From: Hui Zhu <zhuhui@xiaomi.com> To: <minchan@kernel.org>, <ngupta@vflare.org>, <sergey.senozhatsky.work@gmail.com>, <hughd@google.com>, <rostedt@goodmis.org>, <mingo@redhat.com>, <peterz@infradead.org>, <acme@kernel.org>, <alexander.shishkin@linux.intel.com>, <akpm@linux-foundation.org>, <mhocko@suse.com>, <hannes@cmpxchg.org>, <mgorman@techsingularity.net>, <vbabka@suse.cz>, <zhuhui@xiaomi.com>, <redkoi@virtuozzo.com>, <luto@kernel.org>, <kirill.shutemov@linux.intel.com>, <geliangtang@163.com>, <baiyaowei@cmss.chinamobile.com>, <dan.j.williams@intel.com>, <vdavydov@virtuozzo.com>, <aarcange@redhat.com>, <dvlasenk@redhat.com>, <jmarchan@redhat.com>, <koct9i@gmail.com>, <yang.shi@linaro.org>, <dave.hansen@linux.intel.com>, <vkuznets@redhat.com>, <vitalywool@gmail.com>, <ross.zwisler@linux.intel.com>, <tglx@linutronix.de>, <kwapulinski.piotr@gmail.com>, <axboe@fb.com>, <mchristi@redhat.com>, <joe@perches.com>, <namit@vmware.com>, <riel@redhat.com>, <linux-kernel@vger.kernel.org>, <linux-mm@kvack.org> Cc: <teawater@gmail.com> Subject: [RFC 3/4] ZRAM: do not swap the page that compressed size bigger than non_swap Date: Mon, 22 Aug 2016 16:25:08 +0800 [thread overview] Message-ID: <1471854309-30414-4-git-send-email-zhuhui@xiaomi.com> (raw) In-Reply-To: <1471854309-30414-1-git-send-email-zhuhui@xiaomi.com> New option ZRAM_NON_SWAP add a interface "non_swap" to zram. User can set a unsigned int value to zram. If a page that compressed size is bigger than limit, mark it as non-swap. Then this page will add to unevictable lru list. This patch doesn't handle the shmem file pages. Signed-off-by: Hui Zhu <zhuhui@xiaomi.com> --- drivers/block/zram/Kconfig | 11 +++++++++++ drivers/block/zram/zram_drv.c | 39 +++++++++++++++++++++++++++++++++++++++ drivers/block/zram/zram_drv.h | 4 ++++ 3 files changed, 54 insertions(+) diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index b8ecba6..525caaa 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -13,3 +13,14 @@ config ZRAM disks and maybe many more. See zram.txt for more information. + +config ZRAM_NON_SWAP + bool "Enable zram non-swap support" + depends on ZRAM + select NON_SWAP + default n + help + This option add a interface "non_swap" to zram. User can set + a unsigned int value to zram. + If a page that compressed size is bigger than limit, mark it as + non-swap. Then this page will add to unevictable lru list. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 04365b1..8f7f1ec 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -714,6 +714,14 @@ compress_again: goto out; } +#ifdef CONFIG_ZRAM_NON_SWAP + if (!is_partial_io(bvec) && PageAnon(page) && + zram->non_swap && clen > zram->non_swap) { + ret = 0; + SetPageNonSwap(page); + goto out; + } +#endif src = zstrm->buffer; if (unlikely(clen > max_zpage_size)) { clen = PAGE_SIZE; @@ -1180,6 +1188,31 @@ static const struct block_device_operations zram_devops = { .owner = THIS_MODULE }; +#ifdef CONFIG_ZRAM_NON_SWAP +static ssize_t non_swap_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct zram *zram = dev_to_zram(dev); + + return scnprintf(buf, PAGE_SIZE, "%u\n", zram->non_swap); +} + +static ssize_t non_swap_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t len) +{ + struct zram *zram = dev_to_zram(dev); + + zram->non_swap = (unsigned int)memparse(buf, NULL); + + if (zram->non_swap > max_zpage_size) + pr_warn("Nonswap should small than max_zpage_size %zu\n", + max_zpage_size); + + return len; +} +#endif + static DEVICE_ATTR_WO(compact); static DEVICE_ATTR_RW(disksize); static DEVICE_ATTR_RO(initstate); @@ -1190,6 +1223,9 @@ static DEVICE_ATTR_RW(mem_limit); static DEVICE_ATTR_RW(mem_used_max); static DEVICE_ATTR_RW(max_comp_streams); static DEVICE_ATTR_RW(comp_algorithm); +#ifdef CONFIG_ZRAM_NON_SWAP +static DEVICE_ATTR_RW(non_swap); +#endif static struct attribute *zram_disk_attrs[] = { &dev_attr_disksize.attr, @@ -1210,6 +1246,9 @@ static struct attribute *zram_disk_attrs[] = { &dev_attr_mem_used_max.attr, &dev_attr_max_comp_streams.attr, &dev_attr_comp_algorithm.attr, +#ifdef CONFIG_ZRAM_NON_SWAP + &dev_attr_non_swap.attr, +#endif &dev_attr_io_stat.attr, &dev_attr_mm_stat.attr, &dev_attr_debug_stat.attr, diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 74fcf10..bd5f38a 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -119,5 +119,9 @@ struct zram { * zram is claimed so open request will be failed */ bool claim; /* Protected by bdev->bd_mutex */ + +#ifdef CONFIG_ZRAM_NON_SWAP + unsigned int non_swap; +#endif }; #endif -- 1.9.1
