The patch titled
readahead: state based method - routines
has been added to the -mm tree. Its filename is
readahead-state-based-method-routines.patch
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: readahead: state based method - routines
From: Wu Fengguang <wfg@xxxxxxxxxxxxxxxx>
Extend struct file_ra_state to support the adaptive read-ahead logic.
Also define some helpers for it.
Signed-off-by: Wu Fengguang <wfg@xxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxx>
---
include/linux/fs.h | 58 +++++++++++++---
mm/readahead.c | 153 ++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 199 insertions(+), 12 deletions(-)
diff -puN include/linux/fs.h~readahead-state-based-method-routines include/linux/fs.h
--- a/include/linux/fs.h~readahead-state-based-method-routines
+++ a/include/linux/fs.h
@@ -688,21 +688,59 @@ struct fown_struct {
/*
* Track a single file's readahead state
+ *
+ * Diagram for the adaptive readahead logic:
+ *
+ * |--------- old chunk ------->|-------------- new chunk -------------->|
+ * +----------------------------+----------------------------------------+
+ * | # | # |
+ * +----------------------------+----------------------------------------+
+ * ^ ^ ^ ^
+ * file_ra_state.la_index .ra_index .lookahead_index .readahead_index
+ *
+ * Common used deduced sizes:
+ * |----------- readahead size ------------>|
+ * +----------------------------+----------------------------------------+
+ * | # | # |
+ * +----------------------------+----------------------------------------+
+ * |------- invoke interval ------>|-- lookahead size -->|
*/
struct file_ra_state {
- unsigned long start; /* Current window */
- unsigned long size;
- unsigned long flags; /* ra flags RA_FLAG_xxx*/
- unsigned long cache_hit; /* cache hit count*/
- unsigned long prev_page; /* Cache last read() position */
- unsigned long ahead_start; /* Ahead window */
- unsigned long ahead_size;
- unsigned long ra_pages; /* Maximum readahead window */
+ union {
+ struct { /* stock read-ahead */
+ unsigned long start; /* Current window */
+ unsigned long size;
+ unsigned long ahead_start; /* Ahead window */
+ unsigned long ahead_size;
+ unsigned long cache_hit; /* cache hit count */
+ };
+#ifdef CONFIG_ADAPTIVE_READAHEAD
+ struct { /* adaptive read-ahead */
+ pgoff_t la_index; /* old chunk */
+ pgoff_t ra_index;
+ pgoff_t lookahead_index; /* new chunk */
+ pgoff_t readahead_index;
+
+ /*
+ * Snapshot of the (node's) read-ahead aging value
+ * on time of I/O submission.
+ */
+ unsigned long age;
+ };
+#endif
+ };
+
+ /* mmap read-around */
unsigned long mmap_hit; /* Cache hit stat for mmap accesses */
unsigned long mmap_miss; /* Cache miss stat for mmap accesses */
+
+ unsigned long flags; /* RA_FLAG_xxx | ra_class_old | ra_class_new */
+ unsigned long prev_page; /* Cache last read() position */
+ unsigned long ra_pages; /* Maximum readahead window */
};
-#define RA_FLAG_MISS 0x01 /* a cache miss occured against this file */
-#define RA_FLAG_INCACHE 0x02 /* file is already in cache */
+#define RA_FLAG_MISS (1UL<<31) /* a cache miss occured against this file */
+#define RA_FLAG_INCACHE (1UL<<30) /* file is already in cache */
+#define RA_FLAG_MMAP (1UL<<29) /* mmap page access */
struct file {
/*
diff -puN mm/readahead.c~readahead-state-based-method-routines mm/readahead.c
--- a/mm/readahead.c~readahead-state-based-method-routines
+++ a/mm/readahead.c
@@ -780,6 +780,155 @@ out:
}
/*
+ * Some helpers for querying/building a read-ahead request.
+ *
+ * Diagram for some variable names used frequently:
+ *
+ * |<------- la_size ------>|
+ * +-----------------------------------------+
+ * | # |
+ * +-----------------------------------------+
+ * ra_index -->|<---------------- ra_size -------------->|
+ *
+ */
+
+static 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;
+}
+
+static unsigned long ra_readahead_size(struct file_ra_state *ra)
+{
+ return ra->readahead_index - ra->ra_index;
+}
+
+static unsigned long ra_lookahead_size(struct file_ra_state *ra)
+{
+ return ra->readahead_index - ra->lookahead_index;
+}
+
+static unsigned long ra_invoke_interval(struct file_ra_state *ra)
+{
+ return ra->lookahead_index - ra->la_index;
+}
+
+/*
+ * Check if @index falls in the @ra request.
+ */
+static int ra_has_index(struct file_ra_state *ra, pgoff_t index)
+{
+ return (index >= ra->la_index &&
+ index < ra->readahead_index);
+}
+
+/*
+ * Which method is issuing this read-ahead?
+ */
+static 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;
+}
+
+/*
+ * Where is the old read-ahead and look-ahead?
