Re: [PATCH v2 00/47] mm: various (urgent?) fixes

[Muhammad Usama Anjum]

On 29/10/2026 8:32 pm, David Hildenbrand (Arm) wrote:
> See v1 on details. TL;DR various fixes :)
> 
> Thanks to everyone for the review! Hoping I can get some more? :)
> 
> I am planning on picking these myself, moving them to linux-next fairly
> soon through mm/core.git.
> 
> ---
> Changes in v2:
> - "mm/memfd: check for real shmem inodes before accessing shmem state"
>  - Call it inode_is_shmem
> - "mm/truncate: look again if a folio left the mapping"
>  - Different fix for truncate_inode_pages_range
>  - Adjust description
> - "mm/huge_memory: fix zapping migration entries for device-private THPs"
>  - Move handling in zap_deposited_table
> - "mm/mmu_gather: fix flushing ranges with 4 GiB or larger"
>  - Adjust description"
> - "mm/huge_memory: split huge PUDs when adjusting VMA boundaries"
>  - Drop split_pud check
> - Link to v1: https://patch.msgid.link/20261027-fixes_core-v1-0-6f74bec9a5bb@xxxxxxxxxx
I ran Fastpath, a Linux kernel performance benchmarking framework, on
this series against mm-stable on aws-m7g.metal. (I) and (R) indicate
statistically significant improvements and regressions, respectively.
The results show 10 improvements and 1 regression. Other, unmarked
percentage changes can be ignored as statistically insignificant. Hence:

Tested-by: Muhammad Usama Anjum <usama.anjum@xxxxxxx>

Results for SUT Class aws-m7g.metal (arm64):
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| Benchmark                       | Result Class                                             |      mm-stable |  this patch |
+=================================+==========================================================+================+=============+
| lmbench/lat-mem-rd              | size:4MB P:1 stride:128B rnd_read_lat (ns)               |          24.95 |      -2.64% |
|                                 | size:4MB P:1 stride:128B seq_read_lat (ns)               |           2.95 |      -1.76% |
|                                 | size:16MB P:1 stride:128B rnd_read_lat (ns)              |          27.89 |      -2.70% |
|                                 | size:16MB P:1 stride:128B seq_read_lat (ns)              |           2.88 |      -1.19% |
|                                 | size:64MB P:1 stride:128B rnd_read_lat (ns)              |         101.59 |      -0.32% |
|                                 | size:64MB P:1 stride:128B seq_read_lat (ns)              |           5.43 |      -0.82% |
|                                 | size:256MB P:1 stride:128B rnd_read_lat (ns)             |         113.17 |      -0.29% |
|                                 | size:256MB P:1 stride:128B seq_read_lat (ns)             |           5.57 |      -0.30% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| micromm/fork                    | fork: p:1, d:10 (seconds)                                |         0.0074 |      -3.29% |
|                                 | fork: p:16, d:10 (seconds)                               |         0.0061 |       0.25% |
|                                 | fork: p:512, d:10 (seconds)                              |         0.0055 |       0.36% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| micromm/munmap                  | munmap: p:1, d:10 (seconds)                              |          0.043 |      -0.51% |
|                                 | munmap: p:16, d:10 (seconds)                             |         0.0081 |      -0.50% |
|                                 | munmap: p:512, d:10 (seconds)                            |         0.0042 |       0.70% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| micromm/vmalloc                 | fix_align_alloc_test: p:1, h:0, l:500000 (usec)          |      582591.50 |       0.65% |
|                                 | fix_size_alloc_test: p:1, h:0, l:500000 (usec)           |      361468.33 |       1.46% |
|                                 | fix_size_alloc_test: p:4, h:0, l:500000 (usec)           |      419288.33 |       0.73% |
|                                 | fix_size_alloc_test: p:16, h:0, l:500000 (usec)          |      733574.83 |       0.61% |
|                                 | fix_size_alloc_test: p:16, h:1, l:500000 (usec)          |      699803.67 |       0.39% |
|                                 | fix_size_alloc_test: p:64, h:0, l:100000 (usec)          |      394392.00 |       0.07% |
|                                 | fix_size_alloc_test: p:64, h:1, l:100000 (usec)          |      378722.67 |       0.07% |
|                                 | fix_size_alloc_test: p:256, h:0, l:100000 (usec)         |     1399837.00 |      -0.24% |
