From 4f9b16a64753d0bb607454347036dc997fd03b82 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 4 Jun 2014 16:07:14 -0700 Subject: mm: disable zone_reclaim_mode by default When it was introduced, zone_reclaim_mode made sense as NUMA distances punished and workloads were generally partitioned to fit into a NUMA node. NUMA machines are now common but few of the workloads are NUMA-aware and it's routine to see major performance degradation due to zone_reclaim_mode being enabled but relatively few can identify the problem. Those that require zone_reclaim_mode are likely to be able to detect when it needs to be enabled and tune appropriately so lets have a sensible default for the bulk of users. This patch (of 2): zone_reclaim_mode causes processes to prefer reclaiming memory from local node instead of spilling over to other nodes. This made sense initially when NUMA machines were almost exclusively HPC and the workload was partitioned into nodes. The NUMA penalties were sufficiently high to justify reclaiming the memory. On current machines and workloads it is often the case that zone_reclaim_mode destroys performance but not all users know how to detect this. Favour the common case and disable it by default. Users that are sophisticated enough to know they need zone_reclaim_mode will detect it. Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Reviewed-by: Zhang Yanfei Acked-by: Michal Hocko Reviewed-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) (limited to 'Documentation/sysctl') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index dd9d0e33b443..5b6da0fb5fbf 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -772,16 +772,17 @@ This is value ORed together of 2 = Zone reclaim writes dirty pages out 4 = Zone reclaim swaps pages -zone_reclaim_mode is set during bootup to 1 if it is determined that pages -from remote zones will cause a measurable performance reduction. The -page allocator will then reclaim easily reusable pages (those page -cache pages that are currently not used) before allocating off node pages. - -It may be beneficial to switch off zone reclaim if the system is -used for a file server and all of memory should be used for caching files -from disk. In that case the caching effect is more important than +zone_reclaim_mode is disabled by default. For file servers or workloads +that benefit from having their data cached, zone_reclaim_mode should be +left disabled as the caching effect is likely to be more important than data locality. +zone_reclaim may be enabled if it's known that the workload is partitioned +such that each partition fits within a NUMA node and that accessing remote +memory would cause a measurable performance reduction. The page allocator +will then reclaim easily reusable pages (those page cache pages that are +currently not used) before allocating off node pages. + Allowing zone reclaim to write out pages stops processes that are writing large amounts of data from dirtying pages on other nodes. Zone reclaim will write out dirty pages if a zone fills up and so effectively -- cgit v1.2.3 From 4a0da71b96b9d4080c0820e9e7d02470ebe62dc6 Mon Sep 17 00:00:00 2001 From: Denys Vlasenko Date: Wed, 4 Jun 2014 16:11:03 -0700 Subject: Documentation/sysctl/vm.txt: clarify vfs_cache_pressure description Existing description is worded in a way which almost encourages setting of vfs_cache_pressure above 100, possibly way above it. Users are left in a dark what this numeric value is - an int? a percentage? what the scale is? As a result, we are getting reports about noticeable performance degradation from users who have set vfs_cache_pressure to ridiculously high values - because they thought there is no downside to it. Via code inspection it's obvious that this value is treated as a percentage. This patch changes text to reflect this fact, and adds a cautionary paragraph advising against setting vfs_cache_pressure sky high. Signed-off-by: Denys Vlasenko Cc: Alexander Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'Documentation/sysctl') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index 5b6da0fb5fbf..bd4b34c03738 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -746,8 +746,8 @@ Changing this takes effect whenever an application requests memory. vfs_cache_pressure ------------------ -Controls the tendency of the kernel to reclaim the memory which is used for -caching of directory and inode objects. +This percentage value controls the tendency of the kernel to reclaim +the memory which is used for caching of directory and inode objects. At the default value of vfs_cache_pressure=100 the kernel will attempt to reclaim dentries