On Sat, Jun 20, 2020 at 7:17 AM Andres Freund <and...@anarazel.de> wrote: > On 2020-06-19 17:42:41 +1200, Thomas Munro wrote: > > On Thu, Jun 18, 2020 at 6:05 PM Thomas Munro <thomas.mu...@gmail.com> wrote: > > > Here's a version that adds some documentation. > > > > I jumped on a dual socket machine with 36 cores/72 threads and 144GB > > of RAM (Azure F72s_v2) running Linux, configured with 50GB of huge > > pages available, and I ran a very simple test: select count(*) from t > > t1 join t t2 using (i), where the table was created with create table > > t as select generate_series(1, 400000000)::int i, and then prewarmed > > into 20GB of shared_buffers. > > I assume all the data fits into 20GB?
Yep. > Which kernel version is this? Tested on 4.19 (Debian stable/10). > How much of the benefit comes from huge pages being used, how much from > avoiding the dsm overhead, and how much from the page table being shared > for that mapping? Do you have a rough idea? Without huge pages, the 36 process version of the test mentioned above shows around a 1.1x speedup, which is in line with the numbers from my first message (which was from a much smaller computer). The rest of the speedup (2x) is due to huge pages. Further speedups are available by increasing the hash chunk size, and probably doing NUMA-aware allocation, in later work. Here's a new version, using the name min_dynamic_shared_memory, which sounds better to me. Any objections? I also fixed the GUC's maximum setting so that it's sure to fit in size_t.
From 3a77e8ab67e5492340425f1ce4a36a45a8c80d05 Mon Sep 17 00:00:00 2001 From: Thomas Munro <thomas.mu...@gmail.com> Date: Mon, 27 Jul 2020 12:07:05 +1200 Subject: [PATCH v3] Preallocate some DSM space at startup. Create an optional region in the main shared memory segment that can be used to acquire and release "fast" DSM segments, and can benefit from huge pages allocated at cluster startup time, if configured. Fall back to the existing mechanisms when that space is full. The size is controlled by a new GUC min_dynamic_shared_memory, defaulting to 0. Main region DSM segments initially contain whatever garbage the memory held last time they were used, rather than zeroes. That change revealed that DSA areas failed to initialize themselves correctly in memory that wasn't zeroed first, so fix that problem. Discussion: https://postgr.es/m/CA%2BhUKGLAE2QBv-WgGp%2BD9P_J-%3Dyne3zof9nfMaqq1h3EGHFXYQ%40mail.gmail.com --- doc/src/sgml/config.sgml | 26 +++ src/backend/storage/ipc/dsm.c | 184 ++++++++++++++++-- src/backend/storage/ipc/dsm_impl.c | 3 + src/backend/storage/ipc/ipci.c | 3 + src/backend/utils/misc/guc.c | 11 ++ src/backend/utils/misc/postgresql.conf.sample | 1 + src/backend/utils/mmgr/dsa.c | 5 +- src/include/storage/dsm.h | 3 + src/include/storage/dsm_impl.h | 1 + 9 files changed, 212 insertions(+), 25 deletions(-) diff --git a/doc/src/sgml/config.sgml b/doc/src/sgml/config.sgml index 6ce5907896..48fef11041 100644 --- a/doc/src/sgml/config.sgml +++ b/doc/src/sgml/config.sgml @@ -1864,6 +1864,32 @@ include_dir 'conf.d' </listitem> </varlistentry> + <varlistentry id="guc-min-dynamic-shared-memory" xreflabel="min_dynamic_shared_memory"> + <term><varname>min_dynamic_shared_memory</varname> (<type>integer</type>) + <indexterm> + <primary><varname>min_dynamic_shared_memory</varname> configuration parameter</primary> + </indexterm> + </term> + <listitem> + <para> + Specifies the amount of memory that should be allocated at server + startup time for use by parallel queries. When this memory region is + insufficient or exhausted by concurrent parallel queries, new + parallel queries try to allocate extra shared memory temporarily from + the operating system using the method configured with + <varname>dynamic_shared_memory_type</varname>, which may be slower + due to memory management