From 722cdc17232f0f684011407f7cf3c40d39457971 Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 9 Oct 2014 15:29:50 -0700 Subject: zsmalloc: change return value unit of zs_get_total_size_bytes zs_get_total_size_bytes returns a amount of memory zsmalloc consumed with *byte unit* but zsmalloc operates *page unit* rather than byte unit so let's change the API so benefit we could get is that reduce unnecessary overhead (ie, change page unit with byte unit) in zsmalloc. Since return type is pages, "zs_get_total_pages" is better than "zs_get_total_size_bytes". Signed-off-by: Minchan Kim Reviewed-by: Dan Streetman Cc: Sergey Senozhatsky Cc: Jerome Marchand Cc: Cc: Cc: Luigi Semenzato Cc: Nitin Gupta Cc: Seth Jennings Cc: David Horner Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/block/zram/zram_drv.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/block/zram/zram_drv.c') diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index d00831c3d731..f0b8b30a7128 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -103,10 +103,10 @@ static ssize_t mem_used_total_show(struct device *dev, down_read(&zram->init_lock); if (init_done(zram)) - val = zs_get_total_size_bytes(meta->mem_pool); + val = zs_get_total_pages(meta->mem_pool); up_read(&zram->init_lock); - return scnprintf(buf, PAGE_SIZE, "%llu\n", val); + return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT); } static ssize_t max_comp_streams_show(struct device *dev, -- cgit v1.2.3 From 9ada9da9573f3460b156b7755c093e30b258eacb Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 9 Oct 2014 15:29:53 -0700 Subject: zram: zram memory size limitation Since zram has no control feature to limit memory usage, it makes hard to manage system memrory. This patch adds new knob "mem_limit" via sysfs to set up the a limit so that zram could fail allocation once it reaches the limit. In addition, user could change the limit in runtime so that he could manage the memory more dynamically. Initial state is no limit so it doesn't break old behavior. [akpm@linux-foundation.org: fix typo, per Sergey] Signed-off-by: Minchan Kim Cc: Dan Streetman Cc: Sergey Senozhatsky Cc: Jerome Marchand Cc: Cc: Cc: Luigi Semenzato Cc: Nitin Gupta Cc: Seth Jennings Cc: David Horner Cc: Joonsoo Kim Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/ABI/testing/sysfs-block-zram | 9 ++++++ Documentation/blockdev/zram.txt | 24 +++++++++++++--- drivers/block/zram/zram_drv.c | 45 ++++++++++++++++++++++++++++++ drivers/block/zram/zram_drv.h | 5 ++++ 4 files changed, 79 insertions(+), 4 deletions(-) (limited to 'drivers/block/zram/zram_drv.c') diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram index 70ec992514d0..ea67fa3f3cff 100644 --- a/Documentation/ABI/testing/sysfs-block-zram +++ b/Documentation/ABI/testing/sysfs-block-zram @@ -119,3 +119,12 @@ Description: efficiency can be calculated using compr_data_size and this statistic. Unit: bytes + +What: /sys/block/zram/mem_limit +Date: August 2014 +Contact: Minchan Kim +Description: + The mem_limit file is read/write and specifies the maximum + amount of memory ZRAM can use to store the compressed data. The + limit could be changed in run time and "0" means disable the + limit. No limit is the initial state. Unit: bytes diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt index 0595c3f56ccf..82c6a41116db 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.txt @@ -74,14 +74,30 @@ There is little point creating a zram of greater than twice the size of memory since we expect a 2:1 compression ratio. Note that zram uses about 0.1% of the size of the disk when not in use so a huge zram is wasteful. -5) Activate: +5) Set memory limit: Optional + Set memory limit by writing the value to sysfs node 'mem_limit'. + The value can be either in bytes or you can use mem suffixes. + In addition, you could change the value in runtime. + Examples: + # limit /dev/zram0 with 50MB memory + echo $((50*1024*1024)) > /sys/block/zram0/mem_limit + + # Using mem suffixes + echo 