mm, swap: Make VMA based swap readahead configurable
Subsystems (3)
PATCH 1/1 mm, swap: Make VMA based swap readahead configurable
From: Huang Ying <[email protected]>
This patch adds a new Kconfig option VMA_SWAP_READAHEAD and wraps VMA based swap readahead code inside #ifdef CONFIG_VMA_SWAP_READAHEAD/#endif. This is more friendly for tiny kernels. And as pointed to by Minchan Kim, give people who want to disable the swap readahead an opportunity to notice the changes to the swap readahead algorithm and the corresponding knobs.
--- include/linux/mm_types.h | 2 ++ include/linux/swap.h | 64 +++++++++++++++++++++++++----------------------- mm/Kconfig | 20 +++++++++++++++ mm/swap_state.c | 25 ++++++++++++------- 4 files changed, 72 insertions(+), 39 deletions(-)
include/linux/mm_types.h +2 -0
@@ -336,7 +336,9 @@ struct vm_area_struct {struct file * vm_file;/* File we map to (can be NULL). */ void * vm_private_data;/* was vm_pte (shared mem) */ +#ifdef CONFIG_VMA_SWAP_READAHEAD atomic_long_t swap_readahead_info; +#endif #ifndef CONFIG_MMU struct vm_region *vm_region;/* NOMMU mapping region */ #endif
include/linux/swap.h +34 -30
105 lines not on this page · raw message
mm/Kconfig +20 -0
@@ -434,6 +434,26 @@ config THP_SWAP For selection by architectures with reasonable THP sizes. +config VMA_SWAP_READAHEAD + bool "VMA based swap readahead" + depends on SWAP + default y + help + VMA based swap readahead detects page accessing pattern in a + VMA and adjust the swap readahead window for pages in the + VMA accordingly. It works better for more complex workload + compared with the original physical swap readahead. + + It can be controlled via the following sysfs interface, + + /sys/kernel/mm/swap/vma_ra_enabled + /sys/kernel/mm/swap/vma_ra_max_order + + If set to no, the original physical swap readahead will be + used. + + If unsure, say Y to enable VMA based swap readahead. + config TRANSPARENT_HUGE_PAGECACHE def_bool y depends on TRANSPARENT_HUGEPAGE
mm/swap_state.c +16 -9
@@ -37,11 +37,6 @@ static const struct address_space_operations swap_aops = {struct address_space *swapper_spaces[MAX_SWAPFILES ];static unsigned int nr_swapper_spaces[MAX_SWAPFILES ]; -bool swap_vma_readahead = true; - -#define SWAP_RA_MAX_ORDER_DEFAULT 3 - -static int swap_ra_max_order =SWAP_RA_MAX_ORDER_DEFAULT ;#define SWAP_RA_WIN_SHIFT (PAGE_SHIFT / 2)#define SWAP_RA_HITS_MASK ((1UL << SWAP_RA_WIN_SHIFT) - 1)
@@ -324,8 +319,7 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) {struct page *page; -unsigned long ra_info; -int win, hits, readahead; +int readahead; page =find_get_page (swap_address_space (entry),swp_offset (entry));
@@ -335,7 +329,11 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,if (unlikely (PageTransCompound (page)))return page; readahead =TestClearPageReadahead (page); +#ifdef CONFIG_VMA_SWAP_READAHEAD if (vma) { +unsigned long ra_info; +int win, hits; + ra_info =GET_SWAP_RA_VAL (vma); win =SWAP_RA_WIN (ra_info); hits =SWAP_RA_HITS (ra_info);
@@ -344,6 +342,7 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,atomic_long_set (&vma->swap_readahead_info, SWAP_RA_VAL(addr, win, hits)); } +#endif if (readahead) {count_vm_event (SWAP_RA_HIT );if (!vma)
@@ -625,6 +624,13 @@ void exit_swap_address_space(unsigned int type)kvfree (spaces); } +#ifdef CONFIG_VMA_SWAP_READAHEAD +bool swap_vma_readahead = true; + +#define SWAP_RA_MAX_ORDER_DEFAULT 3 + +static int swap_ra_max_order =SWAP_RA_MAX_ORDER_DEFAULT ; + static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma, unsigned long faddr, unsigned long lpfn,
@@ -751,8 +757,9 @@ struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask,return read_swap_cache_async (fentry, gfp_mask, vma, vmf->address, swap_ra->win ==1 ); } +#endif /* CONFIG_VMA_SWAP_READAHEAD */ -#ifdef CONFIG_SYSFS +#if defined(CONFIG_SYSFS ) && defined(CONFIG_VMA_SWAP_READAHEAD )static ssize_t vma_ra_enabled_show (struct kobject *kobj,struct kobj_attribute *attr,char *buf) {
@@ -830,4 +837,4 @@ static int __init swap_init_sysfs(void) return err; }subsys_initcall (swap_init_sysfs); -#endif +#endif /* defined(CONFIG_SYSFS) && defined(CONFIG_VMA_SWAP_READAHEAD) */
Signature · 7 lines
2.14.1 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Hi Huang,
Quoted 166 lines · Ying
From: Huang Ying <[email protected]>
This patch adds a new
