Re: Pycassa vs YCSB results.
On Tue, 2013-02-05 at 13:51 -0500, Edward Capriolo wrote: Without stating the obvious, if you are interested in scale, then why pick python?. I would (kind of) agree with this point.. If you absolutely need performance here then python isn't the right choice. If, however, you are currently working with python and the question was just why is pycassa not as fast as YCSB, can I make it faster then I'd say the fact it was only a constant factor of 2 slower shows it's perfectly possible to stick with python. FYI the setup I'm using to write data to Cassandra is based around a series of 0mq applications - the actual loader is in python, but filtering steps before that are (partly) in C. Tim
Re: Pycassa vs YCSB results.
The first thing I noticed is your script uses python threading library, which is hampered by the Global Interpreter Lock http://docs.python.org/2/library/threading.html You don't really have multiple threads running in parallel, try using the multiprocessor library. Cheers - Aaron Morton Freelance Cassandra Developer New Zealand @aaronmorton http://www.thelastpickle.com On 5/02/2013, at 7:15 AM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, Could some one please let me know any hints, why the pycassa client(attached) is much slower than the YCSB? is it something to attribute to performance difference between python and Java? or the pycassa api has some performance limitations? I don't see any client statements affecting the pycassa performance. Please have a look at the simple python script attached and let me know your suggestions. thanks pradeep On Thu, Jan 31, 2013 at 4:53 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: On Thu, Jan 31, 2013 at 4:49 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Thanks.. Please find the script as attachment. Just re-iterating. Its just a simple python script which submit 4 threads. This script has been scheduled on 8 cores using taskset unix command , thus running 32 threads/node. and then scaling to 16 nodes thanks pradeep On Thu, Jan 31, 2013 at 4:38 PM, Tyler Hobbs ty...@datastax.com wrote: Can you provide the python script that you're using? (I'm moving this thread to the pycassa mailing list (pycassa-disc...@googlegroups.com), which is a better place for this discussion.) On Thu, Jan 31, 2013 at 6:25 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, I am trying to benchmark cassandra on a 12 Data Node cluster using 16 clients ( each client uses 32 threads) using custom pycassa client and YCSB. I found the maximum number of operations/seconds achieved using pycassa client is nearly 70k+ reads/second. Whereas with YCSB it is ~ 120k reads/second. Any thoughts, why I see this huge difference in performance? Here is the description of setup. Pycassa client (a simple python script). 1. Each pycassa client starts 4 threads - where each thread queries 76896 queries. 2. a shell script is used to submit 4threads/each core using taskset unix command on a 8 core single node. ( 8 * 4 * 76896 queries) 3. Another shell script is used to scale the single node shell script to 16 nodes ( total queries now - 16 * 8 * 4 * 76896 queries ) I tried to keep YCSB configuration as much as similar to my custom pycassa benchmarking setup. YCSB - Launched 16 YCSB clients on 16 nodes where each client uses 32 threads for execution and need to query ( 32 * 76896 keys ), i.e 100% reads The dataset is different in each case, but has 1. same number of total records. 2. same number of fields. 3. field length is almost same. Could you please let me know, why I see this huge performance difference and is there any way I can improve the operations/second using pycassa client. thanks pradeep -- Tyler Hobbs DataStax pycassa_client.py
Re: Pycassa vs YCSB results.