|                                 | fix_size_alloc_test: p:256, h:1, l:100000 (usec)         |     1355183.33 |      -0.76% |
|                                 | fix_size_alloc_test: p:512, h:0, l:100000 (usec)         |     2724934.00 |      -0.37% |
|                                 | fix_size_alloc_test: p:512, h:1, l:100000 (usec)         |     1915856.17 |      -0.19% |
|                                 | full_fit_alloc_test: p:1, h:0, l:500000 (usec)           |      563338.00 |       1.51% |
|                                 | kvfree_rcu_1_arg_vmalloc_test: p:1, h:0, l:500000 (usec) |      370179.17 |       0.12% |
|                                 | kvfree_rcu_2_arg_vmalloc_test: p:1, h:0, l:500000 (usec) |      367558.00 |      -0.50% |
|                                 | long_busy_list_alloc_test: p:1, h:0, l:500000 (usec)     |     3532591.00 |      -0.06% |
|                                 | pcpu_alloc_test: p:1, h:0, l:500000 (usec)               |      192186.33 |      -0.87% |
|                                 | random_size_align_alloc_test: p:1, h:0, l:500000 (usec)  |      691912.83 |      -0.66% |
|                                 | random_size_alloc_test: p:1, h:0, l:500000 (usec)        |     1856151.83 |      -0.08% |
|                                 | vm_map_ram_test: p:1, h:0, l:500000 (usec)               |       80702.00 |      -0.20% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| mmtests/hackbench               | hackbench-process-pipes-1 (seconds)                      |           0.14 |      -1.25% |
|                                 | hackbench-process-pipes-4 (seconds)                      |           0.39 |       1.72% |
|                                 | hackbench-process-pipes-7 (seconds)                      |           0.67 |       1.34% |
|                                 | hackbench-process-pipes-12 (seconds)                     |           1.11 |       1.06% |
|                                 | hackbench-process-pipes-21 (seconds)                     |           1.46 |       0.84% |
|                                 | hackbench-process-pipes-30 (seconds)                     |           1.84 |       0.71% |
|                                 | hackbench-process-pipes-48 (seconds)                     |           2.52 |       0.82% |
|                                 | hackbench-process-pipes-79 (seconds)                     |           3.56 |       1.30% |
|                                 | hackbench-process-pipes-110 (seconds)                    |           4.60 |       0.76% |
|                                 | hackbench-process-pipes-141 (seconds)                    |           5.68 |       1.21% |
|                                 | hackbench-process-pipes-172 (seconds)                    |           6.81 |       0.64% |
|                                 | hackbench-process-pipes-203 (seconds)                    |           7.94 |       0.62% |
|                                 | hackbench-process-pipes-234 (seconds)                    |           9.10 |       0.74% |
|                                 | hackbench-process-pipes-256 (seconds)                    |           9.90 |       0.65% |
|                                 | hackbench-process-sockets-1 (seconds)                    |           0.26 |      -0.57% |
|                                 | hackbench-process-sockets-4 (seconds)                    |           0.61 |       0.08% |
|                                 | hackbench-process-sockets-7 (seconds)                    |           0.98 |       0.19% |
|                                 | hackbench-process-sockets-12 (seconds)                   |           1.59 |       0.35% |
|                                 | hackbench-process-sockets-21 (seconds)                   |           2.73 |       0.18% |
|                                 | hackbench-process-sockets-30 (seconds)                   |           3.89 |       0.17% |
|                                 | hackbench-process-sockets-48 (seconds)                   |           6.23 |       0.24% |
|                                 | hackbench-process-sockets-79 (seconds)                   |           9.67 |       0.36% |
|                                 | hackbench-process-sockets-110 (seconds)                  |          13.47 |       0.58% |
|                                 | hackbench-process-sockets-141 (seconds)                  |          17.36 |       0.48% |
|                                 | hackbench-process-sockets-172 (seconds)                  |          21.52 |       0.60% |
|                                 | hackbench-process-sockets-203 (seconds)                  |          25.68 |       0.39% |
|                                 | hackbench-process-sockets-234 (seconds)                  |          30.06 |       0.57% |