KconfigoptionVMA_SWAP_READAHEADand wraps VMA based swap readahead code inside #ifdef CONFIG_VMA_SWAP_READAHEAD/#endif. This is more friendly for tiny kernels. And as pointed to by Minchan Kim, give people who want to disable the swap readahead an opportunity to notice the changes to the swap readahead algorithm and the corresponding knobs.Cc Johannes Weiner <[email protected]>Cc Rik van Riel <[email protected]>Cc Shaohua Li <[email protected]>Cc Hugh Dickins <[email protected]>Cc Fengguang Wu <[email protected]>Cc Tim Chen <[email protected]>Cc Dave Hansen <[email protected]>Suggested-by Minchan Kim <[email protected]>Signed-off-by "Huang, Ying" <[email protected]>--- include/linux/mm_types.h | 2 ++ include/linux/swap.h | 64 +++++++++++++++++++++++++----------------------- mm/Kconfig | 20 +++++++++++++++ mm/swap_state.c | 25 ++++++++++++------- 4 files changed, 72 insertions(+), 39 deletions(-)include/linux/mm_types.h +2
-0@@ -336,7 +336,9 @@ struct vm_area_struct {struct file * vm_file;/* File we map to (can be NULL). */ void * vm_private_data;/* was vm_pte (shared mem) */ +#ifdef CONFIG_VMA_SWAP_READAHEAD atomic_long_t swap_readahead_info; +#endif #ifndef CONFIG_MMU struct vm_region *vm_region;/* NOMMU mapping region */ #endif include/linux/swap.h +34
-30@@ -278,6 +278,7 @@ struct swap_info_struct {#endif struct vma_swap_readahead { +#ifdef CONFIG_VMA_SWAP_READAHEAD unsigned short win;unsigned short offset;unsigned short nr_pte;@@ -286,6 +287,7 @@ struct vma_swap_readahead {#else pte_t ptes[SWAP_RA_PTE_CACHE_SIZE ];#endif +#endif };/* linux/mm/workingset.c */ @@ -387,7 +389,6 @@ int generic_swapfile_activate(struct swap_info_struct *, struct file *,#define SWAP_ADDRESS_SPACE_SHIFT 14#define SWAP_ADDRESS_SPACE_PAGES (1 << SWAP_ADDRESS_SPACE_SHIFT)extern struct address_space *swapper_spaces[]; -extern bool swap_vma_readahead;#define swap_address_space (entry) \ (&swapper_spaces[swp_type(entry)][swp_offset(entry) \ >> SWAP_ADDRESS_SPACE_SHIFT])@@ -412,23 +413,12 @@ extern struct page *__read_swap_cache_async(swp_entry_t, gfp_t,extern struct page *swapin_readahead (swp_entry_t ,gfp_t ,struct vm_area_struct *vma,unsigned long addr); -extern struct page *swap_readahead_detect (struct vm_fault *vmf, -struct vma_swap_readahead *swap_ra); -extern struct page *do_swap_page_readahead (swp_entry_t fentry,gfp_t gfp_mask, -struct vm_fault *vmf, -struct vma_swap_readahead *swap_ra); -/* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages;extern long total_swap_pages;extern atomic_t nr_rotate_swap;extern bool has_usable_swap (void ); -static inline bool swap_use_vma_readahead (void ) -{ -return READ_ONCE (swap_vma_readahead) && !atomic_read (&nr_rotate_swap); -} -/* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full (void ) {@@ -518,24 +508,6 @@ static inline struct page *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,return NULL ; } -static inline bool swap_use_vma_readahead (void ) -{ -return false; -} - -static inline struct page *swap_readahead_detect ( -struct vm_fault *vmf,struct vma_swap_readahead *swap_ra) -{ -return NULL ; -} - -static inline struct page *do_swap_page_readahead ( -swp_entry_t fentry,gfp_t gfp_mask, -struct vm_fault *vmf,struct vma_swap_readahead *swap_ra) -{ -return NULL ; -} -static inline int swap_writepage (struct page *p,struct writeback_control *wbc) {return 0 ;@@ -662,5 +634,37 @@ static inline bool mem_cgroup_swap_full(struct page *page) }#endif +#ifdef CONFIG_VMA_SWAP_READAHEAD +extern bool swap_vma_readahead; + +static inline bool swap_use_vma_readahead (void ) +{ +return READ_ONCE (swap_vma_readahead) && !atomic_read (&nr_rotate_swap); +} +extern struct page *swap_readahead_detect (struct vm_fault *vmf, +struct vma_swap_readahead *swap_ra); +extern struct page *do_swap_page_readahead (swp_entry_t fentry,gfp_t gfp_mask, +struct vm_fault *vmf, +struct vma_swap_readahead *swap_ra); +#else +static inline bool swap_use_vma_readahead (void ) +{ +return false; +} + +static inline struct page *swap_readahead_detect (struct vm_fault *vmf, +struct vma_swap_readahead *swap_ra) +{ +return NULL ; +} + +static inline struct page *do_swap_page_readahead (swp_entry_t fentry, +gfp_t gfp_mask,struct vm_fault *vmf, +struct vma_swap_readahead *swap_ra) +{ +return NULL ; +} +#endif +#endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ mm/Kconfig +4
-0@@ -434,6 +434,26 @@ config THP_SWAP For selection by architectures with reasonable THP sizes. +config VMA_SWAP_READAHEAD + bool "VMA based swap readahead" + depends on SWAP + default y
mm/Kconfig config THP_SWAP · line 450
Quoted 10 lines
mm/Kconfig +10
-0+ help + VMA based swap readahead detects page accessing pattern in a + VMA and adjust the swap readahead window for pages in the + VMA accordingly. It works better for more complex workload + compared with the original physical swap readahead. + + It can be controlled via the following sysfs interface, + + /sys/kernel/mm/swap/vma_ra_enabled + /sys/kernel/mm/swap/vma_ra_max_order
It might be better to discuss in other thread but if you mention new interface here again, I will discuss it here.
