testing HS/SR - 1 vs 2 performance
in [PgSql]
|
Prev: pg_ctl stop -m immediate on the primary server inflatessequences
Next: [HACKERS] non-reproducible failure of random test on HEAD
From: Tom Lane on 25 Apr 2010 13:33 Simon Riggs <simon(a)2ndQuadrant.com> writes: > On Sun, 2010-04-25 at 12:51 -0400, Tom Lane wrote: >> If the comments were correct, I wouldn't be complaining. They're >> misleading or outright wrong on many points. In particular, I don't >> think you actually understand the weak-memory-ordering issue, because >> the comments about that are entirely wrong. > The comments says "on CPUs with > + * weak-memory ordering we can't reliably move pointers atomically, so > the > + * rule is that updates of head and tail of the array require > ProcArrayLock > + * in exclusive mode or (shared mode and known_assigned_xids_lck > spinlock)" > I will reword this, so it is clear that I'm talking about the head and > tail of the array, not pointers in general. It's not about whether the pointers can be assigned atomically; on most hardware they can. It's about whether other processors will see that happen in the correct sequence relative to the changes in the array elements. If you like I'll have a go at rewriting the comments for this patch, because I am currently thinking that the problem is not so much with the code as with the poor explanation of what it's doing. Sometimes the author is too close to the code to understand why other people have a hard time understanding it. regards, tom lane -- Sent via pgsql-hackers mailing list (pgsql-hackers(a)postgresql.org) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-hackers
From: Simon Riggs on 25 Apr 2010 13:45 On Sun, 2010-04-25 at 13:33 -0400, Tom Lane wrote: > If you like I'll have a go at rewriting the comments for this patch, > because I am currently thinking that the problem is not so much with > the code as with the poor explanation of what it's doing. Sometimes > the author is too close to the code to understand why other people > have a hard time understanding it. That would help me, thank you. -- Simon Riggs www.2ndQuadrant.com -- Sent via pgsql-hackers mailing list (pgsql-hackers(a)postgresql.org) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-hackers
From: Tom Lane on 25 Apr 2010 13:51 Simon Riggs <simon(a)2ndQuadrant.com> writes: > On Sun, 2010-04-25 at 13:33 -0400, Tom Lane wrote: >> If you like I'll have a go at rewriting the comments for this patch, >> because I am currently thinking that the problem is not so much with >> the code as with the poor explanation of what it's doing. Sometimes >> the author is too close to the code to understand why other people >> have a hard time understanding it. > That would help me, thank you. OK. You said you were currently working some more on the patch, so I'll wait for v3 and then work on it. regards, tom lane -- Sent via pgsql-hackers mailing list (pgsql-hackers(a)postgresql.org) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-hackers
From: "Erik Rijkers" on 25 Apr 2010 14:25 On Sat, April 24, 2010 01:17, Erik Rijkers wrote: > On Sat, April 24, 2010 00:39, Simon Riggs wrote: >> On Fri, 2010-04-23 at 11:32 -0400, Robert Haas wrote: >>> > >>> > 99% of transactions happen in similar times between primary and standby, >>> > everything dragged down by rare but severe spikes. >>> > >>> > We're looking for something that would delay something that normally >>> > takes <0.1ms into something that takes >100ms, yet does eventually >>> > return. That looks like a severe resource contention issue. >>> >>> Wow. Good detective work. >> >> While we haven't fully established the source of those problems, I am >> now happy that these test results don't present any reason to avoid >> commiting the main patch tested by Erik (not the smaller additional one >> I sent). I expect to commit that on Sunday. >> > > yes, that (main) patch seems to have largely > closed the gap between primary and standby; here > are some results from a lower scale (10): FWIW, here are some more results from pgbench comparing primary and standby (both with Simon's patch). Sorry if it's too much data, but to me at least it was illuminating; I now understand the effects of the different parameters better. pgbench results, all -S (SELECT-only). scale: 10, 100, 500, 1000 clients: 1, 10, 20, 40, 60, 90 for each: 4x primary, 4x standby, for 15 minutes: (port 6565=primary, 6566=standby) scale: 10 clients: 1 tps = 6404.768132 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 10 clients: 1 tps = 6435.072983 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 10 clients: 1 tps = 6458.958549 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 10 clients: 1 tps = 6432.088099 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 10 clients: 1 tps = 6442.519035 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 10 clients: 1 tps = 6449.837931 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 10 clients: 1 tps = 6419.879026 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 10 clients: 1 tps = 6428.290175 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 --- scale: 10 clients: 10 tps = 27624.339871 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 10 clients: 10 tps = 27604.261750 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 10 clients: 10 tps = 28015.093466 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 10 clients: 10 tps = 28422.561280 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 10 clients: 10 tps = 27254.806526 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 10 clients: 10 tps = 27686.470866 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 10 clients: 10 tps = 28078.904035 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 10 clients: 10 tps = 27101.622337 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 ---- scale: 10 clients: 20 tps = 23106.795587 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 10 clients: 20 tps = 23101.681155 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 10 clients: 20 tps = 22893.364004 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 10 clients: 20 tps = 23038.577109 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 10 clients: 20 tps = 22903.578552 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 10 clients: 20 tps = 22970.691946 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 10 clients: 20 tps = 22999.473318 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 10 clients: 20 tps = 22884.854749 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 ---- scale: 10 clients: 40 tps = 23522.499429 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 10 clients: 40 tps = 23611.319191 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 10 clients: 40 tps = 23616.905302 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 10 clients: 40 tps = 23572.213990 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 10 clients: 40 tps = 23714.721220 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 10 clients: 40 tps = 23711.781175 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 10 clients: 40 tps = 23691.867023 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 10 clients: 40 tps = 23691.699231 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 ---- scale: 10 clients: 60 tps = 21987.497095 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 10 clients: 60 tps = 21950.344204 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 10 clients: 60 tps = 22006.461447 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 10 clients: 60 tps = 21824.071303 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 10 clients: 60 tps = 22149.415231 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 10 clients: 60 tps = 22211.064402 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 10 clients: 60 tps = 22164.238081 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 10 clients: 60 tps = 22174.585736 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 ---- scale: 10 clients: 90 tps = 18751.213002 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 10 clients: 90 tps = 18757.115811 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 10 clients: 90 tps = 18692.942329 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 10 clients: 90 tps = 18765.390154 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 10 clients: 90 tps = 18929.462104 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 10 clients: 90 tps = 18999.851184 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 10 clients: 90 tps = 18972.321607 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 10 clients: 90 tps = 18924.058827 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 ---- scale: 100 clients: 1 tps = 5854.489684 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 100 clients: 1 tps = 5852.679267 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 100 clients: 1 tps = 5844.005437 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 100 clients: 1 tps = 5867.593004 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 100 clients: 1 tps = 1111.368215 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 100 clients: 1 tps = 1187.678163 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 100 clients: 1 tps = 1332.544440 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 100 clients: 1 tps = 1488.574446 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 ---- scale: 100 clients: 10 tps = 28948.718439 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 100 clients: 10 tps = 28865.280357 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 100 clients: 10 tps = 28819.426232 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 100 clients: 10 tps = 28868.070716 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 100 clients: 10 tps = 1839.477133 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 100 clients: 10 tps = 2056.574852 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 100 clients: 10 tps = 2501.715270 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 100 clients: 10 tps = 3114.288871 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 ---- scale: 100 clients: 20 tps = 21561.395664 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 100 clients: 20 tps = 21482.860950 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 100 clients: 20 tps = 21447.896216 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 100 clients: 20 tps = 21450.846824 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 100 clients: 20 tps = 4309.312692 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 100 clients: 20 tps = 6786.460948 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 100 clients: 20 tps = 16552.535443 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 100 clients: 20 tps = 21513.519274 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 ---- scale: 100 clients: 40 tps = 20812.709326 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 100 clients: 40 tps = 20750.911233 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 100 clients: 40 tps = 20764.921432 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 100 clients: 40 tps = 20877.705726 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 100 clients: 40 tps = 20818.028682 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 100 clients: 40 tps = 20876.921640 