| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1223373818-13687-3-git-send-email-righi.andrea@gmail.com>
Date: Tue, 7 Oct 2008 12:03:34 +0200
From: Andrea Righi <righi.andrea@...il.com>
To: Balbir Singh <balbir@...ux.vnet.ibm.com>,
Paul Menage <menage@...gle.com>
Cc: agk@...rceware.org, akpm@...ux-foundation.org, axboe@...nel.dk,
baramsori72@...il.com, Carl Henrik Lunde <chlunde@...g.uio.no>,
dave@...ux.vnet.ibm.com, Divyesh Shah <dpshah@...gle.com>,
eric.rannaud@...il.com, fernando@....ntt.co.jp,
Hirokazu Takahashi <taka@...inux.co.jp>,
Li Zefan <lizf@...fujitsu.com>,
Marco Innocenti <m.innocenti@...eca.it>, matt@...ehost.com,
ngupta@...gle.com, randy.dunlap@...cle.com, roberto@...it.it,
Ryo Tsuruta <ryov@...inux.co.jp>,
Satoshi UCHIDA <s-uchida@...jp.nec.com>,
subrata@...ux.vnet.ibm.com, yoshikawa.takuya@....ntt.co.jp,
containers@...ts.linux-foundation.org,
linux-kernel@...r.kernel.org, Andrea Righi <righi.andrea@...il.com>
Subject: [PATCH -mm 2/6] introduce ratelimiting attributes and functionality to res_counter
Introduce attributes and functions in res_counter to implement throttling-based
cgroup subsystems.
The following attributes have been added to struct res_counter:
* @policy: the limiting policy / algorithm
* @capacity: the maximum capacity of the resource
* @timestamp: timestamp of the last accounted resource request
Currently the available policies are: token-bucket and leaky-bucket and the
attribute @capacity is only used by token-bucket policy (to represent the
bucket size).
The following function has been implemented to return the amount of time a
cgroup should sleep to remain within the defined resource limits.
unsigned long long
res_counter_ratelimit_sleep(struct res_counter *res, ssize_t val);
[ Note: only the interfaces needed by the cgroup IO controller are implemented
right now ]
Signed-off-by: Andrea Righi <righi.andrea@...il.com>
---
include/linux/res_counter.h | 69 ++++++++++++++++++++++++++++++----------
kernel/res_counter.c | 73 ++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 124 insertions(+), 18 deletions(-)
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 0ab55c4..80b9ab8 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -14,30 +14,36 @@
*/
#include <linux/cgroup.h>
+#include <linux/jiffies.h>
-/*
- * The core object. the cgroup that wishes to account for some
- * resource may include this counter into its structures and use
- * the helpers described beyond
- */
+/* The various policies that can be used for ratelimiting resources */
+#define RATELIMIT_LEAKY_BUCKET 0
+#define RATELIMIT_TOKEN_BUCKET 1
+/**
+ * struct res_counter - the core object to account cgroup resources
+ *
+ * @usage: the current resource consumption level
+ * @max_usage: the maximal value of the usage from the counter creation
+ * @limit: the limit that usage cannot be exceeded
+ * @failcnt: the number of unsuccessful attempts to consume the resource
+ * @policy: the limiting policy / algorithm
+ * @capacity: the maximum capacity of the resource
+ * @timestamp: timestamp of the last accounted resource request
+ * @lock: the lock to protect all of the above.
+ * The routines below consider this to be IRQ-safe
+ *
+ * The cgroup that wishes to account for some resource may include this counter
+ * into its structures and use the helpers described beyond.
+ */
struct res_counter {
- /*
- * the current resource consumption level
- */
unsigned long long usage;
- /*
- * the maximal value of the usage from the counter creation
- */
unsigned long long max_usage;
- /*
- * the limit that usage cannot exceed
- */
unsigned long long limit;
- /*
- * the number of unsuccessful attempts to consume the resource
- */
unsigned long long failcnt;
+ unsigned long long policy;
+ unsigned long long capacity;
+ unsigned long long timestamp;
/*
* the lock to protect all of the above.
