readahead: make context readahead more conservative

This helps performance on moderately dense random reads on SSD.

Transaction-Per-Second numbers provided by Taobao:

		QPS	case
		-------------------------------------------------------
		7536	disable context readahead totally

w/ patch: 7129 slower size rampup and start RA on the 3rd read
6717 slower size rampup
w/o patch: 5581 unmodified context readahead

Before, readahead will be started whenever reading page N+1 when it happen to read N recently. After patch, we'll only start readahead when *three* random reads happen to access pages N, N+1, N+2. The probability of this happening is extremely low for pure random reads, unless they are very dense, which actually deserves some readahead.

Also start with a smaller readahead window. The impact to interleaved sequential reads should be small, because for a long run stream, the the small readahead window rampup phase is negletable.

The context readahead actually benefits clustered random reads on HDD whose seek cost is pretty high. However as SSD is increasingly used for random read workloads it's better for the context readahead to concentrate on interleaved sequential reads.

Another SSD rand read test from Miao

        # file size:        2GB
        # read IO amount: 625MB
        sysbench --test=fileio          \
                --max-requests=10000    \
                --num-threads=1         \
                --file-num=1            \
                --file-block-size=64K   \
                --file-test-mode=rndrd  \
                --file-fsync-freq=0     \
                --file-fsync-end=off    run

shows the performance of btrfs grows up from 69MB/s to 121MB/s, ext4 from 104MB/s to 121MB/s.

Tested-by Tao Ma <[email protected]>

Tested-by Miao Xie <[email protected]>

Signed-off-by Wu Fengguang <[email protected]>

---
 mm/readahead.c |    8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

mm/readahead.c +2 -2

@@ -371,10 +371,10 @@ static int try_context_readahead(struct
 	size = count_history_pages(mapping, ra, offset, max);
 
 	/*
-	 * no history pages:
+	 * not enough history pages:
 	 * it could be a random read
 	 */
-	if (!size)
+	if (size <= req_size)
 		return 0;
 
 	/*

Hi, everyone

Quoted 39 lines · Fengguang Wu

This helps performance on moderately dense random reads on SSD.

Transaction-Per-Second numbers provided by Taobao:

		QPS	case
		-------------------------------------------------------
		7536	disable context readahead totally

w/ patch: 7129 slower size rampup and start RA on the 3rd read
6717 slower size rampup
w/o patch: 5581 unmodified context readahead

Before, readahead will be started whenever reading page N+1 when it happen to read N recently. After patch, we'll only start readahead when *three* random reads happen to access pages N, N+1, N+2. The probability of this happening is extremely low for pure random reads, unless they are very dense, which actually deserves some readahead.

Also start with a smaller readahead window. The impact to interleaved sequential reads should be small, because for a long run stream, the the small readahead window rampup phase is negletable.

The context readahead actually benefits clustered random reads on HDD whose seek cost is pretty high. However as SSD is increasingly used for random read workloads it's better for the context readahead to concentrate on interleaved sequential reads.

Another SSD rand read test from Miao

        # file size:        2GB
        # read IO amount: 625MB
        sysbench --test=fileio          \
                --max-requests=10000    \
                --num-threads=1         \
                --file-num=1            \
                --file-block-size=64K   \
                --file-test-mode=rndrd  \
                --file-fsync-freq=0     \
                --file-fsync-end=off    run

Quoted 2 lines

shows the performance of btrfs grows up from 69MB/s to 121MB/s, ext4 from 104MB/s to 121MB/s.

I did the same test on the hard disk recently,
for btrfs, there is ~5% regression(10.65MB/s -> 10.09MB/s),
for ext4, the performance grows up a bit.(9.98MB/s -> 10.04MB/s). (I run the test for 4 times, and the above result is the average of the test.)

Any comment?