256K > /sys/block/zram0/mem_limit + echo 512M > /sys/block/zram0/mem_limit + echo 1G > /sys/block/zram0/mem_limit + + # To disable memory limit + echo 0 > /sys/block/zram0/mem_limit + +6) Activate: mkswap /dev/zram0 swapon /dev/zram0 mkfs.ext4 /dev/zram1 mount /dev/zram1 /tmp -6) Stats: +7) Stats: Per-device statistics are exported as various nodes under /sys/block/zram/ disksize @@ -96,11 +112,11 @@ size of the disk when not in use so a huge zram is wasteful. compr_data_size mem_used_total -7) Deactivate: +8) Deactivate: swapoff /dev/zram0 umount /dev/zram1 -8) Reset: +9) Reset: Write any positive value to 'reset' sysfs node echo 1 > /sys/block/zram0/reset echo 1 > /sys/block/zram1/reset diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index f0b8b30a7128..64b27cf9a583 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -122,6 +122,37 @@ static ssize_t max_comp_streams_show(struct device *dev, return scnprintf(buf, PAGE_SIZE, "%d\n", val); } +static ssize_t mem_limit_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u64 val; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + val = zram->limit_pages; + up_read(&zram->init_lock); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT); +} + +static ssize_t mem_limit_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + u64 limit; + char *tmp; + struct zram *zram = dev_to_zram(dev); + + limit = memparse(buf, &tmp); + if (buf == tmp) /* no chars parsed, invalid input */ + return -EINVAL; + + down_write(&zram->init_lock); + zram->limit_pages = PAGE_ALIGN(limit) >> PAGE_SHIFT; + up_write(&zram->init_lock); + + return len; +} + static ssize_t max_comp_streams_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { @@ -513,6 +544,14 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, ret = -ENOMEM; goto out; } + + if (zram->limit_pages && + zs_get_total_pages(meta->mem_pool) > zram->limit_pages) { + zs_free(meta->mem_pool, handle); + ret = -ENOMEM; + goto out; + } + cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO); if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) { @@ -617,6 +656,9 @@ static void zram_reset_device(struct zram *zram, bool reset_capacity) struct zram_meta *meta; down_write(&zram->init_lock); + + zram->limit_pages = 0; + if (!init_done(zram)) { up_write(&zram->init_lock); return; @@ -857,6 +899,8 @@ 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(mem_limit, S_IRUGO | S_IWUSR, mem_limit_show, + mem_limit_store); static DEVICE_ATTR(max_comp_streams, S_IRUGO | S_IWUSR, max_comp_streams_show, max_comp_streams_store); static DEVICE_ATTR(comp_algorithm, S_IRUGO | S_IWUSR, @@ -885,6 +929,7 @@ 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_mem_limit.attr, &dev_attr_max_comp_streams.attr, &dev_attr_comp_algorithm.attr, NULL, diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index e0f725c87cc6..b7aa9c21553f 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -112,6 +112,11 @@ struct zram { u64 disksize; /* bytes */ int max_comp_streams; struct zram_stats stats; + /* + * the number of pages zram can consume for storing compressed data + */ + unsigned long limit_pages; + char compressor[10]; }; #endif -- cgit v1.2.3 From 461a8eee6af3b55745be64bea403ed0b743563cf Mon Sep 17 00:00:00 2001 From: Minchan Kim Date: Thu, 9 Oct 2014 15:29:55 -0700 Subject: zram: report maximum used memory Normally, zram user could get maximum memory usage zram consumed via polling mem_used_total with sysfs in userspace. But it has a critical problem because user can miss peak memory usage during update inverval of polling. For avoiding that, user should poll it with shorter interval(ie, 0.0000000001s) with mlocking to avoid page fault delay when memory pressure is heavy. It would be troublesome. This patch adds new knob "mem_used_max" so user could see the maximum memory usage easily via reading the knob and reset it via "echo 0 > /sys/block/zram0/mem_used_max". Signed-off-by: Minchan Kim Reviewed-by: Dan Streetman Cc: Sergey Senozhatsky Cc: Jerome Marchand Cc: Cc: Cc: Luigi Semenzato Cc: Nitin Gupta Cc: Seth Jennings Reviewed-by: David Horner Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/ABI/testing/sysfs-block-zram | 10 +++++ Documentation/blockdev/zram.txt | 1 + drivers/block/zram/zram_drv.c | 60 +++++++++++++++++++++++++++++- drivers/block/zram/zram_drv.h | 1 + 4 files changed, 70 insertions(+), 2 deletions(-) (limited to 'drivers/block/zram/zram_drv.c') diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram index ea67fa3f3cff..b13dc993291f 100644 --- a/Documentation/ABI/testing/sysfs-block-zram +++ b/Documentation/ABI/testing/sysfs-block-zram @@ -120,6 +120,16 @@ Description: statistic. Unit: bytes +What: /sys/block/zram/mem_used_max +Date: August 2014 +Contact: Minchan Kim +Description: + The mem_used_max file is read/write and specifies the amount + of maximum memory zram have consumed to store compressed data. + For resetting the value, you should write "0". Otherwise, + you could see -EINVAL. + Unit: bytes + What: /sys/block/zram/mem_limit Date: August 2014 Contact: Minchan Kim diff --git a/Documentation/blockdev/zram.txt b/Documentation/blockdev/zram.txt index 82c6a41116db..7fcf9c6592ec 100644 --- a/Documentation/blockdev/zram.txt +++ b/Documentation/blockdev/zram.txt @@ -111,6 +111,7 @@ size of the disk when not in use so a huge zram is wasteful. orig_data_size compr_data_size mem_used_total + mem_used_max 8) Deactivate: swapoff /dev/zram0 diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 64b27cf9a583..d78b245bae06 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -153,6 +153,41 @@ static ssize_t mem_limit_store(struct device *dev, return len; } +static ssize_t mem_used_max_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + u64 val = 0; + struct zram *zram = dev_to_zram(dev); + + down_read(&zram->init_lock); + if (init_done(zram)) + val = atomic_long_read(&zram->stats.max_used_pages); + up_read(&zram->init_lock); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", val << PAGE_SHIFT); +} + +static ssize_t mem_used_max_store(struct device *dev, + struct device_attribute *attr, const char *buf, size_t len) +{ + int err; + unsigned long val; + struct zram *zram = dev_to_zram(dev); + struct zram_meta *meta = zram->meta; + + err = kstrtoul(buf, 10, &val); + if (err || val != 0) + return -EINVAL; + + down_read(&zram->init_lock); + if (init_done(zram)) + atomic_long_set(&zram->stats.max_used_pages, + zs_get_total_pages(meta->mem_pool)); + up_read(&zram->init_lock); + + return len; +} + static ssize_t max_comp_streams_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { @@ -465,6 +500,21 @@ out_cleanup: return ret; } +static inline void update_used_max(struct zram *zram, + const unsigned long pages) +{ + int old_max, cur_max; + + old_max = atomic_long_read(&zram->stats.max_used_pages); + + do { + cur_max = old_max; + if (pages > cur_max) + old_max = atomic_long_cmpxchg( + &zram->stats.max_used_pages, cur_max, pages); + } while (old_max != cur_max); +} + static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, int offset) { @@ -476,6 +526,7 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, struct zram_meta *meta = zram->meta; struct zcomp_strm *zstrm; bool locked = false; + unsigned long alloced_pages; page = bvec->bv_page; if (is_partial_io(bvec)) { @@ -545,13 +596,15 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, goto out; } - if (zram->limit_pages && - zs_get_total_pages(meta->mem_pool) > zram->limit_pages) { + alloced_pages = zs_get_total_pages(meta->mem_pool); + if (zram->limit_pages && alloced_pages > zram->limit_pages) { zs_free(meta->mem_pool, handle); ret = -ENOMEM; goto out; } + update_used_max(zram, alloced_pages); + cmem = zs_map_object(meta->mem_pool, handle, ZS_MM_WO); if ((clen == PAGE_SIZE) && !is_partial_io(bvec)) { @@ -901,6 +954,8 @@ 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(mem_limit, S_IRUGO | S_IWUSR, mem_limit_show, mem_limit_store); +static DEVICE_ATTR(mem_used_max, S_IRUGO | S_IWUSR, mem_used_max_show, + mem_used_max_store); static