Have you tested to be sure the security fixes even affect 1.6.0? The code
was significantly rewritten and I'm unsure if it is even affected.
On Mon, 3 Mar 2014, அண்ணாமலை குருசாமி wrote:
Hi Dormando,
Thanks for your response. Currently MySQL provides a memcached interface
using InnoDB
https://github.com/memcached/memcached/commit/7068e52aa30a5178265549d433d7289ef056b6a3
it was a reporting error in stats settings, fixed in newer versions. Why
did you try .15 and not .17?
The limit is correctly printed under vanilla stats output
(limit_maxbytes or something).
On Tue, 18 Feb
Stupid offhand idea:
If your data tends to fit into different size buckets (ie: sessions are
always this large, other things are always that large), memcached
internally has an LRU bucket per chunk size. You can use slab rebalance to
adjust how much memory each bucket has available. Could force
Can you get 'stats' output? What does listen_disabled_num say? Can you
start memcached with -o maxconns_fast, and does that change the errors you
get?
On Tue, 11 Feb 2014, Joe7 wrote:
Hi Ryan!
The client is PHP/Pecl memcached yes.
It is actually happening before the cache would get full too,
Ah, I saw this late.
Have you been through: http://memcached.org/timeouts yet?
On Tue, 11 Feb 2014, Jozsef Rekedt-Nagy wrote:
Hi,
We are seeing an issue pretty similar to
https://groups.google.com/forum/#!topic/memcached/nOHiaR77KDs
Every couple of seconds (and sometimes minutes, likely
of a leaked process and examine it.
On Fri, 24 Jan 2014, Den Samo wrote:
Hi Dormando,
It took some time but we installed .17 and still observe the same issue with
memory:
after 24 hours of run it consumed almost all memory from 48Gb available on
dedicated box memcached process shows:
Rss
try presizing the hash table and see if that helps for you
as well... but what'd be really interesting is to know if .17 is stable or
not, and if not, get the memcached-debug backtrace. This will allow me to
actually fix the underlying problem.
thank you!
-Dormando
On Wed, 22 Jan 2014, Doruk Deniz
I'm doubting between APC and memcached to store information in the RAM of my
server which has to expire automatically/be removed from the RAM after
x seconds.
Looking at APC for storing the value in RAM with 30 seconds expiration time
leaves the key forever in the RAM, up until someone
hi Dormando,
we use version 1.4.15. So it would be first step to update. Thank you!
Does your memory usage continue to go up while the number of connections is
stable, or do
the number of connections slowly increase with memory usage?
I am doing history query now. But to be sure, do you
On Mon, 30 Dec 2013, Den Samo wrote:
Dormando, thank you for so prompt reply.So, my historical query does not show
anything bad with curr_connections - typical saw without growth
trend. So we update to 17 and do observations. Also, as for fixed bug: do you
mean this
one:
https
Hi everybody,What would be best practice to set max connections? We have
memory leak issue (memory usage grows, eats all available memory,
process crashes). I use quotes as I am not sure that this is actually memory
leak. I still thinking on the way to validate this. One potential
suspect
Howdy memcached,
I've been thinking about how to cancel an in-flight pipelined request to
memcached. I'm using an RPC stack called finagle, and it typically cancels
RPCs in a single, standardized way, by closing the connection. However, if
requests are pipelined, I could
accidentally
http://code.google.com/p/memcached/wiki/ReleaseNotes1417
If you get crashes/hangs/etc, please try this verison and let us know!
I've not been able to properly reproduce the original bug myself.
--
---
You received this message because you are subscribed to the Google Groups
memcached group.
On Thu, 12 Dec 2013, mumb...@gmail.com wrote:
Hi all,
Just tried (and failed) to find any Python client with support for the
new-ish CAS operations on the binary protocol (i.e. CAS delete etc.). Does
anyone know of one - or have any plans for one? Or is there a fork of the C
libmemcached
Hi,
If you're still seeing issues at all; can you try 1.4.16, and use the
memcached-debug binary instead of the normal one? That should give more
useful information on the crash.
There should hardly be any lock contention at 5 threads unless you are
running an older version... The latest code
Pushed your branch, thanks!
On Fri, 29 Nov 2013, emcconville wrote:
Memcached v1.4.15 compiles just fine on OSX 10.9 with GCC v4.8.0. Xcode's
LLVM+clang will have some configuration conflicts.
