| Message ID | 20230911133852.2545-1-zhiguangni01@gmail.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | [V4] NUMA:Improve the efficiency of calculating pages loss | expand |
Friendly Ping On Mon, 11 Sept 2023 at 21:39, Liam Ni <zhiguangni01@gmail.com> wrote: > > Optimize the way of calculating missing pages. > > In the previous implementation, We calculate missing pages as follows: > 1. calculate numaram by traverse all the numa_meminfo's and for each of > them traverse all the regions in memblock.memory to prepare for > counting missing pages. > > 2. Traverse all the regions in memblock.memory again to get e820ram. > > 3. the missing page is (e820ram - numaram ) > > But,it's enough to count memory in ‘memblock.memory’ that doesn't have > the node assigned. > > V3:https://lore.kernel.org/all/CACZJ9cUXiWxDb6hF4JFhWe7Np82k6LopVQ+_AoGFOccN4kjJqA@mail.gmail.com/#r > V2:https://lore.kernel.org/all/20230619075315.49114-1-zhiguangni01@gmail.com/ > V1:https://lore.kernel.org/all/20230615142016.419570-1-zhiguangni01@gmail.com/ > > Signed-off-by: Liam Ni <zhiguangni01@gmail.com> > --- > arch/x86/mm/numa.c | 33 +-------------------------------- > include/linux/memblock.h | 1 + > mm/memblock.c | 21 +++++++++++++++++++++ > 3 files changed, 23 insertions(+), 32 deletions(-) > > diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c > index 2aadb2019b4f..ee5f08adfaf6 100644 > --- a/arch/x86/mm/numa.c > +++ b/arch/x86/mm/numa.c > @@ -447,37 +447,6 @@ int __node_distance(int from, int to) > } > EXPORT_SYMBOL(__node_distance); > > -/* > - * Sanity check to catch more bad NUMA configurations (they are amazingly > - * common). Make sure the nodes cover all memory. > - */ > -static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) > -{ > - u64 numaram, e820ram; > - int i; > - > - numaram = 0; > - for (i = 0; i < mi->nr_blks; i++) { > - u64 s = mi->blk[i].start >> PAGE_SHIFT; > - u64 e = mi->blk[i].end >> PAGE_SHIFT; > - numaram += e - s; > - numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e); > - if ((s64)numaram < 0) > - numaram = 0; > - } > - > - e820ram = max_pfn - absent_pages_in_range(0, max_pfn); > - > - /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ > - if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) { > - printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n", > - (numaram << PAGE_SHIFT) >> 20, > - (e820ram << PAGE_SHIFT) >> 20); > - return false; > - } > - return true; > -} > - > /* > * Mark all currently memblock-reserved physical memory (which covers the > * kernel's own memory ranges) as hot-unswappable. > @@ -583,7 +552,7 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) > return -EINVAL; > } > } > - if (!numa_meminfo_cover_memory(mi)) > + if (!memblock_validate_numa_coverage(SZ_1M)) > return -EINVAL; > > /* Finally register nodes. */ > diff --git a/include/linux/memblock.h b/include/linux/memblock.h > index 1c1072e3ca06..0c3a193ebc58 100644 > --- a/include/linux/memblock.h > +++ b/include/linux/memblock.h > @@ -120,6 +120,7 @@ int memblock_physmem_add(phys_addr_t base, phys_addr_t size); > void memblock_trim_memory(phys_addr_t align); > bool memblock_overlaps_region(struct memblock_type *type, > phys_addr_t base, phys_addr_t size); > +bool memblock_validate_numa_coverage(const u64 limit); > int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); > int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); > int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); > diff --git a/mm/memblock.c b/mm/memblock.c > index 0863222af4a4..8f61f868bec1 100644 > --- a/mm/memblock.c > +++ b/mm/memblock.c > @@ -734,6 +734,27 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) > return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); > } > > +bool __init_memblock memblock_validate_numa_coverage(const u64 limit) > +{ > + unsigned long lose_pg = 0; > + unsigned long start_pfn, end_pfn; > + int nid, i; > + > + /* calculate lose page */ > + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { > + if (nid == NUMA_NO_NODE) > + lose_pg += end_pfn - start_pfn; > + } > + > + if (lose_pg >= limit) { > + pr_err("NUMA: We lost %ld pages.\n", lose_pg); > + return false; > + } > + > + return true; > +} > + > + > /** > * memblock_isolate_range - isolate given range into disjoint memblocks > * @type: memblock type to isolate range for > -- > 2.25.1 >