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 100 clients: 40 tps = 20912.855749 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 100 clients: 40 tps = 20821.271974 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 ---- scale: 100 clients: 60 tps = 18746.870683 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 100 clients: 60 tps = 18752.631011 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 100 clients: 60 tps = 18717.634243 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 100 clients: 60 tps = 18776.138286 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 100 clients: 60 tps = 18850.133061 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 100 clients: 60 tps = 18893.463427 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 100 clients: 60 tps = 18918.599124 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 100 clients: 60 tps = 18903.389147 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 ---- scale: 100 clients: 90 tps = 15915.637099 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 100 clients: 90 tps = 15945.810305 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 100 clients: 90 tps = 15894.238941 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 100 clients: 90 tps = 15926.422587 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 100 clients: 90 tps = 16025.802748 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 100 clients: 90 tps = 16049.977788 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 100 clients: 90 tps = 16053.612396 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 100 clients: 90 tps = 16040.376994 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 ---- scale: 500 clients: 1 tps = 5646.892935 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 500 clients: 1 tps = 5642.544001 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 500 clients: 1 tps = 5633.282536 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 500 clients: 1 tps = 5627.330477 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 500 clients: 1 tps = 5625.659921 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 500 clients: 1 tps = 5645.898120 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 500 clients: 1 tps = 5644.897739 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 500 clients: 1 tps = 5640.990172 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 ---- scale: 500 clients: 10 tps = 28123.467099 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 500 clients: 10 tps = 28230.031309 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 500 clients: 10 tps = 28054.072374 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 500 clients: 10 tps = 28129.229553 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 500 clients: 10 tps = 28187.938585 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 500 clients: 10 tps = 28372.950289 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 500 clients: 10 tps = 28161.909825 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 500 clients: 10 tps = 28224.336096 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 ---- scale: 500 clients: 20 tps = 20932.340860 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 500 clients: 20 tps = 20990.560386 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 500 clients: 20 tps = 20926.001588 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 500 clients: 20 tps = 20903.012936 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 500 clients: 20 tps = 20956.917213 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 500 clients: 20 tps = 21007.634021 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 500 clients: 20 tps = 20982.386759 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 500 clients: 20 tps = 21002.399320 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 ---- scale: 500 clients: 40 tps = 19829.483373 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 500 clients: 40 tps = 19830.187082 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 500 clients: 40 tps = 19757.072979 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 500 clients: 40 tps = 19734.710111 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 500 clients: 40 tps = 19862.051804 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 500 clients: 40 tps = 19834.071543 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 500 clients: 40 tps = 19885.788466 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 500 clients: 40 tps = 19961.407411 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 ---- scale: 500 clients: 60 tps = 17829.256242 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 500 clients: 60 tps = 17816.152137 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 500 clients: 60 tps = 17828.589859 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 500 clients: 60 tps = 17748.044912 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 500 clients: 60 tps = 17926.708964 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 500 clients: 60 tps = 17943.758910 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 500 clients: 60 tps = 17917.713556 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 500 clients: 60 tps = 17932.597396 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 ---- scale: 500 clients: 90 tps = 15044.660043 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 500 clients: 90 tps = 15010.685976 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 500 clients: 90 tps = 15045.828142 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 500 clients: 90 tps = 14976.636159 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 500 clients: 90 tps = 15154.402300 