overheads. + Memory that is allocated at startup time with + <varname>min_dynamic_shared_memory</varname> is affected by the + <varname>huge_pages</varname> setting on operating systems where that + is supported, and may be more likely to benefit from larger pages on + operating systems where page size is managed automatically. Larger + memory pages can improve the performance of parallel hash joins. + The default value is <literal>0</literal> (none). + </para> + </listitem> + </varlistentry> + </variablelist> </sect2> diff --git a/src/backend/storage/ipc/dsm.c b/src/backend/storage/ipc/dsm.c index ef64d08357..b9941496a3 100644 --- a/src/backend/storage/ipc/dsm.c +++ b/src/backend/storage/ipc/dsm.c @@ -35,10 +35,12 @@ #include "lib/ilist.h" #include "miscadmin.h" +#include "port/pg_bitutils.h" #include "storage/dsm.h" #include "storage/ipc.h" #include "storage/lwlock.h" #include "storage/pg_shmem.h" +#include "utils/freepage.h" #include "utils/guc.h" #include "utils/memutils.h" #include "utils/resowner_private.h" @@ -76,6 +78,8 @@ typedef struct dsm_control_item { dsm_handle handle; uint32 refcnt; /* 2+ = active, 1 = moribund, 0 = gone */ + size_t first_page; + size_t npages; void *impl_private_pm_handle; /* only needed on Windows */ bool pinned; } dsm_control_item; @@ -95,10 +99,15 @@ static dsm_segment *dsm_create_descriptor(void); static bool dsm_control_segment_sane(dsm_control_header *control, Size mapped_size); static uint64 dsm_control_bytes_needed(uint32 nitems); +static inline dsm_handle make_main_region_dsm_handle(int slot); +static inline bool is_main_region_dsm_handle(dsm_handle handle); /* Has this backend initialized the dynamic shared memory system yet? */ static bool dsm_init_done = false; +/* The address range of DSM space in the main shared memory segment. */ +static void *dsm_main_space_begin = NULL; + /* * List of dynamic shared memory segments used by this backend. * @@ -247,8 +256,12 @@ dsm_cleanup_using_control_segment(dsm_handle old_control_handle) if (refcnt == 0) continue; - /* Log debugging information. */ + /* If it was using the main shmem area, there is nothing to do. */ handle = old_control->item[i].handle; + if (is_main_region_dsm_handle(handle)) + continue; + + /* Log debugging information. */ elog(DEBUG2, "cleaning up orphaned dynamic shared memory with ID %u (reference count %u)", handle, refcnt); @@ -348,8 +361,11 @@ dsm_postmaster_shutdown(int code, Datum arg) if (dsm_control->item[i].refcnt == 0) continue; - /* Log debugging information. */ handle = dsm_control->item[i].handle; + if (is_main_region_dsm_handle(handle)) + continue; + + /* Log debugging information. */ elog(DEBUG2, "cleaning up orphaned dynamic shared memory with ID %u", handle); @@ -418,6 +434,45 @@ dsm_set_control_handle(dsm_handle h) } #endif +/* + * Reserve some space in the main shared memory segment for DSM segments. + */ +size_t +dsm_estimate_size(void) +{ + return 1024 * 1024 * (size_t) min_dynamic_shared_memory; +} + +/* + * Initialize space in the main shared memory segment for DSM segments. + */ +void +dsm_shmem_init(void) +{ + size_t size = dsm_estimate_size(); + bool found; + + if (size == 0) + return; + + dsm_main_space_begin = ShmemInitStruct("Preallocated DSM", size, &found); + if (!found) + { + FreePageManager *fpm = (FreePageManager *) dsm_main_space_begin; + size_t first_page = 0; + size_t pages; + + /* Reserve space for the FreePageManager. */ + while (first_page * FPM_PAGE_SIZE < sizeof(FreePageManager)) + ++first_page; + + /* Initialize it and give it all the rest of the space. */ + FreePageManagerInitialize(fpm, dsm_main_space_begin); + pages = (size / FPM_PAGE_SIZE) - first_page; + FreePageManagerPut(fpm, first_page, pages); + } +} + /* * Create a new dynamic shared memory segment. * @@ -434,6 +489,10 @@ dsm_create(Size size, int flags) dsm_segment *seg; uint32 