THIS! A well-reasoned and clear explanation of a very difficult topic. This is
the kind of gold that a user mailing list can provide. Thank you, Alain!
Sean Durity
From: Alain RODRIGUEZ <arodr...@gmail.com>
Sent: Tuesday, July 03, 2018 6:37 AM
To: user cassandra.apache.org <user@cassandra.apache.org>
Subject: [EXTERNAL] Re: JVM Heap erratic
Hello Randy,
It's normal that the memory in the heap is having this pattern. Java uses
memory available and when needed clean some memory for new needs, that's the
variation you see. In your case, it's not really regular but this can depend on
the workload as well.
I'm a C# .NET guy, so I have no idea if this is normal Java behavior.
I feel you. I started operating Cassandra with no clue about the Garbage
collection and other JVM stuff. When I started tuning it the first time with
some former colleagues, we ended up removing half of the nodes of the cluster
and still divided latency per 2. It is an important part of Cassandra to tune
and often people (including myself) overlook it because it's too complex. I'll
try to give you a big picture so you can have some analysis of what's going on
and hopefully do some good to this cluster ("some good" - maybe not remove half
of the nodes and reduce the latency, this was really a strong improvement on a
badly tuned GC, but let's see :) ).
The heap is a limited amount of memory used to store Java objects. It's
composed of 3 sections: The New Generation, The Old Generation, the Permananent
Generation. New objects go to the New Gen ('HEAP_NEW_SIZE' in CMS, auto in G1GC
- do not set). From time to time, depending on usage and tuning, surviving
objects are pushed from the Eden Space where they first land to one of the 2
survivor space (the other one is empty). Then, depending on the tenuring
threshold option (in CMS, auto in G1GC too I believe), the data will be passed
from one survivor to the other one, expiring old data in the process. This
cleaning process in the New Gen is called the minor garbage collection (Minor
GC) and is triggered when Eden is full. After the tenuring threshold is reached
and the object was moved around survivor spaces x times, surviving objects will
be promoted (or tenured) to the Old Gen. This promotion of living objects is
referenced as a Major GC.
This is the most expensive GC, and even though it will have to happen from time
to time in almost all cases, it's interesting to reduce the total duration and
frequency of Major GC to improve GC statistics overall. We can ignore the
permanent Gen that is not triggering any important GC activity.
Some more information is available here:
http://www.oracle.com/webfolder/technetwork/tutorials/obe/java/gc01/index.html<https://urldefense.proofpoint.com/v2/url?u=http-3A__www.oracle.com_webfolder_technetwork_tutorials_obe_java_gc01_index.html&d=DwMFaQ&c=MtgQEAMQGqekjTjiAhkudQ&r=aC_gxC6z_4f9GLlbWiKzHm1vucZTtVYWDDvyLkh8IaQ&m=_N23kKi9SY0Tt1hzPDfk1n9Mg6eqAQOI_sIwbUN_L88&s=slQHkmb7FuzuYYwsrwsj1tJsBSECBUGuJoqJoOL199Q&e=>
In Cassandra, especially, in read-heavy workloads, objects can often expire
before being promoted if given enough space and time to do so. And this is way
more performant than promoting objects because we hadn't them surviving long
enough in the New Gen.
Using CMS with 20 GB is not recommended (out of the box, as a starting point at
least) because CMS performances are known to degrade quickly with bigger heap
than 8 GB. 20 GB is a lot. It also depends on the total memory available.
tried 8GB = OOM
tried 12GB = OOM
tried 20GB w/ G1 = OOM (and long GC pauses usually over 2 secs)
tried 20GB w/ CMS = running
OOM are not only related to the space available but also to the impossibility
to clean the heap efficiently enough before we need the space. Thus tuning some
more option than just the heap size might help.
CMS (over G1CG)
HEAP: 8 to 16 GB.
NEW_HEAP: 25 to 50 % - nothing to do with CPU core contrary to
documentation/comments in the file imho
MaxTenuringThreshold: 15 - From 1 all the way up to 15, that's what gave me the
best results in the past, it reduces major GC and makes the most of New
Gen/minor GC, that are less impacting, but still "stop the world GC". Default
is 1, which is often way to short to expire objects...
SurvarorRatio: 2 to 8 - controls survivor spaces size. It will be: 'Survivor
total space = New Gen Size / (SurvarorRatio + 2)'. Dividing by 2 you have the
size of each survivor. Here it will depend how fast the Eden space is
allocated. Increasing the survivor space will disminuish the Eden space (where
new objects are allocated) and there is a tradeoff here as well and a balance
to find.
I would try with these settings on a canary node:
HEAP - 16 GB (if read heavy, if not probably between 8 and 12 GB is better).