All conflicts are minor, and are more related to testing. In this case: clang
works fine, but
SEGFAULTS, LETS FIX IT. SEE THE RELEASE NOTES FOR INFO.
cripes I suck.
-Dormando
--
---
You received this message because you are subscribed to the Google Groups
memcached group.
To unsubscribe from this group and stop receiving emails from it, send an email
to memcached+unsubscr
Hi All,
I want to implement CLOCK replacement policy in memcached to reduce the
contention problem. I remove the mutex_lock(cache_lock); and replace it
with a fine grain lock for each hv i.e., item_lock(hv);
My problem is that I have deadlock in my implementation. This deadlock is not
Hi,
unfortuantely 1.4 and 1.6 drifted apart. nobody's had the time or
motivation to merge them back together. Sorry :(
On Wed, 2 Oct 2013, Conglong Li wrote:
Hi,
I'm a student at Rice University working on a project about Memcached. I
noticed that there is a interesting feature in version
Hi,
I have a fresh CentOS 6.4 installation, up to date. I've installed memcached
and libevent. When I try to start memcache I get:
memcached -u memcached
Failed to open library default_engine.so: default_engine.so: cannot open
shared object file: No such file or directory
Whats strange
I apologize for not understanding more. So, all pages have been allocated
(i.e. Memcached cannot just grab a new page) and there's nothing in the tail
of the queue for something to evict. And that's because all recent items
are being written at the same moment?
That is, there's no
Hi,
I frequently connect via telnet to memcached server and run commands.
However, recently I have enabled SASL authentication support in memcached,
and as I understand telnet can now no longer be used as the binary protocol
has to be mandatorily used. So, I would like
to know if there is
Hi,
This post:
http://oldblog.antirez.com/post/update-on-memcached-redis-benchmark.html
says that running multiple single threaded servers is better than a single
multi threaded server.
A benchmark I did using memslap in the default configuration also support
this claim. using two
Hi,Since the best performance are usually achieved with #threads = #cores and
its recommended to run memcached with #worker_threads = #cores.
I was wondering why does memcached have a specific thread to accept new
connections rather than have the worker threads accept new connections?
One
I have /memcached-1.4.15 installed with libevent-2.0.21-stable on a
Centos/Cpanel server and am running it using:
memcached -d -m 2048 -p 11211 -u nobody -l 127.0.0.1
I do not have any itpatbles rules set allowing 11211 in my CSF firewall, as
it is my understanding that it would be a
You're running a very old version of memcached. Please upgrade, and let us
know if you still have problems.
On Mon, 12 Aug 2013, Patrick Rynhart wrote:
Hello,
We run memcached version 1.4.4-3.el6 for session caching with our Moodle
environment. We are finding that memcached suddenly stops
whaat the hell are you talking about???
It's not a problem! The twemcache people are inept and arrogant at
communicating what the fuck their thing does!
It's a *small* amount of memory. Don't go trying to solve problems because
of a fucking bulletpoint line item in a
Yes.
OS doesn't pre-allocate the full buffer.
Yes.
Memcached should easily handle million concurrent idle connections (given
enough memory).
Except, if user has only allocated 512MB/1GB RAM for TCP, it is possible at
runtime only four connections have eaten up all the memory, which
:)
On Mon, Jul 29, 2013 at 12:30 AM, dormando dorma...@rydia.net wrote:
Yes.
OS doesn't pre-allocate the full buffer.
Yes.
Memcached should easily handle million concurrent idle connections
(given enough memory).
Except, if user has only
Hi,
I've just added your access.
Sorry for the long delay: July got away from me and I'm just getting
through my inbox :( Hope you're still interested and available to help
with the wiki!
On Mon, 8 Jul 2013, Barnaby wrote:
Did you get my email address? I believe I sent it correctly, but I'm
Actually have been using memcached for years and didn't have any problem, but
find a new memcached proxy called twemproxy and it said:
- Maintains persistent server connections.
- Keeps connection count on the backend caching servers low.
Actually what wrong with memcached on the above
Benchmarking binprot is nearly useless: there's nothing inherent in the
protocol which makes it any faster for raw requests/responses. It does
give your application more flexiblity on doing your gets/sets. IE: noreply
commands for issuing sets without waiting for the response. You can also
pack
, Manish Jain wrote:
Nice. Is there any methodology I could apply to actually gather server side
response times, say even at the cost of slightly performance
degradation?
