linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Wu Fengguang <wfg@mail.ustc.edu.cn>
To: Andrew Morton <akpm@osdl.org>
Cc: linux-kernel@vger.kernel.org, Wu Fengguang <wfg@mail.ustc.edu.cn>
Subject: [PATCH 19/33] readahead: initial method - thrashing guard size
Date: Fri, 26 May 2006 19:39:25 +0800	[thread overview]
Message-ID: <348644384.05317@ustc.edu.cn> (raw)
Message-ID: <20060526115309.581525784@localhost.localdomain> (raw)
In-Reply-To: 20060526113906.084341801@localhost.localdomain

[-- Attachment #1: readahead-method-initial-size-thrash.patch --]
[-- Type: text/plain, Size: 1619 bytes --]

backing_dev_info.ra_thrash_bytes is dynamicly updated to be a little above
the thrashing safe read-ahead size. It is used in the initial method where
the thrashing threshold for the particular reader is still unknown.

Signed-off-by: Wu Fengguang <wfg@mail.ustc.edu.cn>
---

 mm/readahead.c |   20 ++++++++++++++++++++
 1 files changed, 20 insertions(+)

--- linux-2.6.17-rc4-mm3.orig/mm/readahead.c
+++ linux-2.6.17-rc4-mm3/mm/readahead.c
@@ -817,6 +817,22 @@ out:
 }
 
 /*
+ * Update `backing_dev_info.ra_thrash_bytes' to be a _biased_ average of
+ * read-ahead sizes. Which makes it an a-bit-risky(*) estimation of the
+ * _minimal_ read-ahead thrashing threshold on the device.
+ *
+ * (*) Note that being a bit risky can _help_ overall performance.
+ */
+static inline void update_ra_thrash_bytes(struct backing_dev_info *bdi,
+						unsigned long ra_size)
+{
+	ra_size <<= PAGE_CACHE_SHIFT;
+	bdi->ra_thrash_bytes = (bdi->ra_thrash_bytes < ra_size) ?
+				(ra_size + bdi->ra_thrash_bytes * 1023) / 1024:
+				(ra_size + bdi->ra_thrash_bytes *    7) /    8;
+}
+
+/*
  * The node's effective length of inactive_list(s).
  */
 static unsigned long node_free_and_cold_pages(void)
@@ -1180,6 +1196,10 @@ state_based_readahead(struct address_spa
 	if (!adjust_rala(growth_limit, &ra_size, &la_size))
 		return 0;
 
+	/* ra_size in its _steady_ state reflects thrashing threshold */
+	if (page && ra_old + ra_old / 8 >= ra_size)
+		update_ra_thrash_bytes(mapping->backing_dev_info, ra_size);
+
 	ra_set_class(ra, RA_CLASS_STATE);
 	ra_set_index(ra, index, ra->readahead_index);
 	ra_set_size(ra, ra_size, la_size);

--

  parent reply	other threads:[~2006-05-26 11:59 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20060526113906.084341801@localhost.localdomain>
     [not found] ` <20060526115259.223408850@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 02/33] radixtree: introduce __radix_tree_lookup_parent() Wu Fengguang
2006-05-26 13:56     ` Christoph Lameter
     [not found]       ` <20060526140951.GA13954@mail.ustc.edu.cn>
2006-05-26 14:09         ` Wu Fengguang
     [not found] ` <20060526115259.809011306@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 03/33] radixtree: introduce radix_tree_scan_hole[_backward]() Wu Fengguang
     [not found] ` <20060526115300.609227164@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 04/33] mm: introduce probe_pages() Wu Fengguang
     [not found] ` <20060526115301.640751284@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 06/33] readahead: add look-ahead support to __do_page_cache_readahead() Wu Fengguang
     [not found] ` <20060526115302.278500703@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 07/33] readahead: delay page release in do_generic_mapping_read() Wu Fengguang
     [not found] ` <20060526115303.499451943@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 09/33] readahead: {MIN,MAX}_RA_PAGES Wu Fengguang
     [not found] ` <20060526115304.094503892@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 10/33] readahead: events accounting Wu Fengguang
     [not found] ` <20060526115304.821789643@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 11/33] readahead: rescue_pages() Wu Fengguang
     [not found] ` <20060526115305.437903777@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 12/33] readahead: sysctl parameters Wu Fengguang
     [not found] ` <20060526115306.535453644@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 14/33] readahead: state based method - aging accounting Wu Fengguang
     [not found] ` <20060526115307.794859372@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 16/33] readahead: state based method Wu Fengguang
     [not found] ` <20060526115308.522890112@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 17/33] readahead: context " Wu Fengguang
     [not found] ` <20060526115309.581525784@localhost.localdomain>
2006-05-26 11:39   ` Wu Fengguang [this message]
     [not found] ` <20060526115310.948231030@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 21/33] readahead: initial method - user recommended size Wu Fengguang
     [not found] ` <20060526115311.541535720@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 22/33] readahead: initial method Wu Fengguang
     [not found] ` <20060526115312.145248016@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 23/33] readahead: backward prefetching method Wu Fengguang
     [not found] ` <20060526115313.491576583@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 25/33] readahead: thrashing recovery method Wu Fengguang
     [not found] ` <20060526115314.929319286@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 26/33] readahead: call scheme Wu Fengguang
     [not found] ` <20060526115315.823465555@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 28/33] readahead: loop case Wu Fengguang
     [not found] ` <20060526115316.335626686@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 29/33] readahead: nfsd case Wu Fengguang
     [not found] ` <20060526115316.925345724@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 30/33] readahead: turn on by default Wu Fengguang
     [not found] ` <20060526115317.663871267@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 31/33] readahead: debug radix tree new functions Wu Fengguang
     [not found] ` <20060526115318.181350700@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 32/33] readahead: debug traces showing accessed file names Wu Fengguang
     [not found] ` <20060526115318.520512078@localhost.localdomain>
2006-05-26 11:39   ` [PATCH 33/33] readahead: debug traces showing read patterns Wu Fengguang
     [not found] <20060524111246.420010595@localhost.localdomain>
     [not found] ` <20060524111906.588647885@localhost.localdomain>
2006-05-24 11:13   ` [PATCH 19/33] readahead: initial method - thrashing guard size Wu Fengguang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=348644384.05317@ustc.edu.cn \
    --to=wfg@mail.ustc.edu.cn \
    --cc=akpm@osdl.org \
    --cc=linux-kernel@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).