NEW_HEAP - 50% of the heap (4 - 8GB)
MaxTenuringThreshold: 15
SurvarorRatio: 4,
When testing GC, there is not a better way than using a canary node, pick one
rack and node(s) you want in this rack to test. This should not impact
availability or consistency. If you're able to reproduce the workload perfectly
in the staging cluster, it's perfect but I don't know much companies/people
able to do this and the use of a canary node should be safe :).
I could probably share some thoughts on what the cluster really needs, rather
than making guesses and suggesting a somewhat arbitrary tuning, as I did above
if you would share a gc.log file with us from one of the nodes. Garbage
Collection tuning is a bit tricky, but a good tuning can divide latency while
cutting in the number of host. I have seen impressives changes in the past
really.
There is a lot of details in this log file about where is the biggest pressure,
the allocation rate, the GC duration distribution for each type of GC, etc.
With this, I could see where the pressure is and suggest how to work on it.
Be aware that extra GC is also sometimes the consequence (and not a cause) of
an issue. Due to pending requests, wide partitions, ongoing compactions,
repairs or an intensive workload, GC can pressure can increase and mask another
underlying, and root issue. You might want to check that the cluster is healthy
other than GC, as a lot of distinct internal parts of Cassandra have an impact
on the GC.
Hope that helps,
C*heers,
-----------------------
Alain Rodriguez - @arodream -
al...@thelastpickle.com<mailto:al...@thelastpickle.com>
France / Spain
The Last Pickle - Apache Cassandra Consulting
http://www.thelastpickle.com<https://urldefense.proofpoint.com/v2/url?u=http-3A__www.thelastpickle.com&d=DwMFaQ&c=MtgQEAMQGqekjTjiAhkudQ&r=aC_gxC6z_4f9GLlbWiKzHm1vucZTtVYWDDvyLkh8IaQ&m=_N23kKi9SY0Tt1hzPDfk1n9Mg6eqAQOI_sIwbUN_L88&s=pcPsSYYtEJTtrRfRCwYCziiHKlKMtY-Zn4x_ZQmHDZQ&e=>
2018-06-28 23:19 GMT+01:00 Elliott Sims
<elli...@backblaze.com<mailto:elli...@backblaze.com>>:
Odd. Your "post-GC" heap level seems a lot lower than your max, which implies
that you should be OK with ~10GB. I'm guessing either you're genuinely getting
a huge surge in needed heap and running out, or it's falling behind and garbage
is building up. If the latter, there might be some tweaking you can do.
Probably worth turning on GC logging and digging through exactly what's
happening.
CMS is kind of hard to tune and can have problems with heap fragmentation since
it doesn't compact, but if it's working for you I'd say stick with it.
On Thu, Jun 28, 2018 at 3:14 PM, Randy Lynn
<rl...@getavail.com<mailto:rl...@getavail.com>> wrote:
Thanks for the feedback..
Getting tons of OOM lately..
You mentioned overprovisioned heap size... well...
tried 8GB = OOM
tried 12GB = OOM
tried 20GB w/ G1 = OOM (and long GC pauses usually over 2 secs)
tried 20GB w/ CMS = running
we're java 8 update 151.
3.11.1.
We've got one table that's got a 400MB partition.. that's the max.. the 99th is
< 100MB, and 95th < 30MB..
So I'm not sure that I'm overprovisioned, I'm just not quite yet to the heap
size based on our partition sizes.
All queries use cluster key, so I'm not accidentally reading a whole partition.
The last place I'm looking - which maybe should be the first - is tombstones.
sorry for the afternoon rant! thanks for your eyes!
On Thu, Jun 28, 2018 at 5:54 PM, Elliott Sims
<elli...@backblaze.com<mailto:elli...@backblaze.com>> wrote:
It depends a bit on which collector you're using, but fairly normal. Heap
grows for a while, then the JVM decides via a variety of metrics that it's time
to run a collection. G1GC is usually a bit steadier and less sawtooth than the
Parallel Mark Sweep , but if your heap's a lot bigger than needed I could see
it producing that pattern.
On Thu, Jun 28, 2018 at 9:23 AM, Randy Lynn
<rl...@getavail.com<mailto:rl...@getavail.com>> wrote:
I have datadog monitoring JVM heap.
Running 3.11.1.
