Re: [PATCH 0/9] mmap read-around and readahead
From: Fengguang Wu
Date: Tue Dec 18 2007 - 07:13:41 EST
On Tue, Dec 18, 2007 at 07:46:09PM +0800, Fengguang Wu wrote:
> No timings for now... but I wrote a debug patch(attached) and watched
> it running for about a week. Here are some interesting numbers:
Here are the (forgotten) readahead-debug.patch:
---
include/linux/fs.h | 43 ++++++++++++++++++++++++++++++++++
mm/Kconfig | 19 +++++++++++++++
mm/filemap.c | 1
mm/readahead.c | 54 ++++++++++++++++++++++++++++++++++++++++++-
4 files changed, 116 insertions(+), 1 deletion(-)
--- linux-2.6.24-rc4-mm1.orig/include/linux/fs.h
+++ linux-2.6.24-rc4-mm1/include/linux/fs.h
@@ -760,11 +760,54 @@ struct file_ra_state {
unsigned int async_size; /* do asynchronous readahead when
there are only # of pages ahead */
+ unsigned int flags;
unsigned int ra_pages; /* Maximum readahead window */
int mmap_miss; /* Cache miss stat for mmap accesses */
loff_t prev_pos; /* Cache last read() position */
};
+#define RA_CLASS_SHIFT 4
+#define RA_CLASS_MASK ((1 << RA_CLASS_SHIFT) - 1)
+/*
+ * Detailed classification of read-ahead behaviors.
+ */
+enum ra_class {
+ RA_CLASS_INIT0,
+ RA_CLASS_INIT,
+ RA_CLASS_SEQUENTIAL,
+ RA_CLASS_INTERLEAVED,
+ RA_CLASS_CONTEXT,
+ RA_CLASS_AROUND,
+ RA_CLASS_COUNT
+};
+
+static inline enum ra_class ra_class_new(struct file_ra_state *ra)
+{
+ return ra->flags & RA_CLASS_MASK;
+}
+
+static inline enum ra_class ra_class_old(struct file_ra_state *ra)
+{
+ return (ra->flags >> RA_CLASS_SHIFT) & RA_CLASS_MASK;
+}
+
+/*
+ * Which method is issuing this read-ahead?
+ */
+static inline void ra_set_class(struct file_ra_state *ra, enum ra_class ra_class)
+{
+ unsigned long flags_mask;
+ unsigned long flags;
+ unsigned long old_ra_class;
+
+ flags_mask = ~(RA_CLASS_MASK | (RA_CLASS_MASK << RA_CLASS_SHIFT));
+ flags = ra->flags & flags_mask;
+
+ old_ra_class = ra_class_new(ra) << RA_CLASS_SHIFT;
+
+ ra->flags = flags | old_ra_class | ra_class;
+}
+
/*
* Check if @index falls in the readahead windows.
*/
--- linux-2.6.24-rc4-mm1.orig/mm/Kconfig
+++ linux-2.6.24-rc4-mm1/mm/Kconfig
@@ -194,3 +194,22 @@ config NR_QUICK
config VIRT_TO_BUS
def_bool y
depends on !ARCH_NO_VIRT_TO_BUS
+
+config DEBUG_READAHEAD
+ bool "Readahead debug and accounting"
+ default y
+ select DEBUG_FS
+ help
+ This option injects extra code to dump detailed debug traces and do
+ readahead events accounting.
