More memory-efficient internal representation for Strings: call for more data
xueming.shen at oracle.com
Wed Dec 3 00:39:13 UTC 2014
On 12/02/2014 03:24 PM, Douglas Surber wrote:
> String construction is a big performance issue for JDBC drivers. Most queries return some number of Strings. The overwhelming majority of those Strings will be short lived. The cost of constructing these Strings from network bytes is a large fraction of total execution time. Any increase in the cost of constructing a String will far out weigh any reduction in memory use, at least for query results.
> All of the proposed compression methods require an additional scan of the entire string. That's exactly the wrong direction. Something like the following pseudo-code is common inside a driver.
> char c = new char[n];
> for (i = 0; i < n; i++) c[i] = charSource.next();
> return new String(c);
In most use cases, the char is a waste if the final target is a String object and the input data is
byte. Optimization had been implemented in StringCoding in early releases to avoid redundant
char copy if possible. For compressed String project, however, if the final internal storage is
byte, it might be ideal to avoid the char in the byte -> char -> byte -> String path. The
"extra scan" can be combined into the byte -> char -> byte decoding phase.
I do have some optimization in StringCoding for asccii, 8859-1 and utf8 in case of the data is ascii
But the benefit might be limited, and the current implementation has a bias on "single byte"
use scenario, with the assumption that most of the String objects inside a live vm heap is single
byte string. More work need to/can be done here, if data shows this indeed is a big issue.
> The array copy inside the String constructor is a significant fraction of JDBC driver execution time. Adding an additional scan on top of it is making things worse regardless of the transient benefit of more compact storage. In the case of a query result the String will be likely never be promoted out of new space; the benefit of compression would be minimal.
> I don't dispute that Strings occupy a significant fraction of the heap or that a lot of those bytes are zero. And I certainly agree that reducing memory footprint is valuable, but any worsening of String construction time will likely be a problem.
> At 02:13 PM 12/2/2014, core-libs-dev-request at openjdk.java.net wrote:
>> Date: Wed, 03 Dec 2014 00:59:10 +0300
>> From: Aleksey Shipilev <aleksey.shipilev at oracle.com>
>> To: Java Core Libs <core-libs-dev at openjdk.java.net>
>> Cc: charlie hunt <charlie.hunt at oracle.com>
>> Subject: More memory-efficient internal representation for Strings:
>> call for more data
>> Message-ID: <547E362E.5010107 at oracle.com>
>> Content-Type: text/plain; charset=utf-8
>> As you may already know, we are looking into more memory efficient
>> representation for Strings:
>> As part of preliminary performance work for this JEP, we have to collect
>> the empirical data on usual characteristics of Strings and char-s
>> normal applications have, as well as figure out the early estimates for
>> the improvements based on that data. What we have so far is written up here:
>> We would appreciate if people who are interested in this JEP can provide
>> the additional data on their applications. It is double-interesting to
>> have the data for the applications that process String data outside
>> Latin1 plane. Our current data says these cases are rather rare. Please
>> read the current report draft, and try to process your own heap dumps
>> using the instructions in the Appendix.
More information about the core-libs-dev