On Tue, 2013-02-05 at 21:38 +1300, aaron morton wrote: The first thing I noticed is your script uses python threading library, which is hampered by the Global Interpreter Lock http://docs.python.org/2/library/threading.html You don't really have multiple threads running in parallel, try using the multiprocessor library. Python _should_ release the GIL around IO-bound work, so this is a situation where the GIL shouldn't be an issue (It's actually a very good use for python's threads as there's no serialization overhead for message passing between processes as there would be in most multi-process examples) A constant factor 2 slowdown really doesn't seem that significant for two different implementations, and I would not worry about this unless you're talking about thousands of machines.. If you are talking about enough machines that this is real $$$, then I do think the python code can be optimised a lot. I'm talking about language/VM specific optimisations - so I'm assuming cpython (the standard /usr/bin/python as in the shebang). I don't know how much of a difference this will make, but I'd be interested in hearing your results: I would start by trying rewriting this: def start_cassandra_client(Threadname): f=open(Threadname,w) for key in lines: key=key.strip() st=time.time() f.write(str(cf.get(key))+\n) et=time.time() f.write(Time taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) f.close() As something like this: def start_cassandra_client(Threadname): # Avoid variable names outside this scope time_fn = time.time colfam = cf f=open(Threadname,w) for key in lines: key=key.strip() st=time_fn() f.write(str(colfam.get(key))+\n) et=time_fn() f.write(Time taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) f.close() If you don't consider it cheating compared to the java version, I would also move the key.strip() call to the module initiation instead of doing it once per thread, as there's a lot of function dispatch overhead in python. I'd also closely compare the IO going on in both versions (the .write calls). For example this may be significantly faster: et=time_fn() f.write(str(colfam.get(key))+\nTime taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) .. I haven't read your java code and I don't know Java IO semantics well enough to compare the behaviour of both. Tim Cheers - Aaron Morton Freelance Cassandra Developer New Zealand @aaronmorton http://www.thelastpickle.com On 5/02/2013, at 7:15 AM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, Could some one please let me know any hints, why the pycassa client(attached) is much slower than the YCSB? is it something to attribute to performance difference between python and Java? or the pycassa api has some performance limitations? I don't see any client statements affecting the pycassa performance. Please have a look at the simple python script attached and let me know your suggestions. thanks pradeep On Thu, Jan 31, 2013 at 4:53 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: On Thu, Jan 31, 2013 at 4:49 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Thanks.. Please find the script as attachment. Just re-iterating. Its just a simple python script which submit 4 threads. This script has been scheduled on 8 cores using taskset unix command , thus running 32 threads/node. and then scaling to 16 nodes thanks pradeep On Thu, Jan 31, 2013 at 4:38 PM, Tyler Hobbs ty...@datastax.com wrote: Can you provide the python script that you're using? (I'm moving this thread to the pycassa mailing list (pycassa-disc...@googlegroups.com), which is a better place for this discussion.) On Thu, Jan 31, 2013 at 6:25 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, I am trying to benchmark cassandra on a 12 Data Node cluster using 16 clients ( each client uses 32 threads) using custom pycassa client and YCSB. I found the maximum number of operations/seconds achieved using pycassa client is nearly 70k+ reads/second. Whereas with YCSB it is ~ 120k reads/second. Any thoughts, why I see this huge difference in performance? Here is the description of setup. Pycassa client (a simple python script). 1. Each pycassa client starts 4 threads - where each thread queries 76896 queries. 2. a shell script is used to submit 4threads/each core using taskset unix command on a 8 core single node. ( 8 * 4 * 76896 queries) 3. Another shell script is used to scale the single node shell script to 16 nodes ( total queries now - 16 * 8 * 4 * 76896 queries ) I tried to keep YCSB configuration as much as similar to my custom pycassa benchmarking setup. YCSB -
Re: Pycassa vs YCSB results.
