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 17/28] readahead: initial method - thrashing guard size
Date: Wed, 15 Nov 2006 15:50:24 +0800 [thread overview]
Message-ID: <363577026.21912@ustc.edu.cn> (raw)
Message-ID: <20061115075029.869472273@localhost.localdomain> (raw)
In-Reply-To: 20061115075007.832957580@localhost.localdomain
[-- Attachment #1: readahead-initial-method-thrashing-guard-size.patch --]
[-- Type: text/plain, Size: 1568 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>
Signed-off-by: Andrew Morton <akpm@osdl.org>
--- linux-2.6.19-rc5-mm2.orig/mm/readahead.c
+++ linux-2.6.19-rc5-mm2/mm/readahead.c
@@ -822,6 +822,22 @@ 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 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 * 127) / 128:
+ (ra_size + bdi->ra_thrash_bytes * 7) / 8;
+}
+
+/*
* Some helpers for querying/building a read-ahead request.
*
* Diagram for some variable names used frequently:
@@ -1118,6 +1134,10 @@ state_based_readahead(struct address_spa
limit_rala(growth_limit, la_old, &ra_size, &la_size);
+ /* 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, offset, ra->readahead_index);
ra_set_size(ra, ra_size, la_size);
--
next prev parent reply other threads:[~2006-11-15 7:52 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20061115075007.832957580@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 00/28] Adaptive readahead V16 Wu Fengguang
[not found] ` <20061115075024.180138257@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 01/28] readahead: kconfig options Wu Fengguang
[not found] ` <20061115075024.503627543@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 02/28] radixtree: introduce scan hole/data functions Wu Fengguang
[not found] ` <20061115075024.850542829@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 03/28] mm: introduce probe_page() Wu Fengguang
[not found] ` <20061115075025.438524224@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 04/28] mm: introduce PG_readahead Wu Fengguang
[not found] ` <20061115075026.121499794@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 06/28] readahead: insert cond_resched() calls Wu Fengguang
[not found] ` <20061115075027.139255636@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 09/28] readahead: rescue_pages() Wu Fengguang
[not found] ` <20061115075027.832896629@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 11/28] readahead: min/max sizes Wu Fengguang
[not found] ` <20061115075028.178039166@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 12/28] readahead: state based method - aging accounting Wu Fengguang
2006-11-15 16:54 ` Christoph Lameter
[not found] ` <20061116133919.GA6645@mail.ustc.edu.cn>
2006-11-16 13:39 ` Wu Fengguang
[not found] ` <20061115075028.494374406@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 13/28] readahead: state based method - routines Wu Fengguang
[not found] ` <20061115075028.829507795@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 14/28] readahead: state based method Wu Fengguang
[not found] ` <20061115075029.205178794@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 15/28] readahead: context " Wu Fengguang
[not found] ` <20061115075029.519507130@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 16/28] readahead: initial method - guiding sizes Wu Fengguang
[not found] ` <20061115075029.869472273@localhost.localdomain>
2006-11-15 7:50 ` Wu Fengguang [this message]
[not found] ` <20061115075030.229339867@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 18/28] readahead: initial method - user recommended size Wu Fengguang
[not found] ` <20061115075030.942942737@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 20/28] readahead: backward prefetching method Wu Fengguang
[not found] ` <20061115075031.286178806@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 21/28] readahead: thrashing recovery method Wu Fengguang
[not found] ` <20061115075031.524129110@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 22/28] readahead: call scheme Wu Fengguang
[not found] ` <20061115075031.909090639@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 23/28] readahead: laptop mode Wu Fengguang
[not found] ` <20061115075032.213167260@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 24/28] readahead: loop case Wu Fengguang
[not found] ` <20061115075032.515501374@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 25/28] readahead: nfsd case Wu Fengguang
[not found] ` <20061115075032.945192537@localhost.localdomain>
2006-11-15 7:50 ` [PATCH 26/28] readahead: turn on by default 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=363577026.21912@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