+ */
+static void ra_set_index(struct file_ra_state *ra,
+ pgoff_t la_index, pgoff_t ra_index)
+{
+ ra->la_index = la_index;
+ ra->ra_index = ra_index;
+}
+
+/*
+ * Where is the new read-ahead and look-ahead?
+ */
+static void ra_set_size(struct file_ra_state *ra,
+ unsigned long ra_size, unsigned long la_size)
+{
+ ra->readahead_index = ra->ra_index + ra_size;
+ ra->lookahead_index = ra->readahead_index - la_size;
+}
+
+/*
+ * Submit IO for the read-ahead request in file_ra_state.
+ */
+static unsigned long ra_submit(struct file_ra_state *ra,
+ struct address_space *mapping, struct file *filp)
+{
+ unsigned long ra_size;
+ unsigned long la_size;
+ pgoff_t eof;
+ int actual;
+
+ eof = /* it's a past-the-end index! */
+ DIV_ROUND_UP(i_size_read(mapping->host), PAGE_CACHE_SIZE);
+
+ if (unlikely(ra->ra_index >= eof))
+ return 0;
+
+ /*
+ * Snap to EOF, if the request
+ * - crossed the EOF boundary;
+ * - is close to EOF(explained below).
+ *
+ * Imagine a file sized 18 pages, and we dicided to read-ahead the
+ * first 16 pages. It is highly possible that in the near future we
+ * will have to do another read-ahead for the remaining 2 pages,
+ * which is an unfavorable small I/O.
+ *
+ * So we prefer to take a bit risk to enlarge the current read-ahead,
+ * to eliminate possible future small I/O.
+ */
+ if (ra->readahead_index + MIN_RA_PAGES
+ + ra_readahead_size(ra) / 4 > eof) {
+ ra->readahead_index = eof;
+ if (ra->lookahead_index > eof)
+ ra->lookahead_index = eof;
+ }
+
+ /* Take down the current read-ahead aging value. */
+ ra->age = nr_scanned_pages_node(numa_node_id());
+
+ ra_size = ra_readahead_size(ra);
+ la_size = ra_lookahead_size(ra);
+ actual = __do_page_cache_readahead(mapping, filp,
+ ra->ra_index, ra_size, la_size);
+
+#ifdef CONFIG_DEBUG_READAHEAD
+ if (ra->flags & RA_FLAG_MMAP)
+ ra_account(ra, RA_EVENT_READAHEAD_MMAP, actual);
+ if (ra->readahead_index == eof)
+ ra_account(ra, RA_EVENT_READAHEAD_EOF, actual);
+ if (la_size)
+ ra_account(ra, RA_EVENT_LOOKAHEAD, la_size);
+ if (ra_size > actual)
+ ra_account(ra, RA_EVENT_IO_CACHE_HIT, ra_size - actual);
+ ra_account(ra, RA_EVENT_READAHEAD, actual);
+
+ dprintk("readahead-%s(ino=%lu, index=%lu:%lu, size=%lu-%lu) = %d\n",
+ ra_class_name[ra_class_new(ra)],
+ mapping->host->i_ino, ra->la_index,
+ ra->ra_index, ra_size, la_size, actual);
+#endif /* CONFIG_DEBUG_READAHEAD */
+
+ return actual;
+}
+
+/*
* ra_min is mainly determined by the size of cache memory. Reasonable?
*
* Table of concrete numbers for 4KB page size:
@@ -855,10 +1004,10 @@ static void ra_account(struct file_ra_st
return;
if (e == RA_EVENT_READAHEAD_HIT && pages < 0) {
- c = (ra->flags >> RA_CLASS_SHIFT) & RA_CLASS_MASK;
+ c = ra_class_old(ra);
pages = -pages;
} else if (ra)
- c = ra->flags & RA_CLASS_MASK;
+ c = ra_class_new(ra);
else
c = RA_CLASS_NONE;
_
Patches currently in -mm which might be from wfg@xxxxxxxxxxxxxxxx are
readahead-kconfig-options.patch
radixtree-introduce-scan-hole-data-functions.patch
mm-introduce-probe_page.patch
mm-introduce-pg_readahead.patch
readahead-add-look-ahead-support-to-__do_page_cache_readahead.patch
readahead-insert-cond_resched-calls.patch
readahead-minmax_ra_pages.patch
readahead-events-accounting.patch
readahead-rescue_pages.patch
readahead-sysctl-parameters.patch
readahead-min-max-sizes.patch
readahead-state-based-method-aging-accounting.patch
readahead-state-based-method-routines.patch
readahead-state-based-method.patch
readahead-context-based-method.patch
readahead-initial-method-guiding-sizes.patch
readahead-initial-method-thrashing-guard-size.patch
readahead-initial-method-user-recommended-size.patch
readahead-initial-method.patch
readahead-backward-prefetching-method.patch
readahead-thrashing-recovery-method.patch
readahead-call-scheme.patch
readahead-laptop-mode.patch
readahead-loop-case.patch
readahead-nfsd-case.patch
readahead-turn-on-by-default.patch
readahead-remove-size-limit-on-read_ahead_kb.patch
readahead-remove-size-limit-of-max_sectors_kb-on-read_ahead_kb.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
