From mboxrd@z Thu Jan  1 00:00:00 1970
From: Adrian Hunter <ext-adrian.hunter@nokia.com>
Subject: fs time granularity
Date: Wed, 09 Apr 2008 18:07:53 +0300
Message-ID: <47FCDBC9.8030602@nokia.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
To: linux-fsdevel@vger.kernel.org
Return-path: <linux-fsdevel-owner@vger.kernel.org>
Received: from smtp.nokia.com ([192.100.105.134]:30888 "EHLO
	mgw-mx09.nokia.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1753475AbYDIPMz (ORCPT
	<rfc822;linux-fsdevel@vger.kernel.org>);
	Wed, 9 Apr 2008 11:12:55 -0400
Received: from esebh106.NOE.Nokia.com (esebh106.ntc.nokia.com [172.21.138.213])
	by mgw-mx09.nokia.com (Switch-3.2.6/Switch-3.2.6) with ESMTP id m39FDdvV005427
	for <linux-fsdevel@vger.kernel.org>; Wed, 9 Apr 2008 10:15:10 -0500
Sender: linux-fsdevel-owner@vger.kernel.org
List-ID: <linux-fsdevel.vger.kernel.org>

I was trying different values for time granularity but did not get the results I expected,
which I think is because of the function below:


/**
 * timespec_trunc - Truncate timespec to a granularity
 * @t: Timespec
 * @gran: Granularity in ns.
 *
 * Truncate a timespec to a granularity. gran must be smaller than a second.
 * Always rounds down.
 *
 * This function should be only used for timestamps returned by
 * current_kernel_time() or CURRENT_TIME, not with do_gettimeofday() because
 * it doesn't handle the better resolution of the latter.
 */
struct timespec timespec_trunc(struct timespec t, unsigned gran)
{
	/*
	 * Division is pretty slow so avoid it for common cases.
	 * Currently current_kernel_time() never returns better than
	 * jiffies resolution. Exploit that.
	 */
	if (gran <= jiffies_to_usecs(1) * 1000) {
		/* nothing */
	} else if (gran == 1000000000) {
		t.tv_nsec = 0;
	} else {
		t.tv_nsec -= t.tv_nsec % gran;
	}
	return t;
}
EXPORT_SYMBOL(timespec_trunc);


The first condition gives no rounding, but although current_kernel_time()
is only updated every jiffy, it is not rounded to that granularity.

With HZ=250 and gran=1000000, I was expecting to see just 3 decimal places
of time.  But instead I get:

# touch a
# stat a
  File: `a'
  Size: 0               Blocks: 0          IO Block: 4096   regular empty file
Device: fc01h/64513d    Inode: 65          Links: 1
Access: (0644/-rw-r--r--)  Uid: (    0/    root)   Gid: (    0/    root)
Access: 2008-04-09 17:05:38.032726306 +0300
Modify: 2008-04-09 17:05:38.032726306 +0300
Change: 2008-04-09 17:05:38.032726306 +0300

If I change gran to 10000000, it works:

# touch a
# stat a
  File: `a'
  Size: 0               Blocks: 0          IO Block: 4096   regular empty file
Device: fc01h/64513d    Inode: 65          Links: 1
Access: (0644/-rw-r--r--)  Uid: (    0/    root)   Gid: (    0/    root)
Access: 2008-04-09 17:34:25.180000000 +0300
Modify: 2008-04-09 17:34:25.180000000 +0300
Change: 2008-04-09 17:34:25.180000000 +0300


Is this how it is meant to be?