20GB heap
G1 for GC.. all the G1GC settings are out-of-the-box
Does this look normal?
https://drive.google.com/file/d/1hLMbG53DWv5zNKSY88BmI3Wd0ic_KQ07/view?usp=sharing<https://urldefense.proofpoint.com/v2/url?u=https-3A__drive.google.com_file_d_1hLMbG53DWv5zNKSY88BmI3Wd0ic-5FKQ07_view-3Fusp-3Dsharing&d=DwMFaQ&c=MtgQEAMQGqekjTjiAhkudQ&r=aC_gxC6z_4f9GLlbWiKzHm1vucZTtVYWDDvyLkh8IaQ&m=_N23kKi9SY0Tt1hzPDfk1n9Mg6eqAQOI_sIwbUN_L88&s=W_XwdIbS2_7_Xo-6V9MlFRy8bVQmwudNLSqMvsDdXRM&e=>
I'm a C# .NET guy, so I have no idea if this is normal Java behavior.
--
Randy Lynn
rl...@getavail.com<mailto:rl...@getavail.com>
office:
859.963.1616 <tel:+1-859-963-1616> ext 202
163 East Main Street - Lexington, KY 40507 -
USA<https://urldefense.proofpoint.com/v2/url?u=https-3A__maps.google.com_-3Fq-3D163-2BEast-2BMain-2BStreet-2B-2D-2BLexington-2C-2BKY-2B40507-2B-2D-2BUSA-26entry-3Dgmail-26source-3Dg&d=DwMFaQ&c=MtgQEAMQGqekjTjiAhkudQ&r=aC_gxC6z_4f9GLlbWiKzHm1vucZTtVYWDDvyLkh8IaQ&m=_N23kKi9SY0Tt1hzPDfk1n9Mg6eqAQOI_sIwbUN_L88&s=i3GCGjiy5RQ8LY7ZBtD3UrUFOo4VkIy3Y8gZf0s42SM&e=>
[https://www.getavail.com/Content/Images/blueavaillogo_small.png]<https://urldefense.proofpoint.com/v2/url?u=https-3A__www.getavail.com_&d=DwMFaQ&c=MtgQEAMQGqekjTjiAhkudQ&r=aC_gxC6z_4f9GLlbWiKzHm1vucZTtVYWDDvyLkh8IaQ&m=_N23kKi9SY0Tt1hzPDfk1n9Mg6eqAQOI_sIwbUN_L88&s=uV08GEj1H0jiUyFDQrQu5Ql0OGXIs29bv0NGqYUH_M0&e=>
getavail.com<https://urldefense.proofpoint.com/v2/url?u=https-3A__www.getavail.com_&d=DwMFaQ&c=MtgQEAMQGqekjTjiAhkudQ&r=aC_gxC6z_4f9GLlbWiKzHm1vucZTtVYWDDvyLkh8IaQ&m=_N23kKi9SY0Tt1hzPDfk1n9Mg6eqAQOI_sIwbUN_L88&s=uV08GEj1H0jiUyFDQrQu5Ql0OGXIs29bv0NGqYUH_M0&e=>
--
Randy Lynn
rl...@getavail.com<mailto:rl...@getavail.com>
office:
859.963.1616 <tel:+1-859-963-1616> ext 202
163 East Main Street - Lexington, KY 40507 -
USA<https://urldefense.proofpoint.com/v2/url?u=https-3A__maps.google.com_-3Fq-3D163-2BEast-2BMain-2BStreet-2B-2D-2BLexington-2C-2BKY-2B40507-2B-2D-2BUSA-26entry-3Dgmail-26source-3Dg&d=DwMFaQ&c=MtgQEAMQGqekjTjiAhkudQ&r=aC_gxC6z_4f9GLlbWiKzHm1vucZTtVYWDDvyLkh8IaQ&m=_N23kKi9SY0Tt1hzPDfk1n9Mg6eqAQOI_sIwbUN_L88&s=i3GCGjiy5RQ8LY7ZBtD3UrUFOo4VkIy3Y8gZf0s42SM&e=>
[https://www.getavail.com/Content/Images/blueavaillogo_small.png]<https://urldefense.proofpoint.com/v2/url?u=https-3A__www.getavail.com_&d=DwMFaQ&c=MtgQEAMQGqekjTjiAhkudQ&r=aC_gxC6z_4f9GLlbWiKzHm1vucZTtVYWDDvyLkh8IaQ&m=_N23kKi9SY0Tt1hzPDfk1n9Mg6eqAQOI_sIwbUN_L88&s=uV08GEj1H0jiUyFDQrQu5Ql0OGXIs29bv0NGqYUH_M0&e=>
getavail.com<https://urldefense.proofpoint.com/v2/url?u=https-3A__www.getavail.com_&d=DwMFaQ&c=MtgQEAMQGqekjTjiAhkudQ&r=aC_gxC6z_4f9GLlbWiKzHm1vucZTtVYWDDvyLkh8IaQ&m=_N23kKi9SY0Tt1hzPDfk1n9Mg6eqAQOI_sIwbUN_L88&s=uV08GEj1H0jiUyFDQrQu5Ql0OGXIs29bv0NGqYUH_M0&e=>
