hbase-user mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From Suraj Varma <svarma...@gmail.com>
Subject Re: HBaseClient recovery from .META. server power down
Date Tue, 10 Jul 2012 17:22:58 GMT

On the maxRetries, though ... I saw the code
this.maxRetries = conf.getInt("hbase.ipc.client.connect.max.retries", 0);

So - looks like by default, the maxRetries is set to 0? So ... there
is effectively no retry (i.e. it is fail-fast)

On Tue, Jul 10, 2012 at 10:12 AM, N Keywal <nkeywal@gmail.com> wrote:
> Thanks for the jira.
> The client can be connected to multiple RS, depending on the rows is
> working on. So yes it's initial, but it's a dynamic initial :-).
> This said there is a retry on error...
> On Tue, Jul 10, 2012 at 6:46 PM, Suraj Varma <svarma.ng@gmail.com> wrote:
>> I will create a JIRA ticket ...
>> The only side-effect I could think of is ... if a RS is having a GC of
>> a few seconds, any _new_ client trying to connect would get connect
>> failures. So ... the _initial_ connection to the RS is what would
>> suffer from a super-low setting of the ipc.socket.timeout. This was my
>> read of the code.
>> So - was hoping to get a confirmation if this is the only side effect.
>> Again - this is on the client side - I wouldn't risk doing this on the
>> cluster side ...
>> --Suraj
>> On Mon, Jul 9, 2012 at 9:44 AM, N Keywal <nkeywal@gmail.com> wrote:
>>> Hi,
>>> What you're describing -the 35 minutes recovery time- seems to match
>>> the code. And it's a bug (still there on trunk). Could you please
>>> create a jira for it? If you have the logs it even better.
>>> Lowering the ipc.socket.timeout seems to be an acceptable partial
>>> workaround. Setting it to 10s seems ok to me. Lower than this... I
>>> don't know.
>>> N.
>>> On Mon, Jul 9, 2012 at 6:16 PM, Suraj Varma <svarma.ng@gmail.com> wrote:
>>>> Hello:
>>>> I'd like to get advice on the below strategy of decreasing the
>>>> "ipc.socket.timeout" configuration on the HBase Client side ... has
>>>> anyone tried this? Has anyone had any issues with configuring this
>>>> lower than the default 20s?
>>>> Thanks,
>>>> --Suraj
>>>> On Mon, Jul 2, 2012 at 5:51 PM, Suraj Varma <svarma.ng@gmail.com> wrote:
>>>>> By "power down" below, I mean powering down the host with the RS that
>>>>> holds the .META. table. (So - essentially, the host IP is unreachable
>>>>> and the RS/DN is gone.)
>>>>> Just wanted to clarify my below steps ...
>>>>> --S
>>>>> On Mon, Jul 2, 2012 at 5:36 PM, Suraj Varma <svarma.ng@gmail.com>
>>>>>> Hello:
>>>>>> We've been doing some failure scenario tests by powering down a .META.
>>>>>> holding region server host and while the HBase cluster itself recovers
>>>>>> and reassigns the META region and other regions (after we tweaked
>>>>>> the default timeouts), our client apps using HBaseClient take a long
>>>>>> time to recover.
>>>>>> hbase-0.90.6 / cdh3u4 / JDK 1.6.0_23
>>>>>> Process:
>>>>>> 1) Apply load via client app on HBase cluster for several minutes
>>>>>> 2) Power down the region server holding the .META. server
>>>>>> 3) Measure how long it takes for cluster to reassign META table and
>>>>>> for client threads to re-lookup and re-orient to the lesser cluster
>>>>>> (minus the RS and DN on that host).
>>>>>> What we see:
>>>>>> 1) Client threads spike up to maxThread size ... and take over 35
>>>>>> to recover (i.e. for the thread count to go back to normal) - no
>>>>>> are being serviced - they are all just backed up on a synchronized
>>>>>> method ...
>>>>>> 2) Essentially, all the client app threads queue up behind the
>>>>>> HBaseClient.setupIOStreams method in oahh.ipc.HBaseClient
>>>>>> (http://grepcode.com/file/repo1.maven.org/maven2/org.apache.hbase/hbase/0.90.2/org/apache/hadoop/hbase/ipc/HBaseClient.java#312).
>>>>>> http://tinyurl.com/7js53dj
>>>>>> After taking several thread dumps we found that the thread within
>>>>>> synchronized method was blocked on
>>>>>>    NetUtils.connect(this.socket, remoteId.getAddress(), getSocketTimeout(conf));
>>>>>> Essentially, the thread which got the lock would try to connect to
>>>>>> dead RS (till socket times out), retrying, and then the next thread
>>>>>> gets in and so forth.
>>>>>> Solution tested:
>>>>>> -------------------
>>>>>> So - the ipc.HBaseClient code shows ipc.socket.timeout default is
>>>>>> We dropped this down to a low number (1000 ms,  100 ms, etc) and
>>>>>> recovery was much faster (in a couple of minutes).
>>>>>> So - we're thinking of setting the HBase client side hbase-site.xml
>>>>>> with an ipc.socket.timeout of 100ms. Looking at the code, it appears
>>>>>> that this is only ever used during the initial "HConnection" setup
>>>>>> the NetUtils.connect and should only ever be used when connectivity
>>>>>> a region server is lost and needs to be re-established. i.e it does
>>>>>> not affect the normal "RPC" actiivity as this is just the connect
>>>>>> timeout.
>>>>>> Am I reading the code right? Any thoughts on how whether this is
>>>>>> low for comfort? (Our internal tests did not show any errors during
>>>>>> normal operation related to timeouts etc ... but, I just wanted to
>>>>>> this by the experts.).
>>>>>> Note that this above timeout tweak is only on the HBase client side.
>>>>>> Thanks,
>>>>>> --Suraj

View raw message