and inodes at a "fair" rate with respect to pagecache and @@ -757,6 +757,11 @@ never reclaim dentries and inodes due to memory pressure and this can easily lead to out-of-memory conditions. Increasing vfs_cache_pressure beyond 100 causes the kernel to prefer to reclaim dentries and inodes. +Increasing vfs_cache_pressure significantly beyond 100 may have negative +performance impact. Reclaim code needs to take various locks to find freeable +directory and inode objects. With vfs_cache_pressure=1000, it will look for +ten times more freeable objects than there are. + ============================================================== zone_reclaim_mode: -- cgit v1.2.3 From f4aacea2f5d1a5f7e3154e967d70cf3f711bcd61 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Fri, 6 Jun 2014 14:37:19 -0700 Subject: sysctl: allow for strict write position handling When writing to a sysctl string, each write, regardless of VFS position, begins writing the string from the start. This means the contents of the last write to the sysctl controls the string contents instead of the first: open("/proc/sys/kernel/modprobe", O_WRONLY) = 1 write(1, "AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"..., 4096) = 4096 write(1, "/bin/true", 9) = 9 close(1) = 0 $ cat /proc/sys/kernel/modprobe /bin/true Expected behaviour would be to have the sysctl be "AAAA..." capped at maxlen (in this case KMOD_PATH_LEN: 256), instead of truncating to the contents of the second write. Similarly, multiple short writes would not append to the sysctl. The old behavior is unlike regular POSIX files enough that doing audits of software that interact with sysctls can end up in unexpected or dangerous situations. For example, "as long as the input starts with a trusted path" turns out to be an insufficient filter, as what must also happen is for the input to be entirely contained in a single write syscall -- not a common consideration, especially for high level tools. This provides kernel.sysctl_writes_strict as a way to make this behavior act in a less surprising manner for strings, and disallows non-zero file position when writing numeric sysctls (similar to what is already done when reading from non-zero file positions). For now, the default (0) is to warn about non-zero file position use, but retain the legacy behavior. Setting this to -1 disables the warning, and setting this to 1 enables the file position respecting behavior. [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: move misplaced hunk, per Randy] Signed-off-by: Kees Cook Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/kernel.txt | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) (limited to 'Documentation/sysctl') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 9886c3d57fc2..708bb7f1b7e0 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -77,6 +77,7 @@ show up in /proc/sys/kernel: - shmmni - stop-a [ SPARC only ] - sysrq ==> Documentation/sysrq.txt +- sysctl_writes_strict - tainted - threads-max - unknown_nmi_panic @@ -762,6 +763,26 @@ without users and with a dead originative process will be destroyed. ============================================================== +sysctl_writes_strict: + +Control how file position affects the behavior of updating sysctl values +via the /proc/sys interface: + + -1 - Legacy per-write sysctl value handling, with no printk warnings. + Each write syscall must fully contain the sysctl value to be + written, and multiple writes on the same sysctl file descriptor + will rewrite the sysctl value, regardless of file position. + 0 - (default) Same behavior as above, but warn about processes that + perform writes to a sysctl file descriptor when the file position + is not 0. + 1 - Respect file position when writing sysctl strings. Multiple writes + will append to the sysctl value buffer. Anything past the max length + of the sysctl value buffer will be ignored. Writes to numeric sysctl + entries must always be at file position 0 and the value must be + fully contained in the buffer sent in the write syscall. + +============================================================== + tainted: Non-zero if the kernel has been tainted. Numeric values, which -- cgit v1.2.3 From 7cd2b0a34ab8e4db971920eef8982f985441adfb Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Mon, 23 Jun 2014 13:22:04 -0700 Subject: mm, pcp: allow restoring percpu_pagelist_fraction default Oleg reports a division by zero error on zero-length write() to the percpu_pagelist_fraction sysctl: divide error: 0000 [#1] SMP DEBUG_PAGEALLOC CPU: 1 PID: 9142 Comm: badarea_io Not tainted 3.15.0-rc2-vm-nfs+ #19 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 