Greeting, FYI, we noticed a 23.9% regression of fsmark.app_overhead due to commit: commit: c5c7d471afa9e432d8dfc1b60e0a509c99eea862 ("btrfs: try to satisfy metadata requests if wen can overcommit") https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master in testcase: fsmark on test machine: 48 threads Intel(R) Xeon(R) CPU E5-2697 v2 @ 2.70GHz with 64G memory with following parameters: iterations: 1x nr_threads: 1t disk: 1BRD_32G fs: btrfs filesize: 4K test_size: 4G sync_method: fsyncBeforeClose nr_files_per_directory: 1fpd cpufreq_governor: performance test-description: The fsmark is a file system benchmark to test synchronous write workloads, for example, mail servers workload. test-url: https://sourceforge.net/projects/fsmark/ Details are as below: --------------------------------------------------------------------------------------------------> To reproduce: git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git cd lkp-tests bin/lkp install job.yaml # job file is attached in this email bin/lkp run job.yaml testcase/path_params/tbox_group/run: fsmark/1x-1t-1BRD_32G-btrfs-4K-4G-fsyncBeforeClose-1fpd-performance/ivb43 9384ca4690ff7f2e c5c7d471afa9e432d8dfc1b60e ---------------- -------------------------- %stddev change %stddev \ | \ 31591275 11% 35216163 ± 33% fsmark.app_overhead 26 ± 19% 5e+04 54851 ± 33% latency_stats.avg.reserve_metadata_bytes.[btrfs].btrfs_block_rsv_add.[btrfs].btrfs_block_rsv_add.[btrfs].start_transaction.[btrfs].btrfs_start_transaction.[btrfs].btrfs_mkdir.[btrfs].vfs_mkdir.SyS_mkdir.entry_SYSCALL_64_fastpath 62397 -6e+04 106 ± 76% latency_stats.avg.reserve_metadata_bytes.[btrfs].btrfs_block_rsv_add.[btrfs].btrfs_block_rsv_add.[btrfs].start_transaction.[btrfs].btrfs_start_transaction.[btrfs].btrfs_create.[btrfs].path_openat.do_filp_open.do_sys_open.SyS_open.entry_SYSCALL_64_fastpath 50 ± 25% 9e+04 92057 ± 35% latency_stats.max.reserve_metadata_bytes.[btrfs].btrfs_block_rsv_add.[btrfs].btrfs_block_rsv_add.[btrfs].start_transaction.[btrfs].btrfs_start_transaction.[btrfs].btrfs_mkdir.[btrfs].vfs_mkdir.SyS_mkdir.entry_SYSCALL_64_fastpath 291 ± 17% 7e+06 6884837 ± 33% latency_stats.sum.reserve_metadata_bytes.[btrfs].btrfs_block_rsv_add.[btrfs].btrfs_block_rsv_add.[btrfs].start_transaction.[btrfs].btrfs_start_transaction.[btrfs].btrfs_mkdir.[btrfs].vfs_mkdir.SyS_mkdir.entry_SYSCALL_64_fastpath 7727955 -8e+06 143645 ± 76% latency_stats.sum.reserve_metadata_bytes.[btrfs].btrfs_block_rsv_add.[btrfs].btrfs_block_rsv_add.[btrfs].start_transaction.[btrfs].btrfs_start_transaction.[btrfs].btrfs_create.[btrfs].path_openat.do_filp_open.do_sys_open.SyS_open.entry_SYSCALL_64_fastpath fsmark.app_overhead 4.5e+07 ++----------------------------------------------------------------+ O O O O O O | 4e+07 +OOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOOO OOOOOO OOO | 3.5e+07 ++ | ************* ***************************************************** 3e+07 ++ * | 2.5e+07 ++ | | | 2e+07 ++ | 1.5e+07 ++ | | | 1e+07 ++ | 5e+06 ++ | | | 0 ++----------------------------------------------------O-----------+ [*] bisect-good sample [O] bisect-bad sample Disclaimer: Results have been estimated based on internal Intel analysis and are provided for informational purposes only. Any difference in system hardware or software design or configuration may affect actual performance. Thanks, Xiaolong