[PATCH, take2] getrusage() : Fill ru_inblock and ru_oublock fields if possible

From: Eric Dumazet
Date: Mon Mar 19 2007 - 06:40:04 EST


Hi Andrew

Here is the new version of this patch. Could you please update mm with it ?

As noticed by Oleg, first version was wrong, reporting three times SELF
values, and no support for RUSAGE_CHILDREN.

RUSAGE_CHILDREN support imply we add cinblock and  coublock in signal_struct,
to be able to accumulate inblock/oublock of  terminated and waited-for
children.

Thank you

[PATCH, take2] getrusage() : Fill ru_inblock and ru_oublock fields if possible

If CONFIG_TASK_IO_ACCOUNTING is defined, we update io accounting counters for
each task.

This patch permits reporting of these values using the well known getrusage()
syscall, filling ru_inblock and ru_oublock instead of null values.

For RUSAGE_CHILDREN support, we must add two new fields in struct
signal_struct, named cinblock and coublock, where we sum the inblock/oublock
values of terminated and waited-for children.

As TASK_IO_ACCOUNTING currently counts bytes, we approximate blocks
count doing : nr_blocks = nr_bytes / 512

Example of use :
----------------------
After patch is applied, /usr/bin/time command can now give a good
approximation of IO that the process (and its children) had to do.

$ /usr/bin/time dd if=/dev/zero of=/tmp/testfile count=1000
1000+0 records in
1000+0 records out
512000 bytes (512 kB) copied, 0.0033976 seconds, 151 MB/s
0.00user 0.00system 0:00.00elapsed 100%CPU (0avgtext+0avgdata 0maxresident)k
0inputs+1000outputs (0major+235minor)pagefaults 0swaps

# /usr/bin/time updatedb
1.63user 6.38system 4:21.42elapsed 3%CPU (0avgtext+0avgdata 0maxresident)k
878112inputs+22448outputs (2major+1148minor)pagefaults 0swaps

# ls -s --block-size=512 /var/lib/slocate/slocate.db
22472 /var/lib/slocate/slocate.db

Signed-off-by: Eric Dumazet <dada1@xxxxxxxxxxxxx>
---
include/linux/sched.h | 1
include/linux/task_io_accounting_ops.h | 44 +++++++++++++++++++++++
kernel/exit.c | 8 ++++
kernel/fork.c | 1
kernel/sys.c | 7 +++
5 files changed, 61 insertions(+)

--- linux-2.6.21-rc4/include/linux/sched.h
+++ linux-2.6.21-rc4-ed/include/linux/sched.h
@@ -457,6 +457,7 @@ struct signal_struct {
cputime_t utime, stime, cutime, cstime;
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
+ unsigned long cinblock, coublock;

/*
* Cumulative ns of scheduled CPU time for dead threads in the
--- linux-2.6.21-rc4/include/linux/task_io_accounting_ops.h
+++ linux-2.6.21-rc4-ed/include/linux/task_io_accounting_ops.h
@@ -10,11 +10,29 @@ static inline void task_io_account_read(
current->ioac.read_bytes += bytes;
}

+/*
+ * We approximate number of blocks, because we account bytes only.
+ * A 'block' is 512 bytes
+ */
+static inline unsigned long task_io_get_inblock(const struct task_struct *p)
+{
+ return p->ioac.read_bytes >> 9;
+}
+
static inline void task_io_account_write(size_t bytes)
{
current->ioac.write_bytes += bytes;
}

+/*
+ * We approximate number of blocks, because we account bytes only.
+ * A 'block' is 512 bytes
+ */
+static inline unsigned long task_io_get_oublock(const struct task_struct *p)
+{
+ return p->ioac.write_bytes >> 9;
+}
+
static inline void task_io_account_cancelled_write(size_t bytes)
{
current->ioac.cancelled_write_bytes += bytes;
@@ -25,16 +43,38 @@ static inline void task_io_accounting_in
memset(&tsk->ioac, 0, sizeof(tsk->ioac));
}

+/*
+ * task_io_account_transfert() is called from __exit_signal()
+ * to be able to provide correct ru_inblock/ru_oublock in struct rusage
+ * This is why we take into account read_bytes and write_bytes only.
+ */
+static inline void task_io_account_transfert(struct task_struct *to,
+ const struct task_struct *from)
+{
+ to->ioac.read_bytes += from->ioac.read_bytes;
+ to->ioac.write_bytes += from->ioac.write_bytes;
+}
+
#else

static inline void task_io_account_read(size_t bytes)
{
}

+static inline unsigned long task_io_get_inblock(const struct task_struct *p)
+{
+ return 0;
+}
+
static inline void task_io_account_write(size_t bytes)
{
}