We are creating new ABI in here so I want to ask question in here.
Did you consier to use /sys/block/xxx/queue/read_ahead_kb for the swap readahead knob? Reusing such common/consistent knob would be better than adding new separate konb.
mm/Kconfig config THP_SWAP · line 453
Quoted 3 lines
mm/Kconfig +3
-0+ + If set to no, the original physical swap readahead will be + used.
In here, could you point out kindly somewhere where describes two readahead algorithm in the system?
I don't mean we should explain how it works. Rather than, there are two parallel algorithm in swap readahead.
Anonymous memory works based on VMA while shm works based on physical block. There are working separately on parallel. Each of knobs are vma_ra_max_order and page-cluster, blah, blah.
Quoted 91 lines
mm/Kconfig +3
-0+ + If unsure, say Y to enable VMA based swap readahead. + config TRANSPARENT_HUGE_PAGECACHE def_bool y depends on TRANSPARENT_HUGEPAGEmm/swap_state.c +16
-9@@ -37,11 +37,6 @@ static const struct address_space_operations swap_aops = {struct address_space *swapper_spaces[MAX_SWAPFILES ];static unsigned int nr_swapper_spaces[MAX_SWAPFILES ]; -bool swap_vma_readahead = true; - -#define SWAP_RA_MAX_ORDER_DEFAULT 3 - -static int swap_ra_max_order =SWAP_RA_MAX_ORDER_DEFAULT ;#define SWAP_RA_WIN_SHIFT (PAGE_SHIFT / 2)#define SWAP_RA_HITS_MASK ((1UL << SWAP_RA_WIN_SHIFT) - 1)@@ -324,8 +319,7 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma, unsigned long addr) {struct page *page; -unsigned long ra_info; -int win, hits, readahead; +int readahead; page =find_get_page (swap_address_space (entry),swp_offset (entry));@@ -335,7 +329,11 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,if (unlikely (PageTransCompound (page)))return page; readahead =TestClearPageReadahead (page); +#ifdef CONFIG_VMA_SWAP_READAHEAD if (vma) { +unsigned long ra_info; +int win, hits; + ra_info =GET_SWAP_RA_VAL (vma); win =SWAP_RA_WIN (ra_info); hits =SWAP_RA_HITS (ra_info);@@ -344,6 +342,7 @@ struct page *lookup_swap_cache(swp_entry_t entry, struct vm_area_struct *vma,atomic_long_set (&vma->swap_readahead_info, SWAP_RA_VAL(addr, win, hits)); } +#endif if (readahead) {count_vm_event (SWAP_RA_HIT );if (!vma)@@ -625,6 +624,13 @@ void exit_swap_address_space(unsigned int type)kvfree (spaces); } +#ifdef CONFIG_VMA_SWAP_READAHEAD +bool swap_vma_readahead = true; + +#define SWAP_RA_MAX_ORDER_DEFAULT 3 + +static int swap_ra_max_order =SWAP_RA_MAX_ORDER_DEFAULT ; + static inline void swap_ra_clamp_pfn(struct vm_area_struct *vma, unsigned long faddr, unsigned long lpfn,@@ -751,8 +757,9 @@ struct page *do_swap_page_readahead(swp_entry_t fentry, gfp_t gfp_mask,return read_swap_cache_async (fentry, gfp_mask, vma, vmf->address, swap_ra->win ==1 ); } +#endif /* CONFIG_VMA_SWAP_READAHEAD */ -#ifdef CONFIG_SYSFS +#if defined(CONFIG_SYSFS ) && defined(CONFIG_VMA_SWAP_READAHEAD )static ssize_t vma_ra_enabled_show (struct kobject *kobj,struct kobj_attribute *attr,char *buf) {@@ -830,4 +837,4 @@ static int __init swap_init_sysfs(void) return err; }subsys_initcall (swap_init_sysfs); -#endif +#endif /* defined(CONFIG_SYSFS) && defined(CONFIG_VMA_SWAP_READAHEAD) */ Signature · 7 lines
2.14.1 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Hi, Minchan,
Quoted 4 lines · Minchan Kim
Hi Huang,
Quoted 1 line · Ying
From: Huang Ying <[email protected]>
[snip]
Quoted 26 lines
Quoted 12 lines
mm/Kconfig +4
-0@@ -434,6 +434,26 @@ config THP_SWAP For selection by architectures with reasonable THP sizes. +config VMA_SWAP_READAHEAD + bool "VMA based swap readahead" + depends on SWAP + default ymm/Kconfig config THP_SWAP · line 450
Quoted 10 lines
mm/Kconfig +10
-0+ help + VMA based swap readahead detects page accessing pattern in a + VMA and adjust the swap readahead window for pages in the + VMA accordingly. It works better for more complex workload + compared with the original physical swap readahead. + + It can be controlled via the following sysfs interface, + + /sys/kernel/mm/swap/vma_ra_enabled + /sys/kernel/mm/swap/vma_ra_max_orderIt might be better to discuss in other thread but if you mention new interface here again, I will discuss it here.
Quoted 5 lines
We are creating new ABI in here so I want to ask question in here.
Did you consier to use
/sys/block/xxx/queue/read_ahead_kbfor the swap readahead knob? Reusing such common/consistent knob would be better than adding new separate konb.
The problem is that the configuration of VMA based swap readahead is global instead of block device specific. And because it works in virtual way, that is, the swap blocks on the different block devices may be readahead together. It's a little hard to use the block device specific configuration.