The simple thing to do would be use the multiprocessing package and eliminate all shared state. On a multicore box python threads can run on different cores and battle over obtaining the GIL. Cheers - Aaron Morton Freelance Cassandra Developer New Zealand @aaronmorton http://www.thelastpickle.com On 5/02/2013, at 11:34 PM, Tim Wintle timwin...@gmail.com wrote: On Tue, 2013-02-05 at 21:38 +1300, aaron morton wrote: The first thing I noticed is your script uses python threading library, which is hampered by the Global Interpreter Lock http://docs.python.org/2/library/threading.html You don't really have multiple threads running in parallel, try using the multiprocessor library. Python _should_ release the GIL around IO-bound work, so this is a situation where the GIL shouldn't be an issue (It's actually a very good use for python's threads as there's no serialization overhead for message passing between processes as there would be in most multi-process examples) A constant factor 2 slowdown really doesn't seem that significant for two different implementations, and I would not worry about this unless you're talking about thousands of machines.. If you are talking about enough machines that this is real $$$, then I do think the python code can be optimised a lot. I'm talking about language/VM specific optimisations - so I'm assuming cpython (the standard /usr/bin/python as in the shebang). I don't know how much of a difference this will make, but I'd be interested in hearing your results: I would start by trying rewriting this: def start_cassandra_client(Threadname): f=open(Threadname,w) for key in lines: key=key.strip() st=time.time() f.write(str(cf.get(key))+\n) et=time.time() f.write(Time taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) f.close() As something like this: def start_cassandra_client(Threadname): # Avoid variable names outside this scope time_fn = time.time colfam = cf f=open(Threadname,w) for key in lines: key=key.strip() st=time_fn() f.write(str(colfam.get(key))+\n) et=time_fn() f.write(Time taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) f.close() If you don't consider it cheating compared to the java version, I would also move the key.strip() call to the module initiation instead of doing it once per thread, as there's a lot of function dispatch overhead in python. I'd also closely compare the IO going on in both versions (the .write calls). For example this may be significantly faster: et=time_fn() f.write(str(colfam.get(key))+\nTime taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) .. I haven't read your java code and I don't know Java IO semantics well enough to compare the behaviour of both. Tim Cheers - Aaron Morton Freelance Cassandra Developer New Zealand @aaronmorton http://www.thelastpickle.com On 5/02/2013, at 7:15 AM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, Could some one please let me know any hints, why the pycassa client(attached) is much slower than the YCSB? is it something to attribute to performance difference between python and Java? or the pycassa api has some performance limitations? I don't see any client statements affecting the pycassa performance. Please have a look at the simple python script attached and let me know your suggestions. thanks pradeep On Thu, Jan 31, 2013 at 4:53 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: On Thu, Jan 31, 2013 at 4:49 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Thanks.. Please find the script as attachment. Just re-iterating. Its just a simple python script which submit 4 threads. This script has been scheduled on 8 cores using taskset unix command , thus running 32 threads/node. and then scaling to 16 nodes thanks pradeep On Thu, Jan 31, 2013 at 4:38 PM, Tyler Hobbs ty...@datastax.com wrote: Can you provide the python script that you're using? (I'm moving this thread to the pycassa mailing list (pycassa-disc...@googlegroups.com), which is a better place for this discussion.) On Thu, Jan 31, 2013 at 6:25 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, I am trying to benchmark cassandra on a 12 Data Node cluster using 16 clients ( each client uses 32 threads) using custom pycassa client and YCSB. I found the maximum number of operations/seconds achieved using pycassa client is nearly 70k+ reads/second. Whereas with YCSB it is ~ 120k reads/second. Any thoughts, why I see this huge difference in performance? Here is the description of setup. Pycassa client (a simple python script). 1. Each pycassa client starts 4 threads - where each thread queries 76896 queries. 2. a shell
Re: Pycassa vs YCSB results.
Thanks, I will use the multiprocessing package, since I need to scale it to multiple nodes. I will also try to optimize the function calls and use global variables. Thank you very much for your help. On Tue, Feb 5, 2013 at 9:12 AM, aaron morton aa...@thelastpickle.comwrote: The simple thing to do would be use the multiprocessing package and eliminate all shared state. On a multicore box python threads can run on different cores and battle over obtaining the GIL. Cheers - Aaron Morton Freelance Cassandra Developer New Zealand @aaronmorton http://www.thelastpickle.com On 5/02/2013, at 11:34 PM, Tim Wintle timwin...