List:Internals« Previous MessageNext Message »
From:Rick James Date:July 3 2008 8:58pm
Subject:RE: mutex contention for the query cache
View as plain text  
> A hint for me has been high idle time reported by vmstat for workloads
> that should be CPU bound on multi-core servers. That has been the case
> for Linux 2.6 on 8 core servers.

I continue to run into anecdotal evidence saying:
  * HyperThreading slows down MySQL; turn it off.
  * 8-core Linux box runs slower than 4-core; turn off 4 cores.
  * "My db is melting down".  But the stats show low Disk usage, cpu
never above 12%.  This is on 8-core box.  (12% ~= 1/8, as if ONLY ONE
cpu is being used)
  * "MySQL does a poor job on inter-cpu contention"

Sorry, I don't yet have enough evidence to distinguish these possible
variables:
  * 4.1 or 5.1  (rather current versions of either)
  * RHEL 4u4 or 4u6
  * 32-bit or 64-bit
  * MyISAM or InnoDB

I see that Venu has talked to you:
http://venublog.com/2008/06/04/innodb-performance-on-4-and-8-core-cpu/

Do you have any further comments?  We stress MySQL a lot here.  And some
groups abandon MySQL for the big O.  I would like to make use of 8
cores, or help them otherwise get the most out of their MySQL box.
Thread
mutex contention for the query cacheMARK CALLAGHAN3 Jul
  • Re: mutex contention for the query cacheMARK CALLAGHAN3 Jul
    • Re: mutex contention for the query cacheMARK CALLAGHAN3 Jul
      • RE: mutex contention for the query cacheRick James3 Jul
        • Re: mutex contention for the query cacheMARK CALLAGHAN3 Jul
          • RE: mutex contention for the query cacheRick James3 Jul
            • Re: mutex contention for the query cacheMARK CALLAGHAN3 Jul
              • Re: mutex contention for the query cacheBrian Aker3 Jul
              • Re: mutex contention for the query cacheSergei Golubchik3 Jul
          • Re: mutex contention for the query cacheKonstantin Osipov3 Jul
            • Re: mutex contention for the query cacheBrian Aker3 Jul
              • Re: mutex contention for the query cacheSergey Petrunia3 Jul
                • Re: mutex contention for the query cacheBrian Aker3 Jul
                  • Re: mutex contention for the query cacheSergei Golubchik3 Jul
                    • Re: mutex contention for the query cacheBrian Aker4 Jul
                      • Re: mutex contention for the query cacheJonas Oreland4 Jul
                        • Re: mutex contention for the query cacheSergei Golubchik4 Jul
                          • Re: mutex contention for the query cacheJonas Oreland4 Jul
                            • Re: mutex contention for the query cacheJonas Oreland4 Jul
                              • Re: mutex contention for the query cacheKonstantin Osipov4 Jul
                      • Re: mutex contention for the query cacheMark Leith4 Jul
                      • Re: mutex contention for the query cacheMARK CALLAGHAN4 Jul
                        • Re: mutex contention for the query cacheBrian Aker4 Jul
                          • Re: mutex contention for the query cacheMARK CALLAGHAN5 Jul
                            • Re: mutex contention for the query cacheBrian Aker5 Jul
                            • Re: mutex contention for the query cacheJonas Oreland2 Aug
                              • Re: mutex contention for the query cacheFrazer Clement5 Aug
  • Re: mutex contention for the query cacheKonstantin Osipov3 Jul
  • Re: mutex contention for the query cacheJocelyn Fournier3 Jul
    • RE: mutex contention for the query cacheRick James3 Jul
      • Re: mutex contention for the query cacheJocelyn Fournier3 Jul
        • RE: mutex contention for the query cacheRick James3 Jul
  • Re: mutex contention for the query cacheAntony T Curtis3 Jul