On Fri, Jul 12, 2013 at 3:47 PM, dormando dorma...@rydia.net wrote:
On a healthy machine, over the network
Howdy, I'm a technical writer at Facebook and I've recently been working on
internal documentation of our internal caching infrastructure. I would
be interested in working on the memcached wiki - not extensively modifying
it, but just cleaning it up, correcting grammar, that kind of thing.
Hi,
Saw something interesting today, hoping someone can confirm. If I run
memcached with these settings:
memcached -vv -m 1m -I 1m -p -t 12 -U 0 -D _ -f 1.05
There are 182 slab classes. I've set the max memory to 1 meg and my page size
to 1 meg. So in theory memcached should only
Can you post your test code?
On Thu, 28 Mar 2013, Oleksandr Drach wrote:
Hello memcacheders!
I am trying to make mass set/add operation from file using bash/php against
memcached server v 1.4.13.
It starts normally but reaching ~1000 items (~200KB) I am seeing that script
operations
start an instance that way does it not spike?
I've removed the machine from the cluster. Might be able to answer these
later after putting it back again.
On Wednesday, March 27, 2013 4:11:24 PM UTC-7, Dormando wrote:
There could be a brief spike when the hash_power_level is being
Hello Dormando!Thanks for your reply.
Description and requirements are:
- Memcached will be used a primary storage (i.e. not for caching MySQL).
- It should have failover feature (in case if one server fails all
connections goes to another server).
Basically something like Master-Slave
Dear memcached community,
It would be really good to build a failover memcached cluster.
As I know this functionality is not provided by default.
Hence as options - you may use CouchBase Server or something like Repcached.
Both of them has disadvantages: CouchBase Server is much slower,
this wrong.. after all its been a few years since I last
looked at the code.
Trond
On Tue, Feb 19, 2013 at 5:07 PM, Brian Aker br...@tangent.org wrote:
Hi,
On Feb 19, 2013, at 12:14 AM, dormando dorma...@rydia.net wrote:
Both keys go out okay, but the no-op at the end seems
Hey,
Looks like your paste got a bit weird, I see thread 3 twice in the second
one? What were the exact commadns you did for each dump?
Is there any chance you could run the memcached-debug binary from the
build tree and get another stack dump? It might help, though this might be
enough
and pony-less, unless I go get that pony myself.
-Dormando
--
---
You received this message because you are subscribed to the Google Groups
memcached group.
To unsubscribe from this group and stop receiving emails from it, send an email
to memcached+unsubscr...@googlegroups.com.
For more
On Feb 18, 2013, at 6:03 PM, Diogo Baeder diogobae...@gmail.com wrote:
I have no clue why libmemcached does that switch in the middle, but I
understood what you said about not expecting things to happen in an exact
order
Are you sure the data is on the same server? Libmemcached
You fork, then push to your own repo that you just forked.
If what you're doing worked, we'd be in one crazy chaotic world.
On Thu, 7 Feb 2013, zfad...@gmail.com wrote:
I tried:
I am getting:
Pushing to g...@github.com:memcached/memcached.git
ERROR: Permission to
what?
On Thu, 7 Feb 2013, zfad...@gmail.com wrote:
I thought you were sleeping? :)
On Thursday, February 7, 2013 11:09:01 AM UTC-8, Dormando wrote:
You fork, then push to your own repo that you just forked.
If what you're doing worked, we'd be in one crazy chaotic world
Hi.
I clone the code from github. After checkout engine-pu, I run autoreconf -f
--install to create configure, and fail.
aclocal tell me, no m4/version.m4. I copy version.sh from branch master, then
everything is ok.
I wonder why there isn't version.sh.
The autogen stuff got moved to a
response, but the data still exists. I installed
the twiemcached and do the same thing again, also, the problem replicated,
but not as frequently as official memcached server.
This afternoon I will try version 1.4.15, and report the result later.
在 2013年1月4日星期五UTC+8下午3时06分54秒,Dormando写道
I did test
this out:
https://github.com/dormando/memcached/commit/56ad41e1a19a7fc99da51bdca4fdcb524a300984
(a little further work would be required to make that change permanent).
On 64bit systems you can do 64bit-aligned 8 byte memory reads atomically,
so as long as the stats structure is all
academically, or do you have a problem
you're trying to solve?
On Fri, 4 Jan 2013, liubo wrote:
remove global mutex will get more speed up,right?
2013/1/4 liubo lb.falc...@gmail.com
For example,slabs_lock?? some global mutex.
