrandr                   0.00     0.00\n0 processes running\n121 maximum processes\n<\/code><\/pre>\n\n\n\n<p>Sample computation block<\/p>\n\n\n\n<pre class=\"wp-block-code\"><code>      53145) scylladb         cpu=9 start=5.74  finish=165.84\n        53146) rm               cpu=11 start=5.74  finish=5.74 \n        53147) scylla           cpu=0 start=5.74  finish=163.82\n          53149) reactor-1        cpu=8 start=5.93  finish=163.82\n            53165) syscall-1        cpu=8 start=5.95  finish=163.82\n          53150) reactor-2        cpu=1 start=5.93  finish=163.82\n            53169) syscall-2        cpu=1 start=5.96  finish=163.82\n          53151) reactor-3        cpu=9 start=5.93  finish=163.82\n            53168) syscall-3        cpu=9 start=5.96  finish=163.82\n          53152) reactor-4        cpu=2 start=5.93  finish=163.82\n            53166) syscall-4        cpu=2 start=5.95  finish=163.82\n          53153) reactor-5        cpu=10 start=5.93  finish=163.82\n            53167) syscall-5        cpu=10 start=5.95  finish=163.82\n          53154) reactor-6        cpu=3 start=5.93  finish=163.82\n            53173) syscall-6        cpu=3 start=5.96  finish=163.82\n          53155) reactor-7        cpu=11 start=5.94  finish=163.82\n            53170) syscall-7        cpu=11 start=5.96  finish=163.82\n          53156) reactor-8        cpu=4 start=5.94  finish=163.82\n            53172) syscall-8        cpu=4 start=5.96  finish=163.82\n          53157) reactor-9        cpu=12 start=5.94  finish=163.82\n            53175) syscall-9        cpu=12 start=5.96  finish=163.82\n          53158) reactor-10       cpu=5 start=5.94  finish=163.82\n            53174) syscall-10       cpu=5 start=5.96  finish=163.82\n          53159) reactor-11       cpu=13 start=5.94  finish=163.82\n            53171) syscall-11       cpu=13 start=5.96  finish=163.82\n          53160) reactor-12       cpu=6 start=5.94  finish=163.82\n            53177) syscall-12       cpu=6 start=5.96  finish=163.82\n          53161) reactor-13       cpu=14 start=5.94  finish=163.82\n            53176) syscall-13       cpu=14 start=5.96  finish=163.82\n          53162) reactor-14       cpu=7 start=5.95  finish=163.82\n            53179) syscall-14       cpu=7 start=5.96  finish=163.82\n          53163) reactor-15       cpu=15 start=5.95  finish=163.82\n            53178) syscall-15       cpu=15 start=5.96  finish=163.82\n          53164) syscall-0        cpu=0 start=5.95  finish=163.82\n        53148) sleep            cpu=2 start=5.74  finish=10.74\n        53180) scylladb         cpu=11 start=10.75 finish=31.50\n          53182) tail             cpu=0 start=10.75 finish=31.50\n        53181) grep             cpu=15 start=10.75 finish=31.50\n        53197) sleep            cpu=3 start=31.50 finish=32.50\n        53199) cassandra-stres  cpu=9 start=32.50 finish=160.81\n          53200) dirname          cpu=4 start=32.51 finish=32.51\n          53201) dirname          cpu=7 start=32.51 finish=32.51\n          53202) cassandra-stres  cpu=13 start=32.51 finish=32.51\n          53203) java             cpu=10 start=32.51 finish=32.55\n            53204) java             cpu=12 start=32.52 finish=32.55\n              53205) GC Thread#0      cpu=-1 start=32.52 finish=32.55\n              53206) G1 Main Marker   cpu=0 start=32.52 finish=32.55\n              53207) G1 Conc#0        cpu=-1 start=32.52 finish=32.55\n              53208) G1 Refine#0      cpu=-1 start=32.52 finish=32.55\n              53209) G1 Young RemSet  cpu=0 start=32.52 finish=32.55\n              53210) VM Thread        cpu=-1 start=32.53 finish=32.55\n              53211) Reference Handl  cpu=-1 start=32.53 finish=32.55\n              53212) Finalizer        cpu=3 start=32.53 finish=32.55\n              53213) Signal Dispatch  cpu=-1 start=32.53 finish=32.55\n              53214) Service Thread   cpu=-1 start=32.53 finish=32.55\n              53215) C2 CompilerThre  cpu=-1 start=32.53 finish=32.55\n                53218) C1 CompilerThre  cpu=-1 start=32.54 finish=32.55\n              53216) C1 CompilerThre  cpu=-1 start=32.53 finish=32.55\n              53217) Sweeper thread   cpu=-1 start=32.53 