Quoted 7 lines
mm/Kconfig config THP_SWAP · line 453
Quoted 3 lines
mm/Kconfig +3
-0+ + If set to no, the original physical swap readahead will be + used.In here, could you point out kindly somewhere where describes two readahead algorithm in the system?
Quoted 6 lines
I don't mean we should explain how it works. Rather than, there are two parallel algorithm in swap readahead.
Anonymous memory works based on VMA while shm works based on physical block. There are working separately on parallel. Each of knobs are
vma_ra_max_orderand page-cluster, blah, blah.
Sure. I will add some description about that somewhere.
Quoted 6 lines
Quoted 6 lines
mm/Kconfig +3
-0+ + If unsure, say Y to enable VMA based swap readahead. + config TRANSPARENT_HUGE_PAGECACHE def_bool y depends on TRANSPARENT_HUGEPAGE
[snip]
Quoted 43 lines · Ying
Hi, Minchan,
Quoted 4 lines · Minchan Kim
Hi Huang,
Quoted 1 line · Ying
From: Huang Ying <[email protected]>
[snip]
Quoted 26 lines
Quoted 12 lines
mm/Kconfig +4
-0@@ -434,6 +434,26 @@ config THP_SWAP For selection by architectures with reasonable THP sizes. +config VMA_SWAP_READAHEAD + bool "VMA based swap readahead" + depends on SWAP + default ymm/Kconfig config THP_SWAP · line 450
Quoted 10 lines
mm/Kconfig +10
-0+ help + VMA based swap readahead detects page accessing pattern in a + VMA and adjust the swap readahead window for pages in the + VMA accordingly. It works better for more complex workload + compared with the original physical swap readahead. + + It can be controlled via the following sysfs interface, + + /sys/kernel/mm/swap/vma_ra_enabled + /sys/kernel/mm/swap/vma_ra_max_orderIt might be better to discuss in other thread but if you mention new interface here again, I will discuss it here.
Quoted 5 lines
We are creating new ABI in here so I want to ask question in here.
Did you consier to use
/sys/block/xxx/queue/read_ahead_kbfor the swap readahead knob? Reusing such common/consistent knob would be better than adding new separate konb.
Quoted 5 lines
The problem is that the configuration of VMA based swap readahead is global instead of block device specific. And because it works in virtual way, that is, the swap blocks on the different block devices may be readahead together. It's a little hard to use the block device specific configuration.
Fair enough. page-cluster from the beginning should have been like that instead of vma_ra_max_order.
One more questions: Do we need separate vma_ra_enable?
Can't we disable it via echo 0 > /sys/kernel/mm/swap/vma_ra_max_order like page-cluster?
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 50 lines · Minchan Kim
Quoted 43 lines · Ying
Hi, Minchan,
Quoted 4 lines · Minchan Kim
Hi Huang,
Quoted 1 line · Ying
From: Huang Ying <[email protected]>
[snip]
Quoted 26 lines
Quoted 12 lines
mm/Kconfig +4
-0@@ -434,6 +434,26 @@ config THP_SWAP For selection by architectures with reasonable THP sizes. +config VMA_SWAP_READAHEAD + bool "VMA based swap readahead" + depends on SWAP + default ymm/Kconfig config THP_SWAP · line 450
Quoted 10 lines
mm/Kconfig +10
-0+ help + VMA based swap readahead detects page accessing pattern in a + VMA and adjust the swap readahead window for pages in the + VMA accordingly. It works better for more complex workload + compared with the original physical swap readahead. + + It can be controlled via the following sysfs interface, + + /sys/kernel/mm/swap/vma_ra_enabled + /sys/kernel/mm/swap/vma_ra_max_orderIt might be better to discuss in other thread but if you mention new interface here again, I will discuss it here.
Quoted 5 lines
We are creating new ABI in here so I want to ask question in here.
Did you consier to use
/sys/block/xxx/queue/read_ahead_kbfor the swap readahead knob? Reusing such common/consistent knob would be better than adding new separate konb.Quoted 5 lines
The problem is that the configuration of VMA based swap readahead is global instead of block device specific. And because it works in virtual way, that is, the swap blocks on the different block devices may be readahead together. It's a little hard to use the block device specific configuration.
Quoted 7 lines
Fair enough. page-cluster from the beginning should have been like that instead of
vma_ra_max_order.One more questions: Do we need separate
vma_ra_enable?Can't we disable it via echo 0 >
/sys/kernel/mm/swap/vma_ra_max_orderlike page-cluster?
The difference is,
vma_ra_eanble: 0
=> use original physical swap readahead
vma_ra_enable: 1 && vma_ra_max_order: 0
=> use VMA based swap readahead and disable the readahead.
Best Regards,
Huang, Ying
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 60 lines · Ying
Quoted 50 lines · Minchan Kim
Quoted 43 lines · Ying
Hi, Minchan,
Quoted 4 lines · Minchan Kim
Hi Huang,
Quoted 1 line · Ying
From: Huang Ying <[email protected]>
[snip]
Quoted 26 lines
Quoted 12 lines
mm/Kconfig +4
-0@@ -434,6 +434,26 @@ config THP_SWAP For selection by architectures with reasonable THP sizes. +config VMA_SWAP_READAHEAD + bool "VMA based swap readahead" + depends on SWAP + default ymm/Kconfig config THP_SWAP · line 450
Quoted 10 lines
mm/Kconfig +10
-0+ help + VMA based swap readahead detects page accessing pattern in a + VMA and adjust the swap readahead window for pages in the + VMA accordingly. It works better for more complex workload + compared with the original physical swap readahead. + + It can be controlled via the following sysfs interface, + + /sys/kernel/mm/swap/vma_ra_enabled + /sys/kernel/mm/swap/vma_ra_max_orderIt might be better to discuss in other thread but if you mention new interface here again, I will discuss it here.