@gmail.com wrote: On Tue, 2013-02-05 at 21:38 +1300, aaron morton wrote: The first thing I noticed is your script uses python threading library, which is hampered by the Global Interpreter Lock http://docs.python.org/2/library/threading.html You don't really have multiple threads running in parallel, try using the multiprocessor library. Python _should_ release the GIL around IO-bound work, so this is a situation where the GIL shouldn't be an issue (It's actually a very good use for python's threads as there's no serialization overhead for message passing between processes as there would be in most multi-process examples) A constant factor 2 slowdown really doesn't seem that significant for two different implementations, and I would not worry about this unless you're talking about thousands of machines.. If you are talking about enough machines that this is real $$$, then I do think the python code can be optimised a lot. I'm talking about language/VM specific optimisations - so I'm assuming cpython (the standard /usr/bin/python as in the shebang). I don't know how much of a difference this will make, but I'd be interested in hearing your results: I would start by trying rewriting this: def start_cassandra_client(Threadname): f=open(Threadname,w) for key in lines: key=key.strip() st=time.time() f.write(str(cf.get(key))+\n) et=time.time() f.write(Time taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) f.close() As something like this: def start_cassandra_client(Threadname): # Avoid variable names outside this scope time_fn = time.time colfam = cf f=open(Threadname,w) for key in lines: key=key.strip() st=time_fn() f.write(str(colfam.get(key))+\n) et=time_fn() f.write(Time taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) f.close() If you don't consider it cheating compared to the java version, I would also move the key.strip() call to the module initiation instead of doing it once per thread, as there's a lot of function dispatch overhead in python. I'd also closely compare the IO going on in both versions (the .write calls). For example this may be significantly faster: et=time_fn() f.write(str(colfam.get(key))+\nTime taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) .. I haven't read your java code and I don't know Java IO semantics well enough to compare the behaviour of both. Tim Cheers - Aaron Morton Freelance Cassandra Developer New Zealand @aaronmorton http://www.thelastpickle.com On 5/02/2013, at 7:15 AM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, Could some one please let me know any hints, why the pycassa client(attached) is much slower than the YCSB? is it something to attribute to performance difference between python and Java? or the pycassa api has some performance limitations? I don't see any client statements affecting the pycassa performance. Please have a look at the simple python script attached and let me know your suggestions. thanks pradeep On Thu, Jan 31, 2013 at 4:53 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: On Thu, Jan 31, 2013 at 4:49 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Thanks.. Please find the script as attachment. Just re-iterating. Its just a simple python script which submit 4 threads. This script has been scheduled on 8 cores using taskset unix command , thus running 32 threads/node. and then scaling to 16 nodes thanks pradeep On Thu, Jan 31, 2013 at 4:38 PM, Tyler Hobbs ty...@datastax.com wrote: Can you provide the python script that you're using? (I'm moving this thread to the pycassa mailing list ( pycassa-disc...@googlegroups.com), which is a better place for this discussion.) On Thu, Jan 31, 2013 at 6:25 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, I am trying to benchmark cassandra on a 12 Data Node cluster using 16 clients ( each client uses 32 threads) using custom pycassa client and YCSB. I found the maximum number of operations/seconds achieved using pycassa client is nearly 70k+ reads/second. Whereas with YCSB it is ~ 120k reads/second. Any
Re: Pycassa vs YCSB results.
Without stating the obvious, if you are interested in scale, then why pick python?. I did want to point out that YCSB is not even the gold standard for benchmarks using cassandra's stress you can get more ops per sec then YCSB. On Tue, Feb 5, 2013 at 1:13 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Thanks, I will use the multiprocessing package, since I need to scale it to multiple nodes. I will also try to optimize the function calls and use global variables. Thank you very much for your help. On Tue, Feb 5, 2013 at 9:12 AM, aaron morton aa...@thelastpickle.com wrote: The simple thing to do would be use the multiprocessing package and eliminate all shared state. On a multicore box python threads can run on different cores and battle over obtaining the GIL. Cheers - Aaron Morton Freelance Cassandra Developer New Zealand @aaronmorton http://www.thelastpickle.com On 5/02/2013, at 11:34 PM, Tim Wintle timwin...@gmail.com wrote: On Tue, 2013-02-05 at 21:38 +1300, aaron morton wrote: The first thing I noticed is your script uses python threading library, which is hampered by the Global Interpreter Lock http://docs.python.org/2/library/threading.html You don't really have multiple threads running in parallel, try using the multiprocessor library. Python _should_ release the GIL around IO-bound work, so this is a situation where the GIL shouldn't be an issue (It's actually a very good use for python's threads as there's no serialization overhead for message passing between processes as there would be in most multi-process examples) A constant factor 2 slowdown really doesn't seem that significant for two different implementations, and I would not worry about this unless you're talking about thousands of machines.. If you are talking about enough machines that