finish=32.55\n              53219) VM Periodic Tas  cpu=0 start=32.54 finish=32.55\n          53220) cassandra-stres  cpu=14 start=32.55 finish=32.55\n            53221) cassandra-stres  cpu=0 start=32.55 finish=32.55\n            53222) grep             cpu=3 start=32.55 finish=32.55\n            53223) awk              cpu=9 start=32.55 finish=32.55\n            53224) cut              cpu=7 start=32.55 finish=32.55\n          53225) cassandra-stres  cpu=0 start=32.55 finish=32.56\n            53226) cassandra-stres  cpu=4 start=32.55 finish=32.55\n            53227) grep             cpu=7 start=32.55 finish=32.56\n            53228) awk              cpu=2 start=32.55 finish=32.56\n          53229) cassandra-stres  cpu=10 start=32.56 finish=32.56\n            53230) cassandra-stres  cpu=14 start=32.56 finish=32.56\n            53231) awk              cpu=9 start=32.56 finish=32.56\n          53232) grep             cpu=3 start=32.56 finish=32.56\n          53233) grep             cpu=6 start=32.56 finish=32.56\n          53234) java             cpu=13 start=32.56 finish=160.76\n            53235) java             cpu=2 start=32.57 finish=160.76\n              53236) GC Thread#0      cpu=-1 start=32.57 finish=160.76\n              53237) G1 Main Marker   cpu=0 start=32.57 finish=160.75\n                53267) G1 Conc#1        cpu=-1 start=33.37 finish=160.75\n                53268) G1 Conc#2        cpu=-1 start=33.37 finish=160.75\n              53238) G1 Conc#0        cpu=-1 start=32.57 finish=160.76\n              53239) G1 Refine#0      cpu=-1 start=32.58 finish=160.75\n                53320) G1 Refine#1      cpu=-1 start=38.52 finish=160.75\n                  53321) G1 Refine#2      cpu=-1 start=38.52 finish=160.75\n              53240) G1 Young RemSet  cpu=0 start=32.58 finish=160.75\n              53241) VM Thread        cpu=-1 start=32.58 finish=160.76\n                53256) GC Thread#1      cpu=-1 start=32.85 finish=160.76\n                53257) GC Thread#2      cpu=-1 start=32.86 finish=160.76\n                53258) GC Thread#3      cpu=-1 start=32.86 finish=160.76\n                53259) GC Thread#4      cpu=-1 start=32.86 finish=160.75\n                53260) GC Thread#5      cpu=-1 start=32.86 finish=160.75\n                53261) GC Thread#6      cpu=-1 start=32.86 finish=160.75\n                53262) GC Thread#7      cpu=-1 start=32.86 finish=160.75\n                53263) GC Thread#8      cpu=-1 start=32.86 finish=160.75\n                53264) GC Thread#9      cpu=-1 start=32.86 finish=160.75\n                53315) GC Thread#10     cpu=-1 start=36.96 finish=160.75\n                53316) GC Thread#11     cpu=-1 start=36.96 finish=160.75\n                53317) GC Thread#12     cpu=-1 start=36.96 finish=160.75\n              53242) Reference Handl  cpu=-1 start=32.59 finish=160.76\n              53243) Finalizer        cpu=3 start=32.59 finish=160.76\n              53244) Signal Dispatch  cpu=-1 start=32.59 finish=160.76\n              53245) Service Thread   cpu=-1 start=32.59 finish=160.76\n              53246) C2 CompilerThre  cpu=-1 start=32.59 finish=160.76\n                53249) C1 CompilerThre  cpu=-1 start=32.60 finish=34.60\n                53250) C1 CompilerThre  cpu=-1 start=32.60 finish=34.60\n                  53253) C2 CompilerThre  cpu=-1 start=32.63 finish=34.90\n                  53273) C2 CompilerThre  cpu=-1 start=33.50 finish=34.60\n                53339) C2 CompilerThre  cpu=-1 start=47.36 finish=47.65\n                53340) C2 CompilerThre  cpu=-1 start=153.71 finish=158.54\n                53341) C2 CompilerThre  cpu=-1 start=153.72 finish=158.54\n                  53342) C2 CompilerThre  cpu=-1 start=153.72 finish=158.54\n                  53343) C2 CompilerThre  cpu=-1 start=153.72 finish=158.54\n                  53344) C2 CompilerThre  cpu=-1 start=153.72 finish=158.54\n                  53345) C2 CompilerThre  cpu=-1 start=153.72 finish=158.54\n              53247) C1 CompilerThre  cpu=-1 start=32.59 finish=160.76\n                53254) C1 CompilerThre  cpu=-1 start=32.70 finish=34.60\n                  53255) C2 CompilerThre  cpu=-1 start=32.85 