|                                 | hackbench-process-sockets-256 (seconds)                  |          33.10 |       0.42% |
|                                 | hackbench-thread-pipes-1 (seconds)                       |           0.18 |       0.95% |
|                                 | hackbench-thread-pipes-4 (seconds)                       |           0.40 |       0.25% |
|                                 | hackbench-thread-pipes-7 (seconds)                       |           0.67 |      -1.28% |
|                                 | hackbench-thread-pipes-12 (seconds)                      |           1.13 |      -0.76% |
|                                 | hackbench-thread-pipes-21 (seconds)                      |           1.50 |       0.07% |
|                                 | hackbench-thread-pipes-30 (seconds)                      |           1.91 |       0.11% |
|                                 | hackbench-thread-pipes-48 (seconds)                      |           2.64 |      -0.09% |
|                                 | hackbench-thread-pipes-79 (seconds)                      |           3.63 |      -0.28% |
|                                 | hackbench-thread-pipes-110 (seconds)                     |           4.75 |      -0.30% |
|                                 | hackbench-thread-pipes-141 (seconds)                     |           5.89 |      -0.25% |
|                                 | hackbench-thread-pipes-172 (seconds)                     |           7.10 |      -0.31% |
|                                 | hackbench-thread-pipes-203 (seconds)                     |           8.31 |      -0.15% |
|                                 | hackbench-thread-pipes-234 (seconds)                     |           9.54 |      -0.23% |
|                                 | hackbench-thread-pipes-256 (seconds)                     |          10.39 |      -0.31% |
|                                 | hackbench-thread-sockets-1 (seconds)                     |           0.28 |       0.84% |
|                                 | hackbench-thread-sockets-4 (seconds)                     |           0.63 |      -0.05% |
|                                 | hackbench-thread-sockets-7 (seconds)                     |           0.99 |      -0.15% |
|                                 | hackbench-thread-sockets-12 (seconds)                    |           1.58 |       0.25% |
|                                 | hackbench-thread-sockets-21 (seconds)                    |           2.70 |       0.07% |
|                                 | hackbench-thread-sockets-30 (seconds)                    |           3.83 |       0.24% |
|                                 | hackbench-thread-sockets-48 (seconds)                    |           6.08 |       0.26% |
|                                 | hackbench-thread-sockets-79 (seconds)                    |           9.44 |       0.45% |
|                                 | hackbench-thread-sockets-110 (seconds)                   |          13.13 |       0.53% |
|                                 | hackbench-thread-sockets-141 (seconds)                   |          16.94 |       0.75% |
|                                 | hackbench-thread-sockets-172 (seconds)                   |          21.07 |       0.93% |
|                                 | hackbench-thread-sockets-203 (seconds)                   |          25.18 |       0.82% |
|                                 | hackbench-thread-sockets-234 (seconds)                   |          29.40 |       0.65% |
|                                 | hackbench-thread-sockets-256 (seconds)                   |          32.39 |       0.64% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| mmtests/kernbench               | kernbench-elsp-64 (seconds)                              |         359.59 |       0.05% |
|                                 | kernbench-syst-64 (seconds)                              |        1084.06 |       1.31% |
|                                 | kernbench-user-64 (seconds)                              |       19753.52 |       0.07% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| mmtests/sysbench-cpu            | sysbenchcpu-1 (ops/second)                               |         835.59 |      -0.01% |
|                                 | sysbenchcpu-4 (ops/second)                               |        3342.07 |       0.00% |
|                                 | sysbenchcpu-7 (ops/second)                               |        5848.46 |       0.00% |
|                                 | sysbenchcpu-12 (ops/second)                              |       10025.89 |      -0.00% |