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 2aadb2019b4f..ee5f08adfaf6 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -447,37 +447,6 @@ int __node_distance(int from, int to) } EXPORT_SYMBOL(__node_distance); -/* - * Sanity check to catch more bad NUMA configurations (they are amazingly - * common). Make sure the nodes cover all memory. - */ -static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) -{ - u64 numaram, e820ram; - int i; - - numaram = 0; - for (i = 0; i < mi->nr_blks; i++) { - u64 s = mi->blk[i].start >> PAGE_SHIFT; - u64 e = mi->blk[i].end >> PAGE_SHIFT; - numaram += e - s; - numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e); - if ((s64)numaram < 0) - numaram = 0; - } - - e820ram = max_pfn - absent_pages_in_range(0, max_pfn); - - /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ - if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) { - printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n", - (numaram << PAGE_SHIFT) >> 20, - (e820ram << PAGE_SHIFT) >> 20); - return false; - } - return true; -} - /* * Mark all currently memblock-reserved physical memory (which covers the * kernel's own memory ranges) as hot-unswappable. @@ -583,7 +552,7 @@ static int __init numa_register_memblks(struct numa_meminfo *mi) return -EINVAL; } } - if (!numa_meminfo_cover_memory(mi)) + if (!memblock_validate_numa_coverage(SZ_1M)) return -EINVAL; /* Finally register nodes. */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1c1072e3ca06..0c3a193ebc58 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -120,6 +120,7 @@ int memblock_physmem_add(phys_addr_t base, phys_addr_t size); void memblock_trim_memory(phys_addr_t align); bool memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size); +bool memblock_validate_numa_coverage(const u64 limit); int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size); int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size); int memblock_mark_mirror(phys_addr_t base, phys_addr_t size); diff --git a/mm/memblock.c b/mm/memblock.c index 0863222af4a4..8f61f868bec1 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -734,6 +734,27 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size) return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0); } +bool __init_memblock memblock_validate_numa_coverage(const u64 limit) +{ + unsigned long lose_pg = 0; + unsigned long start_pfn, end_pfn; + int nid, i; + + /* calculate lose page */ + for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) { + if (nid == NUMA_NO_NODE) + lose_pg += end_pfn - start_pfn; + } + + if (lose_pg >= limit) { + pr_err("NUMA: We lost %ld pages.\n", lose_pg); + return false; + } + + return true; +} + + /** * memblock_isolate_range - isolate given range into disjoint memblocks * @type: memblock type to isolate range for
Optimize the way of calculating missing pages. In the previous implementation, We calculate missing pages as follows: 1. calculate numaram by traverse all the numa_meminfo's and for each of them traverse all the regions in memblock.memory to prepare for counting missing pages. 2. Traverse all the regions in memblock.memory again to get e820ram. 3. the missing page is (e820ram - numaram ) But,it's enough to count memory in ‘memblock.memory’ that doesn't have the node assigned. V3:https://lore.kernel.org/all/CACZJ9cUXiWxDb6hF4JFhWe7Np82k6LopVQ+_AoGFOccN4kjJqA@mail.gmail.com/#r V2:https://lore.kernel.org/all/20230619075315.49114-1-zhiguangni01@gmail.com/ V1:https://lore.kernel.org/all/20230615142016.419570-1-zhiguangni01@gmail.com/ Signed-off-by: Liam Ni <zhiguangni01@gmail.com> --- arch/x86/mm/numa.c | 33 +-------------------------------- include/linux/memblock.h | 1 + mm/memblock.c | 21 +++++++++++++++++++++ 3 files changed, 23 insertions(+), 32 deletions(-)