Re: [WIP] Performance Improvement by reducing WAL for Update Operation

On Saturday, October 06, 2012 7:34 PM Amit Kapila wrote:

> Please find the readings of LZ patch along with Xlog-Scale patch.
> The comparison is between for Update operations
> base code + Xlog Scale Patch
> base code + Xlog Scale Patch + Update WAL Optimization (LZ compression)

This contains all the consolidated data and comparison for both the approaches:

The difference of this testcase as compare to previous one is that it has default value of wal_page_size ( 8K ) as compare to previous one where configuration used for wal_page_size was 1K

pgbench_lz_wal_page_8k (LZ Compression Approach)-
The comparison for Update operations is between
base code + Xlog Scale Patch
base code + Xlog Scale Patch + Update WAL Optimization (LZ compression)

pgbench_wal_mod_wal_page_8K (Offset Approach initialy used + changes suggested by you and noah)

base code + Xlog Scale Patch
base code + Xlog Scale Patch + Update WAL Optimization (Offset Approach including Memcmp of tuples)

Observations From Performance Data

----------------------------------------------

1. With both the approaches Performance data is good.

LZ compression - upto 100% performance improvement.

Offset Approach - upto 160% performance improvement.

2. The performance data is better for LZ compression approach when the changed value of tuple is large. (Refer 500 length changed value).

3. The performance data is better for Offset Approach for 1 thread for any size of Data (it dips for LZ compression Approach).

Can you please send me your feedback about which approach can be finalized.

For LZ Compression - Already the patch is uploaded to Commitfest with fixes for defects found.

For Offset Approach - I can upload it, if the decision is to use Offset based approach.

With Regards,

Amit Kapila.