WARNING: multiple messages have this Message-ID (diff)
From: Hui Zhu <zhuhui@xiaomi.com> To: minchan@kernel.org, ngupta@vflare.org, sergey.senozhatsky.work@gmail.com, hughd@google.com, rostedt@goodmis.org, mingo@redhat.com, peterz@infradead.org, acme@kernel.org, alexander.shishkin@linux.intel.com, akpm@linux-foundation.org, mhocko@suse.com, hannes@cmpxchg.org, mgorman@techsingularity.net, vbabka@suse.cz, zhuhui@xiaomi.com, redkoi@virtuozzo.com, luto@kernel.org, kirill.shutemov@linux.intel.com, geliangtang@163.com, baiyaowei@cmss.chinamobile.com, dan.j.williams@intel.com, vdavydov@virtuozzo.com, aarcange@redhat.com, dvlasenk@redhat.com, jmarchan@redhat.com, koct9i@gmail.com, yang.shi@linaro.org, dave.hansen@linux.intel.com, vkuznets@redhat.com, vitalywool@gmail.com, ross.zwisler@linux.intel.com, tglx@linutronix.de, kwapulinski.piotr@gmail.com, axboe@fb.com, mchristi@redhat.com, joe@perches.com, namit@vmware.com, riel@redhat.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org Cc: teawater@gmail.com Subject: [RFC 3/4] ZRAM: do not swap the page that compressed size bigger than non_swap Date: Mon, 22 Aug 2016 16:25:08 +0800 [thread overview] Message-ID: <1471854309-30414-4-git-send-email-zhuhui@xiaomi.com> (raw) In-Reply-To: <1471854309-30414-1-git-send-email-zhuhui@xiaomi.com> New option ZRAM_NON_SWAP add a interface "non_swap" to zram. User can set a unsigned int value to zram. If a page that compressed size is bigger than limit, mark it as non-swap. Then this page will add to unevictable lru list. This patch doesn't handle the shmem file pages. Signed-off-by: Hui Zhu <zhuhui@xiaomi.com> --- drivers/block/zram/Kconfig | 11 +++++++++++ drivers/block/zram/zram_drv.c | 39 +++++++++++++++++++++++++++++++++++++++ drivers/block/zram/zram_drv.h | 4 ++++ 3 files changed, 54 insertions(+) diff --git a/drivers/block/zram/Kconfig b/drivers/block/zram/Kconfig index b8ecba6..525caaa 100644 --- a/drivers/block/zram/Kconfig +++ b/drivers/block/zram/Kconfig @@ -13,3 +13,14 @@ config ZRAM disks and maybe many more. See zram.txt for more information. + +config ZRAM_NON_SWAP + bool "Enable zram non-swap support" + depends on ZRAM + select NON_SWAP + default n + help + This option add a interface "non_swap" to zram. User can set + a unsigned int value to zram. + If a page that compressed size is bigger than limit, mark it as + non-swap. Then this page will add to unevictable lru list. diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 04365b1..8f7f1ec 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -714,6 +714,14 @@ compress_again: goto out; } +#ifdef CONFIG_ZRAM_NON_SWAP + if (!is_partial_io(bvec) && PageAnon(page) && + zram->non_swap && clen > zram->non_swap) { + ret = 0; + SetPageNonSwap(page); + goto out; + } +#endif src = zstrm->buffer; if (unlikely(clen > max_zpage_size)) { clen = PAGE_SIZE; @@ -1180,6 +1188,31 @@ static const struct block_device_operations zram_devops = { .owner = THIS_MODULE }; +#ifdef CONFIG_ZRAM_NON_SWAP +static ssize_t non_swap_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct zram *zram = dev_to_zram(dev); + + return scnprintf(buf, PAGE_SIZE, "%u\n", zram->non_swap); +} + +static ssize_t non_swap_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t len) +{ + struct zram *zram = dev_to_zram(dev); + + zram->non_swap = (unsigned int)memparse(buf, NULL); + + if (zram->non_swap > max_zpage_size) + pr_warn("Nonswap should small