Quoted 5 lines
We are creating new ABI in here so I want to ask question in here.
Did you consier to use
/sys/block/xxx/queue/read_ahead_kbfor the swap readahead knob? Reusing such common/consistent knob would be better than adding new separate konb.Quoted 5 lines
The problem is that the configuration of VMA based swap readahead is global instead of block device specific. And because it works in virtual way, that is, the swap blocks on the different block devices may be readahead together. It's a little hard to use the block device specific configuration.
Quoted 7 lines
Fair enough. page-cluster from the beginning should have been like that instead of
vma_ra_max_order.One more questions: Do we need separate
vma_ra_enable?Can't we disable it via echo 0 >
/sys/kernel/mm/swap/vma_ra_max_orderlike page-cluster?
Quoted 7 lines
The difference is,
vma_ra_eanble: 0
=> use original physical swap readahead
vma_ra_enable: 1 &&vma_ra_max_order: 0
=> use VMA based swap readahead and disable the readahead.
I understand now. Thanks!
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 5 lines · Ying
From: Huang Ying <[email protected]>
This patch adds a new
KconfigoptionVMA_SWAP_READAHEADand wraps VMA based swap readahead code inside #ifdef CONFIG_VMA_SWAP_READAHEAD/#endif. This is more friendly for tiny kernels.
How (much)?
Quoted 4 lines
And as pointed to by Minchan
Kim, give people who want to disable the swap readahead an opportunity to notice the changes to the swap readahead algorithm and the corresponding knobs.
Why would anyone want that?
Please note that adding new config options make the already complicated config space even more problematic so there should be a good reason to add one. Please make sure your justification is clear on why this is worth the future maintenance and configurability burden.
Signature · 2 lines
Michal Hocko SUSE Labs
Quoted 8 lines · Michal Hocko
Quoted 5 lines · Ying
From: Huang Ying <[email protected]>
This patch adds a new
KconfigoptionVMA_SWAP_READAHEADand wraps VMA based swap readahead code inside #ifdef CONFIG_VMA_SWAP_READAHEAD/#endif. This is more friendly for tiny kernels.How (much)?
OK. I will measure it.
Quoted 11 lines
Quoted 4 lines
And as pointed to by Minchan
Kim, give people who want to disable the swap readahead an opportunity to notice the changes to the swap readahead algorithm and the corresponding knobs.Why would anyone want that?
Please note that adding new config options make the already complicated config space even more problematic so there should be a good reason to add one. Please make sure your justification is clear on why this is worth the future maintenance and configurability burden.
Hi, Minchan,
Could you give more information on this?
Best Regards,
Huang, Ying
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 14 lines · Michal Hocko
Quoted 5 lines · Ying
From: Huang Ying <[email protected]>
This patch adds a new
KconfigoptionVMA_SWAP_READAHEADand wraps VMA based swap readahead code inside #ifdef CONFIG_VMA_SWAP_READAHEAD/#endif. This is more friendly for tiny kernels.How (much)?
Quoted 4 lines
And as pointed to by Minchan
Kim, give people who want to disable the swap readahead an opportunity to notice the changes to the swap readahead algorithm and the corresponding knobs.
Quoted 6 lines
Why would anyone want that?
Please note that adding new config options make the already complicated config space even more problematic so there should be a good reason to add one. Please make sure your justification is clear on why this is worth the future maintenance and configurability burden.
The problem is users have disabled swap readahead by echo 0 > /proc/sys/ vm/page-cluster are regressed by this new interface /sys/kernel/mm/swap/ vma_ra_max_order. Because for disabling readahead completely, they should disable vma_ra_max_order as well as page-cluster from now on.
So, goal of new config to notice new feature to admins so they can be aware of new konb vma_ra_max_order as well as page-cluster.
I canont think other better idea to preventing such regression.
http://lkml.kernel.org/r/%3C20170913014019.GB29422@bbox%3E
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 27 lines · Minchan Kim
Quoted 14 lines · Michal Hocko
Quoted 5 lines · Ying
From: Huang Ying <[email protected]>
This patch adds a new
KconfigoptionVMA_SWAP_READAHEADand wraps VMA based swap readahead code inside #ifdef CONFIG_VMA_SWAP_READAHEAD/#endif. This is more friendly for tiny kernels.How (much)?
Quoted 4 lines
And as pointed to by Minchan
Kim, give people who want to disable the swap readahead an opportunity to notice the changes to the swap readahead algorithm and the corresponding knobs.Quoted 6 lines
Why would anyone want that?
Please note that adding new config options make the already complicated config space even more problematic so there should be a good reason to add one. Please make sure your justification is clear on why this is worth the future maintenance and configurability burden.
The problem is users have disabled swap readahead by echo 0 >
/proc/sys/vm/page-cluster are regressed by this new interface/sys/kernel/mm/swap/vma_ra_max_order. Because for disabling readahead completely, they should disablevma_ra_max_orderas well as page-cluster from now on.
Quoted 5 lines
So, goal of new config to notice new feature to admins so they can be aware of new konb
vma_ra_max_orderas well as page-cluster.
I canont think other better idea to preventing such regression.
So, how are you going to configure this when you do not know whether zram will be used? In other words what should e.g. distribution set this to?
