Re: LWLock statistics collector (was: CSStorm occurred again by postgreSQL8.2) - Mailing list pgsql-hackers

Katsuhiko Okano wrote:
> Since the cause was found and the provisional patch was made 
> and solved about the CSStorm problem in previous mails, it reports.
(snip)
> (A) The algorithm which replaces a buffer is bad.
> A time stamp does not become new until swapout completes 
> the swapout page.
> If access is during swap at other pages, the swapout page will be 
> in the state where it is not used most,
> It is again chosen as the page for swapout.
> (When work load is high)

The following is the patch.


diff -cpr postgresql-8.1.4-orig/src/backend/access/transam/slru.c
postgresql-8.1.4-SlruSelectLRUPage-fix/src/backend/access/transam/slru.c

*** postgresql-8.1.4-orig/src/backend/access/transam/slru.c    2006-01-21 13:38:27.000000000 +0900

--- postgresql-8.1.4-SlruSelectLRUPage-fix/src/backend/access/transam/slru.c    2006-07-25 18:02:49.000000000 +0900

*************** SlruSelectLRUPage(SlruCtl ctl, int pagen

*** 703,710 ****
     for (;;)
     {
         int            slotno;

!         int            bestslot = 0;
         unsigned int bestcount = 0;
 
         /* See if page already has a buffer assigned */
         for (slotno = 0; slotno < NUM_SLRU_BUFFERS; slotno++)

--- 703,712 ----
     for (;;)
     {
         int            slotno;

!         int            bestslot = -1;

!         int            betterslot = -1;
         unsigned int bestcount = 0;

+         unsigned int bettercount = 0;
 
         /* See if page already has a buffer assigned */
         for (slotno = 0; slotno < NUM_SLRU_BUFFERS; slotno++)

*************** SlruSelectLRUPage(SlruCtl ctl, int pagen

*** 720,732 ****
          */
         for (slotno = 0; slotno < NUM_SLRU_BUFFERS; slotno++)
         {

!             if (shared->page_status[slotno] == SLRU_PAGE_EMPTY)

!                 return slotno;

!             if (shared->page_lru_count[slotno] > bestcount &&

!                 shared->page_number[slotno] != shared->latest_page_number)

!             {

!                 bestslot = slotno;

!                 bestcount = shared->page_lru_count[slotno];
             }
         }
 

--- 722,746 ----
          */
         for (slotno = 0; slotno < NUM_SLRU_BUFFERS; slotno++)
         {

!              switch (shared->page_status[slotno])

!              {

!                  case SLRU_PAGE_EMPTY:

!                      return slotno;

!                  case SLRU_PAGE_READ_IN_PROGRESS:

!                  case SLRU_PAGE_WRITE_IN_PROGRESS:

!                     if (shared->page_lru_count[slotno] > bettercount &&

!                         shared->page_number[slotno] != shared->latest_page_number)

!                     {

!                         betterslot = slotno;

!                         bettercount = shared->page_lru_count[slotno];

!                     }

!                  default:    /* SLRU_PAGE_CLEAN,SLRU_PAGE_DIRTY */

!                     if (shared->page_lru_count[slotno] > bestcount &&

!                         shared->page_number[slotno] != shared->latest_page_number)

!                     {

!                         bestslot = slotno;

!                         bestcount = shared->page_lru_count[slotno];

!                     }
             }
         }
 

*************** SlruSelectLRUPage(SlruCtl ctl, int pagen

*** 736,741 ****

--- 750,758 ----
         if (shared->page_status[bestslot] == SLRU_PAGE_CLEAN)
             return bestslot;
 

+         if (bestslot == -1)

+             bestslot = betterslot;

+ 
         /*
          * We need to do I/O.  Normal case is that we have to write it out,
          * but it's possible in the worst case to have selected a read-busy



Regards,
--------
Katsuhiko Okano
okano katsuhiko _at_ oss ntt co jp