i; uint32 nitems; + size_t npages = 0; + size_t first_page = 0; + FreePageManager *dsm_main_space_fpm = dsm_main_space_begin; + bool using_main_dsm_region = false; /* Unsafe in postmaster (and pointless in a stand-alone backend). */ Assert(IsUnderPostmaster); @@ -444,20 +503,48 @@ dsm_create(Size size, int flags) /* Create a new segment descriptor. */ seg = dsm_create_descriptor(); - /* Loop until we find an unused segment identifier. */ - for (;;) + /* + * Lock the control segment while we try to allocate from the main shared + * memory area, if configured. + */ + if (dsm_main_space_fpm) { - Assert(seg->mapped_address == NULL && seg->mapped_size == 0); - seg->handle = random(); - if (seg->handle == DSM_HANDLE_INVALID) /* Reserve sentinel */ - continue; - if (dsm_impl_op(DSM_OP_CREATE, seg->handle, size, &seg->impl_private, - &seg->mapped_address, &seg->mapped_size, ERROR)) - break; + npages = size / FPM_PAGE_SIZE; + if (size % FPM_PAGE_SIZE > 0) + ++npages; + + LWLockAcquire(DynamicSharedMemoryControlLock, LW_EXCLUSIVE); + if (FreePageManagerGet(dsm_main_space_fpm, npages, &first_page)) + { + /* We can carve out a piece of the main shared memory segment. */ + seg->mapped_address = (char *) dsm_main_space_begin + + first_page * FPM_PAGE_SIZE; + seg->mapped_size = npages * FPM_PAGE_SIZE; + using_main_dsm_region = true; + /* We'll choose a handle below. */ + } } - /* Lock the control segment so we can register the new segment. */ - LWLockAcquire(DynamicSharedMemoryControlLock, LW_EXCLUSIVE); + if (!using_main_dsm_region) + { + /* + * We need to create a new memory segment. Loop until we find an + * unused segment identifier. + */ + if (dsm_main_space_fpm) + LWLockRelease(DynamicSharedMemoryControlLock); + for (;;) + { + Assert(seg->mapped_address == NULL && seg->mapped_size == 0); + seg->handle = random() & ~1; /* Even numbers only */ + if (seg->handle == DSM_HANDLE_INVALID) /* Reserve sentinel */ + continue; + if (dsm_impl_op(DSM_OP_CREATE, seg->handle, size, &seg->impl_private, + &seg->mapped_address, &seg->mapped_size, ERROR)) + break; + } + LWLockAcquire(DynamicSharedMemoryControlLock, LW_EXCLUSIVE); + } /* Search the control segment for an unused slot. */ nitems = dsm_control->nitems; @@ -465,6 +552,14 @@ dsm_create(Size size, int flags) { if (dsm_control->item[i].refcnt == 0) { + if (using_main_dsm_region) + { + seg->handle = make_main_region_dsm_handle(i); + dsm_control->item[i].first_page = first_page; + dsm_control->item[i].npages = npages; + } + else + Assert(!is_main_region_dsm_handle(seg->handle)); dsm_control->item[i].handle = seg->handle; /* refcnt of 1 triggers destruction, so start at 2 */ dsm_control->item[i].refcnt = 2; @@ -479,9 +574,12 @@ dsm_create(Size size, int flags) /* Verify that we can support an additional mapping. */ if (nitems >= dsm_control->maxitems) { + if (using_main_dsm_region) + FreePageManagerPut(dsm_main_space_fpm, first_page, npages); LWLockRelease(DynamicSharedMemoryControlLock); - dsm_impl_op(DSM_OP_DESTROY, seg->handle, 0, &seg->impl_private, - &seg->mapped_address, &seg->mapped_size, WARNING); + if (!using_main_dsm_region) + dsm_impl_op(DSM_OP_DESTROY, seg->handle, 0, &seg->impl_private, + &seg->mapped_address, &seg->mapped_size, WARNING); if (seg->resowner != NULL) ResourceOwnerForgetDSM(seg->resowner, seg); dlist_delete(&seg->node); @@ -495,6 +593,12 @@ dsm_create(Size size, int flags) } /* Enter the handle into a new array slot. */ + if (using_main_dsm_region) + { + seg->handle = make_main_region_dsm_handle(nitems); + dsm_control->item[i].first_page = first_page; + dsm_control->item[i].npages = npages; + } dsm_control->item[nitems].handle = seg->handle; /* refcnt of 1 triggers destruction, so start at 2 */ dsm_control->item[nitems].refcnt = 2; @@ -580,6 +684,12 @@ dsm_attach(dsm_handle h) /* Otherwise we've found a match. */ dsm_control->item[i].refcnt++; seg->control_slot = i; + if (is_main_region_dsm_handle(seg->handle)) + { + seg->mapped_address = (char *) dsm_main_space_begin + + dsm_control->item[i].first_page * FPM_PAGE_SIZE; + seg->mapped_size = dsm_control->item[i].npages * FPM_PAGE_SIZE; + } break; } LWLockRelease(DynamicSharedMemoryControlLock); @@ -597,8 +707,9 @@ dsm_attach(dsm_handle h) } /* Here's where we actually try to map the segment. */ - dsm_impl_op(DSM_OP_ATTACH, seg->handle, 0, &seg->impl_private, - &seg->mapped_address, &seg->mapped_size, ERROR); + if (!is_main_region_dsm_handle(seg->handle)) + dsm_impl_op(DSM_OP_ATTACH, seg->handle, 0, &seg->impl_private, + &seg->mapped_address, &seg->mapped_size, ERROR); return seg; } @@ -688,8 +799,9 @@ dsm_detach(dsm_segment *seg) */ if (seg->mapped_address != NULL) { - dsm_impl_op(DSM_OP_DETACH, seg->handle, 0, &seg->impl_private, - &seg->mapped_address, &seg->mapped_size, WARNING); + if (!is_main_region_dsm_handle(seg->handle)) + dsm_impl_op(DSM_OP_DETACH, seg->handle, 0, &seg->impl_private, + &seg->mapped_address, &seg->mapped_size, WARNING); seg->impl_private = NULL; seg->mapped_address = NULL; seg->mapped_size = 0; @@ -729,10 +841,15 @@ dsm_detach(dsm_segment *seg) * other reason, the postmaster may not have any better luck than * we did. There's not much we can do about that, though. */ - if (dsm_impl_op(DSM_OP_DESTROY, seg->handle, 0, &seg->impl_private, + if (is_main_region_dsm_handle(seg->handle) || + dsm_impl_op(DSM_OP_DESTROY, seg->handle, 0, &seg->impl_private, &seg->mapped_address, &seg->mapped_size, WARNING)) { LWLockAcquire(DynamicSharedMemoryControlLock, LW_EXCLUSIVE); + if (is_main_region_dsm_handle(seg->handle)) + FreePageManagerPut((FreePageManager *) dsm_main_space_begin, + dsm_control->item[control_slot].first_page, + dsm_control->item[control_slot].npages); Assert(dsm_control->item[control_slot].handle == seg->handle); Assert(dsm_control->item[control_slot].refcnt == 1); dsm_control->item[control_slot].refcnt = 0; @@ -894,10 +1011,15 @@ dsm_unpin_segment(dsm_handle handle) * pass the mapped size, mapped address, and private data as NULL * here. */ - if (dsm_impl_op(DSM_OP_DESTROY, handle, 0, &junk_impl_private, + if (is_main_region_dsm_handle(handle) || + dsm_impl_op(DSM_OP_DESTROY, handle, 0, &junk_impl_private, &junk_mapped_address, &junk_mapped_size, WARNING)) { LWLockAcquire(DynamicSharedMemoryControlLock, LW_EXCLUSIVE); + if (is_main_region_dsm_handle(handle)) + FreePageManagerPut((FreePageManager *) dsm_main_space_begin, + dsm_control->item[control_slot].first_page, + dsm_control->item[control_slot].npages); Assert(dsm_control->item[control_slot].handle == handle); Assert(dsm_control->item[control_slot].refcnt == 1); dsm_control->item[control_slot].refcnt = 0; @@ -1094,3 +1216,23 @@ dsm_control_bytes_needed(uint32 nitems) return offsetof(dsm_control_header, item) + sizeof(dsm_control_item) * (uint64) nitems; } + +static inline dsm_handle +make_main_region_dsm_handle(int slot) +{ + /* + * We need to create a handle that doesn't collide with any existing extra + * segment created by dsm_impl_op(), so we'll make it odd. It also + * mustn't collide with any other main area pseudo-segment, so we'll + * include the slot number in some of the bits. We also want to make an + * effort to avoid newly created and recently destroyed handles from being + * confused, so we'll make the rest of the bits random. + */ + return 1 | (slot << 1) | (random() << (pg_leftmost_one_pos32(dsm_control->maxitems) + 1)); +} + +static inline bool +is_main_region_dsm_handle(dsm_handle handle) +{ + return handle & 1; +} diff --git a/src/backend/storage/ipc/dsm_impl.c b/src/backend/storage/ipc/dsm_impl.c index 1972aecbed..d4306418dc 100644 --- a/src/backend/storage/ipc/dsm_impl.c +++ b/src/backend/storage/ipc/dsm_impl.c @@ -113,6 +113,9 @@ const struct config_enum_entry