From 07fe7cb7c7c179f473fd9c823348fd3eb5dad369 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: Create a dynamically sized pool of threads for doing very slow work items Create a dynamically sized pool of threads for doing very slow work items, such as invoking mkdir() or rmdir() - things that may take a long time and may sleep, holding mutexes/semaphores and hogging a thread, and are thus unsuitable for workqueues. The number of threads is always at least a settable minimum, but more are started when there's more work to do, up to a limit. Because of the nature of the load, it's not suitable for a 1-thread-per-CPU type pool. A system with one CPU may well want several threads. This is used by FS-Cache to do slow caching operations in the background, such as looking up, creating or deleting cache objects. Signed-off-by: David Howells Acked-by: Serge Hallyn Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/slow-work.h | 88 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 88 insertions(+) create mode 100644 include/linux/slow-work.h (limited to 'include/linux/slow-work.h') diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h new file mode 100644 index 000000000000..4dd754af393e --- /dev/null +++ b/include/linux/slow-work.h @@ -0,0 +1,88 @@ +/* Worker thread pool for slow items, such as filesystem lookups or mkdirs + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#ifndef _LINUX_SLOW_WORK_H +#define _LINUX_SLOW_WORK_H + +#ifdef CONFIG_SLOW_WORK + +struct slow_work; + +/* + * The operations used to support slow work items + */ +struct slow_work_ops { + /* get a ref on a work item + * - return 0 if successful, -ve if not + */ + int (*get_ref)(struct slow_work *work); + + /* discard a ref to a work item */ + void (*put_ref)(struct slow_work *work); + + /* execute a work item */ + void (*execute)(struct slow_work *work); +}; + +/* + * A slow work item + * - A reference is held on the parent object by the thread pool when it is + * queued + */ +struct slow_work { + unsigned long flags; +#define SLOW_WORK_PENDING 0 /* item pending (further) execution */ +#define SLOW_WORK_EXECUTING 1 /* item currently executing */ +#define SLOW_WORK_ENQ_DEFERRED 2 /* item enqueue deferred */ +#define SLOW_WORK_VERY_SLOW 3 /* item is very slow */ + const struct slow_work_ops *ops; /* operations table for this item */ + struct list_head link; /* link in queue */ +}; + +/** + * slow_work_init - Initialise a slow work item + * @work: The work item to initialise + * @ops: The operations to use to handle the slow work item + * + * Initialise a slow work item. + */ +static inline void slow_work_init(struct slow_work *work, + const struct slow_work_ops *ops) +{ + work->flags = 0; + work->ops = ops; + INIT_LIST_HEAD(&work->link); +} + +/** + * slow_work_init - Initialise a very slow work item + * @work: The work item to initialise + * @ops: The operations to use to handle the slow work item + * + * Initialise a very slow work item. This item will be restricted such that + * only a certain number of the pool threads will be able to execute items of + * this type. + */ +static inline void vslow_work_init(struct slow_work *work, + const struct slow_work_ops *ops) +{ + work->flags = 1 << SLOW_WORK_VERY_SLOW; + work->ops = ops; + INIT_LIST_HEAD(&work->link); +} + +extern int slow_work_enqueue(struct slow_work *work); +extern int slow_work_register_user(void); +extern void slow_work_unregister_user(void); + + +#endif /* CONFIG_SLOW_WORK */ +#endif /* _LINUX_SLOW_WORK_H */ -- cgit v1.3-8-gc7d7 From 12e22c5e4bc08ab4b05ac079fe40d9891c5e81a0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: Make the slow work pool configurable Make the slow work pool configurable through /proc/sys/kernel/slow-work. (*) /proc/sys/kernel/slow-work/min-threads The minimum number of threads that should be in the pool as long as it is in use. This may be anywhere between 2 and max-threads. (*) /proc/sys/kernel/slow-work/max-threads The maximum number of threads that should in the pool. This may be anywhere between min-threads and 255 or NR_CPUS * 2, whichever is greater. (*) /proc/sys/kernel/slow-work/vslow-percentage The percentage of active threads in the pool that may be used to execute very slow work items. This may be between 1 and 99. The