finish=34.90\n                53288) C2 CompilerThre  cpu=-1 start=36.66 finish=39.60\n                53289) C1 CompilerThre  cpu=-1 start=36.66 finish=40.43\n                53290) C1 CompilerThre  cpu=-1 start=36.66 finish=39.36\n                  53313) C2 CompilerThre  cpu=-1 start=36.77 finish=38.24\n                  53314) C2 CompilerThre  cpu=-1 start=36.86 finish=37.92\n                53291) C2 CompilerThre  cpu=-1 start=36.66 finish=38.92\n                  53318) C2 CompilerThre  cpu=-1 start=37.02 finish=37.89\n                53310) C1 CompilerThre  cpu=-1 start=36.72 finish=39.36\n                  53311) C2 CompilerThre  cpu=-1 start=36.73 finish=38.92\n                53312) C2 CompilerThre  cpu=-1 start=36.74 finish=38.49\n                53371) C2 CompilerThre  cpu=-1 start=158.55 finish=159.65\n              53248) Sweeper thread   cpu=-1 start=32.59 finish=160.76\n              53251) Common-Cleaner   cpu=0 start=32.60 finish=160.76\n              53252) VM Periodic Tas  cpu=0 start=32.61 finish=160.75\n              53265) cluster1-connec  cpu=6 start=33.26 finish=160.75\n              53266) cluster1-schedu  cpu=7 start=33.33 finish=158.54\n                53283) cluster1-worker  cpu=7 start=33.58 finish=63.59\n                53285) cluster1-worker  cpu=0 start=33.60 finish=63.61\n                53287) cluster1-worker  cpu=13 start=33.62 finish=63.63\n              53270) ObjectCleanerTh  cpu=0 start=33.38 finish=160.75\n              53271) cluster1-nio-wo  cpu=7 start=33.38 finish=160.75\n                53272) cluster1-timeou  cpu=3 start=33.40 finish=160.75\n              53274) cluster1-nio-wo  cpu=12 start=33.52 finish=160.75\n                53282) cluster1-worker  cpu=15 start=33.58 finish=63.58\n                53284) cluster1-worker  cpu=11 start=33.60 finish=63.60\n                53286) cluster1-worker  cpu=12 start=33.62 finish=63.62\n                53309) cluster1-worker  cpu=9 start=36.71 finish=66.72\n              53275) cluster1-nio-wo  cpu=8 start=33.52 finish=160.75\n              53276) cluster1-nio-wo  cpu=13 start=33.52 finish=160.75\n              53277) cluster1-nio-wo  cpu=1 start=33.52 finish=160.75\n              53278) cluster1-nio-wo  cpu=6 start=33.52 finish=160.75\n              53279) cluster1-nio-wo  cpu=7 start=33.52 finish=160.75\n              53280) cluster1-nio-wo  cpu=1 start=33.53 finish=160.75\n              53281) cluster1-nio-wo  cpu=9 start=33.54 finish=160.75\n              53292) Thread-3         cpu=8 start=36.70 finish=38.52\n              53293) Thread-4         cpu=8 start=36.70 finish=38.52\n              53294) Thread-5         cpu=3 start=36.70 finish=38.52\n              53295) Thread-6         cpu=1 start=36.70 finish=38.52\n              53296) Thread-7         cpu=5 start=36.70 finish=38.52\n              53297) Thread-8         cpu=15 start=36.70 finish=38.52\n              53298) Thread-9         cpu=0 start=36.70 finish=38.52\n              53299) Thread-10        cpu=9 start=36.70 finish=38.52\n              53300) Thread-11        cpu=6 start=36.70 finish=38.52\n              53301) Thread-12        cpu=10 start=36.70 finish=38.51\n              53302) Thread-13        cpu=1 start=36.70 finish=38.52\n              53303) Thread-14        cpu=9 start=36.70 finish=38.52\n              53304) Thread-15        cpu=13 start=36.70 finish=38.52\n              53305) Thread-16        cpu=15 start=36.70 finish=38.52\n              53306) Thread-17        cpu=11 start=36.70 finish=38.52\n              53307) Thread-18        cpu=2 start=36.70 finish=38.52\n              53308) StressMetrics    cpu=15 start=36.71 finish=38.52\n              53322) Thread-20        cpu=11 start=38.53 finish=158.54\n              53323) Thread-21        cpu=7 start=38.53 finish=158.54\n              53324) Thread-22        cpu=13 start=38.53 finish=158.54\n              53325) Thread-23        cpu=12 start=38.53 finish=158.54\n              53326) Thread-24        cpu=3 start=38.53 finish=158.54\n              53327) Thread-25        cpu=14 start=38.53 finish=158.54\n              53328) Thread-26        cpu=6 start=38.53 finish=158.54\n              53329) Thread-27        