We made new binaries for MySQL 5.0.67 build 10 which include next fixes:
- We addressed concerns about potential logging and statistics overhead, so now you can fully turn on / off query statistics for microslow patch and user statistics in runtime.
Next variables were added:
1 2 3 4 5 6 | | slow_query_log | ON | | slow_query_log_file | /var/lib/mysql/slow_query.log | for compatibility with MySQL 5.1 and | userstat_running | OFF | to control gathering of user statistics. |
With both slow_query_log = OFF and userstat_running = OFF we have no performance penalties of using of patches.
- Also we fixed potential memory leaks in microslow and userstats patches, the leak appeared under some workloads.
The -percona release includes:
1 2 3 4 5 6 7 8 9 10 11 12 | | innodb_check_defrag.patch | Session status to check fragmentation of the last InnoDB scan | 1.0 | Percona <info@percona.com> | GPL | The names are Innodb_scan_* | | userstatsv2.patch | SHOW USER/TABLE/INDEX statistics | V2 | Google | GPL | Added INFORMATION_SCHEMA.*_STATISTICS | | show_patches.patch | SHOW PATCHES | 1.0 | Jeremy Cole | N/A | | | innodb_io_patches.patch | Cluster of past InnoDB IO patches | 1.0 | Percona | GPL | This patch contains fixed (control_flush_and_merge_and_read, control_io-threads, adaptive_flush) | | innodb_show_hashed_memory.patch | Adds additional information of InnoDB internal hash table memories in SHOW INNODB STATUS | 1.0 | Percona <info@percona.com> | GPL | | | innodb_io_pattern.patch | Information schema table of InnoDB IO counts for each datafile pages | 1.0 | Percona <info@percona.com> | GPL | INFORMATION_SCHEMA.INNODB_IO_PATTERN | | microsec_process.patch | Adds INFOMATION_SCHEMA.PROCESSLIST with TIME_MS column | 1.0 | Percona <info@percona.com> | GPL | | | innodb_locks_held.patch | Add locks held, remove locked records in SHOW INNODB STATUS | 1.0 | Baron Schwartz <baron@xaprb.com> | GPL | Bug #29126 fix | | microslow_innodb.patch | Extended statistics in slow.log | 1.1 | Percona <info@percona.com> | GPL | | | mysqld_safe_syslog.patch | Patch allows redirect output of error.log to syslog-ng | 1.0 | Percona <info@percona.com> | GPL | Ported from Debian | | innodb_fsync_source.patch | Information of fsync callers in InnoDB | 1.0 | Google | GPL | | | innodb_show_bp.patch | show innodb buffer pool content | 1.0 | Percona <info@percona.com> | GPL | | |
and -percona-highperf release additionaly includes
1 2 | | split_buf_pool_mutex_fixed_optimistic_safe.patch | InnoDB patch to fix buffer pool scalability | 1.0 | Yasufumi Kinoshita | BSD | | | innodb_rw_lock.patch | Fix of InnoDB rw_locks | 1.0 | Yasufumi Kinoshita | BSD | |
You can download RPMs for RedHat / CentOS 4.x and 5.x for x86_64, binaries, sources and patches there
OurDelta builds of this should becoming soon.
When we are can see the release 5.1 with percona patches ?
Si,
No decided date yet, we are working on porting patch fixes to new tree.
Is there any specific method you suggest to follow upgrade path from 5.0.51 (or whatever) standard mysql to your percona-highperf build?
Assuming you’re using RPM with same layout you can upgrade same way as you would upgrade to MySQL versions of them.
(RPM from RedHat and MySQL for example use a bit different layout for the same platform)
Actually just update may not work. As we use different Vendor in RPM .spec the way to install is to delete old RPM (rpm -e) and install new one (rpm -i)
No build for win32? 🙂 ourdelta doesn’t do it either…
kas,
We have not focused on win32 development, and I even guess some our patches break windows compilation.
It comes from the fact we fix performance problems on production boxes, but MySQL is rarely run on Win32 production system.
I’m going to see if I can set aside some time to do some Win32 builds … And I’ll look at learning how to create msi binaries so that they may be easily installed.
If I have enough spare moments, I may build the Win32 binaries to permit storage engines to be installed as plugins. The last time I did that was an internal mysql “proof of concept” build I did more than 2 years ago. AFAIK, the zip file is still attached to the worklog. 2
Antony,
We may look into, though I expect problem with compilation (even for Solaris it is not compiled clean). And I don’t think we can make rw_lock working on Win32 (though we may exclude this patch)
Hello,
we have been using the 67-b10 version since around release, and we see a memory usage development that would indicate a meory leak?
Server version: 5.0.67-percona-highperf-b10-log MySQL Percona High Performance Edition (GPL)
http://nicholas.users.linpro.no/mysql-memory-month.png
Week 50 we ran stock redhat mysql . Early week 51 we installed the percona version. since then memory usage has been growing. Last week orso it ran out of swap space, so we added some more today 😉
We also run https://www.percona.com/mysql/5.0.68/RPM/rhel5/ another place, without the same problems.
greetings
-nicholas
nicholas,
can you show your my.cnf and SHOW GLOBAL VARIABLES
you can send me it in private email to vadim @ thisdomain
nicholas,
We created bug for this problem – https://bugs.launchpad.net/percona-patches/+bug/315619