resultant number is bounded to between 1 and one fewer than the number of active threads. This ensures there is always at least one thread that can process very slow work items, and always at least one thread that won't. Signed-off-by: David Howells Acked-by: Serge Hallyn Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- include/linux/slow-work.h | 5 ++ kernel/slow-work.c | 118 +++++++++++++++++++++++++++++++++++++++++++++- kernel/sysctl.c | 9 ++++ 3 files changed, 130 insertions(+), 2 deletions(-) (limited to 'include/linux/slow-work.h') diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h index 4dd754af393e..8262809dfa8b 100644 --- a/include/linux/slow-work.h +++ b/include/linux/slow-work.h @@ -14,6 +14,8 @@ #ifdef CONFIG_SLOW_WORK +#include + struct slow_work; /* @@ -83,6 +85,9 @@ extern int slow_work_enqueue(struct slow_work *work); extern int slow_work_register_user(void); extern void slow_work_unregister_user(void); +#ifdef CONFIG_SYSCTL +extern ctl_table slow_work_sysctls[]; +#endif #endif /* CONFIG_SLOW_WORK */ #endif /* _LINUX_SLOW_WORK_H */ diff --git a/kernel/slow-work.c b/kernel/slow-work.c index 454abb21c8bd..3f65900aa3cb 100644 --- a/kernel/slow-work.c +++ b/kernel/slow-work.c @@ -14,7 +14,6 @@ #include #include #include -#include #define SLOW_WORK_CULL_TIMEOUT (5 * HZ) /* cull threads 5s after running out of * things to do */ @@ -24,6 +23,14 @@ static void slow_work_cull_timeout(unsigned long); static void slow_work_oom_timeout(unsigned long); +#ifdef CONFIG_SYSCTL +static int slow_work_min_threads_sysctl(struct ctl_table *, int, struct file *, + void __user *, size_t *, loff_t *); + +static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *, + void __user *, size_t *, loff_t *); +#endif + /* * The pool of threads has at least min threads in it as long as someone is * using the facility, and may have as many as max. @@ -34,6 +41,51 @@ static unsigned slow_work_min_threads = 2; static unsigned slow_work_max_threads = 4; static unsigned vslow_work_proportion = 50; /* % of threads that may process * very slow work */ + +#ifdef CONFIG_SYSCTL +static const int slow_work_min_min_threads = 2; +static int slow_work_max_max_threads = 255; +static const int slow_work_min_vslow = 1; +static const int slow_work_max_vslow = 99; + +ctl_table slow_work_sysctls[] = { + { + .ctl_name = CTL_UNNUMBERED, + .procname = "min-threads", + .data = &slow_work_min_threads, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = slow_work_min_threads_sysctl, + .extra1 = (void *) &slow_work_min_min_threads, + .extra2 = &slow_work_max_threads, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "max-threads", + .data = &slow_work_max_threads, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = slow_work_max_threads_sysctl, + .extra1 = &slow_work_min_threads, + .extra2 = (void *) &slow_work_max_max_threads, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "vslow-percentage", + .data = &vslow_work_proportion, + .maxlen = sizeof(unsigned), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .extra1 = (void *) &slow_work_min_vslow, + .extra2 = (void *) &slow_work_max_vslow, + }, + { .ctl_name = 0 } +}; +#endif + +/* + * The active state of the thread pool + */ static atomic_t slow_work_thread_count; static atomic_t vslow_work_executing_count; @@ -427,6 +479,64 @@ static void slow_work_oom_timeout(unsigned long data) slow_work_may_not_start_new_thread = false; } +#ifdef CONFIG_SYSCTL +/* + * Handle adjustment of the minimum number of threads + */ +static int slow_work_min_threads_sysctl(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int n; + + if (ret == 0) { + mutex_lock(&slow_work_user_lock); + if (slow_work_user_count > 0) { + /* see if we need to start or stop threads */ + n = atomic_read(&slow_work_thread_count) - + slow_work_min_threads; + + if (n < 0 && !slow_work_may_not_start_new_thread) + slow_work_enqueue(&slow_work_new_thread); + else if (n > 0) + mod_timer(&slow_work_cull_timer, + jiffies + SLOW_WORK_CULL_TIMEOUT); + } + mutex_unlock(&slow_work_user_lock); + } + + return ret; +} + +/* + * Handle adjustment of the maximum number of threads + */ +static int slow_work_max_threads_sysctl(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, + size_t *lenp, loff_t *ppos) +{ + int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos); + int n; + + if (ret == 0) { + mutex_lock(&slow_work_user_lock); + if (slow_work_user_count > 0) { + /* see if we need to stop threads */ + n = slow_work_max_threads - + atomic_read(&slow_work_thread_count); + + if (n < 0) + mod_timer(&slow_work_cull_timer, + jiffies + SLOW_WORK_CULL_TIMEOUT); + } + mutex_unlock(&slow_work_user_lock); + } + + return ret; +} +#endif /* CONFIG_SYSCTL */ + /** * slow_work_register_user - Register a user of the facility * @@ -516,8 +626,12 @@ static int __init init_slow_work(void) { unsigned nr_cpus = num_possible_cpus(); - if (nr_cpus > slow_work_max_threads) + if (slow_work_max_threads < nr_cpus) slow_work_max_threads = nr_cpus; +#ifdef CONFIG_SYSCTL + if (slow_work_max_max_threads < nr_cpus * 2) + slow_work_max_max_threads = nr_cpus * 2; +#endif return 0; } diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 5ec4543dfc06..82350f8f04f6 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -48,6 +48,7 @@ #include #include #include +#include #include #include @@ -897,6 +898,14 @@ static struct ctl_table kern_table[] = { .proc_handler = &scan_unevictable_handler, }, #endif +#ifdef CONFIG_SLOW_WORK + { + .ctl_name = CTL_UNNUMBERED, + .procname = "slow-work", + .mode = 0555, + .child = slow_work_sysctls, + }, +#endif /* * NOTE: do not add new entries to this table unless you have read * Documentation/sysctl/ctl_unnumbered.txt -- cgit v1.3-8-gc7d7 From 8f0aa2f25b31ba27db84259141e52ee6ec0d2820 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 3 Apr 2009 16:42:35 +0100 Subject: Document the slow work thread pool Document the slow work thread pool. Signed-off-by: David Howells Acked-by: Steve Dickson Acked-by: Trond Myklebust Acked-by: Al Viro Tested-by: Daire Byrne --- Documentation/slow-work.txt | 174 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/slow-work.h | 2 + kernel/slow-work.c | 2 + 3 files changed, 178 insertions(+) create mode 100644 Documentation/slow-work.txt (limited to 'include/linux/slow-work.h') diff --git a/Documentation/slow-work.txt b/Documentation/slow-work.txt new file mode 100644 index 000000000000..ebc50f808ea4 --- /dev/null +++ b/Documentation/slow-work.txt @@ -0,0 +1,174 @@ + ==================================== + SLOW WORK ITEM EXECUTION THREAD POOL + ==================================== + +By: David Howells + +The slow work item execution thread pool is a pool of threads for performing +things that take a relatively long time, such as making mkdir calls. +Typically, when processing something, these items will spend a lot of time +blocking a thread on I/O, thus making that thread unavailable for doing other +work. + +The standard workqueue model is unsuitable for this class of work item as that +limits the owner to a single thread or a single thread per CPU. For some +tasks, however, more threads - or fewer - are required. + +There is just one pool per system. It contains no threads unless something +wants to use it - and that something must register its interest first. When +the pool is active, the number of threads it contains is dynamic, varying +between a maximum and minimum setting, depending on the load. + + +==================== +CLASSES OF WORK ITEM +==================== + +This pool support two classes of work items: + + (*) Slow work items. + + (*) Very slow work items. + +The former are expected to finish much quicker than the latter. + +An operation of the very slow class may do a batch combination of several +lookups, mkdirs, and a create for instance. + +An operation of the ordinarily slow class may, for example, write stuff or +expand files, provided the time taken to do so isn't too long. + +Operations of both types may sleep during execution, thus tying up the thread +loaned to it. + + +THREAD-TO-CLASS ALLOCATION +-------------------------- + +Not all the threads in the pool are available to work on very slow work items. +The number will be between one and one fewer than the number of active threads. +This is configurable (see the "Pool Configuration" section). + +All the threads are available to work on ordinarily slow work items, but a +percentage of the threads will prefer to work on very slow work items. + +The configuration ensures that at least one thread will be available to work on +very slow work items, and at least one thread will be available that won't work +on very slow work items at all. + + +===================== +USING SLOW WORK ITEMS +===================== + +Firstly, a module or subsystem wanting to make use of slow work items must +register its interest: + + int ret = slow_work_register_user(); + +This will return 0 if successful, or a -ve error upon failure. + + +Slow work items may then be set up by: + + (1) Declaring a slow_work struct type variable: + + #include + + struct slow_work myitem; + + (2) Declaring the operations to be used for this item: + + struct slow_work_ops myitem_ops = { + .get_ref = myitem_get_ref, + .put_ref = myitem_put_ref, + .execute = myitem_execute, + }; + + [*] For a description of the ops, see section "Item Operations". + + (3) Initialising the item: + + slow_work_init(&myitem, &myitem_ops); + + or: + + vslow_work_init(&myitem, &myitem_ops); + + depending on its class. + +A suitably set up work item can then be enqueued for processing: + + int ret = slow_work_enqueue(&myitem); + +This will return a -ve error if the thread pool is unable to gain a reference +on the item, 0 otherwise. + + +The items are reference counted, so there ought to be no need for a flush +operation. When all a module's slow work items have been processed, and the +module has no further interest in the facility, it should unregister its +interest: + + slow_work_unregister_user(); + + +=============== +ITEM OPERATIONS +=============== + +Each work item requires a table of operations of type struct slow_work_ops. +All members are required: + + (*) Get a reference on an item: + + int (*get_ref)(struct slow_work *work); + + This allows the thread pool to attempt to pin an item by getting a + reference on it. This function should return 0 if the reference was + granted, or a -ve error otherwise. If an error is returned, + slow_work_enqueue() will fail. + + The reference is held whilst the item is queued and whilst it is being + executed. The item may then be requeued with the same reference held, or + the reference will be released. + + (*) Release a reference on an item: + + void (*put_ref)(struct slow_work *work); + + This allows the thread pool to unpin an item by releasing the reference on + it. The thread pool will not touch the item again once this has been + called. + + (*) Execute an item: + + void (*execute)(struct slow_work *work); + + This should perform the work required of the item. It may sleep, it may + perform disk I/O and it may wait for locks. + + +================== +POOL CONFIGURATION +================== + +The slow-work thread pool has a number of configurables: + + (*) /proc/sys/kernel/slow-work/min-threads + + The minimum number of threads that should be in the pool whilst it is in + use. This may be anywhere between 2 and max-threads. + + (*) /proc/sys/kernel/slow-work/max-threads + + The maximum number of threads that should in the pool. This may be + anywhere between min-threads and 255 or NR_CPUS * 2, whichever is greater. + + (*) /proc/sys/kernel/slow-work/vslow-percentage + + The percentage of active threads in the pool that may be used to execute + very slow work items. This may be between 1 and 99. The resultant number + is bounded to between 1 and one fewer than the number of active threads. + This ensures there is always at least one thread that can process very + slow work items, and always at least one thread that won't. diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h index 8262809dfa8b..85958277f83d 100644 --- a/include/linux/slow-work.h +++ b/include/linux/slow-work.h @@ -7,6 +7,8 @@ * modify it under the terms of the GNU General Public Licence * as published by the Free Software Foundation; either version * 2 of the Licence, or (at your option) any later version. + * + * See Documentation/slow-work.txt */ #ifndef _LINUX_SLOW_WORK_H diff --git a/kernel/slow-work.c b/kernel/slow-work.c index 3f65900aa3cb..cf2bc01186ef 100644 --- a/kernel/slow-work.c +++ b/kernel/slow-work.c @@ -7,6 +7,8 @@ * modify it under the terms of the GNU General Public Licence * as published by the Free Software Foundation; either version * 2 of the Licence, or (at your option) any later version. + * + * See Documentation/slow-work.txt */ #include -- cgit v1.3-8-gc7d7