task: ffff8800d5aeb6e0 ti: ffff8800d87a2000 task.ti: ffff8800d87a2000 RIP: 0010: percpu_pagelist_fraction_sysctl_handler+0x84/0x120 RSP: 0018:ffff8800d87a3e78 EFLAGS: 00010246 RAX: 0000000000000f89 RBX: ffff88011f7fd000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000001 RDI: 0000000000000010 RBP: ffff8800d87a3e98 R08: ffffffff81d002c8 R09: ffff8800d87a3f50 R10: 000000000000000b R11: 0000000000000246 R12: 0000000000000060 R13: ffffffff81c3c3e0 R14: ffffffff81cfddf8 R15: ffff8801193b0800 FS: 00007f614f1e9740(0000) GS:ffff88011f440000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007f614f1fa000 CR3: 00000000d9291000 CR4: 00000000000006e0 Call Trace: proc_sys_call_handler+0xb3/0xc0 proc_sys_write+0x14/0x20 vfs_write+0xba/0x1e0 SyS_write+0x46/0xb0 tracesys+0xe1/0xe6 However, if the percpu_pagelist_fraction sysctl is set by the user, it is also impossible to restore it to the kernel default since the user cannot write 0 to the sysctl. This patch allows the user to write 0 to restore the default behavior. It still requires a fraction equal to or larger than 8, however, as stated by the documentation for sanity. If a value in the range [1, 7] is written, the sysctl will return EINVAL. This successfully solves the divide by zero issue at the same time. Signed-off-by: David Rientjes Reported-by: Oleg Drokin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'Documentation/sysctl') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index bd4b34c03738..4415aa915681 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -702,7 +702,8 @@ The batch value of each per cpu pagelist is also updated as a result. It is set to pcp->high/4. The upper limit of batch is (PAGE_SHIFT * 8) The initial value is zero. Kernel does not use this value at boot time to set -the high water marks for each per cpu page list. +the high water marks for each per cpu page list. If the user writes '0' to this +sysctl, it will revert to this default behavior. ============================================================== -- cgit v1.2.3 From ed235875e2ca983197831337a986f0517074e1a0 Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Mon, 23 Jun 2014 13:22:05 -0700 Subject: kernel/watchdog.c: print traces for all cpus on lockup detection A 'softlockup' is defined as a bug that causes the kernel to loop in kernel mode for more than a predefined period to time, without giving other tasks a chance to run. Currently, upon detection of this condition by the per-cpu watchdog task, debug information (including a stack trace) is sent to the system log. On some occasions, we have observed that the "victim" rather than the actual "culprit" (i.e. the owner/holder of the contended resource) is reported to the user. Often this information has proven to be insufficient to assist debugging efforts. To avoid loss of useful debug information, for architectures which support NMI, this patch makes it possible to improve soft lockup reporting. This is accomplished by issuing an NMI to each cpu to obtain a stack trace. If NMI is not supported we just revert back to the old method. A sysctl and boot-time parameter is available to toggle this feature. [dzickus@redhat.com: add CONFIG_SMP in certain areas] [akpm@linux-foundation.org: additional CONFIG_SMP=n optimisations] [mq@suse.cz: fix warning] Signed-off-by: Aaron Tomlin Signed-off-by: Don Zickus Cc: David S. Miller Cc: Mateusz Guzik Cc: Oleg Nesterov Signed-off-by: Jan Moskyto Matejka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/kernel.txt | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'Documentation/sysctl') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 708bb7f1b7e0..c14374e71775 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -75,6 +75,7 @@ show up in /proc/sys/kernel: - shmall - shmmax [ sysv ipc ] - shmmni +- softlockup_all_cpu_backtrace - stop-a [ SPARC only ] - sysrq ==> Documentation/sysrq.txt - sysctl_writes_strict @@ -783,6 +784,22 @@ via the /proc/sys interface: ============================================================== +softlockup_all_cpu_backtrace: + +This value controls the soft lockup detector thread's behavior +when a soft lockup condition is detected as to whether or not +to gather further debug information. If enabled, each cpu will +be issued an NMI and instructed to capture stack trace. + +This feature is only applicable for architectures which support +NMI. + +0: do nothing. This is the default behavior. + +1: on detection capture more debug information. + +============================================================== + tainted: Non-zero if the kernel has been tainted. Numeric values, which -- cgit v1.2.3