dynamic_shared_memory_options[] = { /* Implementation selector. */ int dynamic_shared_memory_type; +/* Amount of space reserved for DSM segments in the main area. */ +int min_dynamic_shared_memory; + /* Size of buffer to be used for zero-filling. */ #define ZBUFFER_SIZE 8192 diff --git a/src/backend/storage/ipc/ipci.c b/src/backend/storage/ipc/ipci.c index 427b0d59cd..3c3b102b2b 100644 --- a/src/backend/storage/ipc/ipci.c +++ b/src/backend/storage/ipc/ipci.c @@ -119,6 +119,7 @@ CreateSharedMemoryAndSemaphores(void) size = add_size(size, SpinlockSemaSize()); size = add_size(size, hash_estimate_size(SHMEM_INDEX_SIZE, sizeof(ShmemIndexEnt))); + size = add_size(size, dsm_estimate_size()); size = add_size(size, BufferShmemSize()); size = add_size(size, LockShmemSize()); size = add_size(size, PredicateLockShmemSize()); @@ -208,6 +209,8 @@ CreateSharedMemoryAndSemaphores(void) */ InitShmemIndex(); + dsm_shmem_init(); + /* * Set up xlog, clog, and buffers */ diff --git a/src/backend/utils/misc/guc.c b/src/backend/utils/misc/guc.c index 6f603cbbe8..b973459b0f 100644 --- a/src/backend/utils/misc/guc.c +++ b/src/backend/utils/misc/guc.c @@ -2241,6 +2241,17 @@ static struct config_int ConfigureNamesInt[] = NULL, NULL, NULL }, + { + {"min_dynamic_shared_memory", PGC_POSTMASTER, RESOURCES_MEM, + gettext_noop("Amount of dynamic shared memory reserved at startup."), + NULL, + GUC_UNIT_MB + }, + &min_dynamic_shared_memory, + 0, 0, Min(INT_MAX, SIZE_MAX / 1024 / 1024), + NULL, NULL, NULL + }, + /* * We sometimes multiply the number of shared buffers by two without * checking for overflow, so we mustn't allow more than INT_MAX / 2. diff --git a/src/backend/utils/misc/postgresql.conf.sample b/src/backend/utils/misc/postgresql.conf.sample index 5a0b8e9821..cc48d58aa2 100644 --- a/src/backend/utils/misc/postgresql.conf.sample +++ b/src/backend/utils/misc/postgresql.conf.sample @@ -147,6 +147,7 @@ # windows # mmap # (change requires restart) +#min_dynamic_shared_memory = 0MB # (change requires restart) # - Disk - diff --git a/src/backend/utils/mmgr/dsa.c b/src/backend/utils/mmgr/dsa.c index b7ad8e62ef..6e5e412429 100644 --- a/src/backend/utils/mmgr/dsa.c +++ b/src/backend/utils/mmgr/dsa.c @@ -1223,6 +1223,7 @@ create_internal(void *place, size_t size, * space. */ control = (dsa_area_control *) place; + memset(place, 0, sizeof(*control)); control->segment_header.magic = DSA_SEGMENT_HEADER_MAGIC ^ control_handle ^ 0; control->segment_header.next = DSA_SEGMENT_INDEX_NONE; @@ -1233,14 +1234,10 @@ create_internal(void *place, size_t size, control->handle = control_handle; control->max_total_segment_size = (size_t) -1; control->total_segment_size = size; - memset(&control->segment_handles[0], 0, - sizeof(dsm_handle) * DSA_MAX_SEGMENTS); control->segment_handles[0] = control_handle; for (i = 0; i < DSA_NUM_SEGMENT_BINS; ++i) control->segment_bins[i] = DSA_SEGMENT_INDEX_NONE; - control->high_segment_index = 0; control->refcnt = 1; - control->freed_segment_counter = 0; control->lwlock_tranche_id = tranche_id; /* diff --git a/src/include/storage/dsm.h b/src/include/storage/dsm.h index 408c0543a6..0455576f4a 100644 --- a/src/include/storage/dsm.h +++ b/src/include/storage/dsm.h @@ -29,6 +29,9 @@ extern void dsm_postmaster_startup(struct PGShmemHeader *); extern void dsm_backend_shutdown(void); extern void dsm_detach_all(void); +extern size_t dsm_estimate_size(void); +extern void dsm_shmem_init(void); + #ifdef EXEC_BACKEND extern void dsm_set_control_handle(dsm_handle h); #endif diff --git a/src/include/storage/dsm_impl.h b/src/include/storage/dsm_impl.h index 562cb781a8..f6841e2534 100644 --- a/src/include/storage/dsm_impl.h +++ b/src/include/storage/dsm_impl.h @@ -40,6 +40,7 @@ /* GUC. */ extern int dynamic_shared_memory_type; +extern int min_dynamic_shared_memory; /* * Directory for on-disk state. -- 2.20.1