2013/1/4 dormando dorma...@rydia.net
Hello.
I found
On Thu, 3 Jan 2013, 马庆升 wrote:
Server : 10 distributed memcached server, version 1.4.13, installed on 10
linux server with centos 6.3, no replication.Client : spymemcached 2.8.4
Problem:
I need to delete a cached data, with spymemcached client, I sent out the
delete request, and also
Hi,
Assume I have two memcached nodes (node A, B) at the beginning, and when I
added a new node C, portion of keys are remapped and thanks to consistent
hashing, only some of them.
Let assume a value with key foo originally at server A, is now being to
mapped to server C.
When I
If someone else wants to make them work, go for it.
I've already spent too much time making it work on old platforms with
outdated and increasingly rare architectures :/ The fallback isn't so
terrible and making everything portable is painful.
On Tue, 18 Dec 2012, David Walter wrote:
I thought
address them directly instead of
ignoring them and asking more off-topic questions.
Thanks, and my apologies,
-Dormando
On Sat, 27 Oct 2012, Kiran Kumar wrote:
Hi ,
I have Two Memcache Servers set up for my Application as shown below
String location = 10.1.1.1:11211 10.1.1.2:11211
?
That's fairly immature.
On Sat, 27 Oct 2012, Kiran Kumar wrote:
Hi ,
It seems that you are quite upset with my postings .
I am asking because i am working on a existing architecture , and i need to
follow the things as per now .
On Saturday, 27 October 2012 13:47:40 UTC+5:30, Dormando
http://memcached.org/timeouts
enjoy!
On Sat, 13 Oct 2012, aaron_08544 wrote:
Hi guys,
We have 2 memcached instance 3.5G each and is currently using 2.1G and 2.2G
without evictions cache hit rate is 100%. However from newrelic I am seeing
200ms ADD to memcached. It doesn't happen very
I am working on a heavy traffic web site , where there will be GB's of data
written per minute into our Memcache . So we have decided to use two separate
instances of Memcache for the application .
Right now the setup is that , there is NO clustering between Memcache1 and
Memcache2
if
Data is read from one instance needs to
delete from another instance at the same time .
Hope i am clear here .
On Thursday, 11 October 2012 21:14:50 UTC+5:30, Dormando wrote:
I am working on a heavy traffic web site , where there will be GB's
of data written per minute into our
http://memcached.org/tutorial
http://memcached.org/about
distributed, not replicated.
how many times are you going to ask this?
On Mon, 8 Oct 2012, Kiran Kumar wrote:
Is it posible that two Seperate Instances of Memcache communicate with each
other ??
Hi ,
I have got two applications
http://memcached.org/tutorial
http://memcached.org/about
distributed, not replicated.
On Mon, 8 Oct 2012, Kiran Kumar wrote:
I am going to have multiple Instances of Memcache Up and running for my
Application .
(Means Memcache-1 running on Server-A and Memcache-2 running on Server-B .
Hello Everyone.
I have a simple question.
I hope someone can help me.
Ok, let's go to the question.
Is there any way to configure memcached to generate logs?
Any times memcached stop to response requisitions and i don't know why
the proccess still up but doesn't work.. =//
free_chunks_end is just a counter for how many chunks are available in a
recently allocated slab page. So if a slab class grabs 1MB of new memory,
it'll have something in free_chunks_end temporarily, then it all moves
into free_chunks or otherwise gets used.
In 1.4.15 this counter is gone
Maybe I forgot to remove the stat.
Again, you're not doing anything wrong. free_chunks_end is just a weird
indicator.
free_chunks == free_chunks + free_chunks_end. that's all.
On Wed, 19 Sep 2012, mmsilveira wrote:
Dormando,
Thank you for your reply!
I understood your explanation. But I
Actually I think I made that change in 1.4.14, not 1.4.15. but whatever :P
I'll remove the stat for the next cut, sorry!
On Wed, 19 Sep 2012, dormando wrote:
Maybe I forgot to remove the stat.
Again, you're not doing anything wrong. free_chunks_end is just a weird
indicator.
free_chunks
! :)
But, without free_chunks_end indicator, what about the column Full? of
memcached-tool?
Mauricio
Em quarta-feira, 19 de setembro de 2012 17h15min51s UTC-3, Dormando escreveu:
Actually I think I made that change in 1.4.14, not 1.4.15. but whatever
:P
I'll remove the stat
Hi,
I don't know if this is a feature already - but is it possible to pause
memcache's expiry?
