[大数据]SQLite学习之路④ cache具体结构（2021SC@SDUSC）

PgHdr1在pcache1.c里定义,PgHdr在pcache.c里定义，MemPage在btree.c里定义。PgHdr1的头是sqlite3_pcache_page的子类pghdr1包含需要查找的页面的页号信息；PgHdr保存了哪些页面是脏页；MemPage包含了数据库页的一些信息，可以理解为MemPage结构体。
sqlite3_pcache_page中的pBuf指向数据库页内容的开始地方，pExtra指向PgHdr
sqlite3_pcache_page结构体如下：

struct sqlite3_pcache_page {
  void *pBuf;        /* The content of the page */
  void *pExtra;      /* Extra information associated with the page */
};

新建一个page cache：

pPg = pcache1Alloc(pCache->szAlloc);
p = (PgHdr1 *)&((u8 *)pPg)[pCache->szPage];
p->page.pBuf = pPg;
p->page.pExtra = &p[1];

PCache 结构体如下：

struct PCache {
  PgHdr *pDirty, *pDirtyTail;         /* List of dirty pages in LRU order */
  PgHdr *pSynced;                     /* Last synced page in dirty page list */
  int nRefSum;                        /* Sum of ref counts over all pages */
  int szCache;                        /* Configured cache size */
  int szSpill;                        /* Size before spilling occurs */
  int szPage;                         /* Size of every page in this cache */
  int szExtra;                        /* Size of extra space for each page */
  u8 bPurgeable;                      /* True if pages are on backing store */
  u8 eCreate;                         /* eCreate value for for xFetch() */
  int (*xStress)(void*,PgHdr*);       /* Call to try make a page clean */
  void *pStress;                      /* Argument to xStress */
  sqlite3_pcache *pCache;             /* Pluggable cache module */
};

PCache 结构体如下：

struct PCache1 {
  /* Cache configuration parameters. Page size (szPage) and the purgeable
  ** flag (bPurgeable) and the pnPurgeable pointer are all set when the
  ** cache is created and are never changed thereafter. nMax may be
  ** modified at any time by a call to the pcache1Cachesize() method.
  ** The PGroup mutex must be held when accessing nMax.
  */
  PGroup *pGroup;                     /* PGroup this cache belongs to */
  unsigned int *pnPurgeable;          /* Pointer to pGroup->nPurgeable */
  int szPage;                         /* Size of database content section */
  int szExtra;                        /* sizeof(MemPage)+sizeof(PgHdr) */
  int szAlloc;                        /* Total size of one pcache line */
  int bPurgeable;                     /* True if cache is purgeable */
  unsigned int nMin;                  /* Minimum number of pages reserved */
  unsigned int nMax;                  /* Configured "cache_size" value */
  unsigned int n90pct;                /* nMax*9/10 */
  unsigned int iMaxKey;               /* Largest key seen since xTruncate() */
  unsigned int nPurgeableDummy;       /* pnPurgeable points here when not used*/

  /* Hash table of all pages. The following variables may only be accessed
  ** when the accessor is holding the PGroup mutex.
  */
  unsigned int nRecyclable;           /* Number of pages in the LRU list */
  unsigned int nPage;                 /* Total number of pages in apHash */
  unsigned int nHash;                 /* Number of slots in apHash[] */
  PgHdr1 **apHash;                    /* Hash table for fast lookup by key */
  PgHdr1 *pFree;                      /* List of unused pcache-local pages */
  void *pBulk;                        /* Bulk memory used by pcache-local */
};

PCache主要是对脏页面链表进行管理。并使用了LRU算法(近期最少使用算法)，而PCache1是页面缓冲区的具体实现。这个缓冲区中有多个页，这些页存储在Hash表apHash中。apHash是一链接法解决地址冲突的Hash表，而apHash是PgHdr1结构中采用的指针数组，且有nHash个槽位，每个槽位上是一个页面链表。

PgHdr 结构体如下：

struct PgHdr {
  sqlite3_pcache_page *pPage;    /* Pcache object page handle */
  void *pData;                   /* Page data */
  void *pExtra;                  /* Extra content */
  PCache *pCache;                /* PRIVATE: Cache that owns this page */
  PgHdr *pDirty;                 /* Transient list of dirty sorted by pgno */
  Pager *pPager;                 /* The pager this page is part of */
  Pgno pgno;                     /* Page number for this page */
#ifdef SQLITE_CHECK_PAGES
  u32 pageHash;                  /* Hash of page content */
#endif
  u16 flags;                     /* PGHDR flags defined below */

  /**********************************************************************
  ** Elements above, except pCache, are public.  All that follow are
  ** private to pcache.c and should not be accessed by other modules.
  ** pCache is grouped with the public elements for efficiency.
  */
  i16 nRef;                      /* Number of users of this page */
  PgHdr *pDirtyNext;             /* Next element in list of dirty pages */
  PgHdr *pDirtyPrev;             /* Previous element in list of dirty pages */
                          /* NB: pDirtyNext and pDirtyPrev are undefined if the
                          ** PgHdr object is not dirty */
};

PgHdr1结构体如下：

struct PgHdr1 {
  sqlite3_pcache_page page;      /* Base class. Must be first. pBuf & pExtra */
  unsigned int iKey;             /* Key value (page number) */
  u16 isBulkLocal;               /* This page from bulk local storage */
  u16 isAnchor;                  /* This is the PGroup.lru element */
  PgHdr1 *pNext;                 /* Next in hash table chain */
  PCache1 *pCache;               /* Cache that currently owns this page */
  PgHdr1 *pLruNext;              /* Next in LRU list of unpinned pages */
  PgHdr1 *pLruPrev;              /* Previous in LRU list of unpinned pages */
                                 /* NB: pLruPrev is only valid if pLruNext!=0 */
};

Struct PgHdr 是页面的头部，用来控制缓冲区中页面；Struct PgHdr1每个缓冲区入口，可以大致理解为：通过它，可以获得数据库页面的渠道。