|                                 | sysbenchcpu-21 (ops/second)                              |       17544.27 |      -0.00% |
|                                 | sysbenchcpu-30 (ops/second)                              |       25061.51 |      -0.00% |
|                                 | sysbenchcpu-48 (ops/second)                              |       40094.33 |      -0.01% |
|                                 | sysbenchcpu-79 (ops/second)                              |       53449.56 |      -0.00% |
|                                 | sysbenchcpu-110 (ops/second)                             |       53441.85 |      -0.00% |
|                                 | sysbenchcpu-128 (ops/second)                             |       53438.27 |      -0.00% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| mmtests/sysbench-mutex          | sysbenchmutex-1 (usec)                                   |         194.35 |       0.04% |
|                                 | sysbenchmutex-4 (usec)                                   |         200.54 |      -0.12% |
|                                 | sysbenchmutex-7 (usec)                                   |         200.98 |       0.04% |
|                                 | sysbenchmutex-12 (usec)                                  |         201.34 |      -0.14% |
|                                 | sysbenchmutex-21 (usec)                                  |         202.08 |      -0.17% |
|                                 | sysbenchmutex-30 (usec)                                  |         202.87 |      -0.34% |
|                                 | sysbenchmutex-48 (usec)                                  |         235.24 |       0.58% |
|                                 | sysbenchmutex-79 (usec)                                  |         362.89 |       0.03% |
|                                 | sysbenchmutex-110 (usec)                                 |         495.17 |      -4.54% |
|                                 | sysbenchmutex-128 (usec)                                 |         599.52 |       3.37% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| mmtests/sysbench-thread         | sysbenchthread-1 (usec)                                  |           0.36 |      -0.62% |
|                                 | sysbenchthread-4 (usec)                                  |           0.52 |      -0.77% |
|                                 | sysbenchthread-7 (usec)                                  |           2.85 |       4.31% |
|                                 | sysbenchthread-12 (usec)                                 |           6.42 |      -0.19% |
|                                 | sysbenchthread-21 (usec)                                 |          13.52 |      -5.83% |
|                                 | sysbenchthread-30 (usec)                                 |          17.14 |       6.86% |
|                                 | sysbenchthread-48 (usec)                                 |          30.64 |       2.04% |
|                                 | sysbenchthread-79 (usec)                                 |          62.83 |       3.59% |
|                                 | sysbenchthread-110 (usec)                                |          95.75 |       0.87% |
|                                 | sysbenchthread-128 (usec)                                |         112.12 |      -0.27% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| perf/futex                      | hash (ops/sec)                                           |     2661114.13 |      -1.22% |
|                                 | lock-pi (ops/sec)                                        |         281.00 |       0.00% |
|                                 | requeue (ms)                                             |          0.028 |       6.37% |
|                                 | wake (ms)                                                |          0.079 |       6.65% |
|                                 | wake-parallel (ms)                                       |         0.0044 |       2.47% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| perf/mem                        | memset -k 1GB -f default -s 16GB (bytes/sec)             | 65384265194.20 |      -1.20% |
|                                 | mmap -p 1GB -f demand -s 32GB -l 5 (bytes/sec)           | 63873483711.66 |      -0.51% |
|                                 | mmap -p 4KB -f demand -s 32GB -l 5 (bytes/sec)           | 50086884685.75 |       0.33% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| perf/sched                      | messaging -l 10000 (sec)                                 |           1.32 |       1.11% |
|                                 | pipe (ops/sec)                                           |      746693.53 |  (I) 10.81% |
