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, 122 insertions, 2 deletions

diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 72e8071f9d73..c06f75f54718 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -24,6 +24,21 @@ struct zcomp_strm_single {
         struct zcomp_strm *zstrm;
 };
 
+/*
+ * multi zcomp_strm backend
+ */
+struct zcomp_strm_multi {
+        /* protect strm list */
+        spinlock_t strm_lock;
+        /* max possible number of zstrm streams */
+        int max_strm;
+        /* number of available zstrm streams */
+        int avail_strm;
+        /* list of available strms */
+        struct list_head idle_strm;
+        wait_queue_head_t strm_wait;
+};
+
 static struct zcomp_backend *find_backend(const char *compress)
 {
         if (strncmp(compress, "lzo", 3) == 0)
@@ -62,6 +77,107 @@ static struct zcomp_strm *zcomp_strm_alloc(struct zcomp *comp)
         return zstrm;
 }
 
+/*
+ * get idle zcomp_strm or wait until other process release
+ * (zcomp_strm_release()) one for us
+ */
+static struct zcomp_strm *zcomp_strm_multi_find(struct zcomp *comp)
+{
+        struct zcomp_strm_multi *zs = comp->stream;
+        struct zcomp_strm *zstrm;
+
+        while (1) {
+                spin_lock(&zs->strm_lock);
+                if (!list_empty(&zs->idle_strm)) {
+                        zstrm = list_entry(zs->idle_strm.next,
+                                        struct zcomp_strm, list);
+                        list_del(&zstrm->list);
+                        spin_unlock(&zs->strm_lock);
+                        return zstrm;
+                }
+                /* zstrm streams limit reached, wait for idle stream */
+                if (zs->avail_strm >= zs->max_strm) {
+                        spin_unlock(&zs->strm_lock);
+                        wait_event(zs->strm_wait, !list_empty(&zs->idle_strm));
+                        continue;
+                }
+                /* allocate new zstrm stream */
+                zs->avail_strm++;
+                spin_unlock(&zs->strm_lock);
+
+                zstrm = zcomp_strm_alloc(comp);
+                if (!zstrm) {
+                        spin_lock(&zs->strm_lock);
+                        zs->avail_strm--;
+                        spin_unlock(&zs->strm_lock);
+                        wait_event(zs->strm_wait, !list_empty(&zs->idle_strm));
+                        continue;
+                }
+                break;
+        }
+        return zstrm;
+}
+
+/* add stream back to idle list and wake up waiter or free the stream */
+static void zcomp_strm_multi_release(struct zcomp *comp, struct zcomp_strm *zstrm)
+{
+        struct zcomp_strm_multi *zs = comp->stream;
+
+        spin_lock(&zs->strm_lock);
+        if (zs->avail_strm <= zs->max_strm) {
+                list_add(&zstrm->list, &zs->idle_strm);
+                spin_unlock(&zs->strm_lock);
+                wake_up(&zs->strm_wait);
+                return;
+        }
+
+        zs->avail_strm--;
+        spin_unlock(&zs->strm_lock);
+        zcomp_strm_free(comp, zstrm);
+}
+
+static void zcomp_strm_multi_destroy(struct zcomp *comp)
+{
+        struct zcomp_strm_multi *zs = comp->stream;
+        struct zcomp_strm *zstrm;
+
+        while (!list_empty(&zs->idle_strm)) {
+                zstrm = list_entry(zs->idle_strm.next,
+                                struct zcomp_strm, list);
+                list_del(&zstrm->list);
+                zcomp_strm_free(comp, zstrm);
+        }
+        kfree(zs);
+}
+
+static int zcomp_strm_multi_create(struct zcomp *comp, int max_strm)
+{
+        struct zcomp_strm *zstrm;
+        struct zcomp_strm_multi *zs;
+
+        comp->destroy = zcomp_strm_multi_destroy;
+        comp->strm_find = zcomp_strm_multi_find;
+        comp->strm_release = zcomp_strm_multi_release;
+        zs = kmalloc(sizeof(struct zcomp_strm_multi), GFP_KERNEL);
+        if (!zs)
+                return -ENOMEM;
+
+        comp->stream = zs;
+        spin_lock_init(&zs->strm_lock);
+        INIT_LIST_HEAD(&zs->idle_strm);
+        init_waitqueue_head(&zs->strm_wait);
+        zs->max_strm = max_strm;
+        zs->avail_strm = 1;
+
+        zstrm = zcomp_strm_alloc(comp);
+        if (!zstrm) {
+                kfree(zs);
+                return -ENOMEM;
+        }
+        list_add(&zstrm->list, &zs->idle_strm);
+        return 0;
+}
+
 static struct zcomp_strm *zcomp_strm_single_find(struct zcomp *comp)
 {
         struct zcomp_strm_single *zs = comp->stream;
@@ -139,7 +255,7 @@ void zcomp_destroy(struct zcomp *comp)
  * if requested algorithm is not supported or in case
  * of init error
  */
-struct zcomp *zcomp_create(const char *compress)
+struct zcomp *zcomp_create(const char *compress, int max_strm)
 {
         struct zcomp *comp;
         struct zcomp_backend *backend;
@@ -153,7 +269,11 @@ struct zcomp *zcomp_create(const char *compress)
                 return NULL;
 
         comp->backend = backend;
-        if (zcomp_strm_single_create(comp) != 0) {
+        if (max_strm > 1)
+                zcomp_strm_multi_create(comp, max_strm);
+        else
+                zcomp_strm_single_create(comp);
+        if (!comp->stream) {
                 kfree(comp);
                 return NULL;
         }