task IO accounting: provide distinct tgid/tid I/O statistics
Report per-thread I/O statistics in /proc/pid/task/tid/io and aggregate
parent I/O statistics in /proc/pid/io. This approach follows the same
model used to account per-process and per-thread CPU times.
As a practial application, this allows for example to quickly find the top
I/O consumer when a process spawns many child threads that perform the
actual I/O work, because the aggregated I/O statistics can always be found
in /proc/pid/io.
[ Oleg Nesterov points out that we should check that the task is still
alive before we iterate over the threads, but also says that we can do
that fixup on top of this later. - Linus ]
Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Andrea Righi <righi.andrea@gmail.com>
Cc: Matt Heaton <matt@hostmonster.com>
Cc: Shailabh Nagar <nagar@watson.ibm.com>
Acked-by-with-comments: Oleg Nesterov <oleg@tv-sign.ru>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 58c3e6a..a891fe4 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2376,29 +2376,82 @@
}
#ifdef CONFIG_TASK_IO_ACCOUNTING
-static int proc_pid_io_accounting(struct task_struct *task, char *buffer)
+static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
{
+ u64 rchar, wchar, syscr, syscw;
+ struct task_io_accounting ioac;
+
+ if (!whole) {
+ rchar = task->rchar;
+ wchar = task->wchar;
+ syscr = task->syscr;
+ syscw = task->syscw;
+ memcpy(&ioac, &task->ioac, sizeof(ioac));
+ } else {
+ unsigned long flags;
+ struct task_struct *t = task;
+ rchar = wchar = syscr = syscw = 0;
+ memset(&ioac, 0, sizeof(ioac));
+
+ rcu_read_lock();
+ do {
+ rchar += t->rchar;
+ wchar += t->wchar;
+ syscr += t->syscr;
+ syscw += t->syscw;
+
+ ioac.read_bytes += t->ioac.read_bytes;
+ ioac.write_bytes += t->ioac.write_bytes;
+ ioac.cancelled_write_bytes +=
+ t->ioac.cancelled_write_bytes;
+ t = next_thread(t);
+ } while (t != task);
+ rcu_read_unlock();
+
+ if (lock_task_sighand(task, &flags)) {
+ struct signal_struct *sig = task->signal;
+
+ rchar += sig->rchar;
+ wchar += sig->wchar;
+ syscr += sig->syscr;
+ syscw += sig->syscw;
+
+ ioac.read_bytes += sig->ioac.read_bytes;
+ ioac.write_bytes += sig->ioac.write_bytes;
+ ioac.cancelled_write_bytes +=
+ sig->ioac.cancelled_write_bytes;
+
+ unlock_task_sighand(task, &flags);
+ }
+ }
+
return sprintf(buffer,
-#ifdef CONFIG_TASK_XACCT
"rchar: %llu\n"
"wchar: %llu\n"
"syscr: %llu\n"
"syscw: %llu\n"
-#endif
"read_bytes: %llu\n"
"write_bytes: %llu\n"
"cancelled_write_bytes: %llu\n",
-#ifdef CONFIG_TASK_XACCT
- (unsigned long long)task->rchar,
- (unsigned long long)task->wchar,
- (unsigned long long)task->syscr,
- (unsigned long long)task->syscw,
-#endif
- (unsigned long long)task->ioac.read_bytes,
- (unsigned long long)task->ioac.write_bytes,
- (unsigned long long)task->ioac.cancelled_write_bytes);
+ (unsigned long long)rchar,
+ (unsigned long long)wchar,
+ (unsigned long long)syscr,
+ (unsigned long long)syscw,
+ (unsigned long long)ioac.read_bytes,
+ (unsigned long long)ioac.write_bytes,
+ (unsigned long long)ioac.cancelled_write_bytes);
}
-#endif
+
+static int proc_tid_io_accounting(struct task_struct *task, char *buffer)
+{
+ return do_io_accounting(task, buffer, 0);
+}
+
+static int proc_tgid_io_accounting(struct task_struct *task, char *buffer)
+{
+ return do_io_accounting(task, buffer, 1);
+}
+#endif /* CONFIG_TASK_IO_ACCOUNTING */
/*
* Thread groups
@@ -2470,7 +2523,7 @@
REG("coredump_filter", S_IRUGO|S_IWUSR, coredump_filter),
#endif
#ifdef CONFIG_TASK_IO_ACCOUNTING
- INF("io", S_IRUGO, pid_io_accounting),
+ INF("io", S_IRUGO, tgid_io_accounting),
#endif
};
@@ -2797,6 +2850,9 @@
#ifdef CONFIG_FAULT_INJECTION
REG("make-it-fail", S_IRUGO|S_IWUSR, fault_inject),
#endif
+#ifdef CONFIG_TASK_IO_ACCOUNTING
+ INF("io", S_IRUGO, tid_io_accounting),
+#endif
};
static int proc_tid_base_readdir(struct file * filp,