|                                 | seccomp-notify (ops/sec)                                 |      239242.23 |       0.99% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| perf/syscall                    | basic (ops/sec)                                          |     5120478.20 |   (I) 3.58% |
|                                 | execve (ops/sec)                                         |        2361.40 |   (I) 3.32% |
|                                 | fork (ops/sec)                                           |        4036.27 |   (I) 5.89% |
|                                 | getpgid (ops/sec)                                        |     5263958.43 |      -0.51% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| pts/memtier-benchmark           | Protocol: Redis Clients: 50 Ratio: 1:1 (Ops/sec)         |     1881192.47 |       1.76% |
|                                 | Protocol: Redis Clients: 50 Ratio: 1:5 (Ops/sec)         |     2029301.38 |       1.10% |
|                                 | Protocol: Redis Clients: 50 Ratio: 5:1 (Ops/sec)         |     1676141.91 |       1.81% |
|                                 | Protocol: Redis Clients: 100 Ratio: 1:1 (Ops/sec)        |     1887013.22 |       1.44% |
|                                 | Protocol: Redis Clients: 100 Ratio: 1:5 (Ops/sec)        |     1992665.04 |   (I) 5.00% |
|                                 | Protocol: Redis Clients: 100 Ratio: 5:1 (Ops/sec)        |     1796984.06 |      -1.13% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| pts/nginx                       | Connections: 200 (Requests Per Second)                   |      265772.36 |       0.15% |
|                                 | Connections: 1000 (Requests Per Second)                  |      256136.45 |       0.23% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| pts/perl-benchmark              | Test: Interpreter (Seconds)                              |         0.0011 |  (I) 12.50% |
|                                 | Test: Pod2html (Seconds)                                 |           0.12 |       0.71% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| pts/pybench                     | Total For Average Test Times (Milliseconds)              |        1005.50 |      -0.02% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| pts/redis                       | Test: GET Connections: 50 (Requests Per Second)          |     2265966.17 |       1.63% |
|                                 | Test: GET Connections: 1000 (Requests Per Second)        |     2219967.42 |       1.40% |
|                                 | Test: LPOP Connections: 50 (Requests Per Second)         |     1569488.21 |       2.28% |
|                                 | Test: LPOP Connections: 1000 (Requests Per Second)       |     1551803.58 |       2.42% |
|                                 | Test: LPUSH Connections: 50 (Requests Per Second)        |     1525781.50 |       2.68% |
|                                 | Test: LPUSH Connections: 1000 (Requests Per Second)      |     1428476.58 |       2.60% |
|                                 | Test: SADD Connections: 50 (Requests Per Second)         |     2030311.52 |       1.26% |
|                                 | Test: SADD Connections: 1000 (Requests Per Second)       |     2004562.54 |       1.64% |
|                                 | Test: SET Connections: 50 (Requests Per Second)          |     1839073.31 |       0.64% |
|                                 | Test: SET Connections: 1000 (Requests Per Second)        |     1806245.08 |       1.11% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| pts/sqlite-speedtest            | Timed Time - Size 1,000 (Seconds)                        |          75.65 |       1.63% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| repro-collection/mysql-workload | db transaction rate (transactions/min)                   |      236380.17 |       0.65% |
|                                 | new order rate (orders/min)                              |       77978.33 |       0.69% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| schbench/thread-contention      | -m 16 -t 1 -r 10 -s 1000, avg_rps (req/sec)              |        1360.03 |       1.79% |
|                                 | -m 16 -t 1 -r 10 -s 1000, req_latency_p99 (usec)         |       15084.80 |      -0.06% |
|                                 | -m 16 -t 1 -r 10 -s 1000, wakeup_latency_p99 (usec)      |           3.00 |       0.00% |
|                                 | -m 16 -t 4 -r 10 -s 1000, avg_rps (req/sec)              |        4367.47 |  (I) 20.95% |
|                                 | -m 16 -t 4 -r 10 -s 1000, req_latency_p99 (usec)         |       15141.60 |       0.02% |