this is real $$$, then I do think the python code can be optimised a lot. I'm talking about language/VM specific optimisations - so I'm assuming cpython (the standard /usr/bin/python as in the shebang). I don't know how much of a difference this will make, but I'd be interested in hearing your results: I would start by trying rewriting this: def start_cassandra_client(Threadname): f=open(Threadname,w) for key in lines: key=key.strip() st=time.time() f.write(str(cf.get(key))+\n) et=time.time() f.write(Time taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) f.close() As something like this: def start_cassandra_client(Threadname): # Avoid variable names outside this scope time_fn = time.time colfam = cf f=open(Threadname,w) for key in lines: key=key.strip() st=time_fn() f.write(str(colfam.get(key))+\n) et=time_fn() f.write(Time taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) f.close() If you don't consider it cheating compared to the java version, I would also move the key.strip() call to the module initiation instead of doing it once per thread, as there's a lot of function dispatch overhead in python. I'd also closely compare the IO going on in both versions (the .write calls). For example this may be significantly faster: et=time_fn() f.write(str(colfam.get(key))+\nTime taken for a single query is + str(round(1000*(et-st),2))+ milli secs\n) .. I haven't read your java code and I don't know Java IO semantics well enough to compare the behaviour of both. Tim Cheers - Aaron Morton Freelance Cassandra Developer New Zealand @aaronmorton http://www.thelastpickle.com On 5/02/2013, at 7:15 AM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, Could some one please let me know any hints, why the pycassa client(attached) is much slower than the YCSB? is it something to attribute to performance difference between python and Java? or the pycassa api has some performance limitations? I don't see any client statements affecting the pycassa performance. Please have a look at the simple python script attached and let me know your suggestions. thanks pradeep On Thu, Jan 31, 2013 at 4:53 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: On Thu, Jan 31, 2013 at 4:49 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Thanks.. Please find the script as attachment. Just re-iterating. Its just a simple python script which submit 4 threads. This script has been scheduled on 8 cores using taskset unix command , thus running 32 threads/node. and then scaling to 16 nodes thanks pradeep On Thu, Jan 31, 2013 at 4:38 PM, Tyler Hobbs ty...@datastax.com wrote: Can you provide the python script that you're using? (I'm moving this thread to the pycassa mailing list (pycassa-disc...@googlegroups.com), which is a better place for this discussion.) On Thu, Jan 31, 2013 at 6:25 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, I am
Re: Pycassa vs YCSB results.
Hi, Could some one please let me know any hints, why the pycassa client(attached) is much slower than the YCSB? is it something to attribute to performance difference between python and Java? or the pycassa api has some performance limitations? I don't see any client statements affecting the pycassa performance. Please have a look at the simple python script attached and let me know your suggestions. thanks pradeep On Thu, Jan 31, 2013 at 4:53 PM, Pradeep Kumar Mantha pradeep...@gmail.comwrote: On Thu, Jan 31, 2013 at 4:49 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Thanks.. Please find the script as attachment. Just re-iterating. Its just a simple python script which submit 4 threads. This script has been scheduled on 8 cores using taskset unix command , thus running 32 threads/node. and then scaling to 16 nodes thanks pradeep On Thu, Jan 31, 2013 at 4:38 PM, Tyler Hobbs ty...@datastax.com wrote: Can you provide the python script that you're using? (I'm moving this thread to the pycassa mailing list ( pycassa-disc...@googlegroups.com), which is a better place for this discussion.) On Thu, Jan 31, 2013 at 6:25 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, I am trying to benchmark cassandra on a 12 Data Node cluster using 16 clients ( each client uses 32 threads) using custom pycassa client and YCSB. I found the maximum number of operations/seconds achieved using pycassa client is nearly 70k+ reads/second. Whereas with YCSB it is ~ 120k reads/second. Any thoughts, why I see this huge difference in performance? Here is the description of setup. Pycassa client (a simple python script). 1. Each pycassa client starts 4 threads - where each thread queries 76896 queries. 2. a shell script is used to submit 4threads/each core using taskset unix command on a 8 core single node. ( 8 * 4 * 76896 queries) 3. Another shell script is used to scale the single node shell script to 16 nodes ( total queries now - 16 * 8 * 4 * 76896 queries ) I tried to keep YCSB configuration as much as similar to my custom pycassa benchmarking setup. YCSB - Launched 16 YCSB clients on 16 nodes where each client uses 32 threads for execution and need to query ( 32 * 76896 keys ), i.e 100% reads The dataset is different in each case, but has 1. same number of total records. 2. same number of fields. 3. field length is almost same. Could you please let me know, why I see this huge performance difference and is there any way I can improve the operations/second using pycassa client. thanks pradeep -- Tyler Hobbs DataStax http://datastax.com/ pycassa_client.py Description: Binary data
Re: Pycassa vs YCSB results.
