From: Gao Xiang <gaoxiang25@huawei.com>
To: Alexander Viro <viro@zeniv.linux.org.uk>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Andrew Morton <akpm@linux-foundation.org>,
Theodore Ts'o <tytso@mit.edu>,
Linus Torvalds <torvalds@linux-foundation.org>
Cc: devel@driverdev.osuosl.org, linux-erofs@lists.ozlabs.org,
Chao Yu <yuchao0@huawei.com>, LKML <linux-kernel@vger.kernel.org>,
Li Guifu <bluce.liguifu@huawei.com>,
Fang Wei <fangwei1@huawei.com>,
linux-fsdevel@vger.kernel.org, Miao Xie <miaoxie@huawei.com>
Subject: [PATCH v2 17/24] erofs: introduce per-CPU buffers implementation
Date: Thu, 11 Jul 2019 22:57:48 +0800 [thread overview]
Message-ID: <20190711145755.33908-18-gaoxiang25@huawei.com> (raw)
In-Reply-To: <20190711145755.33908-1-gaoxiang25@huawei.com>
This patch introduces per-CPU buffers in order for
the upcoming generic decompression framework to use.
Note that I tried to use in-kernel per-CPU buffer or
per-CPU page approaches to clean up further, however
noticeable performanace regression (about 2% for
sequential read) was observed.
Let's leave it as-is for now.
Signed-off-by: Gao Xiang <gaoxiang25@huawei.com>
---
fs/erofs/Kconfig | 14 ++++++++++++++
fs/erofs/internal.h | 24 ++++++++++++++++++++++++
fs/erofs/utils.c | 12 ++++++++++++
3 files changed, 50 insertions(+)
diff --git a/fs/erofs/Kconfig b/fs/erofs/Kconfig
index f6b6eb0250b8..ae6c7c69ab76 100644
--- a/fs/erofs/Kconfig
+++ b/fs/erofs/Kconfig
@@ -89,3 +89,17 @@ config EROFS_FS_ZIP
If you don't want to enable compression feature, say N.
+config EROFS_FS_CLUSTER_PAGE_LIMIT
+ int "EROFS Cluster Pages Hard Limit"
+ depends on EROFS_FS_ZIP
+ range 1 256
+ default "1"
+ help
+ Indicates maximum # of pages of a compressed
+ physical cluster.
+
+ For example, if files in a image were compressed
+ into 8k-unit, hard limit should not be configured
+ less than 2. Otherwise, the image will be refused
+ to mount on this kernel.
+
diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h
index f603ae8aa9b1..5e06e2d12b5e 100644
--- a/fs/erofs/internal.h
+++ b/fs/erofs/internal.h
@@ -222,6 +222,15 @@ static inline int erofs_wait_on_workgroup_freezed(struct erofs_workgroup *grp)
return v;
}
#endif
+
+#ifdef CONFIG_EROFS_FS_CLUSTER_PAGE_LIMIT
+#define Z_EROFS_CLUSTER_MAX_PAGES (CONFIG_EROFS_FS_CLUSTER_PAGE_LIMIT)
+#else
+#define Z_EROFS_CLUSTER_MAX_PAGES 1
+#endif
+#define EROFS_PCPUBUF_NR_PAGES Z_EROFS_CLUSTER_MAX_PAGES
+#else
+#define EROFS_PCPUBUF_NR_PAGES 0
#endif
/* we strictly follow PAGE_SIZE and no buffer head yet */
@@ -486,6 +495,21 @@ int erofs_namei(struct inode *dir, struct qstr *name,
extern const struct file_operations erofs_dir_fops;
/* utils.c */
+#if (EROFS_PCPUBUF_NR_PAGES > 0)
+void *erofs_get_pcpubuf(unsigned int pagenr);
+#define erofs_put_pcpubuf(buf) do { \
+ (void)&(buf); \
+ preempt_enable(); \
+} while (0)
+#else
+static inline void *erofs_get_pcpubuf(unsigned int pagenr)
+{
+ return ERR_PTR(-ENOTSUPP);
+}
+
+#define erofs_put_pcpubuf(buf) do {} while (0)
+#endif
+
#ifdef CONFIG_EROFS_FS_ZIP
int erofs_workgroup_put(struct erofs_workgroup *grp);
struct erofs_workgroup *erofs_find_workgroup(struct super_block *sb,
diff --git a/fs/erofs/utils.c b/fs/erofs/utils.c
index 45fd780e6429..c430790a02e0 100644
--- a/fs/erofs/utils.c
+++ b/fs/erofs/utils.c
@@ -9,6 +9,18 @@
#include "internal.h"
#include <linux/pagevec.h>
+#if (EROFS_PCPUBUF_NR_PAGES > 0)
+static struct {
+ u8 data[PAGE_SIZE * EROFS_PCPUBUF_NR_PAGES];