+
+ To actually get the data:
+
+ mkdir /debug
+ mount -t debug none /debug
+
+ After that you can do the following:
+
+ echo > /debug/readahead/events # reset the counters
+ cat /debug/readahead/events # check the counters
+
--- linux-2.6.24-rc4-mm1.orig/mm/readahead.c
+++ linux-2.6.24-rc4-mm1/mm/readahead.c
@@ -16,6 +16,29 @@
#include <linux/task_io_accounting_ops.h>
#include <linux/pagevec.h>
#include <linux/pagemap.h>
+#include <linux/debugfs.h>
+
+static const char * const ra_class_name[] = {
+ [RA_CLASS_INIT0] = "init0",
+ [RA_CLASS_INIT] = "init",
+ [RA_CLASS_SEQUENTIAL] = "sequential",
+ [RA_CLASS_INTERLEAVED] = "interleaved",
+ [RA_CLASS_CONTEXT] = "context",
+ [RA_CLASS_AROUND] = "around",
+};
+
+#ifdef CONFIG_DEBUG_READAHEAD
+static u32 readahead_debug_level = 1;
+# define debug_option(o) (o)
+#else
+# define debug_option(o) (0)
+# define readahead_debug_level (0)
+#endif /* CONFIG_DEBUG_READAHEAD */
+
+#define dprintk(args...) \
+ do { if (readahead_debug_level >= 2) printk(KERN_DEBUG args); } while(0)
+#define ddprintk(args...) \
+ do { if (readahead_debug_level >= 3) printk(KERN_DEBUG args); } while(0)
void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
{
@@ -220,6 +243,13 @@ unsigned long max_sane_readahead(unsigne
static int __init readahead_init(void)
{
+#ifdef CONFIG_DEBUG_READAHEAD
+ struct dentry *root;
+
+ root = debugfs_create_dir("readahead", NULL);
+
+ debugfs_create_u32("debug_level", 0644, root, &readahead_debug_level);
+#endif
return bdi_init(&default_backing_dev_info);
}
subsys_initcall(readahead_init);
@@ -235,6 +265,15 @@ unsigned long ra_submit(struct file_ra_s
actual = __do_page_cache_readahead(mapping, filp,
ra->start, ra->size, ra->async_size);
+ dprintk("readahead-%s(process: %s/%d, file: %s/%s, "
+ "offset=%ld:%ld, ra=%ld+%d-%d) = %d\n",
+ ra_class_name[ra_class_new(ra)],
+ current->comm, current->pid,
+ mapping->host->i_sb->s_id,
+ filp->f_path.dentry->d_iname,
+ (long)(filp->f_pos >> PAGE_CACHE_SHIFT),
+ (long)(ra->prev_pos >> PAGE_CACHE_SHIFT),
+ ra->start, ra->size, ra->async_size, actual);
return actual;
}
@@ -337,6 +376,7 @@ ondemand_readahead(struct address_space
ra->start += ra->size;
ra->size = get_next_ra_size(ra, max);
ra->async_size = ra->size;
+ ra_set_class(ra, RA_CLASS_SEQUENTIAL);
goto readit;
}
@@ -348,8 +388,15 @@ ondemand_readahead(struct address_space
* Read as is, and do not pollute the readahead state.
*/
if (!hit_readahead_marker && !sequential) {
- return __do_page_cache_readahead(mapping, filp,
+ int actual = __do_page_cache_readahead(mapping, filp,
offset, req_size, 0);
+ dprintk("read-random(process: %s/%d, file: %s/%s, "
+ "req=%ld+%ld) = %d\n",
+ current->comm, current->pid,
+ mapping->host->i_sb->s_id,
+ filp->f_path.dentry->d_iname,
+ offset, req_size, actual);
+ return actual;
}
/*
@@ -372,6 +419,7 @@ ondemand_readahead(struct address_space
ra->size = start - offset; /* old async_size */
ra->size = get_next_ra_size(ra, max);
ra->async_size = ra->size;
+ ra_set_class(ra, RA_CLASS_INTERLEAVED);
goto readit;
}
@@ -385,6 +433,10 @@ ondemand_readahead(struct address_space
ra->start = offset;
ra->size = get_init_ra_size(req_size, max);
ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size;
+ if (offset)
+ ra_set_class(ra, RA_CLASS_INIT);
+ else
+ ra_set_class(ra, RA_CLASS_INIT0);
readit:
/*
--- linux-2.6.24-rc4-mm1.orig/mm/filemap.c
+++ linux-2.6.24-rc4-mm1/mm/filemap.c
@@ -1340,6 +1340,7 @@ static void do_sync_mmap_readahead(struc
ra->start = max_t(long, 0, offset - ra_pages / 2);
ra->size = ra_pages;
ra->async_size = 0;
+ ra_set_class(ra, RA_CLASS_AROUND);
ra_submit(ra, mapping, file);
}
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/