Oninit Logo
The Down System Specialists
+1-913-674-0360
+44-2081-337529
Partnerships Contact
Onstat -a -b/-B -C -c -d/-D -F -f -G -h -i -j -k/-K -L -l -m -o -P -p -R -r -s -t/-T -u -X -x -z

onstat -R LRU Queues

The onstat -R command displays the current status of the LRU queues. The buffer pool is broken into a series of queues to improve accessibility and reduce buffer contention, with each LRU queue being further broken down into a free/clean side (FLRU) and a modified side (MLRU).


Buffer pool page size: 2048

32 buffer LRU queue pairs              priority levels
# f/m   pair total     % of    length       LOW      HIGH
 0 f      93736      99.9%    93626      83079      10547
 1 m                  0.1%      110         67         43
 2 f      93759      99.9%    93661      83114      10547
 3 m                  0.1%       98         50         48
 4 f      93751      99.9%    93628      83081      10547
 5 m                  0.1%      123         71         52
 6 f      93760      99.9%    93664      83117      10547
 7 m                  0.1%       96         52         44
.....
62 f      93753      99.9%    93655      83108      10547
63 m                  0.1%       98         53         45
3361 dirty, 3000000 queued, 3000000 total, 4194304 hash buckets, 2048 buffer size
start clean at  60.000% (of pair total) dirty, or 56250 buffs dirty, stop at
  50.000%

Buffer pool page size: 16384

32 buffer LRU queue pairs              priority levels
# f/m   pair total     % of    length       LOW      HIGH
 0 f      15625      97.2%    15194      14412        782
 1 m                  2.8%      431        228        203
 2 f      15624      97.0%    15149      14370        779
 3 m                  3.0%      475        214        261
 4 f      15625      97.2%    15186      14453        733
 5 m                  2.8%      439        199        240
 6 f      15625      96.9%    15135      14327        808
 7 m                  3.1%      490        241        249
....
62 f      15625      96.9%    15148      14326        822
63 m                  3.1%      477        229        248
15094 dirty, 500000 queued, 500000 total, 524288 hash buckets, 16384 buffer size
start clean at  60.000% (of pair total) dirty, or 9374 buffs dirty, stop at
  50.000%

Output Description

Heading Description Format See Also
Buffer pool page size Is the page size of the buffer pool in bytes Int  
# The LRU number (sequentially assigned). Each LRU is paired into a modified (MLRU) and free/clean side (FLRU). Dec  
f/m Describes the LRU queue type using the following coded values:
  f Free FLRU queue
  F Free FLRU with fewest buffers.
  m MRU queue
  M MRU is currently being cleaned by flusher
Str onstat -F
pair total The number of buffers currently assigned to this queue. Dec  
%of The percentage of the LRU this element of the pair represents. Flt  
length The total number of buffers on this LRU queue. Dec  
LOW The number of buffers on the low priority queue. Dec  
MED_LOW The number of buffers on the medium low priority queue. Dec  
MED_HIGH The number of buffers on the medium high priority queue. Dec  
HIGH The number of buffers on the high priority queue. Dec  

Summary Definitions

Label Description
dirty The total number of dirty pages within the LRUs.
queued The total number of pages queued into the LRUs. This number won’t necessarily match BUFFERS.
total The total number of buffer pages assigned to the LRU queue (same as BUFFERS).
hash buckets The number of hash buckets created to track the pages placed into the buffer pool.
buffer size The size of a single page within this OnLine instance. Page sizes can be 2K or 4K based on the port.
start clean Is the value specified in the lru_max_dirty field of the BUFFERPOOL configuration parameter
stop at Is the value specified in the lru_min_dirty field of the BUFFERPOOL configuration parameter
priority downgrades The number of buffers that have been downgraded from a higher priority queue to a lower priority queue.
priority upgrades The number of buffers that have been upgraded from a lower priority queue to a higher priority queue.

Notes

    The onstat -R command is not included as part of the onstat -a output.

    A free page is one that has not been used. A clean page is free page that has had a page written to it, but not modified. A dirty page is a clean page that has had modifications made to it.

    Pages can migrate amongst the LRU queues. For this reason, the number queued and the total number of buffers may not always correspond. In addition, the number of buffer pages per LRU queue may become slightly unbalanced.

    Each LRU queue is divided up into four separate priority queues: LOW, MED_LOW, MED_HIGH and HIGH.

    Pages with a priority of HIGH are considered last for page replacement; pages with a priority of LOW are considered first for page replacement. Page replacement priorities are utilized when no free pages exist in the buffer pool.

    Priorities are part of the Dynamic Buffer Management API incorporated into the server.

Monitoring and Tuning

    Upon startup, OnLine will divide the number of pages in the buffer pool among the LRU queues as evenly as possible. The LRU queues are designed to help reduce contention among active threads within the same OnLine instance. In addition, they assist in reducing the processing load required for a checkpoint. When the LRU_MAX_DIRTY percentage of pages for an LRU is exceeded, a page cleaner is assigned to the LRU to begin flushing dirty pages out to disk until only the LRU_MIN_DIRTY percentage of pages remains in the queue.

    Setting the value for LRU_MIN_DIRTY and LRU_MAX_DIRTY should be driven by the length of the system checkpoints. If the checkpoint duration is too long, it can possibly be reduced by lowering the values for LRU_MIN_DIRTY and LRU_MAX_DIRTY. This will reduce the overall number of dirty pages remaining in the buffer pool.

    Tuning the value for LRUS, which defaults to 8, depends on whether the tuning is being performed to reduce buffer contention or reduce checkpoint duration.

    There is no metric to determine that they are too few LRUS, but LRU contention can be tested via onstat -g spi. If there is contention you need more LRUs. Contention is the ratio of the total spin waits and the sum of the page reads and bufferwrits [onstat -p.

To discuss how Oninit ® can assist please call on +1-913-674-0360 or alternatively just send an email specifying your requirements.