Thanks Federico. I will look into this patch.

We are using .94.6.1 version. 

On Aug 29, 2013, at 8:37 AM, Federico Gaule <[email protected]> wrote:

> In 0.94.11 Release, has been included an optimization for MultiGets: 
> https://issues.apache.org/jira/browse/HBASE-9087
> 
> What version have you deployed?
> 
> 
> On 08/29/2013 01:29 AM, lars hofhansl wrote:
>> A 1s SLA is tough in HBase (or any large memory JVM application).
>> 
>> 
>> Maybe, if you presplit your table, play with JDK7 and the G1 collector, but 
>> nobody here will vouch for such an SLA in the 99th percentile.
>> I heard some folks have experimented with 30GB heaps and G1 and have 
>> reported max GC times of 200ms, but I have not verified that.
>> 
>> -- Lars
>> 
>> 
>> 
>> ----- Original Message -----
>> From: Saurabh Yahoo <[email protected]>
>> To: "[email protected]" <[email protected]>
>> Cc: "[email protected]" <[email protected]>
>> Sent: Wednesday, August 28, 2013 3:17 PM
>> Subject: Re: experiencing high latency for few reads in HBase
>> 
>> Hi Vlad,
>> 
>> Thanks for your response.
>> 
>> 1. Our SLA is less than one sec. we cannot afford latency more than 1 sec.
>> 
>> We can increase heap size if that help, we have enough memory on server. 
>> What would be the optimal heap size?
>> 
>> 2. Cache hit ratio is 95%.  One thing I don't understand that we have 
>> allocated only 4gb for block cache out of 12gb. That left 8gb for rest of 
>> JVM. There is no write. Memcache is empty. Is 8gb not enough for hbase to 
>> process the requests? What are the most memory consuming objects in region 
>> server?
>> 
>> 3. We will change the cf to IN_memory and report back performance difference.
>> 
>> Thanks,
>> Saurabh.
>> 
>> On Aug 28, 2013, at 3:15 PM, Vladimir Rodionov <[email protected]> 
>> wrote:
>> 
>>> 1. 4 sec max latency is not that bad taking into account 12GB heap.  It can 
>>> be much larger. What is your SLA?
>>> 2. Block evictions is the result of a poor cache hit rate and the root 
>>> cause of a periodic stop-the-world GC pauses (max latencies
>>>     latencies you have been observing in the test)
>>> 3. Block cache consists of 3 parts (25% young generation, 50% - tenured, 
>>> 25% - permanent). Permanent part is for CF with
>>> IN_MEMORY = true (you can specify this when you create CF).  Block first 
>>> stored in 'young gen' space, then gets promoted to 'tenured gen' space
>>> (or gets evicted). May be your 'perm gen' space is underutilized? This is 
>>> exact 25% of 4GB (1GB). Although HBase LruBlockCache should use all the 
>>> space allocated for block cache -
>>> there is no guarantee (as usual). If you don have in_memory column families 
>>> you may decrease
>>> 
>>> 
>>> 
>>> Best regards,
>>> Vladimir Rodionov
>>> Principal Platform Engineer
>>> Carrier IQ, www.carrieriq.com
>>> e-mail: [email protected]
>>> 
>>> ________________________________________
>>> From: Saurabh Yahoo [[email protected]]
>>> Sent: Wednesday, August 28, 2013 5:10 AM
>>> To: [email protected]
>>> Subject: experiencing high latency for few reads in HBase
>>> 
>>> Hi,
>>> 
>>> We are running a stress test in our 5 node cluster and we are getting the 
>>> expected mean latency of 10ms. But we are seeing around 20 reads out of 25 
>>> million reads having latency more than 4 seconds. Can anyone provide the 
>>> insight what we can do to meet below second SLA for each and every read?
>>> 
>>> We observe the following things -
>>> 
>>> 1. Reads are evenly distributed among 5 nodes.  CPUs remain under 5% 
>>> utilized.
>>> 
>>> 2. We have 4gb block cache (30% block cache out of 12gb) setup. 3gb block 
>>> cache got filled up but around 1gb remained free. There are a large number 
>>> of cache eviction.
>>> 
>>> Questions to experts -
>>> 
>>> 1. If there are still 1gb of free block cache available, why is hbase 
>>> evicting the block from cache?
>>> 
>>> 4. We are seeing memory went up to 10gb three times before dropping sharply 
>>> to 5gb.
>>> 
>>> Any help is highly appreciable,
>>> 
>>> Thanks,
>>> Saurabh.
>>> 
>>> Confidentiality Notice:  The information contained in this message, 
>>> including any attachments hereto, may be confidential and is intended to be 
>>> read only by the individual or entity to whom this message is addressed. If 
>>> the reader of this message is not the intended recipient or an agent or 
>>> designee of the intended recipient, please note that any review, use, 
>>> disclosure or distribution of this message or its attachments, in any form, 
>>> is strictly prohibited.  If you have received this message in error, please 
>>> immediately notify the sender and/or [email protected] and delete 
>>> or destroy any copy of this message and its attachments.
> 

Reply via email to