On Wed, Dec 18, 2019 at 3:53 AM James(王旭) <wangxu@gu360.com> wrote:
>
> Hello,
>>
>> I encountered into this kernel message, and I cannot login into the Linux system anymore:
>>
>>
>>
>>> Dec 17 23:01:50 hq-pg kernel: sh (6563): drop_caches: 1
>>>
>>> Dec 17 23:02:30 hq-pg kernel: INFO: task sync:6573 blocked for more than 120 seconds.
>>>
>>> Dec 17 23:02:30 hq-pg kernel: "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
>>>
>>> Dec 17 23:02:30 hq-pg kernel: sync D ffff965ebabd1040 0 6573 6572 0x00000080
>>>
>>> Dec 17 23:02:30 hq-pg kernel: Call Trace:
>>>
>>> Dec 17 23:02:30 hq-pg kernel: [<ffffffffa48760a0>] ? generic_write_sync+0x70/0x70
>>
>>
>> After some google I guess it's the problem that IO speed is low, while the insert requests are coming too much
quickly.SoPG put these into cache first then kernel called sync.
>>
>> I know I can queue the requests, so that POSTGRES will not accept these requests which will result in an increase in
systemcache.
>>
>> But is there any way I can tell POSTGRES, that you can only handle 20000 records per second, or 4M per second,
pleasedon't accept inserts more than that speed.
>>
>> For me, POSTGRES just waiting is much better than current behavior.
>>
>>
>> Any help will be much appreciated.
This is more a problem with the o/s than with postgres itself.
synchronous_commit is one influential parameter that can possibly help
mitigate the issue with some safety tradeoffs (read the docs). For
linux, one possible place to look is tuning dirty_background_ratio and
related parameters. The idea is you want the o/s to be more
aggressive about syncing to reduce the impact of i/o storm; basically
you are trading off some burst performance for consistency of
performance. Another place to look is checkpoint behavior. Do some
searches, there is tons of information about this on the net.
merlin
