Home | About | Sematext search-lucene.com search-hadoop.com
 Search Hadoop and all its subprojects:

Switch to Threaded View
Accumulo >> mail # user >> Performance of table with large number of column families


Copy link to this message
-
Re: Performance of table with large number of column families
I'll ask for someone to verify this comment for me (look @ u John W Vines),
but the bloom filter helps when you have a discrete number of column
families that will appear across many rows.

On Fri, Nov 9, 2012 at 12:18 PM, Anthony Fox <[EMAIL PROTECTED]> wrote:

> Ah, ok, I was under the impression that this would be really fast since I
> have a column family bloom filter turned on.  Is this not correct?
>
>
> On Fri, Nov 9, 2012 at 12:15 PM, William Slacum <
> [EMAIL PROTECTED]> wrote:
>
>> When I said smaller of tablets, I really mean smaller number of rows :)
>> My apologies.
>>
>> So if you're searching for a random column family in a table, like with a
>> `scan -c <cf>` in the shell, it will start at row 0 and work sequentially
>> up to row 10000000 until it finds the cf.
>>
>>
>> On Fri, Nov 9, 2012 at 12:11 PM, Anthony Fox <[EMAIL PROTECTED]>wrote:
>>
>>> This scan is without the intersecting iterator.  I'm just trying to pull
>>> back a single data record at the moment which corresponds to scanning for
>>> one column family.  I'll try with a smaller number of tablets, but is the
>>> computation effort the same for the scan I am doing?
>>>
>>>
>>> On Fri, Nov 9, 2012 at 12:02 PM, William Slacum <
>>> [EMAIL PROTECTED]> wrote:
>>>
>>>> So that means you have roughly 312.5k rows per tablet, which means
>>>> about 725k column families in any given tablet. The intersecting iterator
>>>> will work at a row per time, so I think at any given moment, it will be
>>>> working through 32 at a time and doing a linear scan through the RFile
>>>> blocks. With RFile indices, that check is usually pretty fast, but you're
>>>> having go through 4 orders of magnitude more data sequentially than you can
>>>> work on. If you can experiment and re-ingest with a smaller number of
>>>> tablets, anywhere between 15 and 45, I think you will see better
>>>> performance.
>>>>
>>>> On Fri, Nov 9, 2012 at 11:53 AM, Anthony Fox <[EMAIL PROTECTED]>wrote:
>>>>
>>>>> Failed to answer the original question - 15 tablet servers, 32
>>>>> tablets/splits.
>>>>>
>>>>>
>>>>> On Fri, Nov 9, 2012 at 11:52 AM, Anthony Fox <[EMAIL PROTECTED]>wrote:
>>>>>
>>>>>> I've tried a number of different settings of table.split.threshold.
>>>>>>  I started at 1G and bumped it down to 128M and the cf scan is still ~30
>>>>>> seconds for both.  I've also used less rows - 00000 to 99999 and still see
>>>>>> similar performance numbers.  I thought the column family bloom filter
>>>>>> would help deal with large row space but sparsely populated column space.
>>>>>>  Is that correct?
>>>>>>
>>>>>>
>>>>>> On Fri, Nov 9, 2012 at 11:49 AM, William Slacum <
>>>>>> [EMAIL PROTECTED]> wrote:
>>>>>>
>>>>>>> I'm more inclined to believe it's because you have to search across
>>>>>>> 10M different rows to find any given column family, since they're randomly,
>>>>>>> and possibly uniformly, distributed. How many tablets are you searching
>>>>>>> across?
>>>>>>>
>>>>>>>
>>>>>>> On Fri, Nov 9, 2012 at 11:45 AM, Anthony Fox <[EMAIL PROTECTED]>wrote:
>>>>>>>
>>>>>>>> Yes, there are 10M possible partitions.  I do not have a hash from
>>>>>>>> value to partition, the data is essentially randomly balanced across all
>>>>>>>> the tablets.  Unlike the bloom filter and intersecting iterator examples, I
>>>>>>>> do not have locality groups turned on and I have data in the cq and the
>>>>>>>> value for both index entries and record entries.  Could this be the issue?
>>>>>>>>  Each record entry has approximately 30 column qualifiers with data in the
>>>>>>>> value for each.
>>>>>>>>
>>>>>>>>
>>>>>>>> On Fri, Nov 9, 2012 at 11:41 AM, William Slacum <
>>>>>>>> [EMAIL PROTECTED]> wrote:
>>>>>>>>
>>>>>>>>> I guess assuming you have 10M possible partitions, if you're using
>>>>>>>>> a relatively uniform hash to generate your IDs, you'll average about 2 per
>>>>>>>>> partition. Do you have any index for term/value to partition? This will
>>>>