Signature · 8 lines
Michal Hocko SUSE Labs -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 32 lines · Michal Hocko
Quoted 31 lines · Minchan Kim
Quoted 14 lines · Michal Hocko
Quoted 5 lines · Ying
From: Huang Ying <[email protected]>
This patch adds a new
KconfigoptionVMA_SWAP_READAHEADand wraps VMA based swap readahead code inside #ifdef CONFIG_VMA_SWAP_READAHEAD/#endif. This is more friendly for tiny kernels.How (much)?
Quoted 4 lines
And as pointed to by Minchan
Kim, give people who want to disable the swap readahead an opportunity to notice the changes to the swap readahead algorithm and the corresponding knobs.Quoted 6 lines
Why would anyone want that?
Please note that adding new config options make the already complicated config space even more problematic so there should be a good reason to add one. Please make sure your justification is clear on why this is worth the future maintenance and configurability burden.
The problem is users have disabled swap readahead by echo 0 >
/proc/sys/vm/page-cluster are regressed by this new interface/sys/kernel/mm/swap/vma_ra_max_order. Because for disabling readahead completely, they should disablevma_ra_max_orderas well as page-cluster from now on.So, goal of new config to notice new feature to admins so they can be aware of new konb
vma_ra_max_orderas well as page-cluster.
I canont think other better idea to preventing such regression.
Quoted 5 lines
So, how are you going to configure this when you do not know whether zram will be used? In other words what should e.g. distribution set this to?
I have no idea. Unfortunately, it depends on them. If they want to use zram as swap, they should fix the script. Surely, I don't like it. Instead, I wanted that page-cluster zeroing disables both virtual/pysical swap readahead not to break current userspace. However, Huang doesn't liek it.
If you have better idea, please suggest.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 2 lines · Minchan Kim
Quoted 1 line · Michal Hocko
On Wed 27-09-17 14:04:01, Minchan Kim wrote:
[...]
Quoted 15 lines
Quoted 9 lines
Quoted 9 lines
The problem is users have disabled swap readahead by echo 0 >
/proc/sys/vm/page-cluster are regressed by this new interface/sys/kernel/mm/swap/vma_ra_max_order. Because for disabling readahead completely, they should disablevma_ra_max_orderas well as page-cluster from now on.So, goal of new config to notice new feature to admins so they can be aware of new konb
vma_ra_max_orderas well as page-cluster.
I canont think other better idea to preventing such regression.Quoted 5 lines
So, how are you going to configure this when you do not know whether zram will be used? In other words what should e.g. distribution set this to?
Quoted 6 lines
I have no idea. Unfortunately, it depends on them. If they want to use zram as swap, they should fix the script. Surely, I don't like it. Instead, I wanted that page-cluster zeroing disables both virtual/pysical swap readahead not to break current userspace. However, Huang doesn't liek it.
If you have better idea, please suggest.
I understand your frustration but config options are not there to bypass proper design decisions. Why cannot we unconditionally disable all the read ahead when zram is enabled?
Signature · 8 lines
Michal Hocko SUSE Labs -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 26 lines · Michal Hocko
Quoted 2 lines · Minchan Kim
Quoted 1 line · Michal Hocko
On Wed 27-09-17 14:04:01, Minchan Kim wrote:
[...]
Quoted 15 lines
Quoted 9 lines
Quoted 9 lines
The problem is users have disabled swap readahead by echo 0 >
/proc/sys/vm/page-cluster are regressed by this new interface/sys/kernel/mm/swap/vma_ra_max_order. Because for disabling readahead completely, they should disablevma_ra_max_orderas well as page-cluster from now on.So, goal of new config to notice new feature to admins so they can be aware of new konb
vma_ra_max_orderas well as page-cluster.
I canont think other better idea to preventing such regression.Quoted 5 lines
So, how are you going to configure this when you do not know whether zram will be used? In other words what should e.g. distribution set this to?
Quoted 6 lines
I have no idea. Unfortunately, it depends on them. If they want to use zram as swap, they should fix the script. Surely, I don't like it. Instead, I wanted that page-cluster zeroing disables both virtual/pysical swap readahead not to break current userspace. However, Huang doesn't liek it.
If you have better idea, please suggest.
Quoted 3 lines
I understand your frustration but config options are not there to bypass proper design decisions. Why cannot we unconditionally disable all the read ahead when zram is enabled?
It's not a zram specific issue. Every users who have disabled swap readahead via page-cluster will be broken, too.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 27 lines · Minchan Kim
Quoted 26 lines · Michal Hocko
Quoted 2 lines · Minchan Kim
Quoted 1 line · Michal Hocko
On Wed 27-09-17 14:04:01, Minchan Kim wrote:
[...]
Quoted 21 lines
Quoted 9 lines
Quoted 9 lines
The problem is users have disabled swap readahead by echo 0 >
/proc/sys/vm/page-cluster are regressed by this new interface/sys/kernel/mm/swap/vma_ra_max_order. Because for disabling readahead completely, they should disablevma_ra_max_orderas well as page-cluster from now on.So, goal of new config to notice new feature to admins so they can be aware of new konb
vma_ra_max_orderas well as page-cluster.
I canont think other better idea to preventing such regression.Quoted 5 lines
So, how are you going to configure this when you do not know whether zram will be used? In other words what should e.g. distribution set this to?
I have no idea. Unfortunately, it depends on them. If they want to use zram as swap, they should fix the script. Surely, I don't like it. Instead, I wanted that page-cluster zeroing disables both virtual/pysical swap readahead not to break current userspace. However, Huang doesn't liek it.
