Re: [DISCUSS] HFile block decompression can be faster

2025-02-18 Thread Lars Francke
Sorry for the late/slow response. This happens to be a path I also recently looked at (I had a thread here somewhere) and I'm with Duo: Performance improvements are welcome and everything seems sensible to me. Thank you for bringing it up! On Wed, Feb 12, 2025 at 10:56 AM Reid Chan wrote: > > +1

Re: [DISCUSS] HFile block decompression can be faster

2025-02-12 Thread Reid Chan
+1 --- Best Regards, R.C On Tue, Feb 11, 2025 at 6:37 PM 张铎(Duo Zhang) wrote: > Performance improvement is always welcome. > > I've reviewed the google doc, seems fine to me. > > So are there any blockers here? If not, let's just implement it and try? > > Thanks. > > Charles Connell 于2025年2月

Re: [DISCUSS] HFile block decompression can be faster

2025-02-11 Thread Charles Connell
Sounds good, I've got the first ticket open at https://issues.apache.org/jira/browse/HBASE-29123 On Tue, Feb 11, 2025 at 5:37 AM 张铎(Duo Zhang) wrote: > > Performance improvement is always welcome. > > I've reviewed the google doc, seems fine to me. > > So are there any blockers here? If not, let

Re: [DISCUSS] HFile block decompression can be faster

2025-02-11 Thread Duo Zhang
Performance improvement is always welcome. I've reviewed the google doc, seems fine to me. So are there any blockers here? If not, let's just implement it and try? Thanks. Charles Connell 于2025年2月11日周二 01:26写道: > > Hi folks, > > I've been thinking about ways to improve HBase's performance when

[DISCUSS] HFile block decompression can be faster

2025-02-10 Thread Charles Connell
Hi folks, I've been thinking about ways to improve HBase's performance when reading HFiles, and I believe there is significant opportunity. I collected my findings in a Google Doc: https://docs.google.com/document/d/1-OxTsWQ0cF8bd82NpZNqzOpdFnJM4976MzNWVk-QRys/edit?usp=sharing I welcome feedback