+} ____cacheline_aligned_in_smp erofs_pcpubuf[NR_CPUS];
+
+void *erofs_get_pcpubuf(unsigned int pagenr)
+{
+ preempt_disable();
+ return &erofs_pcpubuf[smp_processor_id()].data[pagenr * PAGE_SIZE];
+}
+#endif
+
#ifdef CONFIG_EROFS_FS_ZIP
/* global shrink count (for all mounted EROFS instances) */
static atomic_long_t erofs_global_shrink_cnt;
--
2.17.1
_______________________________________________
devel mailing list
devel@linuxdriverproject.org
http://driverdev.linuxdriverproject.org/mailman/listinfo/driverdev-devel
next prev parent reply other threads:[~2019-07-11 14:57 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-11 14:57 [PATCH v2 00/24] erofs: promote erofs from staging Gao Xiang
2019-07-11 14:57 ` [PATCH v2 01/24] erofs: add on-disk layout Gao Xiang
2019-07-11 14:57 ` [PATCH v2 02/24] erofs: add erofs in-memory stuffs Gao Xiang
2019-07-11 14:57 ` [PATCH v2 03/24] erofs: add super block operations Gao Xiang
2019-07-20 22:49 ` Al Viro
2019-07-21 3:08 ` Gao Xiang
2019-07-21 4:05 ` Al Viro
2019-07-21 4:12 ` Gao Xiang
2019-07-21 18:05 ` Gao Xiang
2019-07-11 14:57 ` [PATCH v2 04/24] erofs: add raw address_space operations Gao Xiang
2019-07-11 14:57 ` [PATCH v2 05/24] erofs: add inode operations Gao Xiang
2019-07-11 14:57 ` [PATCH v2 06/24] erofs: support special inode Gao Xiang
2019-07-11 14:57 ` [PATCH v2 07/24] erofs: add directory operations Gao Xiang
2019-07-11 14:57 ` [PATCH v2 08/24] erofs: add namei functions Gao Xiang
2019-07-11 14:57 ` [PATCH v2 09/24] erofs: support tracepoint Gao Xiang
2019-07-11 14:57 ` [PATCH v2 10/24] erofs: update Kconfig and Makefile Gao Xiang
2019-07-11 14:57 ` [PATCH v2 11/24] erofs: introduce xattr & posixacl support Gao Xiang
2019-07-11 14:57 ` [PATCH v2 12/24] erofs: introduce tagged pointer Gao Xiang
2019-07-11 14:57 ` [PATCH v2 13/24] erofs: add compression indexes support Gao Xiang
2019-07-11 14:57 ` [PATCH v2 14/24] erofs: introduce superblock registration Gao Xiang
2019-07-11 14:57 ` [PATCH v2 15/24] erofs: introduce erofs shrinker Gao Xiang
2019-07-11 14:57 ` [PATCH v2 16/24] erofs: introduce workstation for decompression Gao Xiang
2019-07-11 14:57 ` Gao Xiang [this message]
2019-07-11 14:57 ` [PATCH v2 18/24] erofs: introduce pagevec for decompression subsystem Gao Xiang
2019-07-11 14:57 ` [PATCH v2 19/24] erofs: add erofs_allocpage() Gao Xiang
2019-07-11 14:57 ` [PATCH v2 20/24] erofs: introduce generic decompression backend Gao Xiang
2019-07-11 14:57 ` [PATCH v2 21/24] erofs: introduce LZ4 decompression inplace Gao Xiang
2019-07-11 14:57 ` [PATCH v2 22/24] erofs: introduce the decompression frontend Gao Xiang
2019-07-11 14:57 ` [PATCH v2 23/24] erofs: introduce cached decompression Gao Xiang
2019-07-11 14:57 ` [PATCH v2 24/24] erofs: add document Gao Xiang
2019-07-14 10:49 ` [PATCH v2 00/24] erofs: promote erofs from staging Pavel Machek
2019-07-14 20:17 ` Gao Xiang
2019-07-15 7:56 ` Pavel Machek
2019-07-15 8:37 ` Gao Xiang
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=20190711145755.33908-18-gaoxiang25@huawei.com \
--to=gaoxiang25@huawei.com \
--cc=akpm@linux-foundation.org \
--cc=bluce.liguifu@huawei.com \
--cc=devel@driverdev.osuosl.org \
--cc=fangwei1@huawei.com \
--cc=gregkh@linuxfoundation.org \
--cc=linux-erofs@lists.ozlabs.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=miaoxie@huawei.com \
--cc=torvalds@linux-foundation.org \
--cc=tytso@mit.edu \
--cc=viro@zeniv.linux.org.uk \
--cc=yuchao0@huawei.com \
/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).