If you have better idea, please suggest.
Quoted 6 lines
Quoted 3 lines
I understand your frustration but config options are not there to bypass proper design decisions. Why cannot we unconditionally disable all the read ahead when zram is enabled?
It's not a zram specific issue. Every users who have disabled swap readahead via page-cluster will be broken, too.
Do you have any examples outside of zram? Also I do not see why we simply cannot disable swap readahead when page-cluster is 0?
Signature · 8 lines
Michal Hocko SUSE Labs -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 28 lines · Michal Hocko
Quoted 27 lines · Minchan Kim
Quoted 26 lines · Michal Hocko
Quoted 2 lines · Minchan Kim
Quoted 1 line · Michal Hocko
On Wed 27-09-17 14:04:01, Minchan Kim wrote:
[...]
Quoted 21 lines
Quoted 9 lines
Quoted 9 lines
The problem is users have disabled swap readahead by echo 0 >
/proc/sys/vm/page-cluster are regressed by this new interface/sys/kernel/mm/swap/vma_ra_max_order. Because for disabling readahead completely, they should disablevma_ra_max_orderas well as page-cluster from now on.So, goal of new config to notice new feature to admins so they can be aware of new konb
vma_ra_max_orderas well as page-cluster.
I canont think other better idea to preventing such regression.Quoted 5 lines
So, how are you going to configure this when you do not know whether zram will be used? In other words what should e.g. distribution set this to?
I have no idea. Unfortunately, it depends on them. If they want to use zram as swap, they should fix the script. Surely, I don't like it. Instead, I wanted that page-cluster zeroing disables both virtual/pysical swap readahead not to break current userspace. However, Huang doesn't liek it.
If you have better idea, please suggest.
Quoted 8 lines
Quoted 6 lines
Quoted 3 lines
I understand your frustration but config options are not there to bypass proper design decisions. Why cannot we unconditionally disable all the read ahead when zram is enabled?
It's not a zram specific issue. Every users who have disabled swap readahead via page-cluster will be broken, too.
Do you have any examples outside of zram? Also I do not see why we
I'm not a god to know every usecases on earth. It's just knob and it's have been there for a long time with following semantic:
Zero disables swap readahead completely.
So, anyuser can use it by their reasons(e.g., small memory system)
I don't want to play with pointless game "Hey, give me an example. If you couldn't, no worth to keep the semantic" on such long time simple/clear semantic.
Quoted 1 line
simply cannot disable swap readahead when page-cluster is 0?
That's was what I want really but Huang want to use two readahead algorithms in parallel so he wanted to keep two separated disable knobs.
Quoted 3 lines
Signature · 2 lines
Michal Hocko SUSE Labs
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 1 line · Minchan Kim
On Wed, Sep 27, 2017 at 03:22:41PM +0200, Michal Hocko wrote:
[...]
Quoted 5 lines
Quoted 1 line
simply cannot disable swap readahead when page-cluster is 0?
That's was what I want really but Huang want to use two readahead algorithms in parallel so he wanted to keep two separated disable knobs.
If it breaks existing and documented behavior then it is a clear regression and it should be fixed. I do not see why this should be disputable at all.
Working around an issue with a config option sounds like the wrong way to go because those who cannot do that unconditionally would still see a regression.
Signature · 8 lines
Michal Hocko SUSE Labs -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 5 lines · Michal Hocko
Quoted 1 line · Minchan Kim
On Wed, Sep 27, 2017 at 03:22:41PM +0200, Michal Hocko wrote:
[...]
Quoted 2 lines
Quoted 1 line
simply cannot disable swap readahead when page-cluster is 0?
Quoted 7 lines
Quoted 3 lines
That's was what I want really but Huang want to use two readahead algorithms in parallel so he wanted to keep two separated disable knobs.
If it breaks existing and documented behavior then it is a clear regression and it should be fixed. I do not see why this should be disputable at all.
Indeed but Huang doesn't think so. He has thought it's not a regression. Frankly speaking, I'm really bored of discussing with it.
https://marc.info/?l=linux-mm&m=150526413319763&w=2
So I passed the decision to Andrew.
http://lkml.kernel.org/r/<20170913014019.GB29422@bbox>
The config option idea is compromise approach although I don't like it and still believe it's simple clear *regression* so 0 page-cluster should keep the swap readahead disabled.
Quoted 4 lines
Working around an issue with a config option sounds like the wrong way to go because those who cannot do that unconditionally would still see a regression.
I absolutely agree but as I said, the discussion was not productive even though I did best effort to persuade. That's all for my side as contributor/reviewer. Decision is up to maintainer. ;-)
Thanks for the opinion, Michal.
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Quoted 10 lines · Minchan Kim
Quoted 9 lines · Michal Hocko
Quoted 1 line · Minchan Kim
On Wed, Sep 27, 2017 at 03:22:41PM +0200, Michal Hocko wrote:
[...]
Quoted 5 lines
Quoted 1 line
simply cannot disable swap readahead when page-cluster is 0?
That's was what I want really but Huang want to use two readahead algorithms in parallel so he wanted to keep two separated disable knobs.
Quoted 7 lines
Quoted 3 lines
If it breaks existing and documented behavior then it is a clear regression and it should be fixed. I do not see why this should be disputable at all.
Indeed but Huang doesn't think so. He has thought it's not a regression. Frankly speaking, I'm really bored of discussing with it.
https://marc.info/?l=linux-mm&m=150526413319763&w=2
Then send a patch explaining why you consider this a regression with some numbers backing it and I will happily ack it.