+static inline unsigned long task_io_get_oublock(const struct task_struct *p)
+{
+ return 0;
+}
+
static inline void task_io_account_cancelled_write(size_t bytes)
{
}
@@ -43,5 +83,9 @@ static inline void task_io_accounting_in
{
}

+static inline void task_io_account_transfert(struct task_struct *to,
+ const struct task_struct *from)
+{
+}
#endif /* CONFIG_TASK_IO_ACCOUNTING */
#endif /* __TASK_IO_ACCOUNTING_OPS_INCLUDED */
--- linux-2.6.21-rc4/kernel/sys.c
+++ linux-2.6.21-rc4-ed/kernel/sys.c
@@ -29,6 +29,7 @@
#include <linux/signal.h>
#include <linux/cn_proc.h>
#include <linux/getcpu.h>
+#include <linux/task_io_accounting_ops.h>

#include <linux/compat.h>
#include <linux/syscalls.h>
@@ -2021,6 +2022,8 @@ static void k_getrusage(struct task_stru
r->ru_nivcsw = p->signal->cnivcsw;
r->ru_minflt = p->signal->cmin_flt;
r->ru_majflt = p->signal->cmaj_flt;
+ r->ru_inblock = p->signal->cinblock;
+ r->ru_oublock = p->signal->coublock;

if (who == RUSAGE_CHILDREN)
break;
@@ -2032,6 +2035,8 @@ static void k_getrusage(struct task_stru
r->ru_nivcsw += p->signal->nivcsw;
r->ru_minflt += p->signal->min_flt;
r->ru_majflt += p->signal->maj_flt;
+ r->ru_inblock += task_io_get_inblock(p->signal);
+ r->ru_oublock += task_io_get_oublock(p->signal);
t = p;
do {
utime = cputime_add(utime, t->utime);
@@ -2040,6 +2045,8 @@ static void k_getrusage(struct task_stru
r->ru_nivcsw += t->nivcsw;
r->ru_minflt += t->min_flt;
r->ru_majflt += t->maj_flt;
+ r->ru_inblock += task_io_get_inblock(t);
+ r->ru_oublock += task_io_get_oublock(t);
t = next_thread(t);
} while (t != p);
break;
--- linux-2.6.21-rc4/kernel/fork.c
+++ linux-2.6.21-rc4-ed/kernel/fork.c
@@ -874,6 +874,7 @@ static inline int copy_signal(unsigned l
sig->utime = sig->stime = sig->cutime = sig->cstime = cputime_zero;
sig->nvcsw = sig->nivcsw = sig->cnvcsw = sig->cnivcsw = 0;
sig->min_flt = sig->maj_flt = sig->cmin_flt = sig->cmaj_flt = 0;
+ sig->cinblock = sig->coublock = 0;
sig->sched_time = 0;
INIT_LIST_HEAD(&sig->cpu_timers[0]);
INIT_LIST_HEAD(&sig->cpu_timers[1]);
--- linux-2.6.21-rc4/kernel/exit.c
+++ linux-2.6.21-rc4-ed/kernel/exit.c
@@ -42,6 +42,7 @@
#include <linux/audit.h> /* for audit_free() */
#include <linux/resource.h>
#include <linux/blkdev.h>
+#include <linux/task_io_accounting_ops.h>

#include <asm/uaccess.h>
#include <asm/unistd.h>
@@ -113,6 +114,7 @@ static void __exit_signal(struct task_st
sig->nvcsw += tsk->nvcsw;
sig->nivcsw += tsk->nivcsw;
sig->sched_time += tsk->sched_time;
+ task_io_account_transfert(sig, tsk);
sig = NULL; /* Marker for below. */
}

@@ -1191,6 +1193,12 @@ static int wait_task_zombie(struct task_
p->nvcsw + sig->nvcsw + sig->cnvcsw;
psig->cnivcsw +=
p->nivcsw + sig->nivcsw + sig->cnivcsw;
+ psig->cinblock +=
+ task_io_get_inblock(p) +
+ task_io_get_inblock(sig) + sig->cinblock;
+ psig->coublock +=
+ task_io_get_oublock(p) +
+ task_io_get_oublock(sig) + sig->coublock;
spin_unlock_irq(&p->parent->sighand->siglock);
}

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/