cpu=15 start=38.53 finish=158.54\n              53330) Thread-28        cpu=4 start=38.53 finish=158.54\n              53331) Thread-29        cpu=1 start=38.53 finish=158.54\n              53332) Thread-30        cpu=2 start=38.53 finish=158.54\n              53333) Thread-31        cpu=9 start=38.53 finish=158.54\n              53334) Thread-32        cpu=12 start=38.53 finish=158.54\n              53335) Thread-33        cpu=7 start=38.53 finish=158.54\n              53336) Thread-34        cpu=5 start=38.53 finish=158.54\n              53337) Thread-35        cpu=8 start=38.53 finish=158.54\n              53338) StressMetrics    cpu=14 start=38.53 finish=158.54\n              53346) Shutdown-checke  cpu=1 start=158.54 finish=160.75\n                53347) globalEventExec  cpu=9 start=158.54 finish=158.55\n                53348) cluster1-nio-wo  cpu=14 start=158.54 finish=160.75\n                53349) cluster1-nio-wo  cpu=6 start=158.54 finish=160.75\n                53350) cluster1-nio-wo  cpu=2 start=158.54 finish=160.75\n                  53372) globalEventExec  cpu=2 start=160.75 finish=160.75\n                53351) cluster1-nio-wo  cpu=2 start=158.54 finish=160.75\n                53352) cluster1-nio-wo  cpu=0 start=158.54 finish=160.75\n                53353) cluster1-nio-wo  cpu=1 start=158.54 finish=160.75\n                53354) cluster1-nio-wo  cpu=14 start=158.54 finish=160.75\n                53355) cluster1-nio-wo  cpu=10 start=158.55 finish=160.75\n                53356) cluster1-nio-wo  cpu=4 start=158.55 finish=160.75\n                53357) cluster1-nio-wo  cpu=8 start=158.55 finish=160.75\n                53358) cluster1-nio-wo  cpu=3 start=158.55 finish=160.75\n                53359) cluster1-nio-wo  cpu=12 start=158.55 finish=160.75\n                53360) cluster1-nio-wo  cpu=14 start=158.55 finish=160.75\n                53361) cluster1-nio-wo  cpu=14 start=158.55 finish=160.75\n                53362) cluster1-nio-wo  cpu=2 start=158.55 finish=160.75\n                53363) cluster1-nio-wo  cpu=0 start=158.55 finish=160.75\n                53364) cluster1-nio-wo  cpu=4 start=158.55 finish=160.75\n                53365) cluster1-nio-wo  cpu=6 start=158.55 finish=160.75\n                53366) cluster1-nio-wo  cpu=13 start=158.55 finish=160.75\n                53367) cluster1-nio-wo  cpu=15 start=158.55 finish=160.75\n                53368) cluster1-nio-wo  cpu=8 start=158.55 finish=160.75\n                53369) cluster1-nio-wo  cpu=11 start=158.55 finish=160.75\n                53370) cluster1-nio-wo  cpu=15 start=158.55 finish=160.75\n              53373) Logging-Cleaner  cpu=3 start=160.75 finish=160.75\n              53374) Thread-0         cpu=6 start=160.75 finish=160.75\n        53375) sleep            cpu=10 start=160.81 finish=163.81\n        53376) sleep            cpu=13 start=163.82 finish=165.82\n        53377) rm               cpu=3 start=165.82 finish=165.84\n<\/code><\/pre>\n","protected":false},"excerpt":{"rendered":"<p>ScylladDB open source NoSQL DB compatible with Apache Cassandra. Tested with three workloads. Number of runnable processes is frequently more than the number of logical cores. Topdown profile shows frontend stalls as dominating. AMD metrics show little floating point, with <span class=\"excerpt-dots\">&hellip;<\/span> <a class=\"more-link\" href=\"https:\/\/mvermeulen.org\/perf\/workloads\/phoronix\/scylladb\/\"><span class=\"more-msg\">Continue reading &rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":58,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-2280","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2280","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/comments?post=2280"}],"version-history":[{"count":2,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2280\/revisions"}],"predecessor-version":[{"id":2293,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/2280\/revisions\/2293"}],"up":[{"embeddable":true,"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/pages\/58"}],"wp:attachment":[{"href":"https:\/\/mvermeulen.org\/perf\/wp-json\/wp\/v2\/media?parent=2280"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}