For example we cache a lot of data in memcached (sourced from MySQL) that is
read only. If the underlying code knows the MySQL server has failed it would
be handy to signal memcached, and
This morning, for about 12 minutes I experienced a period where my memcached
instance was not allowing me to set/add anything. Upon checking the
memcached.log file I found Failed to write, and not due to blocking: Broken
pipe
Memcached: 1.4.13
Server: RHEL 5
Client: PHP Memcache
Runs on
Hi,
I'm having major problems with installing the PHP client on my application
servers, so I'm trying to find another way to utilize the memcached
server.
I was thinking of installing both the server and client on a dedicated server
and writing a simple PHP API that will eventually just
Available at http://memcached.org/
No major fixes, just further performance tuning. Slowly rolling out
modernization of the thread scaling, and using this as a base for
once-a-month feature pushes that might even actually happen this time!
-Dormando
Hi all,
I've made a few little experiments with Memcached, and it fits my needs well
for 90% of my web application that is a simple CGI or FastCGI with
request/response services. The rest of my web app is a set of long-running
daemons that subscribe to a message queue and
wait for events
http://code.google.com/p/memcached/wiki/NewPerformance
http://code.google.com/p/memcached/wiki/Timeouts
If it's none of these issues, you should be strace'ing your update process
to see exactly what's taking time. strace (or similar tools) are
indespensible for any operator or engineer.
On Mon,
Dormando. I really appreciate your help.
On Monday, July 30, 2012 1:40:08 PM UTC+5:30, Dormando wrote:
Well if you have evictions, you're probably out of memory? This isn't
what
you were saying before though.
Get moar memoryyy?
On Mon, 30 Jul 2012, U.S. Adha wrote
(heh), so the page size can be
reduced to 512k or even 256k.
So we'll see what happens in a month!
-Dormando
As I said in my other response, you need to look into your client's error
handling. You're either overwriting items, not successfully setting some
items, or causing your client to break.
I don't think danga client has been actively supported for a very long
time, and it could be loaded with bugs.
Your startup options are bizarre...
memcached -m 8000 -l 127.0.0.1 -p 11211
^ just do that. don't add -L or -R and see if that helps any.
Also, we need to know the version and make of the client you're using. Any
example code or data for how you're trying to load it will be required to
see
Hi everyone
I'm a final year student in computer science at Universidad de Concepción,
Chile. My graduation project is about enhancing Memcached performance
using wait-free techniques in order to improve multithreading scalability.
I would like to know if someone has tried this before and
/25 dormando dorma...@rydia.net:
Hi everyone
I'm a final year student in computer science at Universidad de Concepción,
Chile. My graduation project is about enhancing Memcached performance
using wait-free techniques in order to improve multithreading scalability.
I would like to know
I recently tracked down a performance problem in our memcached setup, whose
source was the 50 item depth search that occurs in item_alloc. I was pleased
to see this fixed in 1.4.10, and we will be upgrading past this version soon.
Because this wiki page says that active development is
Stop advertising on everything. jesus.
On Wed, 18 Jul 2012, Yiftach Shoolman wrote:
We have integrated this capability into our memcached-cloud service, see more
details here
On Tue, Jul 17, 2012 at 3:43 AM, memcac...@googlecode.com wrote:
Status: New
Owner:
Have you seen/gone through this: http://memcached.org/timeouts
checked the common stuff on the page (not swapping a little bit or under
memory pressure/etc), and used the independent connection tester tool to
validate that just sets instead of gets or new connections are being
problematic? Going
Can you include the output of stats from your memcached instances?
Also that client is deprecated I think... you may have better luck with
one of the newer ones as listed on memcached.org/wiki
On Sun, 15 Jul 2012, shubham srivastava wrote:
Any update on the same.
Regards,
Shubham
On
Note that new enough (betaish?) mysqld's actually speak memcached
protocol, so you're not stuck with handlersocket.
On Sun, 8 Jul 2012, Ren wrote:
Probably worth noting that Wikipedia wanted a disk based cache last year.
They initially went with EhCache, but found it not good.
Eventually
included in the source tarball which also implements
the automove algorithm using manual move commands. You can write your own
in your own language, and submit ideas upstream that we may include later.
-Dormando
1. How would you port the redis command “KEYS *” to memcached?
[Assume that this will be used for a very large number of keys in a
production environment. Please justify your answers and explain how they meet
the stated needs.]
