How do explicit table partitions in Databricks affect write performance?

Question

We have the following scenario:

We have an existing table containing approx. 15 billion records. It was not explicitly partitioned on creation.
We are creating a copy of this table with partitions, hoping for faster read time on certain types of queries.
Our tables are on Databricks Cloud, and we use Databricks Delta.
We commonly filter by two columns, one of which is the ID of an entity (350k distinct values) and one of which is the date at which an event occurred (31 distinct values so far, but increasing every day!).

So, in creating our new table, we ran a query like this:

CREATE TABLE the_new_table
USING DELTA
PARTITIONED BY (entity_id, date)
AS SELECT
  entity_id,
  another_id,
  from_unixtime(timestamp) AS timestamp,
  CAST(from_unixtime(timestamp) AS DATE) AS date
FROM the_old_table

This query has run for 48 hours and counting. We know that it is making progress, because we have found around 250k prefixes corresponding to the first partition key in the relevant S3 prefix, and there are certainly some big files in the prefixes that exist.

However, we're having some difficulty monitoring exactly how much progress has been made, and how much longer we can expect this to take.

While we waited, we tried out a query like this:

CREATE TABLE a_test_table (
  entity_id STRING,
  another_id STRING,
  timestamp TIMESTAMP,
  date DATE
)
USING DELTA
PARTITIONED BY (date);

INSERT INTO a_test_table
SELECT
  entity_id,
  another_id,
  from_unixtime(timestamp) AS timestamp,
  CAST(from_unixtime(timestamp) AS DATE) AS date
FROM the_old_table
  WHERE CAST(from_unixtime(timestamp) AS DATE) = '2018-12-01'

Notice the main difference in the new table's schema here is that we partitioned only on date, not on entity id. The date we chose contains almost exactly four percent of the old table's data, which I want to point out because it's much more than 1/31. Of course, since we are selecting by a single value that happens to be the same thing we partitioned on, we are in effect only writing one partition, vs. the probably hundred thousand or so.

The creation of this test table took 16 minutes using the same number of worker-nodes, so we would expect (based on this) that the creation of a table 25x larger would only take around 7 hours.

This answer appears to partially acknowledge that using too many partitions can cause the problem, but the underlying causes appear to have greatly changed in the last couple of years, so we seek to understand what the current issues might be; the Databricks docs have not been especially illuminating.

Based on the posted request rate guidelines for S3, it seems like increasing the number of partitions (key prefixes) should improve performance. The partitions being detrimental seems counter-intuitive.

In summary: we are expecting to write many thousands of records in to each of many thousands of partitions. It appears that reducing the number of partitions dramatically reduces the amount of time it takes to write the table data. Why would this be true? Are there any general guidelines on the number of partitions that should be created for data of a certain size?

Brad · Answer 1 · 2019-03-01T16:30:09.687

You should partition your data by date because it sounds like you are continually adding data as time passes chronologically. This is the generally accepted approach to partitioning time series data. It means that you will be writing to one date partition each day, and your previous date partitions are not updated again (a good thing).

You can of course use a secondary partition key if your use case benefits from it (i.e. PARTITIONED BY (date, entity_id))

Partitioning by date will necessitate that your reading of this data will always be made by date as well, to get the best performance. If this is not your use case, then you would have to clarify your question.

How many partitions?

No one can give you answer on how many partitions you should use because every data set (and processing cluster) is different. What you do want to avoid is "data skew", where one worker is having to process huge amounts of data, while other workers are idle. In your case that would happen if one clientid was 20% of your data set, for example. Partitioning by date has to assume that each day has roughly the same amount of data, so each worker is kept equally busy.

I don't know specifically about how Databricks writes to disk, but on Hadoop I would want to see each worker node writing it's own file part, and therefore your write performance is paralleled at this level.

We were trying to use the composite partition key because we expect to query on date 100% of the time and on the entity-id in question 95% of the time. As you've correctly guessed, the data is much more evenly-distributed across dates than across events-related-to-the-entity, so there's _extreme_ data skew that wasn't considered when we first attempted to write this table. We are currently debating whether the id partition is really that important; if it is, we will try ranking ids by row count, and write in batches that contain similarly-ranked ids. Thank you so much! — Jesse Amano, Mar 01 '19 at 20:11

hlagos · Accepted Answer · 2019-03-04T03:17:41.923

I am not a databricks expert at all but hopefully this bullets can help

Number of partitions

The number of partitions and files created will impact the performance of your job no matter what, especially using s3 as data storage however this number of files should be handled easily by a cluster of descent size

Dynamic partition

There is a huge difference between partition dynamically by your 2 keys instead of one, let me try to address this in more details.

When you partition data dynamically, depending on the number of tasks and the size of the data, a big number of small files could be created per partition, this could (and probably will) impact the performance of next jobs that will require use this data, especially if your data is stored in ORC, parquet or any other columnar format. Note that this will require only a map only job.

The issue explained before, is addressed in different ways, being the most common the file consolidation. For this, data is repartitioned with the purpose of create bigger files. As result, shuffling of data will be required.

Your queries

For your first query, the number of partitions will be 350k*31 (around 11MM!), which is really big considering the amount of shuffling and task required to handle the job.

For your second query (which takes only 16 minutes), the number of required tasks and shuffling required is much more smaller.

The number of partitions (shuffling/sorting/tasks scheduling/etc) and the time of your job execution does not have a linear relationship, that is why the math doesn't add up in this case.

Recomendation

I think you already got it, you should split your etl job in 31 one different queries which will allow to optimize the execution time

Thank you! I think the key insight in your answer is that the scheduler will need to continue _shuffling_ the data until it's confident everything has been written to the correct location, and the complexity of that task increases with the number of distinct locations possible. Your recommendations are also extremely helpful, and suggest good general "best practices" for our future work (which will undoubtedly involve many similarly large and complicated tables). — Jesse Amano, Mar 01 '19 at 20:17
your welcome! I forgot to add, like Brad said, I would recommend partition by date however if the 100% of the time you will be quering by entity, I would recommend keep your partitions as (entity, date) considering that quering for 1 single entity will be more efficient using non-hive frameworks because you will target 1 single folder instead of N or add a additional logic to look for the correct ones. — hlagos, Mar 04 '19 at 03:14

score 0 · Answer 3 · answered Sep 11 '20 at 23:42

My recommendations in case of occupying partitioned columns is

Identify the cardinality of all the columns and select those that have a finite amount in time, therefore exclude identifiers and date columns
Identify the main search to the table, perhaps it is date or by some categorical field
Generate sub columns with a finite cardinality in order to speed up the search example in the case of dates it is possible to decompose it into year, month, day, etc. , or in the case of integer identifiers, decompose them into the integer division of these IDs% [1,2,3 ...]

As I mentioned earlier, using columns with a high cardinality to partition, will cause poor performance, by generating a lot of files which is the worst working case.

It is advisable to work with files that do not exceed 1 GB for this when creating the delta table it is recommended to occupy "coalesce (1)"

If you need to perform updates or insertions, specify the largest number of partitioned columns to rule out the inceserary cases of file reading, which is very effective to reduce times.

How do explicit table partitions in Databricks affect write performance?

3 Answers3