fs: annotate refault stalls from bdev_read_page
Subsystems (3)
PATCH 1/1 fs: annotate refault stalls from bdev_read_page
From: Minchan Kim <[email protected]>
If block device supports rw_page operation, it doesn't submit bio so annotation in submit_bio for refault stall doesn't work. It happens with zram in android, especially swap read path which could consume CPU cycle for decompress.
Annotate bdev_read_page() to account the synchronous IO overhead to prevent underreport memory pressure.
--- fs/block_dev.c | 13 +++++++++++++ mm/memory.c | 1 + 2 files changed, 14 insertions(+)
fs/block_dev.c +13 -0
@@ -26,6 +26,7 @@#include <linux/writeback.h> #include <linux/mpage.h> #include <linux/mount.h> +#include <linux/psi.h> #include <linux/pseudo_fs.h> #include <linux/uio.h> #include <linux/namei.h>
@@ -701,6 +702,8 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, {const struct block_device_operations *ops = bdev->bd_disk->fops;int result = -EOPNOTSUPP ; +unsigned long pflags; +bool workingset_read;if (!ops->rw_page ||bdev_get_integrity (bdev))return result;
@@ -708,9 +711,19 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, result =blk_queue_enter (bdev->bd_queue,0 );if (result)return result; + + workingset_read =PageWorkingset (page); +if (workingset_read) +psi_memstall_enter (&pflags); + result = ops->rw_page (bdev, sector +get_start_sect (bdev), page,REQ_OP_READ ); + +if (workingset_read) +psi_memstall_leave (&pflags); +blk_queue_exit (bdev->bd_queue); +return result; }EXPORT_SYMBOL_GPL (bdev_read_page);
mm/memory.c +1 -0
@@ -2801,6 +2801,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)if (page) {__SetPageLocked (page);__SetPageSwapBacked (page); +SetPageWorkingset (page);set_page_private (page, entry.val);lru_cache_add_anon (page);swap_readpage (page, true);
Signature · 1 line
2.23.0.581.g78d2f28ef7-goog
Quoted 7 lines · Minchan Kim
From: Minchan Kim <[email protected]>
If block device supports
rw_pageoperation, it doesn't submit bio so annotation insubmit_biofor refault stall doesn't work. It happens with zram in android, especially swap read path which could consume CPU cycle for decompress.
What about zswap? Do we need the same in zswap_frontswap_load()?
Quoted 67 lines
Annotate
bdev_read_page()to account the synchronous IO overhead to prevent underreport memory pressure.Cc Johannes Weiner <[email protected]>Signed-off-by Minchan Kim <[email protected]>--- fs/block_dev.c | 13 +++++++++++++ mm/memory.c | 1 + 2 files changed, 14 insertions(+)fs/block_dev.c +13
-0@@ -26,6 +26,7 @@#include <linux/writeback.h> #include <linux/mpage.h> #include <linux/mount.h> +#include <linux/psi.h> #include <linux/pseudo_fs.h> #include <linux/uio.h> #include <linux/namei.h> @@ -701,6 +702,8 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, {const struct block_device_operations *ops = bdev->bd_disk->fops;int result = -EOPNOTSUPP ; +unsigned long pflags; +bool workingset_read;if (!ops->rw_page ||bdev_get_integrity (bdev))return result;@@ -708,9 +711,19 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, result =blk_queue_enter (bdev->bd_queue,0 );if (result)return result; + + workingset_read =PageWorkingset (page); +if (workingset_read) +psi_memstall_enter (&pflags); + result = ops->rw_page (bdev, sector +get_start_sect (bdev), page,REQ_OP_READ ); + +if (workingset_read) +psi_memstall_leave (&pflags); +blk_queue_exit (bdev->bd_queue); +return result; }EXPORT_SYMBOL_GPL (bdev_read_page);mm/memory.c +1
-1@@ -2801,6 +2801,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)if (page) {__SetPageLocked (page);__SetPageSwapBacked (page); +SetPageWorkingset (page);set_page_private (page, entry.val);lru_cache_add_anon (page);swap_readpage (page, true); --2.23.0.581.g78d2f28ef7-goog
Quoted 10 lines · Shakeel Butt
Quoted 7 lines · Minchan Kim
From: Minchan Kim <[email protected]>
If block device supports
rw_pageoperation, it doesn't submit bio so annotation insubmit_biofor refault stall doesn't work. It happens with zram in android, especially swap read path which could consume CPU cycle for decompress.What about zswap? Do we need the same in
zswap_frontswap_load()?
Yub, it needs it. Maybe, a annotation in swap_readpage will cover both all at once in real pratice unless we need to take care of nvdimms which supports rw_page operation.
Thanks.
Quoted 68 lines
Quoted 68 lines
Annotate
bdev_read_page()to account the synchronous IO overhead to prevent underreport memory pressure.Cc Johannes Weiner <[email protected]>Signed-off-by Minchan Kim <[email protected]>--- fs/block_dev.c | 13 +++++++++++++ mm/memory.c | 1 + 2 files changed, 14 insertions(+)fs/block_dev.c +13
-0@@ -26,6 +26,7 @@#include <linux/writeback.h> #include <linux/mpage.h> #include <linux/mount.h> +#include <linux/psi.h> #include <linux/pseudo_fs.h> #include <linux/uio.h> #include <linux/namei.h> @@ -701,6 +702,8 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, {const struct block_device_operations *ops = bdev->bd_disk->fops;int result = -EOPNOTSUPP ; +unsigned long pflags; +bool workingset_read;if (!ops->rw_page ||bdev_get_integrity (bdev))return result;@@ -708,9 +711,19 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, result =blk_queue_enter (bdev->bd_queue,0 );if (result)return result; + + workingset_read =PageWorkingset (page); +if (workingset_read) +psi_memstall_enter (&pflags); + result = ops->rw_page (bdev, sector +get_start_sect (bdev), page,REQ_OP_READ ); + +if (workingset_read) +psi_memstall_leave (&pflags); +blk_queue_exit (bdev->bd_queue); +return result; }EXPORT_SYMBOL_GPL (bdev_read_page);mm/memory.c +1
-1@@ -2801,6 +2801,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)if (page) {__SetPageLocked (page);__SetPageSwapBacked (page); +SetPageWorkingset (page);set_page_private (page, entry.val);lru_cache_add_anon (page);swap_readpage (page, true); --2.23.0.581.g78d2f28ef7-goog