# git rev-parse -q --verify 8fc63a91e785ef06fb7f1aba59297793d85095f7^{commit} 8fc63a91e785ef06fb7f1aba59297793d85095f7 already have revision, skipping fetch # git checkout -q -f -B kisskb 8fc63a91e785ef06fb7f1aba59297793d85095f7 # git clean -qxdf # < git log -1 # commit 8fc63a91e785ef06fb7f1aba59297793d85095f7 # Merge: 6f4b7052daa0 c46975715f5a # Author: Michael Ellerman # Date: Fri Dec 15 13:51:56 2023 +1100 # # Merge branch 'smp-topo' into next # # Merge a branch containing SMP topology updates from Srikar, purely so we can # include the cover letter which has a lot of good detail here: # # PowerVM systems configured in shared processors mode have some unique # challenges. Some device-tree properties will be missing on a shared # processor. Hence some sched domains may not make sense for shared processor # systems. # # Most shared processor systems are over-provisioned. Underlying PowerVM # Hypervisor would schedule at a Big Core (SMT8) granularity. The most recent # power processors support two almost independent cores. In a lightly loaded # condition, it helps the overall system performance if we pack to lesser number # of Big Cores. # # Since each thread-group is independent, running threads on both the # thread-groups of a SMT8 core, should have a minimal adverse impact in # non over provisioned scenarios. These changes in this patchset will not # affect in the over provisioned scenario. If there are more threads than # SMT domains, then asym_packing will not kick-in. # # System Configuration # type=Shared mode=Uncapped smt=8 lcpu=96 mem=1066409344 kB cpus=96 ent=64.00 # So *64 Entitled cores/ 96 Virtual processor* Scenario # # lscpu # Architecture: ppc64le # Byte Order: Little Endian # CPU(s): 768 # On-line CPU(s) list: 0-767 # Model name: POWER10 (architected), altivec supported # Model: 2.0 (pvr 0080 0200) # Thread(s) per core: 8 # Core(s) per socket: 16 # Socket(s): 6 # Hypervisor vendor: pHyp # Virtualization type: para # L1d cache: 6 MiB (192 instances) # L1i cache: 9 MiB (192 instances) # NUMA node(s): 6 # NUMA node0 CPU(s): 0-7,32-39,80-87,128-135,176-183,224-231,272-279,320-327,368-375,416-423,464-471,512-519,560-567,608-615,656-663,704-711,752-759 # NUMA node1 CPU(s): 8-15,40-47,88-95,136-143,184-191,232-239,280-287,328-335,376-383,424-431,472-479,520-527,568-575,616-623,664-671,712-719,760-767 # NUMA node4 CPU(s): 64-71,112-119,160-167,208-215,256-263,304-311,352-359,400-407,448-455,496-503,544-551,592-599,640-647,688-695,736-743 # NUMA node5 CPU(s): 16-23,48-55,96-103,144-151,192-199,240-247,288-295,336-343,384-391,432-439,480-487,528-535,576-583,624-631,672-679,720-727 # NUMA node6 CPU(s): 72-79,120-127,168-175,216-223,264-271,312-319,360-367,408-415,456-463,504-511,552-559,600-607,648-655,696-703,744-751 # NUMA node7 CPU(s): 24-31,56-63,104-111,152-159,200-207,248-255,296-303,344-351,392-399,440-447,488-495,536-543,584-591,632-639,680-687,728-735 # # ebizzy -t 32 -S 200 (5 iterations) Records per second. (Higher is better) # Kernel N Min Max Median Avg Stddev %Change # 6.6.0-rc3 5 3840178 4059268 3978042 3973936.6 84264.456 # +patch 5 3768393 3927901 3874994 3854046 71532.926 -3.01692 # # >From lparstat (when the workload stabilized) # Kernel %user %sys %wait %idle physc %entc lbusy app vcsw phint # 6.6.0-rc3 4.16 0.00 0.00 95.84 26.06 40.72 4.16 69.88 276906989 578 # +patch 4.16 0.00 0.00 95.83 17.70 27.66 4.17 78.26 70436663 119 # # ebizzy -t 128 -S 200 (5 iterations) Records per second. (Higher is better) # Kernel N Min Max Median Avg Stddev %Change # 6.6.0-rc3 5 5520692 5981856 5717709 5727053.2 176093.2 # +patch 5 5305888 6259610 5854590 5843311 375917.03 2.02998 # # >From lparstat (when the workload stabilized) # Kernel %user %sys %wait %idle physc %entc lbusy app vcsw phint # 6.6.0-rc3 16.66 0.00 0.00 83.33 45.49 71.08 16.67 50.50 288778533 581 # +patch 16.65 0.00 0.00 83.35 30.15 47.11 16.65 65.76 85196150 133 # # ebizzy -t 512 -S 200 (5 iterations) Records per second. (Higher is better) # Kernel N Min Max Median Avg Stddev %Change # 6.6.0-rc3 5 19563921 20049955 19701510 19728733 198295.18 # +patch 5 19455992 20176445 19718427 19832017 304094.05 0.523521 # # >From lparstat (when the workload stabilized) # %Kernel user %sys %wait %idle physc %entc lbusy app vcsw phint # 66.6.0-rc3 6.44 0.01 0.00 33.55 94.14 147.09 66.45 1.33 313345175 621 # 6+patch 6.44 0.01 0.00 33.55 94.15 147.11 66.45 1.33 109193889 309 # # System Configuration # type=Shared mode=Uncapped smt=8 lcpu=40 mem=1067539392 kB cpus=96 ent=40.00 # So *40 Entitled cores/ 40 Virtual processor* Scenario # # lscpu # Architecture: ppc64le # Byte Order: Little Endian # CPU(s): 320 # On-line CPU(s) list: 0-319 # Model name: POWER10 (architected), altivec supported # Model: 2.0 (pvr 0080 0200) # Thread(s) per core: 8 # Core(s) per socket: 10 # Socket(s): 4 # Hypervisor vendor: pHyp # Virtualization type: para # L1d cache: 2.5 MiB (80 instances) # L1i cache: 3.8 MiB (80 instances) # NUMA node(s): 4 # NUMA node0 CPU(s): 0-7,32-39,64-71,96-103,128-135,160-167,192-199,224-231,256-263,288-295 # NUMA node1 CPU(s): 8-15,40-47,72-79,104-111,136-143,168-175,200-207,232-239,264-271,296-303 # NUMA node4 CPU(s): 16-23,48-55,80-87,112-119,144-151,176-183,208-215,240-247,272-279,304-311 # NUMA node5 CPU(s): 24-31,56-63,88-95,120-127,152-159,184-191,216-223,248-255,280-287,312-319 # # ebizzy -t 32 -S 200 (5 iterations) Records per second. (Higher is better) # Kernel N Min Max Median Avg Stddev %Change # 6.6.0-rc3 5 3535518 3864532 3745967 3704233.2 130216.76 # +patch 5 3608385 3708026 3649379 3651596.6 37862.163 -1.42099 # # %Kernel user %sys %wait %idle physc %entc lbusy app vcsw phint # 6.6.0-rc3 10.00 0.01 0.00 89.99 22.98 57.45 10.01 41.01 1135139 262 # +patch 10.00 0.00 0.00 90.00 16.95 42.37 10.00 47.05 925561 19 # # ebizzy -t 64 -S 200 (5 iterations) Records per second. (Higher is better) # Kernel N Min Max Median Avg Stddev %Change # 6.6.0-rc3 5 4434984 4957281 4548786 4591298.2 211770.2 # +patch 5 4461115 4835167 4544716 4607795.8 151474.85 0.359323 # # %Kernel user %sys %wait %idle physc %entc lbusy app vcsw phint # 6.6.0-rc3 20.01 0.00 0.00 79.99 38.22 95.55 20.01 25.77 1287553 265 # +patch 19.99 0.00 0.00 80.01 25.55 63.88 19.99 38.44 1077341 20 # # ebizzy -t 256 -S 200 (5 iterations) Records per second. (Higher is better) # Kernel N Min Max Median Avg Stddev %Change # 6.6.0-rc3 5 8850648 8982659 8951911 8936869.2 52278.031 # +patch 5 8751038 9060510 8981409 8942268.4 117070.6 0.0604149 # # %Kernel