DEVICE_ATTR(max_comp_streams, S_IRUGO | S_IWUSR, max_comp_streams_show, max_comp_streams_store); static DEVICE_ATTR(comp_algorithm, S_IRUGO | S_IWUSR, @@ -930,6 +985,7 @@ static struct attribute *zram_disk_attrs[] = { &dev_attr_compr_data_size.attr, &dev_attr_mem_used_total.attr, &dev_attr_mem_limit.attr, + &dev_attr_mem_used_max.attr, &dev_attr_max_comp_streams.attr, &dev_attr_comp_algorithm.attr, NULL, diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index b7aa9c21553f..c6ee271317f5 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -90,6 +90,7 @@ struct zram_stats { atomic64_t notify_free; /* no. of swap slot free notifications */ atomic64_t zero_pages; /* no. of zero filled pages */ atomic64_t pages_stored; /* no. of pages currently stored */ + atomic_long_t max_used_pages; /* no. of maximum pages stored */ }; struct zram_meta { -- cgit v1.2.3 From 015254daf1753003c19c46b90ee85a963260d270 Mon Sep 17 00:00:00 2001 From: Sergey Senozhatsky Date: Thu, 9 Oct 2014 15:29:57 -0700 Subject: zram: use notify_free to account all free notifications `notify_free' device attribute accounts the number of slot free notifications and internally represents the number of zram_free_page() calls. Slot free notifications are sent only when device is used as a swap device, hence `notify_free' is used only for swap devices. Since f4659d8e620d08 (zram: support REQ_DISCARD) ZRAM handles yet another one free notification (also via zram_free_page() call) -- REQ_DISCARD requests, which are sent by a filesystem, whenever some data blocks are discarded. However, there is no way to know the number of notifications in the latter case. Use `notify_free' to account the number of pages freed by zram_bio_discard() and zram_slot_free_notify(). Depending on usage scenario `notify_free' represents: a) the number of pages freed because of slot free notifications, which is equal to the number of swap_slot_free_notify() calls, so there is no behaviour change b) the number of pages freed because of REQ_DISCARD notifications Signed-off-by: Sergey Senozhatsky Acked-by: Minchan Kim Acked-by: Jerome Marchand Cc: Nitin Gupta Cc: Chao Yu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/ABI/testing/sysfs-block-zram | 13 ++++++++----- drivers/block/zram/zram_drv.c | 1 + 2 files changed, 9 insertions(+), 5 deletions(-) (limited to 'drivers/block/zram/zram_drv.c') diff --git a/Documentation/ABI/testing/sysfs-block-zram b/Documentation/ABI/testing/sysfs-block-zram index b13dc993291f..a6148eaf91e5 100644 --- a/Documentation/ABI/testing/sysfs-block-zram +++ b/Documentation/ABI/testing/sysfs-block-zram @@ -77,11 +77,14 @@ What: /sys/block/zram/notify_free Date: August 2010 Contact: Nitin Gupta Description: - The notify_free file is read-only and specifies the number of - swap slot free notifications received by this device. These - notifications are sent to a swap block device when a swap slot - is freed. This statistic is applicable only when this disk is - being used as a swap disk. + The notify_free file is read-only. Depending on device usage + scenario it may account a) the number of pages freed because + of swap slot free notifications or b) the number of pages freed + because of REQ_DISCARD requests sent by bio. The former ones + are sent to a swap block device when a swap slot is freed, which + implies that this disk is being used as a swap disk. The latter + ones are sent by filesystem mounted with discard option, + whenever some data blocks are getting discarded. What: /sys/block/zram/zero_pages Date: August 2010 diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index d78b245bae06..3b850164c65c 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -698,6 +698,7 @@ static void zram_bio_discard(struct zram *zram, u32 index, bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); zram_free_page(zram, index); bit_spin_unlock(ZRAM_ACCESS, &meta->table[index].value); + atomic64_inc(&zram->stats.notify_free); index++; n -= PAGE_SIZE; } -- cgit v1.2.3