Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On Fri, Jan 6, 2017 at 11:06 AM, Andres Freund wrote: > On 2017-01-06 11:01:32 -0500, Robert Haas wrote: >> On Fri, Jan 6, 2017 at 10:43 AM, Andres Freund wrote: >> > On 2016-12-16 09:34:31 -0800, Andres Freund wrote: >> >> > To fix his issue, we need

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On 2017-01-06 11:01:32 -0500, Robert Haas wrote: > On Fri, Jan 6, 2017 at 10:43 AM, Andres Freund wrote: > > On 2016-12-16 09:34:31 -0800, Andres Freund wrote: > >> > To fix his issue, we need something like your 0001. Are you going to > >> > polish that up soon here? > >> >

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On Fri, Jan 6, 2017 at 10:43 AM, Andres Freund wrote: > On 2016-12-16 09:34:31 -0800, Andres Freund wrote: >> > To fix his issue, we need something like your 0001. Are you going to >> > polish that up soon here? >> >> Yes. > > I've two versions of a fix for this. One of them

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On 2016-12-16 09:34:31 -0800, Andres Freund wrote: > > To fix his issue, we need something like your 0001. Are you going to > > polish that up soon here? > > Yes. I've two versions of a fix for this. One of them basically increases the "spread" of buckets when the density goes up too much. It

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On 2016-12-16 10:12:42 -0500, Robert Haas wrote: > On Wed, Dec 14, 2016 at 11:20 PM, Robert Haas wrote: > > I've got no problem with that at all, but I want to unbreak things > > more or less immediately and then you/we can further improve it later. > > Committed Thanks.

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On Wed, Dec 14, 2016 at 11:20 PM, Robert Haas wrote: > I've got no problem with that at all, but I want to unbreak things > more or less immediately and then you/we can further improve it later. Committed, although I realize now that doesn't fix Dilip's problem, only my

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On Wed, Dec 14, 2016 at 10:08 PM, Andres Freund wrote: > On 2016-12-14 22:00:45 -0500, Robert Haas wrote: >> I took a look at Andres's patches today and saw that they can't really >> be applied as-is, because they "temporarily" change the master's >> ParallelWorkerNumber but

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On 2016-12-14 22:00:45 -0500, Robert Haas wrote: > I took a look at Andres's patches today and saw that they can't really > be applied as-is, because they "temporarily" change the master's > ParallelWorkerNumber but have no provision for restoring it after an > ERROR. Yea, that's not quite right.

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On Thu, Dec 8, 2016 at 5:23 PM, Robert Haas wrote: > On Wed, Nov 23, 2016 at 3:33 AM, Andres Freund wrote: >> On 2016-11-18 08:00:40 -0500, Robert Haas wrote: >>> On Tue, Nov 15, 2016 at 2:28 PM, Andres Freund wrote: >>> > I've a

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On Wed, Nov 23, 2016 at 3:33 AM, Andres Freund wrote: > On 2016-11-18 08:00:40 -0500, Robert Haas wrote: >> On Tue, Nov 15, 2016 at 2:28 PM, Andres Freund wrote: >> > I've a working fix for this, and for a similar issue Robert found. I'm >> > still playing

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On Wed, Nov 23, 2016 at 2:03 PM, Andres Freund wrote: > Here's my WIP series addressing this and related problems. With this > we're again noticeably faster than the dynahash implementation, in both > the case here, and the query you brought up over IM. > > This definitely

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On 2016-11-18 08:00:40 -0500, Robert Haas wrote: > On Tue, Nov 15, 2016 at 2:28 PM, Andres Freund wrote: > > I've a working fix for this, and for a similar issue Robert found. I'm > > still playing around with it, but basically the fix is to make the > > growth policy a bit

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On Tue, Nov 15, 2016 at 2:28 PM, Andres Freund wrote: > I've a working fix for this, and for a similar issue Robert found. I'm > still playing around with it, but basically the fix is to make the > growth policy a bit more adaptive. Any chance you can post a patch soon? --

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

On Wed, Nov 16, 2016 at 12:58 AM, Andres Freund wrote: > It's not really related to lossy pages, it's just that due to deletions > / insertions a lot more "shapes" of the hashtable are hit. Okay.. > > I suspect that this is with parallelism disabled? Without that the query >

Re: [HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

Hi Dilip, thanks for noticing that one. On 2016-11-09 21:17:22 +0530, Dilip Kumar wrote: > While testing bitmap performance, I have observed that some of the > TPCH queries taking huge time in BitmapIndexScan node, when there are > lossy pages. It's not really related to lossy pages, it's just

[HACKERS] Performance degradation in Bitmapscan (commit 75ae538bc3168bf44475240d4e0487ee2f3bb376)

While testing bitmap performance, I have observed that some of the TPCH queries taking huge time in BitmapIndexScan node, when there are lossy pages. I suspected 75ae538bc3168bf44475240d4e0487ee2f3bb376 commit, because prior to that it used to take very less time. So I tested by reverting