Quoted 6 lines
So I passed the decision to Andrew.
http://lkml.kernel.org/r/<20170913014019.GB29422@bbox>The config option idea is compromise approach although I don't like it and still believe it's simple clear *regression* so 0 page-cluster should keep the swap readahead disabled.
It is not a compromise. The regression is still there for many users potentially (just consider zram distribution kernel users...).
Signature · 8 lines
Michal Hocko SUSE Labs -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Hi, Michal,
Quoted 15 lines · Michal Hocko
Quoted 14 lines · Minchan Kim
Quoted 12 lines · Michal Hocko
Quoted 1 line · Minchan Kim
On Wed, Sep 27, 2017 at 03:22:41PM +0200, Michal Hocko wrote:
[...]
Quoted 5 lines
Quoted 1 line
simply cannot disable swap readahead when page-cluster is 0?
That's was what I want really but Huang want to use two readahead algorithms in parallel so he wanted to keep two separated disable knobs.
If it breaks existing and documented behavior then it is a clear regression and it should be fixed. I do not see why this should be disputable at all.
Quoted 6 lines
Quoted 3 lines
Indeed but Huang doesn't think so. He has thought it's not a regression. Frankly speaking, I'm really bored of discussing with it.
https://marc.info/?l=linux-mm&m=150526413319763&w=2Then send a patch explaining why you consider this a regression with some numbers backing it and I will happily ack it.
I still think there may be a performance regression for some users because of the change of the algorithm and the knobs, and the performance regression can be resolved via setting the new knob. But I don't think there will be a functionality regression. Do you agree?
Best Regards,
Huang, Ying
Quoted 9 lines
Quoted 6 lines
So I passed the decision to Andrew.
http://lkml.kernel.org/r/<20170913014019.GB29422@bbox>The config option idea is compromise approach although I don't like it and still believe it's simple clear *regression* so 0 page-cluster should keep the swap readahead disabled.
It is not a compromise. The regression is still there for many users potentially (just consider zram distribution kernel users...).
Quoted 23 lines · Ying
Hi, Michal,
Quoted 19 lines · Michal Hocko
Quoted 17 lines · Minchan Kim
Quoted 5 lines · Michal Hocko
Quoted 1 line · Minchan Kim
On Wed, Sep 27, 2017 at 03:22:41PM +0200, Michal Hocko wrote:
[...]
Quoted 2 lines
Quoted 1 line
simply cannot disable swap readahead when page-cluster is 0?
Quoted 7 lines
Quoted 3 lines
That's was what I want really but Huang want to use two readahead algorithms in parallel so he wanted to keep two separated disable knobs.
If it breaks existing and documented behavior then it is a clear regression and it should be fixed. I do not see why this should be disputable at all.
Indeed but Huang doesn't think so. He has thought it's not a regression. Frankly speaking, I'm really bored of discussing with it.
https://marc.info/?l=linux-mm&m=150526413319763&w=2
Quoted 7 lines
Quoted 2 lines
Then send a patch explaining why you consider this a regression with some numbers backing it and I will happily ack it.
I still think there may be a performance regression for some users because of the change of the algorithm and the knobs, and the performance regression can be resolved via setting the new knob. But I don't think there will be a functionality regression. Do you agree?
I am not sure I understand. One thing is clear though. Your change has introduced a regression as described by Minchan. And that has to be resolved no matter what. You cannot expect users will tweak the system to resolve it or configure their systems in a specific way.
Signature · 2 lines
Michal Hocko SUSE Labs
Quoted 4 lines · Ying
I still think there may be a performance regression for some users because of the change of the algorithm and the knobs, and the performance regression can be resolved via setting the new knob. But I don't think there will be a functionality regression. Do you agree?
A performance regression is a regression. I don't understand why we are splitting hairs as to what kind of regression it is.
Are you only willing to fix it if it's a functional regression?
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>
Andrew Morton
maintainerQuoted 9 lines · On Mon, 2 Oct 2017 08:45:40 -0700 Dave Hansen <[email protected]> wrote:
Quoted 4 lines · Ying
I still think there may be a performance regression for some users because of the change of the algorithm and the knobs, and the performance regression can be resolved via setting the new knob. But I don't think there will be a functionality regression. Do you agree?
A performance regression is a regression. I don't understand why we are splitting hairs as to what kind of regression it is.
Yes.
Ying, please find us a way of avoiding any disruption to existing system setups. One which doesn't require that the operator perform a configuration change to restore prior behaviour/performance. And please let's get this done well in advance of the 4.14 release.
Thanks.
Quoted 12 lines · Andrew Morton
Quoted 9 lines · On Mon, 2 Oct 2017 08:45:40 -0700 Dave Hansen <[email protected]> wrote:
Quoted 4 lines · Ying
I still think there may be a performance regression for some users because of the change of the algorithm and the knobs, and the performance regression can be resolved via setting the new knob. But I don't think there will be a functionality regression. Do you agree?
A performance regression is a regression. I don't understand why we are splitting hairs as to what kind of regression it is.
Quoted 5 lines
Yes.
Ying, please find us a way of avoiding any disruption to existing system setups. One which doesn't require that the operator perform a configuration change to restore prior behaviour/performance.
Sorry for late. I am in holiday recently.
OK. For me, I think the most clean way is to use page_cluster to control both the virtual and physical swap readahead. If you are OK with that, I will prepare the patch.
Quoted 1 line
And please let's get this done well in advance of the 4.14 release.
Sure.
Best Regards,
Huang, Ying
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to [email protected]. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"[email protected]"> [email protected] </a>