zram: add multi stream functionality

Existing zram (zcomp) implementation has only one compression stream
(buffer and algorithm private part), so in order to prevent data
corruption only one write (compress operation) can use this compression
stream, forcing all concurrent write operations to wait for stream lock
to be released.  This patch changes zcomp to keep a compression streams
list of user-defined size (via sysfs device attr).  Each write operation
still exclusively holds compression stream, the difference is that we
can have N write operations (depending on size of streams list)
executing in parallel.  See TEST section later in commit message for
performance data.

Introduce struct zcomp_strm_multi and a set of functions to manage
zcomp_strm stream access.  zcomp_strm_multi has a list of idle
zcomp_strm structs, spinlock to protect idle list and wait queue, making
it possible to perform parallel compressions.

The following set of functions added:
- zcomp_strm_multi_find()/zcomp_strm_multi_release()
  find and release a compression stream, implement required locking
- zcomp_strm_multi_create()/zcomp_strm_multi_destroy()
  create and destroy zcomp_strm_multi

zcomp ->strm_find() and ->strm_release() callbacks are set during
initialisation to zcomp_strm_multi_find()/zcomp_strm_multi_release()
correspondingly.

Each time zcomp issues a zcomp_strm_multi_find() call, the following set
of operations performed:

- spin lock strm_lock
- if idle list is not empty, remove zcomp_strm from idle list, spin
  unlock and return zcomp stream pointer to caller
- if idle list is empty, current adds itself to wait queue. it will be
  awaken by zcomp_strm_multi_release() caller.

zcomp_strm_multi_release():
- spin lock strm_lock
- add zcomp stream to idle list
- spin unlock, wake up sleeper

Minchan Kim reported that spinlock-based locking scheme has demonstrated
a severe perfomance regression for single compression stream case,
comparing to mutex-based (see https://lkml.org/lkml/2014/2/18/16)

base                      spinlock                    mutex

==Initial write           ==Initial write             ==Initial  write
records:  5               records:  5                 records:   5
avg:      1642424.35      avg:      699610.40         avg:       1655583.71
std:      39890.95(2.43%) std:      232014.19(33.16%) std:       52293.96
max:      1690170.94      max:      1163473.45        max:       1697164.75
min:      1568669.52      min:      573429.88         min:       1553410.23
==Rewrite                 ==Rewrite                   ==Rewrite
records:  5               records:  5                 records:   5
avg:      1611775.39      avg:      501406.64         avg:       1684419.11
std:      17144.58(1.06%) std:      15354.41(3.06%)   std:       18367.42
max:      1641800.95      max:      531356.78         max:       1706445.84
min:      1593515.27      min:      488817.78         min:       1655335.73

When only one compression stream available, mutex with spin on owner
tends to perform much better than frequent wait_event()/wake_up().  This
is why single stream implemented as a special case with mutex locking.

Introduce and document zram device attribute max_comp_streams.  This
attr shows and stores current zcomp's max number of zcomp streams
(max_strm).  Extend zcomp's zcomp_create() with `max_strm' parameter.
`max_strm' limits the number of zcomp_strm structs in compression
backend's idle list (max_comp_streams).

max_comp_streams used during initialisation as follows:
-- passing to zcomp_create() max_strm equals to 1 will initialise zcomp
using single compression stream zcomp_strm_single (mutex-based locking).
-- passing to zcomp_create() max_strm greater than 1 will initialise zcomp
using multi compression stream zcomp_strm_multi (spinlock-based locking).

default max_comp_streams value is 1, meaning that zram with single stream
will be initialised.

Later patch will introduce configuration knob to change max_comp_streams
on already initialised and used zcomp.

TEST
iozone -t 3 -R -r 16K -s 60M -I +Z

       test           base       1 strm (mutex)     3 strm (spinlock)
-----------------------------------------------------------------------
 Initial write      589286.78       583518.39          718011.05
       Rewrite      604837.97       596776.38         1515125.72
  Random write      584120.11       595714.58         1388850.25
        Pwrite      535731.17       541117.38          739295.27
        Fwrite     1418083.88      1478612.72         1484927.06

Usage example:
set max_comp_streams to 4
        echo 4 > /sys/block/zram0/max_comp_streams

show current max_comp_streams (default value is 1).
        cat /sys/block/zram0/max_comp_streams

Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Minchan Kim <minchan@kernel.org>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Nitin Gupta <ngupta@vflare.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 41 insertions, 1 deletions

diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 98823f9ca8b..bdc7eb8c6df 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -108,6 +108,40 @@ static ssize_t mem_used_total_show(struct device *dev,
 	return sprintf(buf, "%llu\n", val);
 }
 
+static ssize_t max_comp_streams_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	int val;
+	struct zram *zram = dev_to_zram(dev);
+
+	down_read(&zram->init_lock);
+	val = zram->max_comp_streams;
+	up_read(&zram->init_lock);
+
+	return sprintf(buf, "%d\n", val);
+}
+
+static ssize_t max_comp_streams_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t len)
+{
+	int num;
+	struct zram *zram = dev_to_zram(dev);
+
+	if (kstrtoint(buf, 0, &num))
+		return -EINVAL;
+	if (num < 1)
+		return -EINVAL;
+	down_write(&zram->init_lock);
+	if (init_done(zram)) {
+		up_write(&zram->init_lock);
+		pr_info("Can't set max_comp_streams for initialized device\n");
+		return -EBUSY;
+	}
+	zram->max_comp_streams = num;
+	up_write(&zram->init_lock);
+	return len;
+}
+
 /* flag operations needs meta->tb_lock */
 static int zram_test_flag(struct zram_meta *meta, u32 index,
 			enum zram_pageflags flag)
@@ -502,6 +536,8 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity)
 	}
 
 	zcomp_destroy(zram->comp);
+	zram->max_comp_streams = 1;
+
 	zram_meta_free(zram->meta);
 	zram->meta = NULL;
 	/* Reset stats */
@@ -537,7 +573,7 @@ static ssize_t disksize_store(struct device *dev,
 		goto out_free_meta;
 	}
 
-	zram->comp = zcomp_create(default_compressor);
+	zram->comp = zcomp_create(default_compressor, zram->max_comp_streams);
 	if (!zram->comp) {
 		pr_info("Cannot initialise %s compressing backend\n",
 				default_compressor);
@@ -698,6 +734,8 @@ static DEVICE_ATTR(initstate, S_IRUGO, initstate_show, NULL);
 static DEVICE_ATTR(reset, S_IWUSR, NULL, reset_store);
 static DEVICE_ATTR(orig_data_size, S_IRUGO, orig_data_size_show, NULL);
 static DEVICE_ATTR(mem_used_total, S_IRUGO, mem_used_total_show, NULL);
+static DEVICE_ATTR(max_comp_streams, S_IRUGO | S_IWUSR,
+		max_comp_streams_show, max_comp_streams_store);
 
 ZRAM_ATTR_RO(num_reads);
 ZRAM_ATTR_RO(num_writes);
@@ -722,6 +760,7 @@ static struct attribute *zram_disk_attrs[] = {
 	&dev_attr_orig_data_size.attr,
 	&dev_attr_compr_data_size.attr,
 	&dev_attr_mem_used_total.attr,
+	&dev_attr_max_comp_streams.attr,
 	NULL,
 };
 
@@ -784,6 +823,7 @@ static int create_device(struct zram *zram, int device_id)
 	}
 
 	zram->meta = NULL;
+	zram->max_comp_streams = 1;
 	return 0;
 
 out_free_disk: