Updating Mtmaps

[raczman]

Well, if you think machine is not loaded enough, add another thread? CPU is expensive, make it work to prove its worth

[higi]

Well, if you think machine is not loaded enough, add another thread? CPU is expensive, make it work to prove its worth

have 2x xoen quade core

tryied 8threads vs 16threads its we can say same result, main thread still takes too mutch:(/

anyway to improve your patch , or some good points?)

thx)

[leak]

I also tried 8 vs. 4 threads on quadcore - same results.

At 1100 ppl the spell lag starts to get annoying no matter which mtmaps patch i use. The database server is mostly idle (load: 0.01 0.04 0.00) doing around 250 qps.

[IAmParadox]

I also tried 8 vs. 4 threads on quadcore - same results.

At 1100 ppl the spell lag starts to get annoying no matter which mtmaps patch i use. The database server is mostly idle (load: 0.01 0.04 0.00) doing around 250 qps.

I don't have much experience with spell lag, as I don't run a big server, just me and my kids, mostly, but, looking at the way spells are handled in the core, I wonder if some of this couldn't be fixed by coming up with a more efficient way to handle them.

[leak]

20095 mangos    20   0 3365M 3086M  9204 S  0.0 38.8  0:22.05   1  |       `- ./mangos-worldd
20114 mangos    20   0 3365M 3086M  9204 S 15.0 38.8 18:41.60   3  |           `- ./mangos-worldd net
20113 mangos    20   0 3365M 3086M  9204 R 15.0 38.8 19:02.37   3  |           `- ./mangos-worldd net
20112 mangos    20   0 3365M 3086M  9204 S  0.0 38.8  2:08.27   4  |           `- ./mangos-worldd
20111 mangos    20   0 3365M 3086M  9204 S  0.0 38.8  0:00.07   3  |           `- ./mangos-worldd
20110 mangos    20   0 3365M 3086M  9204 S  3.0 38.8  8:36.75   3  |           `- ./mangos-worldd 1
20109 mangos    20   0 3365M 3086M  9204 S  5.0 38.8  8:38.27   4  |           `- ./mangos-worldd 2
20108 mangos    20   0 3365M 3086M  9204 S  0.0 38.8  0:05.35   3  |           `- ./mangos-worldd
20107 mangos    20   0 3365M 3086M  9204 S  4.0 38.8  8:35.49   4  |           `- ./mangos-worldd 3
20106 mangos    20   0 3365M 3086M  9204 S  7.0 38.8  8:40.32   3  |           `- ./mangos-worldd 4
20105 mangos    20   0 3365M 3086M  9204 S  7.0 38.8  8:38.72   1  |           `- ./mangos-worldd 5
20104 mangos    20   0 3365M 3086M  9204 S  3.0 38.8  8:38.34   2  |           `- ./mangos-worldd 6
20103 mangos    20   0 3365M 3086M  9204 S  2.0 38.8  2:36.87   3  |           `- ./mangos-worldd
20102 mangos    20   0 3365M 3086M  9204 S  7.0 38.8  8:35.39   2  |           `- ./mangos-worldd 7
20101 mangos    20   0 3365M 3086M  9204 R 71.0 38.8  1h19:04   1  |           `- ./mangos-worldd main
20099 mangos    20   0 3365M 3086M  9204 S  0.0 38.8  0:07.50   3  |           `- ./mangos-worldd
20098 mangos    20   0 3365M 3086M  9204 S  0.0 38.8  0:47.75   3  |           `- ./mangos-worldd
20097 mangos    20   0 3365M 3086M  9204 S  0.0 38.8  0:18.69   2  |           `- ./mangos-worldd

A new shot of racz new mtmaps patch. Clearly there is missing one thread (set to 8) and offloading the work from the main thread behaves like derex patch. It moves the lag border from 700 to 1100 for me but that's it - the hardware is still not really under load.

[panaut0lordv]

1100 is not MaNGOS lag starting barrier.

A lot of ppl get 2k+ on MaNGOS, but remember - SQL setup is essential.

[leak]

I've seen my mysql doing around 2000 qps without any problem. During mangos runtime the db server is almost idle with ~250 qps.

I'd really like to try a config from someone who claims to have 2k ppl online without noticeable lag.

[raczman]

net_buffer_length = 1024K

join_buffer_size = 2M

sort_buffer_size = 2M

read_buffer_size = 2M

read_rnd_buffer_size = 2M

table_cache = 500

max_allowed_packet = 4M

max_connections=300

max_user_connections=350

key_buffer = 256M

key_buffer_size = 256M

thread_cache = 256M

thread_concurrency = 8

thread_cache_size = 1024

thread_stack = 128K

default-character-set = utf8

innodb_flush_method=O_DIRECT

innodb_buffer_pool_size=1800M <= this depends on size of your characters DB

innodb_additional_mem_pool_size=50M

innodb_log_file_size=5M

innodb_log_buffer_size=4M

innodb_flush_log_at_trx_commit=0

innodb_thread_concurrency=8

innodb_file_per_table

innodb_table_locks=0

Well, dump tables before using, etc. 2k+ on that config.

[leak]

My config pretty much looks the same:

net_buffer_length         = 1024K
join_buffer_size          = 2M
sort_buffer_size          = 2M
read_buffer_size          = 2M
read_rnd_buffer_size      = 2M
table_cache                  = 500
max_allowed_packet        = 4M

max_connections         = 50

key_buffer_size              = 16M
thread_cache                = 256M
thread_concurrency        = 8
thread_cache_size          = 1024
thread_stack                = 128K

max_heap_table_size     = 32M
tmp_table_size          = 32M
long_query_time         = 5

innodb_buffer_pool_size         = 4196M
innodb_additional_mem_pool_size = 50M
innodb_data_file_path           = ibdata1:10M:autoextend
innodb_log_file_size            = 172M
innodb_log_buffer_size          = 7M
innodb_log_files_in_group       = 2
innodb_flush_method             = O_DIRECT
innodb_flush_log_at_trx_commit  = 0
innodb_thread_concurrency       = 8
innodb_file_per_table
innodb_table_locks              = 0

max_connections is useless since mangos needs only about 4.

the "key_buffer" variable doesn't exist and it is for MyISAM anyways

My innodb_buffer_pool_size might be a little too big since my last db cleanup but i never heard that could hurt.

[raczman]

That DB was connected to some php frontend and other tools used it, hence the max_connections

[higi]

any news about this? patch dont work like it should

[raczman]

First, i dont have time, second /* mod edit until further notice */. If you want to follow this patch's development (ill update it in few days), youll know where to look for it.

[Ambal]

i really think trying to support mangos was a mistake

Do you really think that helping community with patches/suggestions was a mistake? If so, then get lost, and do it quick...

[divisorxx]

First, i dont have time, second /* mod edit until further notice */. If you want to follow this patch's development (ill update it in few days), youll know where to look for it.

I'm glad to hear that you still working on this

[panaut0lordv]

Wyk3d, I think you're taking it too serious... calm down

To quote megamage:

"Alliance and Horde are fighting together against the Lich King. Why cannot Mangos and Trinity?"

[Merlin2009]

Raczman,

Does it work with FreeBSD too? I've gcc 4.2.1

[raczman]

Should work, if you have gcc.

[Merlin2009]

Should work, if you have gcc.

Thank you, it seems to work fine.

[Alex]

Nice innovation. Works fine, though I still do not understand how it avoid so much critical sections in threads, must be OpenMP magic somewhere

Oops. It does not avoid anything except explicitly specified random generator functions. This is potential source for a lot of problems with two threads writing the same data.

[painejake]

Working a treat

Here's the diff for anyone who wants it: http://painejake.gotdns.com/

Finally got round to updating it

[leak]

Is the part with the missing thread fixed?

[painejake]

Well its working fine for me.

This is the mtmaps3 patch from the TC patch queue however i haven't included the Windows side of this in there you will have to add those in if needed.. Or give me a bit more time to add it in. Seems to be no missing thread.

With near 200 users online all vmaps and 16 map threads: http://i257.photobucket.com/albums/hh232/painejake/Capture.png all thread show active.