From: "Gautham R. Shenoy" <e...@linux.vnet.ibm.com> Hi,
This is the fifth iteration of the patchset to add support for big-core on POWER9. This patch also optimizes the task placement on such big-core systems. The previous versions can be found here: v5: https://lkml.org/lkml/2018/8/6/587 v4: https://lkml.org/lkml/2018/7/24/79 v3: https://lkml.org/lkml/2018/7/6/255 v2: https://lkml.org/lkml/2018/7/3/401 v1: https://lkml.org/lkml/2018/5/11/245 Changes : v5 --> v6: - Fixed the code to build without warnings for !CONFIG_SCHED_SMT. - While checking for shared caches on big-core system, use the smallcore_sibling_mask to compare with compare with l2_cache_mask, which will ensure that the CACHE level sched-domain is created. - Added benchmark results with hackbench to demonstrate the benefits of having the CACHE level sched-domain. v4 --> v5: - Patch 2 is entirely different: Instead of using CPU_FTR_ASYM_SMT feature, use the small core siblings at the SMT level sched-domain. This was suggested by Nicholas Piggin and Michael Ellerman. - A more detailed description follows below. v3 --> v4: - Build fix for powerpc-g5 : Enable CPU_FTR_ASYM_SMT only on CONFIG_PPC_POWERNV and CONFIG_PPC_PSERIES. - Fixed a minor error in the ABI description. v2 --> v3 - Set sane values in the tg->property, tg->nr_groups inside parse_thread_groups before returning due to an error. - Define a helper function to determine whether a CPU device node is a big-core or not. - Updated the comments around the functions to describe the arguments passed to them. v1 --> v2 - Added comments explaining the "ibm,thread-groups" device tree property. - Uses cleaner device-tree parsing functions to parse the u32 arrays. - Adds a sysfs file listing the small-core siblings for every CPU. - Enables the scheduler optimization by setting the CPU_FTR_ASYM_SMT bit in the cur_cpu_spec->cpu_features on detecting the presence of interleaved big-core. - Handles the corner case where there is only a single thread-group or when there is a single thread in a thread-group. Description: ~~~~~~~~~~~~~~~~~~~~ A pair of IBM POWER9 SMT4 cores can be fused together to form a big-core with 8 SMT threads. This can be discovered via the "ibm,thread-groups" CPU property in the device tree which will indicate which group of threads that share the L1 cache, translation cache and instruction data flow. If there are multiple such group of threads, then the core is a big-core. Furthermore, on POWER9 the thread-ids of such a big-core is obtained by interleaving the thread-ids of the component SMT4 cores. Eg: Threads in the pair of component SMT4 cores of an interleaved big-core are numbered {0,2,4,6} and {1,3,5,7} respectively. ------------------------- | L1 Cache | ---------------------------------- |L2| | | | | | | 0 | 2 | 4 | 6 |Small Core0 |C | | | | | Big |a -------------------------- Core |c | | | | | |h | 1 | 3 | 5 | 7 | Small Core1 |e | | | | | ----------------------------- | L1 Cache | -------------------------- On such a big-core system, when multiple tasks are scheduled to run on the big-core, we get the best performance when the tasks are spread across the pair of SMT4 cores. Eg: Suppose there 4 tasks {p1, p2, p3, p4} are run on a big core, then An Example of Optimal Task placement: -------------------------- | | | | | | 0 | 2 | 4 | 6 | Small Core0 | (p1)| (p2)| | | Big Core -------------------------- | | | | | | 1 | 3 | 5 | 7 | Small Core1 | | (p3)| | (p4) | -------------------------- An example of Suboptimal Task placement: -------------------------- | | | | | | 0 | 2 | 4 | 6 | Small Core0 | (p1)| (p2)| | (p4)| Big Core -------------------------- | | | | | | 1 | 3 | 5 | 7 | Small Core1 | | (p3)| | | -------------------------- In order to achieve optimal task placement, on big-core systems, we define the SMT level sched-domain to consist of the threads belonging to the small cores. The CACHE level sched domain will consist of all the threads belonging to the big-core. With this, the Linux Kernel load-balancer will ensure that the tasks are spread across all the component small cores in the system, thereby yielding optimum performance. Furthermore, this solution works correctly across all SMT modes (8,4,2), as the interleaved thread-ids ensures that when we go to lower SMT modes (4,2) the threads are offlined in a descending order, thereby leaving equal number of threads from the component small cores online as illustrated below. With Patches: (ppc64_cpu --smt=on) : SMT domain ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ CPU0 attaching sched-domain(s): domain-0: span=0,2,4,6 level=SMT groups: 0:{ span=0 cap=294 }, 2:{ span=2 cap=294 }, 4:{ span=4 cap=294 }, 6:{ span=6 cap=294 } CPU1 attaching sched-domain(s): domain-0: span=1,3,5,7 level=SMT groups: 1:{ span=1 cap=294 }, 3:{ span=3 cap=294 }, 5:{ span=5 cap=294 }, 7:{ span=7 cap=294 } Optimal Task placement (SMT 8) -------------------------- | | | | | | 0 | 2 | 4 | 6 | Small Core0 | (p1)| (p2)| | | Big Core -------------------------- | | | | | | 1 | 3 | 5 | 7 | Small Core1 | | (p3)| | (p4) | -------------------------- With Patches : (ppc64_cpu --smt=4) : SMT domain ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ CPU0 attaching sched-domain(s): domain-0: span=0,2 level=SMT groups: 0:{ span=0 cap=589 }, 2:{ span=2 cap=589 } CPU1 attaching sched-domain(s): domain-0: span=1,3 level=SMT groups: 1:{ span=1 cap=589 }, 3:{ span=3 cap=589 } Optimal Task placement (SMT 4) -------------------------- | | | | | | 0 | 2 | 4 | 6 | Small Core0 | (p1)| (p2)| Off | Off | Big Core -------------------------- | | | | | | 1 | 3 | 5 | 7 | Small Core1 | (p4)| (p3)| Off | Off | -------------------------- With Patches : (ppc64_cpu --smt=2) : SMT domain ceases to exist. ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Optimal Task placement (SMT 2) -------------------------- | (p2)| | | | | 0 | 2 | 4 | 6 | Small Core0 | (p1)| Off | Off | Off | Big Core -------------------------- | (p3)| | | | | 1 | 3 | 5 | 7 | Small Core1 | (p4)| Off | Off | Off | -------------------------- Thus, as an added advantage in SMT=2 mode, we will only have 3 levels in the sched-domain topology (CACHE, DIE and NUMA). The SMT levels, without the patches are as follows. Without Patches: (ppc64_cpu --smt=on) : SMT domain ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ CPU0 attaching sched-domain(s): domain-0: span=0-7 level=SMT groups: 0:{ span=0 cap=147 }, 1:{ span=1 cap=147 }, 2:{ span=2 cap=147 }, 3:{ span=3 cap=147 }, 4:{ span=4 cap=147 }, 5:{ span=5 cap=147 }, 6:{ span=6 cap=147 }, 7:{ span=7 cap=147 } CPU1 attaching sched-domain(s): domain-0: span=0-7 level=SMT groups: 1:{ span=1 cap=147 }, 2:{ span=2 cap=147 }, 3:{ span=3 cap=147 }, 4:{ span=4 cap=147 }, 5:{ span=5 cap=147 }, 6:{ span=6 cap=147 }, 7:{ span=7 cap=147 }, 0:{ span=0 cap=147 } Without Patches: (ppc64_cpu --smt=4) : SMT domain ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ CPU0 attaching sched-domain(s): domain-0: span=0-3 level=SMT groups: 0:{ span=0 cap=294 }, 1:{ span=1 cap=294 }, 2:{ span=2 cap=294 }, 3:{ span=3 cap=294 }, CPU1 attaching sched-domain(s): domain-0: span=0-3 level=SMT groups: 1:{ span=1 cap=294 }, 2:{ span=2 cap=294 }, 3:{ span=3 cap=294 }, 0:{ span=0 cap=294 } Without Patches: (ppc64_cpu --smt=2) : SMT domain ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ CPU0 attaching sched-domain(s): domain-0: span=0-1 level=SMT groups: 0:{ span=0 cap=589 }, 1:{ span=1 cap=589 }, CPU1 attaching sched-domain(s): domain-0: span=0-1 level=SMT groups: 1:{ span=1 cap=589 }, 0:{ span=0 cap=589 }, This patchset contains two patches which on detecting the presence of big-cores, defines the SMT level sched domain to correspond to the threads of the small cores. Patch 1: adds support to detect the presence of big-cores and reports the small-core siblings of each CPU X via the sysfs file "/sys/devices/system/cpu/cpuX/small_core_siblings". Patch 2: Defines the SMT level sched domain to correspond to the threads of the small cores. Results: ~~~~~~~~~~~~~~~~~ 1) 2 thread ebizzy ~~~~~~~~~~~~~~~~~~~~~~ Experimental results for ebizzy with 2 threads, bound to a single big-core show a marked improvement with this patchset over the 4.18-rc5 vanilla kernel. The result of 100 such runs for 4.18-rc7 kernel and the 4.18-rc7 + big-core-smt-patches are as follows 4.18.0-rc7 vanilla ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ records/s : # samples : Histogram ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [ 0 - 1000000] : 0 : # [1000000 - 2000000] : 3 : # [2000000 - 3000000] : 7 : ## [3000000 - 4000000] : 26 : ###### [4000000 - 5000000] : 4 : # [5000000 - 6000000] : 60 : ############# 4.18.0-rc7 + big-core-smt-patches ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ records/s : # samples : Histogram ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ [ 0 - 1000000] : 0 : # [1000000 - 2000000] : 0 : # [2000000 - 3000000] : 11 : ### [3000000 - 4000000] : 0 : # [4000000 - 5000000] : 0 : # [5000000 - 6000000] : 89 : ################## 2) Hackbench (perf bench sched pipe) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 100 iterations of the hackbench run both on 4.18-rc7 vanilla kernel and v.18-rc7 + big-core-smt-patches. All the values are time in seconds (Lower the better) 4.18.0-rc7 vanilla ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ N Min Max Median Avg Stddev x 100 4.225 9.754 6.174 6.00402 0.88311027 4.18.0-rc7 + big-core-smt-patches (v6 : the present version) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ N Min Max Median Avg Stddev x 100 4.069 6.745 6.08 5.72414 0.73853727 The presence of the CACHE level sched-domain in v6, which was absent in v5 of the patches seems to be making a difference, as the median and the average times taken by hackbench both drop. 4.18.0-rc7 + big-core-smt-patches (v5 : the previous version) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ N Min Max Median Avg Stddev x 100 4.972 10.123 6.177 6.323 0.68728617 Gautham R. Shenoy (2): powerpc: Detect the presence of big-cores via "ibm,thread-groups" powerpc: Use cpu_smallcore_sibling_mask at SMT level on bigcores Documentation/ABI/testing/sysfs-devices-system-cpu | 8 ++ arch/powerpc/include/asm/cputhreads.h | 22 +++ arch/powerpc/include/asm/smp.h | 6 + arch/powerpc/kernel/setup-common.c | 154 +++++++++++++++++++++ arch/powerpc/kernel/smp.c | 62 ++++++++- arch/powerpc/kernel/sysfs.c | 35 +++++ 6 files changed, 282 insertions(+), 5 deletions(-) -- 1.9.4