The bdflush kernel daemon is a simple kernel daemon that provides a dynamic response to the system having too many dirty buffers; buffers that contain data that must be written out to disk at some time. It is started as a kernel thread at system startup time and, rather confusingly, it calls itself “kflushd” and that is the name that you will see if you use the ps command to show the processes in the system. Mostly this daemon sleeps waiting for the number of dirty buffers in the system to grow too large. As buffers are allocated and discarded the number of dirty buffers in the system is checked. If there are too many as a percentage of the total number of buffers in the system then bdflush is woken up. The default threshold is 60% but, if the system is desperate for buffers, bdflush will be woken up anyway. This value can be seen and changed using the update command:
# update -d bdflush version 1.4 0: 60 Max fraction of LRU list to examine for dirty blocks 1: 500 Max number of dirty blocks to write each time bdflush activated 2: 64 Num of clean buffers to be loaded onto free list by refill_freelist 3: 256 Dirty block threshold for activating bdflush in refill_freelist 4: 15 Percentage of cache to scan for free clusters 5: 3000 Time for data buffers to age before flushing 6: 500 Time for non-data (dir, bitmap, etc) buffers to age before flushing 7: 1884 Time buffer cache load average constant 8: 2 LAV ratio (used to determine threshold for buffer fratricide).
All of the dirty buffers are linked into the BUF_DIRTY LRU list whenever they are made dirty by having data written to them and bdflush tries to write a reasonable number of them out to their owning disks. Again this number can be seen and controlled by the update command and the default is 500 (see above).