Your phrasing sounds like you're reading from a
Sorry, it's called COPYING, not LICENSE.
On Fri, 6 Jul 2012, jennindg wrote:
I just downloaded the latest tarball yesterday but did not see a LICENSE
file. There is a README, AUTHORS, NEWS and COPYING file but none of these
refer to a license.
On Thursday, July 5, 2012 2:36:35 PM UTC-4,
Hi guys,
What storage engines have been built for memcached now that it supports
different ones? Is there a list anywhere? I am in need of a key/value with
persistence and if there is something already in the works for memcached as a
storage engine, I will just jump on that. If not, I will
This is still a cache you're talking about?
If I use the definition that I used in my last memcached talk, no. I just
really want something as easy to use as memcached to store key/values that can
replicate and survive a node failure without data loss or loss of service and
is not
4:49:07 PM UTC-7, Dormando wrote:
That's a start, yes!
but:
2.5: switch to engine-pu branch (after cloning)
4: push back to your own branch
are all of the details.
On Thu, 21 Jun 2012, rajiv wrote:
OK I am going to do it the right way
)
==
On Sunday, June 24, 2012 11:18:00 PM UTC-7, Dormando wrote:
git clone etc
cd memcached
git checkout -b rajiv origin/engine-pu
On Sun, 24 Jun 2012, rajiv wrote:
I am having some git newbe trouble with the step 2.5
to diagnose a
problem, you're giving us the information from the bottom up. What is your
setup and what are the symptoms of you actual problem? get speed isn't
high enough? set speed isn't high enough? How are you testing memcached's
performance?
-Dormando
Hi all,
Suppose I have, say, 5 memcached servers and 3 clients. Let's say all the
processes are fine, but for whatever reason, a connection between one
client and one server is lost, e.g. there's a timeout and the socket closes.
Now what? The one client now only see 4 servers, but the
try to not ship code
which is patent encumbered, so please disclose any which may be in use in
your changes.
We really appreciate you taking the time to do this, at any rate. I would
love to see the code!
have fun,
-Dormando
On Wed, 20 Jun 2012, rajiv wrote:
Hi,
I work at Intel and we have
?
What I downloaded was:
memcached-memcached-1.6.0-beta1-77-ge70f5ac.zip
Just want to make sure I grabbed the right tree.
thanks,
\rajiv
On Wednesday, June 20, 2012 11:10:46 PM UTC-7, Dormando wrote:
Hey,
Wow, that sounds neat! I was hoping to bum some free hardware from
Is there any value in posting what I have today that was written against
1.6.0 Beta1?
Go for it, if you want!
on GitHub
2. Clone the repository to my local machine
3. Make my changes to the code locally
4. Push the commits back to gitHub
thanks,
\rajiv
On Thursday, June 21, 2012 10:54:15 AM UTC-7, Dormando wrote:
Life will be much easier if you can use git to check out the code tree
I had memcached version 1.2.5 installed in a test environment and using the
stats detail dump command to monitor gets, hits and sets on individual
keys.
I upgraded to 1.4.5 and then 1.4.13 and for both of these versions after I
turn on stats detail on, stats detail dump only returns END
Hello Yiftach, Dormando and everyone,
I work with Eyal exactly on that: OSes that get and lose physical memory at
runtime.
We are interested in memcached because it is an important cloud benchmark
which stresses the memory.
I think the way memcached deals with changes in the value
there's the -I commandline option?
On Thu, 14 Jun 2012, Raghu wrote:
I need to compile 32 bit version of memcached for windows. To increase item
size from 1 MB, what needs to be done? I don't see POWER_BLOCK in slabs.c. I
see
POWER_SMALLEST set to 1 in default_engine.h, is this the setting
Hi
I was wandering if is there any modification of memcached where the
cache size can be dynamically controlled?
If there is no such thing, how difficult will it be to create one?
The idea is that once in a while a thread will wake up and change the
cache size according to the available
http://code.google.com/p/memcached/wiki/Timeouts
have you been through this page, yet?
On Thu, 7 Jun 2012, Bahadir wrote:
Hi,
Lately we got traffic trouble with our news site so decided to start
using memcache. I've read about memcached but never tried it on
production.
Now i have a test
When we are under high load (10k+ requests per second) we start
getting communication failures (connection timouts,closed connection
during header) to memcached.
After a small period of time in this state we start getting mangled
returns from the cache. Some returns will contain two pages
501 - 600 of 993 matches
Mail list logo