* the routines below consider this to be IRQ-safe
@@ -80,6 +86,9 @@ enum {
RES_USAGE,
RES_MAX_USAGE,
RES_LIMIT,
+ RES_POLICY,
+ RES_TIMESTAMP,
+ RES_CAPACITY,
RES_FAILCNT,
};
@@ -126,6 +135,15 @@ static inline bool res_counter_limit_check_locked(struct res_counter *cnt)
return false;
}
+static inline unsigned long long
+res_counter_ratelimit_delta_t(struct res_counter *res)
+{
+ return (long long)get_jiffies_64() - (long long)res->timestamp;
+}
+
+unsigned long long
+res_counter_ratelimit_sleep(struct res_counter *res, ssize_t val);
+
/*
* Helper function to detect if the cgroup is within it's limit or
* not. It's currently called from cgroup_rss_prepare()
@@ -159,6 +177,23 @@ static inline void res_counter_reset_failcnt(struct res_counter *cnt)
spin_unlock_irqrestore(&cnt->lock, flags);
}
+static inline int
+res_counter_ratelimit_set_limit(struct res_counter *cnt,
+ unsigned long long policy,
+ unsigned long long limit, unsigned long long max)
+{
+ unsigned long flags;
+
+ spin_lock_irqsave(&cnt->lock, flags);
+ cnt->limit = limit;
+ cnt->capacity = max;
+ cnt->policy = policy;
+ cnt->timestamp = get_jiffies_64();
+ cnt->usage = 0;
+ spin_unlock_irqrestore(&cnt->lock, flags);
+ return 0;
+}
+
static inline int res_counter_set_limit(struct res_counter *cnt,
unsigned long long limit)
{
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index f275c8e..e55c674 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -9,6 +9,7 @@
#include <linux/types.h>
#include <linux/parser.h>
+#include <linux/jiffies.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/res_counter.h>
@@ -19,6 +20,8 @@ void res_counter_init(struct res_counter *counter)
{
spin_lock_init(&counter->lock);
counter->limit = (unsigned long long)LLONG_MAX;
+ counter->capacity = (unsigned long long)LLONG_MAX;
+ counter->timestamp = get_jiffies_64();
}
int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
@@ -62,7 +65,6 @@ void res_counter_uncharge(struct res_counter *counter, unsigned long val)
spin_unlock_irqrestore(&counter->lock, flags);
}
-
static inline unsigned long long *
res_counter_member(struct res_counter *counter, int member)
{
@@ -73,6 +75,12 @@ res_counter_member(struct res_counter *counter, int member)
return &counter->max_usage;
case RES_LIMIT:
return &counter->limit;
+ case RES_POLICY:
+ return &counter->policy;
+ case RES_TIMESTAMP:
+ return &counter->timestamp;
+ case RES_CAPACITY:
+ return &counter->capacity;
case RES_FAILCNT:
return &counter->failcnt;
};
@@ -137,3 +145,66 @@ int res_counter_write(struct res_counter *counter, int member,
spin_unlock_irqrestore(&counter->lock, flags);
return 0;
}
+
+static unsigned long long
+ratelimit_leaky_bucket(struct res_counter *res, ssize_t val)
+{
+ unsigned long long delta, t;
+
+ res->usage += val;
+ delta = res_counter_ratelimit_delta_t(res);
+ if (!delta)
+ return 0;
+ t = res->usage * USEC_PER_SEC;
+ t = usecs_to_jiffies(div_u64(t, res->limit));
+ if (t > delta)
+ return t - delta;
+ /* Reset i/o statistics */
+ res->usage = 0;
+ res->timestamp = get_jiffies_64();
+ return 0;
+}
+
+static unsigned long long
+ratelimit_token_bucket(struct res_counter *res, ssize_t val)
+{
+ unsigned long long delta;
+ long long tok;
+
+ res->usage -= val;
+ delta = jiffies_to_msecs(res_counter_ratelimit_delta_t(res));
+ res->timestamp = get_jiffies_64();
+ tok = (long long)res->usage * MSEC_PER_SEC;
+ if (delta) {
+ long long max = (long long)res->capacity * MSEC_PER_SEC;
+
+ tok += delta * res->limit;
+ if (tok > max)
+ tok = max;
+ res->usage = (unsigned long long)div_s64(tok, MSEC_PER_SEC);
+ }
+ return (tok < 0) ? msecs_to_jiffies(div_u64(-tok, res->limit)) : 0;
+}
+
+unsigned long long
+res_counter_ratelimit_sleep(struct res_counter *res, ssize_t val)
+{
+ unsigned long long sleep = 0;
+ unsigned long flags;
+
+ spin_lock_irqsave(&res->lock, flags);
+ if (res->limit)
+ switch (res->policy) {
+ case RATELIMIT_LEAKY_BUCKET:
+ sleep = ratelimit_leaky_bucket(res, val);
+ break;
+ case RATELIMIT_TOKEN_BUCKET:
+ sleep = ratelimit_token_bucket(res, val);
+ break;
+ default:
+ WARN_ON(1);
+ break;
+ }
+ spin_unlock_irqrestore(&res->lock, flags);
+ return sleep;
+}
--
1.5.4.3
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists