diff options
Diffstat (limited to 'Documentation/admin-guide/sysctl')
| -rw-r--r-- | Documentation/admin-guide/sysctl/kernel.rst | 142 | ||||
| -rw-r--r-- | Documentation/admin-guide/sysctl/net.rst | 62 | ||||
| -rw-r--r-- | Documentation/admin-guide/sysctl/vm.rst | 53 |
3 files changed, 179 insertions, 78 deletions
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst index 0e486f41185e..98d1b198b2b4 100644 --- a/Documentation/admin-guide/sysctl/kernel.rst +++ b/Documentation/admin-guide/sysctl/kernel.rst @@ -38,8 +38,8 @@ acct If BSD-style process accounting is enabled these values control its behaviour. If free space on filesystem where the log lives -goes below ``lowwater``% accounting suspends. If free space gets -above ``highwater``% accounting resumes. ``frequency`` determines +goes below ``lowwater``\ % accounting suspends. If free space gets +above ``highwater``\ % accounting resumes. ``frequency`` determines how often do we check the amount of free space (value is in seconds). Default: @@ -65,6 +65,11 @@ combining the following values: 4 s3_beep = ======= +arch +==== + +The machine hardware name, the same output as ``uname -m`` +(e.g. ``x86_64`` or ``aarch64``). auto_msgmni =========== @@ -592,68 +597,59 @@ to the guest kernel command line (see Documentation/admin-guide/kernel-parameters.rst). -numa_balancing -============== - -Enables/disables automatic page fault based NUMA memory -balancing. Memory is moved automatically to nodes -that access it often. - -Enables/disables automatic NUMA memory balancing. On NUMA machines, there -is a performance penalty if remote memory is accessed by a CPU. When this -feature is enabled the kernel samples what task thread is accessing memory -by periodically unmapping pages and later trapping a page fault. At the -time of the page fault, it is determined if the data being accessed should -be migrated to a local memory node. +nmi_wd_lpm_factor (PPC only) +============================ -The unmapping of pages and trapping faults incur additional overhead that -ideally is offset by improved memory locality but there is no universal -guarantee. If the target workload is already bound to NUMA nodes then this -feature should be disabled. Otherwise, if the system overhead from the -feature is too high then the rate the kernel samples for NUMA hinting -faults may be controlled by the `numa_balancing_scan_period_min_ms, -numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, -numa_balancing_scan_size_mb`_, and numa_balancing_settle_count sysctls. +Factor to apply to the NMI watchdog timeout (only when ``nmi_watchdog`` is +set to 1). This factor represents the percentage added to +``watchdog_thresh`` when calculating the NMI watchdog timeout during an +LPM. The soft lockup timeout is not impacted. +A value of 0 means no change. The default value is 200 meaning the NMI +watchdog is set to 30s (based on ``watchdog_thresh`` equal to 10). -numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb -=============================================================================================================================== +numa_balancing +============== -Automatic NUMA balancing scans tasks address space and unmaps pages to -detect if pages are properly placed or if the data should be migrated to a -memory node local to where the task is running. Every "scan delay" the task -scans the next "scan size" number of pages in its address space. When the -end of the address space is reached the scanner restarts from the beginning. +Enables/disables and configures automatic page fault based NUMA memory +balancing. Memory is moved automatically to nodes that access it often. +The value to set can be the result of ORing the following: -In combination, the "scan delay" and "scan size" determine the scan rate. -When "scan delay" decreases, the scan rate increases. The scan delay and -hence the scan rate of every task is adaptive and depends on historical -behaviour. If pages are properly placed then the scan delay increases, -otherwise the scan delay decreases. The "scan size" is not adaptive but -the higher the "scan size", the higher the scan rate. += ================================= +0 NUMA_BALANCING_DISABLED +1 NUMA_BALANCING_NORMAL +2 NUMA_BALANCING_MEMORY_TIERING += ================================= -Higher scan rates incur higher system overhead as page faults must be -trapped and potentially data must be migrated. However, the higher the scan -rate, the more quickly a tasks memory is migrated to a local node if the -workload pattern changes and minimises performance impact due to remote -memory accesses. These sysctls control the thresholds for scan delays and -the number of pages scanned. +Or NUMA_BALANCING_NORMAL to optimize page placement among different +NUMA nodes to reduce remote accessing. On NUMA machines, there is a +performance penalty if remote memory is accessed by a CPU. When this +feature is enabled the kernel samples what task thread is accessing +memory by periodically unmapping pages and later trapping a page +fault. At the time of the page fault, it is determined if the data +being accessed should be migrated to a local memory node. -``numa_balancing_scan_period_min_ms`` is the minimum time in milliseconds to -scan a tasks virtual memory. It effectively controls the maximum scanning -rate for each task. +The unmapping of pages and trapping faults incur additional overhead that +ideally is offset by improved memory locality but there is no universal +guarantee. If the target workload is already bound to NUMA nodes then this +feature should be disabled. -``numa_balancing_scan_delay_ms`` is the starting "scan delay" used for a task -when it initially forks. +Or NUMA_BALANCING_MEMORY_TIERING to optimize page placement among +different types of memory (represented as different NUMA nodes) to +place the hot pages in the fast memory. This is implemented based on +unmapping and page fault too. -``numa_balancing_scan_period_max_ms`` is the maximum time in milliseconds to -scan a tasks virtual memory. It effectively controls the minimum scanning -rate for each task. +numa_balancing_promote_rate_limit_MBps +====================================== -``numa_balancing_scan_size_mb`` is how many megabytes worth of pages are -scanned for a given scan. +Too high promotion/demotion throughput between different memory types +may hurt application latency. This can be used to rate limit the +promotion throughput. The per-node max promotion throughput in MB/s +will be limited to be no more than the set value. +A rule of thumb is to set this to less than 1/10 of the PMEM node +write bandwidth. oops_all_cpu_backtrace ====================== @@ -795,6 +791,8 @@ bit 1 print system memory info bit 2 print timer info bit 3 print locks info if ``CONFIG_LOCKDEP`` is on bit 4 print ftrace buffer +bit 5 print all printk messages in buffer +bit 6 print all CPUs backtrace (if available in the arch) ===== ============================================ So for example to print tasks and memory info on panic, user can:: @@ -813,6 +811,13 @@ is useful to define the root cause of RCU stalls using a vmcore. 1 panic() after printing RCU stall messages. = ============================================================ +max_rcu_stall_to_panic +====================== + +When ``panic_on_rcu_stall`` is set to 1, this value determines the +number of times that RCU can stall before panic() is called. + +When ``panic_on_rcu_stall`` is set to 0, this value is has no effect. perf_cpu_time_max_percent ========================= @@ -905,6 +910,17 @@ enabled, otherwise writing to this file will return ``-EBUSY``. The default value is 8. +perf_user_access (arm64 only) +================================= + +Controls user space access for reading perf event counters. When set to 1, +user space can read performance monitor counter registers directly. + +The default value is 0 (access disabled). + +See Documentation/arm64/perf.rst for more information. + + pid_max ======= @@ -1013,28 +1029,22 @@ This is a directory, with the following entries: * ``boot_id``: a UUID generated the first time this is retrieved, and unvarying after that; +* ``uuid``: a UUID generated every time this is retrieved (this can + thus be used to generate UUIDs at will); + * ``entropy_avail``: the pool's entropy count, in bits; * ``poolsize``: the entropy pool size, in bits; * ``urandom_min_reseed_secs``: obsolete (used to determine the minimum - number of seconds between urandom pool reseeding). - -* ``uuid``: a UUID generated every time this is retrieved (this can - thus be used to generate UUIDs at will); + number of seconds between urandom pool reseeding). This file is + writable for compatibility purposes, but writing to it has no effect + on any RNG behavior; * ``write_wakeup_threshold``: when the entropy count drops below this (as a number of bits), processes waiting to write to ``/dev/random`` - are woken up. - -If ``drivers/char/random.c`` is built with ``ADD_INTERRUPT_BENCH`` -defined, these additional entries are present: - -* ``add_interrupt_avg_cycles``: the average number of cycles between - interrupts used to feed the pool; - -* ``add_interrupt_avg_deviation``: the standard deviation seen on the - number of cycles between interrupts used to feed the pool. + are woken up. This file is writable for compatibility purposes, but + writing to it has no effect on any RNG behavior. randomize_va_space diff --git a/Documentation/admin-guide/sysctl/net.rst b/Documentation/admin-guide/sysctl/net.rst index 4150f74c521a..6394f5dc2303 100644 --- a/Documentation/admin-guide/sysctl/net.rst +++ b/Documentation/admin-guide/sysctl/net.rst @@ -31,17 +31,18 @@ see only some of them, depending on your kernel's configuration. Table : Subdirectories in /proc/sys/net - ========= =================== = ========== ================== + ========= =================== = ========== =================== Directory Content Directory Content - ========= =================== = ========== ================== - core General parameter appletalk Appletalk protocol - unix Unix domain sockets netrom NET/ROM - 802 E802 protocol ax25 AX25 - ethernet Ethernet protocol rose X.25 PLP layer + ========= =================== = ========== =================== + 802 E802 protocol mptcp Multipath TCP + appletalk Appletalk protocol netfilter Network Filter + ax25 AX25 netrom NET/ROM + bridge Bridging rose X.25 PLP layer + core General parameter tipc TIPC + ethernet Ethernet protocol unix Unix domain sockets ipv4 IP version 4 x25 X.25 protocol - bridge Bridging decnet DEC net - ipv6 IP version 6 tipc TIPC - ========= =================== = ========== ================== + ipv6 IP version 6 + ========= =================== = ========== =================== 1. /proc/sys/net/core - Network core options ============================================ @@ -101,6 +102,9 @@ Values: - 1 - enable JIT hardening for unprivileged users only - 2 - enable JIT hardening for all users +where "privileged user" in this context means a process having +CAP_BPF or CAP_SYS_ADMIN in the root user name space. + bpf_jit_kallsyms ---------------- @@ -271,7 +275,7 @@ poll cycle or the number of packets processed reaches netdev_budget. netdev_max_backlog ------------------ -Maximum number of packets, queued on the INPUT side, when the interface +Maximum number of packets, queued on the INPUT side, when the interface receives packets faster than kernel can process them. netdev_rss_key @@ -322,6 +326,14 @@ a leaked reference faster. A larger value may be useful to prevent false warnings on slow/loaded systems. Default value is 10, minimum 1, maximum 3600. +skb_defer_max +------------- + +Max size (in skbs) of the per-cpu list of skbs being freed +by the cpu which allocated them. Used by TCP stack so far. + +Default: 64 + optmem_max ---------- @@ -365,6 +377,36 @@ new netns has been created. Default : 0 (for compatibility reasons) +txrehash +-------- + +Controls default hash rethink behaviour on listening socket when SO_TXREHASH +option is set to SOCK_TXREHASH_DEFAULT (i. e. not overridden by setsockopt). + +If set to 1 (default), hash rethink is performed on listening socket. +If set to 0, hash rethink is not performed. + +gro_normal_batch +---------------- + +Maximum number of the segments to batch up on output of GRO. When a packet +exits GRO, either as a coalesced superframe or as an original packet which +GRO has decided not to coalesce, it is placed on a per-NAPI list. This +list is then passed to the stack when the number of segments reaches the +gro_normal_batch limit. + +high_order_alloc_disable +------------------------ + +By default the allocator for page frags tries to use high order pages (order-3 +on x86). While the default behavior gives good results in most cases, some users +might have hit a contention in page allocations/freeing. This was especially +true on older kernels (< 5.14) when high-order pages were not stored on per-cpu +lists. This allows to opt-in for order-0 allocation instead but is now mostly of +historical importance. + +Default: 0 + 2. /proc/sys/net/unix - Parameters for Unix domain sockets ---------------------------------------------------------- diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst index 5e795202111f..988f6a4c8084 100644 --- a/Documentation/admin-guide/sysctl/vm.rst +++ b/Documentation/admin-guide/sysctl/vm.rst @@ -62,6 +62,7 @@ Currently, these files are in /proc/sys/vm: - overcommit_memory - overcommit_ratio - page-cluster +- page_lock_unfairness - panic_on_oom - percpu_pagelist_high_fraction - stat_interval @@ -561,6 +562,43 @@ Change the minimum size of the hugepage pool. See Documentation/admin-guide/mm/hugetlbpage.rst +hugetlb_optimize_vmemmap +======================== + +This knob is not available when the size of 'struct page' (a structure defined +in include/linux/mm_types.h) is not power of two (an unusual system config could +result in this). + +Enable (set to 1) or disable (set to 0) HugeTLB Vmemmap Optimization (HVO). + +Once enabled, the vmemmap pages of subsequent allocation of HugeTLB pages from +buddy allocator will be optimized (7 pages per 2MB HugeTLB page and 4095 pages +per 1GB HugeTLB page), whereas already allocated HugeTLB pages will not be +optimized. When those optimized HugeTLB pages are freed from the HugeTLB pool +to the buddy allocator, the vmemmap pages representing that range needs to be +remapped again and the vmemmap pages discarded earlier need to be rellocated +again. If your use case is that HugeTLB pages are allocated 'on the fly' (e.g. +never explicitly allocating HugeTLB pages with 'nr_hugepages' but only set +'nr_overcommit_hugepages', those overcommitted HugeTLB pages are allocated 'on +the fly') instead of being pulled from the HugeTLB pool, you should weigh the +benefits of memory savings against the more overhead (~2x slower than before) +of allocation or freeing HugeTLB pages between the HugeTLB pool and the buddy +allocator. Another behavior to note is that if the system is under heavy memory +pressure, it could prevent the user from freeing HugeTLB pages from the HugeTLB +pool to the buddy allocator since the allocation of vmemmap pages could be +failed, you have to retry later if your system encounter this situation. + +Once disabled, the vmemmap pages of subsequent allocation of HugeTLB pages from +buddy allocator will not be optimized meaning the extra overhead at allocation +time from buddy allocator disappears, whereas already optimized HugeTLB pages +will not be affected. If you want to make sure there are no optimized HugeTLB +pages, you can set "nr_hugepages" to 0 first and then disable this. Note that +writing 0 to nr_hugepages will make any "in use" HugeTLB pages become surplus +pages. So, those surplus pages are still optimized until they are no longer +in use. You would need to wait for those surplus pages to be released before +there are no optimized pages in the system. + + nr_hugepages_mempolicy ====================== @@ -720,7 +758,7 @@ and don't use much of it. The default value is 0. -See Documentation/vm/overcommit-accounting.rst and +See Documentation/mm/overcommit-accounting.rst and mm/util.c::__vm_enough_memory() for more information. @@ -754,6 +792,14 @@ extra faults and I/O delays for following faults if they would have been part of that consecutive pages readahead would have brought in. +page_lock_unfairness +==================== + +This value determines the number of times that the page lock can be +stolen from under a waiter. After the lock is stolen the number of times +specified in this file (default is 5), the "fair lock handoff" semantics +will apply, and the waiter will only be awakened if the lock can be taken. + panic_on_oom ============ @@ -880,6 +926,9 @@ calls without any restrictions. The default value is 0. +Another way to control permissions for userfaultfd is to use +/dev/userfaultfd instead of userfaultfd(2). See +Documentation/admin-guide/mm/userfaultfd.rst. user_reserve_kbytes =================== @@ -948,7 +997,7 @@ how much memory needs to be free before kswapd goes back to sleep. The unit is in fractions of 10,000. The default value of 10 means the distances between watermarks are 0.1% of the available memory in the -node/system. The maximum value is 1000, or 10% of memory. +node/system. The maximum value is 3000, or 30% of memory. A high rate of threads entering direct reclaim (allocstall) or kswapd going to sleep prematurely (kswapd_low_wmark_hit_quickly) can indicate |