than max_zpage_size %zu\n", + max_zpage_size); + + return len; +} +#endif + static DEVICE_ATTR_WO(compact); static DEVICE_ATTR_RW(disksize); static DEVICE_ATTR_RO(initstate); @@ -1190,6 +1223,9 @@ static DEVICE_ATTR_RW(mem_limit); static DEVICE_ATTR_RW(mem_used_max); static DEVICE_ATTR_RW(max_comp_streams); static DEVICE_ATTR_RW(comp_algorithm); +#ifdef CONFIG_ZRAM_NON_SWAP +static DEVICE_ATTR_RW(non_swap); +#endif static struct attribute *zram_disk_attrs[] = { &dev_attr_disksize.attr, @@ -1210,6 +1246,9 @@ static struct attribute *zram_disk_attrs[] = { &dev_attr_mem_used_max.attr, &dev_attr_max_comp_streams.attr, &dev_attr_comp_algorithm.attr, +#ifdef CONFIG_ZRAM_NON_SWAP + &dev_attr_non_swap.attr, +#endif &dev_attr_io_stat.attr, &dev_attr_mm_stat.attr, &dev_attr_debug_stat.attr, diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h index 74fcf10..bd5f38a 100644 --- a/drivers/block/zram/zram_drv.h +++ b/drivers/block/zram/zram_drv.h @@ -119,5 +119,9 @@ struct zram { * zram is claimed so open request will be failed */ bool claim; /* Protected by bdev->bd_mutex */ + +#ifdef CONFIG_ZRAM_NON_SWAP + unsigned int non_swap; +#endif }; #endif -- 1.9.1 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2016-08-22 8:44 UTC|newest] Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top 2016-08-22 8:25 [RFC 0/4] ZRAM: make it just store the high compression rate page Hui Zhu 2016-08-22 8:25 ` Hui Zhu 2016-08-22 8:25 ` [RFC 1/4] vmscan.c: shrink_page_list: unmap anon pages after pageout Hui Zhu 2016-08-22 8:25 ` Hui Zhu 2016-08-22 8:25 ` [RFC 2/4] Add non-swap page flag to mark a page will not swap Hui Zhu 2016-08-22 8:25 ` Hui Zhu 2016-09-06 15:35 ` Steven Rostedt 2016-09-06 15:35 ` Steven Rostedt 2016-08-22 8:25 ` Hui Zhu [this message] 2016-08-22 8:25 ` [RFC 3/4] ZRAM: do not swap the page that compressed size bigger than non_swap Hui Zhu 2016-08-22 8:25 ` [RFC 4/4] vmscan.c: zram: add non swap support for shmem file pages Hui Zhu 2016-08-22 8:25 ` Hui Zhu 2016-08-24 1:04 ` [RFC 0/4] ZRAM: make it just store the high compression rate page Minchan Kim 2016-08-24 1:04 ` Minchan Kim 2016-08-24 1:29 ` Hui Zhu 2016-08-24 1:29 ` Hui Zhu 2016-08-25 6:09 ` Sergey Senozhatsky 2016-08-25 6:09 ` Sergey Senozhatsky 2016-08-25 8:25 ` Hui Zhu 2016-08-25 8:25 ` Hui Zhu 2016-09-05 2:18 ` Minchan Kim 2016-09-05 2:18 ` Minchan Kim 2016-09-05 3:59 ` Sergey Senozhatsky 2016-09-05 3:59 ` Sergey Senozhatsky 2016-09-05 5:12 ` Hui Zhu 2016-09-05 5:12 ` Hui Zhu 2016-09-05 5:51 ` Minchan Kim 2016-09-05 5:51 ` Minchan Kim 2016-09-05 6:02 ` Hui Zhu 2016-09-05 6:02 ` Hui Zhu 2016-09-05 2:12 ` Minchan Kim 2016-09-05 2:12 ` Minchan Kim
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=1471854309-30414-4-git-send-email-zhuhui@xiaomi.com \ --to=zhuhui@xiaomi.com \ --cc=aarcange@redhat.com \ --cc=acme@kernel.org \ --cc=akpm@linux-foundation.org \ --cc=alexander.shishkin@linux.intel.com \ --cc=axboe@fb.com \ --cc=baiyaowei@cmss.chinamobile.com \ --cc=dan.j.williams@intel.com \ --cc=dave.hansen@linux.intel.com \ --cc=dvlasenk@redhat.com \ --cc=geliangtang@163.com \ --cc=hannes@cmpxchg.org \ --cc=hughd@google.com \ --cc=jmarchan@redhat.com \ --cc=joe@perches.com \ --cc=kirill.shutemov@linux.intel.com \ --cc=koct9i@gmail.com \ --cc=kwapulinski.piotr@gmail.com \ --cc=linux-kernel@vger.kernel.org \ --cc=linux-mm@kvack.org \ --cc=luto@kernel.org \ --cc=mchristi@redhat.com \ --cc=mgorman@techsingularity.net \ --cc=mhocko@suse.com \ --cc=minchan@kernel.org \ --cc=mingo@redhat.com \ --cc=namit@vmware.com \ --cc=ngupta@vflare.org \ --cc=peterz@infradead.org \ --cc=redkoi@virtuozzo.com \ --cc=riel@redhat.com \ --cc=ross.zwisler@linux.intel.com \ --cc=rostedt@goodmis.org \ --cc=sergey.senozhatsky.work@gmail.com \ --cc=teawater@gmail.com \ --cc=tglx@linutronix.de \ --cc=vbabka@suse.cz \ --cc=vdavydov@virtuozzo.com \ --cc=vitalywool@gmail.com \ --cc=vkuznets@redhat.com \ --cc=yang.shi@linaro.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.