We have a client with 320GB database (running FB CS v2.5) reporting performance issues, while we are investigating possible application sources, I have been reviewing their Firebird config.

 

Yesterday, I ran fb_lock_print to check on the database and found a “Mutex wait” value of 20.9%, which I knew that a “bad thing”.  So, I increased (by 50%) the “Hash slots” value from 60011 to 90001.

 

Now, today, I checked the lock print values again, and got even worse numbers!!!

 

        LOCK_HEADER BLOCK

                Version: 145, Active owner:      0, Length: 67108864, Used: 32723368

                Flags: 0x0001

                Enqs: 712175161, Converts: 9327661, Rejects: 1440802, Blocks: 15963765

                Deadlock scans:      9, Deadlocks:      0, Scan interval:  10

                Acquires: 1133127873, Acquire blocks: 256464312, Spin count:   0

                Mutex wait: 22.6%

                Hash slots: 90001, Hash lengths (min/avg/max):    0/   0/   5

                Remove node:      0, Insert queue:      0, Insert prior:      0

                Owners (288):   forward: 732776, backward: 29775680

                Free owners (400):      forward: 9817904, backward: 9548560

                Free locks (28162):     forward: 20344528, backward: 18378944

                Free requests (293517): forward: 7727280, backward: 23127520

                Lock Ordering: Enabled

 

 

Any suggestions on how I can improve the numbers?

 

Thanks in advance

 

Sean