user %sys %wait %idle physc %entc lbusy app vcsw phint # 6.6.0-rc3 80.02 0.01 0.01 19.96 40.00 100.00 80.03 24.00 1597665 276 # +patch 80.02 0.01 0.01 19.96 40.00 100.00 80.03 23.99 1383921 63 # # Observation: # We are able to see Improvement in ebizzy throughput even with lesser # core utilization (almost half the core utilization) in low utilization # scenarios while still retaining throughput in mid and higher utilization # scenarios. # Note: The numbers are with Uncapped + no-noise case. In the Capped and/or # noise case, due to contention on the Cores, the numbers are expected to # further improve. # # Note: The numbers included (sched/fair: Enable group_asym_packing in find_idlest_group) # https://lore.kernel.org/all/20231018155036.2314342-1-srikar@linux.vnet.ibm.com/ # < /opt/cross/kisskb/korg/gcc-5.5.0-nolibc/powerpc64-linux/bin/powerpc64-linux-gcc --version # < /opt/cross/kisskb/korg/gcc-5.5.0-nolibc/powerpc64-linux/bin/powerpc64-linux-ld --version # < git log --format=%s --max-count=1 8fc63a91e785ef06fb7f1aba59297793d85095f7 # make -s -j 40 ARCH=powerpc O=/kisskb/build/powerpc-next_mpc85xx_smp_defconfig_powerpc-gcc5 CROSS_COMPILE=/opt/cross/kisskb/korg/gcc-5.5.0-nolibc/powerpc64-linux/bin/powerpc64-linux- mpc85xx_smp_defconfig Using /kisskb/src/arch/powerpc/configs/mpc85xx_base.config as base Merging /kisskb/src/arch/powerpc/configs/85xx-32bit.config Merging /kisskb/src/arch/powerpc/configs/85xx-smp.config Merging /kisskb/src/arch/powerpc/configs/85xx-hw.config Merging /kisskb/src/arch/powerpc/configs/fsl-emb-nonhw.config # # merged configuration written to .config (needs make) # # < make -s -j 40 ARCH=powerpc O=/kisskb/build/powerpc-next_mpc85xx_smp_defconfig_powerpc-gcc5 CROSS_COMPILE=/opt/cross/kisskb/korg/gcc-5.5.0-nolibc/powerpc64-linux/bin/powerpc64-linux- help # make -s -j 40 ARCH=powerpc O=/kisskb/build/powerpc-next_mpc85xx_smp_defconfig_powerpc-gcc5 CROSS_COMPILE=/opt/cross/kisskb/korg/gcc-5.5.0-nolibc/powerpc64-linux/bin/powerpc64-linux- olddefconfig # make -s -j 40 ARCH=powerpc O=/kisskb/build/powerpc-next_mpc85xx_smp_defconfig_powerpc-gcc5 CROSS_COMPILE=/opt/cross/kisskb/korg/gcc-5.5.0-nolibc/powerpc64-linux/bin/powerpc64-linux- In file included from /kisskb/src/include/linux/build_bug.h:5:0, from /kisskb/src/include/linux/container_of.h:5, from /kisskb/src/include/linux/list.h:5, from /kisskb/src/include/linux/module.h:12, from /kisskb/src/drivers/net/ethernet/freescale/fs_enet/mac-scc.c:15: /kisskb/src/drivers/net/ethernet/freescale/fs_enet/mac-scc.c: In function 'allocate_bd': /kisskb/src/include/linux/err.h:28:49: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast] #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO) ^ /kisskb/src/include/linux/compiler.h:77:42: note: in definition of macro 'unlikely' # define unlikely(x) __builtin_expect(!!(x), 0) ^ /kisskb/src/drivers/net/ethernet/freescale/fs_enet/mac-scc.c:138:6: note: in expansion of macro 'IS_ERR_VALUE' if (IS_ERR_VALUE(fep->ring_mem_addr)) ^ /kisskb/src/drivers/net/ethernet/freescale/fs_enet/mac-scc.c: At top level: cc1: warning: unrecognized command line option '-Wno-shift-negative-value' Completed OK # rm -rf /kisskb/build/powerpc-next_mpc85xx_smp_defconfig_powerpc-gcc5 # Build took: 0:01:22.400354