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 500 clients: 90 tps = 15131.532084 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 500 clients: 90 tps = 15154.148091 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 500 clients: 90 tps = 15130.337148 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 ---- scale: 1000 clients: 1 tps = 222.307686 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 1000 clients: 1 tps = 261.163445 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 1000 clients: 1 tps = 307.343862 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 1000 clients: 1 tps = 367.285821 pgbench -p 6565 -n -S -c 1 -T 900 -j 1 scale: 1000 clients: 1 tps = 550.457516 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 1000 clients: 1 tps = 4347.697078 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 1000 clients: 1 tps = 5601.036491 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 scale: 1000 clients: 1 tps = 5604.021799 pgbench -p 6566 -n -S -c 1 -T 900 -j 1 ---- scale: 1000 clients: 10 tps = 3370.534977 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 1000 clients: 10 tps = 23156.038162 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 1000 clients: 10 tps = 28029.755911 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 1000 clients: 10 tps = 28179.609982 pgbench -p 6565 -n -S -c 10 -T 900 -j 1 scale: 1000 clients: 10 tps = 2880.404087 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 1000 clients: 10 tps = 13593.595875 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 1000 clients: 10 tps = 28033.649640 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 scale: 1000 clients: 10 tps = 28115.126500 pgbench -p 6566 -n -S -c 10 -T 900 -j 1 ---- scale: 1000 clients: 20 tps = 4876.882880 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 1000 clients: 20 tps = 21262.273826 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 1000 clients: 20 tps = 20403.533099 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 1000 clients: 20 tps = 20753.634216 pgbench -p 6565 -n -S -c 20 -T 900 -j 1 scale: 1000 clients: 20 tps = 3024.129307 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 1000 clients: 20 tps = 18786.862049 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 1000 clients: 20 tps = 20807.372965 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 scale: 1000 clients: 20 tps = 20896.373925 pgbench -p 6566 -n -S -c 20 -T 900 -j 1 ---- scale: 1000 clients: 40 tps = 5910.319107 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 1000 clients: 40 tps = 19705.088545 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 1000 clients: 40 tps = 19658.237802 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 1000 clients: 40 tps = 19593.955166 pgbench -p 6565 -n -S -c 40 -T 900 -j 1 scale: 1000 clients: 40 tps = 6555.937102 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 1000 clients: 40 tps = 19845.691237 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 1000 clients: 40 tps = 19755.112514 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 scale: 1000 clients: 40 tps = 19765.648969 pgbench -p 6566 -n -S -c 40 -T 900 -j 1 ---- scale: 1000 clients: 60 tps = 7104.451848 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 1000 clients: 60 tps = 17638.393625 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 1000 clients: 60 tps = 17621.464080 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 1000 clients: 60 tps = 17538.189171 pgbench -p 6565 -n -S -c 60 -T 900 -j 1 scale: 1000 clients: 60 tps = 6721.909857 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 1000 clients: 60 tps = 17798.542731 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 1000 clients: 60 tps = 17797.145061 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 scale: 1000 clients: 60 tps = 17739.437864 pgbench -p 6566 -n -S -c 60 -T 900 -j 1 ---- scale: 1000 clients: 90 tps = 6682.605788 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 1000 clients: 90 tps = 14853.076617 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 1000 clients: 90 tps = 14851.040207 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 1000 clients: 90 tps = 14859.575164 pgbench -p 6565 -n -S -c 90 -T 900 -j 1 scale: 1000 clients: 90 tps = 6208.586575 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 1000 clients: 90 tps = 15065.536476 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 1000 clients: 90 tps = 15033.388676 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 scale: 1000 clients: 90 tps = 15030.808207 pgbench -p 6566 -n -S -c 90 -T 900 -j 1 Hardware: 2x Xeon (quadcore) 5482; 32 GB; Areca 1280ML CentOS release 5.4 (Final), x86_64 Linux, 2.6.18-164.el5 Both instances on a raid volume of 12 disks (sata 7200) (and of course, server otherwise idle) hth, Erik Rijkers -- Sent via pgsql-hackers mailing list (pgsql-hackers(a)postgresql.org) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-hackers
From: Tom Lane on 25 Apr 2010 14:55
"Erik Rijkers" <er(a)xs4all.nl> writes: > FWIW, here are some more results from pgbench comparing > primary and standby (both with Simon's patch). That seems weird. Why do most of the runs show primary and standby as having comparable speed, but a few show the standby as much slower? The parameters for those runs don't seem obviously different from cases where it's fast. I think there might have been something else going on on the standby during those runs. Or do you think those represent cases where the mystery slowdown event happened? regards, tom lane -- Sent via pgsql-hackers mailing list (pgsql-hackers(a)postgresql.org) To make changes to your subscription: http://www.postgresql.org/mailpref/pgsql-hackers |