Simon Riggs <[EMAIL PROTECTED]> writes: > The output you gave wasn't anything I recognize in the code. Assuming > its not already there, please can you share code you are using to find > the evidence, even if its just privately in some form?
See below. Also, the message I previously mentioned shows a different tack on the same theme: http://archives.postgresql.org/pgsql-patches/2003-12/msg00365.php although in the light of later events I think that keeping the counts in shared memory like that is a bad idea --- too likely to skew the results. > You're looking at the number of spins to acquire each lock? Number of semop waits. > Manfred's earlier patch provides very clear output for observing > contention, including full summaries. Could we commit that, so we can > all use this for analysis? Updated with the wait info. What patch would that be? regards, tom lane *** src/backend/storage/ipc/ipc.c.orig Tue Nov 22 16:06:33 2005 --- src/backend/storage/ipc/ipc.c Tue Nov 29 12:27:13 2005 *************** *** 125,130 **** --- 125,132 ---- { elog(DEBUG3, "shmem_exit(%d)", code); + LWLockStats(); + /* * call all the registered callbacks. * *** src/backend/storage/lmgr/lwlock.c.orig Tue Dec 6 18:08:33 2005 --- src/backend/storage/lmgr/lwlock.c Tue Dec 6 18:16:05 2005 *************** *** 21,26 **** --- 21,28 ---- */ #include "postgres.h" + #include <unistd.h> + #include "access/clog.h" #include "access/multixact.h" #include "access/subtrans.h" *************** *** 32,37 **** --- 34,43 ---- /* We use the ShmemLock spinlock to protect LWLockAssign */ extern slock_t *ShmemLock; + static int num_counts; + static int *sh_acquire_counts; + static int *ex_acquire_counts; + static int *block_counts; typedef struct LWLock { *************** *** 209,214 **** --- 215,226 ---- LWLockCounter = (int *) ((char *) LWLockArray - 2 * sizeof(int)); LWLockCounter[0] = (int) NumFixedLWLocks; LWLockCounter[1] = numLocks; + + /* local counter space */ + num_counts = numLocks; + sh_acquire_counts = calloc(numLocks, sizeof(int)); + ex_acquire_counts = calloc(numLocks, sizeof(int)); + block_counts = calloc(numLocks, sizeof(int)); } *************** *** 257,262 **** --- 269,278 ---- int extraWaits = 0; PRINT_LWDEBUG("LWLockAcquire", lockid, lock); + if (mode == LW_EXCLUSIVE) + ex_acquire_counts[lockid]++; + else + sh_acquire_counts[lockid]++; /* * We can't wait if we haven't got a PGPROC. This should only occur *************** *** 328,333 **** --- 344,351 ---- if (!mustwait) break; /* got the lock */ + block_counts[lockid]++; + /* * Add myself to wait queue. * *************** *** 598,601 **** --- 616,640 ---- return true; } return false; + } + + void + LWLockStats(void) + { + int pid = getpid(); + int i; + + LWLockAcquire(0, LW_EXCLUSIVE); + + for (i = 0; i < num_counts; i++) + { + if (sh_acquire_counts[i] || ex_acquire_counts[i] || block_counts[i]) + { + fprintf(stderr, "PID %d lwlock %d: shacq %u exacq %u blk %u\n", + pid, i, sh_acquire_counts[i], ex_acquire_counts[i], + block_counts[i]); + } + } + + LWLockRelease(0); } ---------------------------(end of broadcast)--------------------------- TIP 2: Don't 'kill -9' the postmaster