Can you provide the python script that you're using? (I'm moving this thread to the pycassa mailing list ( pycassa-disc...@googlegroups.com), which is a better place for this discussion.) On Thu, Jan 31, 2013 at 6:25 PM, Pradeep Kumar Mantha pradeep...@gmail.comwrote: Hi, I am trying to benchmark cassandra on a 12 Data Node cluster using 16 clients ( each client uses 32 threads) using custom pycassa client and YCSB. I found the maximum number of operations/seconds achieved using pycassa client is nearly 70k+ reads/second. Whereas with YCSB it is ~ 120k reads/second. Any thoughts, why I see this huge difference in performance? Here is the description of setup. Pycassa client (a simple python script). 1. Each pycassa client starts 4 threads - where each thread queries 76896 queries. 2. a shell script is used to submit 4threads/each core using taskset unix command on a 8 core single node. ( 8 * 4 * 76896 queries) 3. Another shell script is used to scale the single node shell script to 16 nodes ( total queries now - 16 * 8 * 4 * 76896 queries ) I tried to keep YCSB configuration as much as similar to my custom pycassa benchmarking setup. YCSB - Launched 16 YCSB clients on 16 nodes where each client uses 32 threads for execution and need to query ( 32 * 76896 keys ), i.e 100% reads The dataset is different in each case, but has 1. same number of total records. 2. same number of fields. 3. field length is almost same. Could you please let me know, why I see this huge performance difference and is there any way I can improve the operations/second using pycassa client. thanks pradeep -- Tyler Hobbs DataStax http://datastax.com/
Re: Pycassa vs YCSB results.
Thanks.. Please find the script as attachment. Just re-iterating. Its just a simple python script which submit 4 threads. This script has been scheduled on 8 cores using taskset unix command , thus running 32 threads/node. and then scaling to 16 nodes thanks pradeep On Thu, Jan 31, 2013 at 4:38 PM, Tyler Hobbs ty...@datastax.com wrote: Can you provide the python script that you're using? (I'm moving this thread to the pycassa mailing list ( pycassa-disc...@googlegroups.com), which is a better place for this discussion.) On Thu, Jan 31, 2013 at 6:25 PM, Pradeep Kumar Mantha pradeep...@gmail.com wrote: Hi, I am trying to benchmark cassandra on a 12 Data Node cluster using 16 clients ( each client uses 32 threads) using custom pycassa client and YCSB. I found the maximum number of operations/seconds achieved using pycassa client is nearly 70k+ reads/second. Whereas with YCSB it is ~ 120k reads/second. Any thoughts, why I see this huge difference in performance? Here is the description of setup. Pycassa client (a simple python script). 1. Each pycassa client starts 4 threads - where each thread queries 76896 queries. 2. a shell script is used to submit 4threads/each core using taskset unix command on a 8 core single node. ( 8 * 4 * 76896 queries) 3. Another shell script is used to scale the single node shell script to 16 nodes ( total queries now - 16 * 8 * 4 * 76896 queries ) I tried to keep YCSB configuration as much as similar to my custom pycassa benchmarking setup. YCSB - Launched 16 YCSB clients on 16 nodes where each client uses 32 threads for execution and need to query ( 32 * 76896 keys ), i.e 100% reads The dataset is different in each case, but has 1. same number of total records. 2. same number of fields. 3. field length is almost same. Could you please let me know, why I see this huge performance difference and is there any way I can improve the operations/second using pycassa client. thanks pradeep -- Tyler Hobbs DataStax http://datastax.com/ pycassa_client.py Description: Binary data