|                                 | -m 16 -t 4 -r 10 -s 1000, wakeup_latency_p99 (usec)      |           4.15 | (R) -13.99% |
|                                 | -m 16 -t 16 -r 10 -s 1000, avg_rps (req/sec)             |        1331.22 |       3.94% |
|                                 | -m 16 -t 16 -r 10 -s 1000, req_latency_p99 (usec)        |      950041.60 |       1.54% |
|                                 | -m 16 -t 16 -r 10 -s 1000, wakeup_latency_p99 (usec)     |       15538.40 |      -1.25% |
|                                 | -m 16 -t 64 -r 10 -s 1000, avg_rps (req/sec)             |         433.65 |      -0.14% |
|                                 | -m 16 -t 64 -r 10 -s 1000, req_latency_p99 (usec)        |    11090329.60 |      -0.18% |
|                                 | -m 16 -t 64 -r 10 -s 1000, wakeup_latency_p99 (usec)     |       64028.80 |      -0.15% |
|                                 | -m 32 -t 1 -r 10 -s 1000, avg_rps (req/sec)              |        2962.10 |       4.76% |
|                                 | -m 32 -t 1 -r 10 -s 1000, req_latency_p99 (usec)         |       15096.80 |      -0.03% |
|                                 | -m 32 -t 1 -r 10 -s 1000, wakeup_latency_p99 (usec)      |           3.00 |       0.00% |
|                                 | -m 32 -t 4 -r 10 -s 1000, avg_rps (req/sec)              |        2365.75 |  (I) 10.92% |
|                                 | -m 32 -t 4 -r 10 -s 1000, req_latency_p99 (usec)         |       56864.00 |      -0.45% |
|                                 | -m 32 -t 4 -r 10 -s 1000, wakeup_latency_p99 (usec)      |        6064.00 |      -0.07% |
|                                 | -m 32 -t 16 -r 10 -s 1000, avg_rps (req/sec)             |         709.63 |       1.97% |
|                                 | -m 32 -t 16 -r 10 -s 1000, req_latency_p99 (usec)        |     3780096.00 |      -1.87% |
|                                 | -m 32 -t 16 -r 10 -s 1000, wakeup_latency_p99 (usec)     |       31720.00 |       0.57% |
|                                 | -m 32 -t 64 -r 10 -s 1000, avg_rps (req/sec)             |         387.14 |       0.21% |
|                                 | -m 32 -t 64 -r 10 -s 1000, req_latency_p99 (usec)        |    16696524.80 |       0.00% |
|                                 | -m 32 -t 64 -r 10 -s 1000, wakeup_latency_p99 (usec)     |      126131.20 |      -0.15% |
|                                 | -m 64 -t 1 -r 10 -s 1000, avg_rps (req/sec)              |        6545.98 |       1.53% |
|                                 | -m 64 -t 1 -r 10 -s 1000, req_latency_p99 (usec)         |       15108.00 |      -0.05% |
|                                 | -m 64 -t 1 -r 10 -s 1000, wakeup_latency_p99 (usec)      |           4.00 |       0.00% |
|                                 | -m 64 -t 4 -r 10 -s 1000, avg_rps (req/sec)              |        1243.98 |       0.56% |
|                                 | -m 64 -t 4 -r 10 -s 1000, req_latency_p99 (usec)         |      910310.40 |      -0.17% |
|                                 | -m 64 -t 4 -r 10 -s 1000, wakeup_latency_p99 (usec)      |       13161.60 |      -0.07% |
|                                 | -m 64 -t 16 -r 10 -s 1000, avg_rps (req/sec)             |         456.27 |       0.02% |
|                                 | -m 64 -t 16 -r 10 -s 1000, req_latency_p99 (usec)        |    11055104.00 |      -0.20% |
|                                 | -m 64 -t 16 -r 10 -s 1000, wakeup_latency_p99 (usec)     |       61657.60 |      -1.58% |
|                                 | -m 64 -t 64 -r 10 -s 1000, avg_rps (req/sec)             |         535.45 |       0.14% |
|                                 | -m 64 -t 64 -r 10 -s 1000, req_latency_p99 (usec)        |    36939366.40 |      -0.02% |
|                                 | -m 64 -t 64 -r 10 -s 1000, wakeup_latency_p99 (usec)     |      241779.20 |      -0.33% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| specjbb/composite               | critical-jOPS (jOPS)                                     |       95699.00 |   (I) 2.13% |
|                                 | max-jOPS (jOPS)                                          |      116191.00 |       1.27% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| speedometer/v2.0                | score (runs/min)                                         |         154.50 |       1.51% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+
| speedometer/v2.1                | score (runs/min)                                         |         161.67 |   (I) 2.78% |
+---------------------------------+----------------------------------------------------------+----------------+-------------+

-- 
Thanks,
Usama