Transferring same file between PC's one direction is faster than the other

[videobruce]

I hope this is the right place to ask this. here is the situation;



Two PC' s
one a newer tower running Win 7, the other a older laptop running XP Pro
Wired connection thru a router and a 'switch' with no special priorities or restrictions to bandwidth. Both static IP's (if that matters)


The file is a mp4 around 100MB that I chose specifically to test 50' CAT5e jumper cables before I 'fish' them. I used the "move" function from and to the same partitions on both PC's. All apples to apples.


Using the laptop as the control; from that to the tower speed is fairly steady at 75 Mbps
returning the file, speed is between around 20 to 55 Mbs


Now, the same test, but from the tower; transferring the file from the tower to the Laptop speed varies from 66 to 95 Mbps,
returning the file from the Laptop back to the tower speed is 95 Mbps with a couple drops to 65 Mbps.


Ok, why is the speed far faster using the tower as the control station than the laptop transferring the exact same file, the exact same way???

 

[Alaric]

Better hardware controlling the transfer?

 

[Janus67]

same antivirus on both? what speed hard drive is in both machines?

 

[videobruce]

No 'active' A/V running on either box.

To possibly sum this us clearer;
File X transfer from A to B using A as the controler
File X transfer back from B to A using A as the controller

then;
File X transfer from A to B using B as the controller,
File X transfer back from B to A using B as the controller

The ONLY differences are the direction and which PC initiated the command.


Both PC's are AMD based,
Tower has a AMDFX-8350 & a AMD 970A chipset MB. The NIC is a Realtek PCIe GBE. The specific HDD that has the file is a Hitachi 7200rpm HUA723020
Laptop has a AMD Turion II M600 (the specs doesn't show the MB chipset) The NIC is a Marvell 88E8072. The (only) HDD is a 7200rpm WD WD5000BPKX

Win7 is 64 bit, XP Pro sp3 is 32 bit

 

[wagex]

probably because the laptop's hard drive is receiving and those tend to have a slower write speed than a desktop drive between that and the file being cached to memory probably is the reason for such variations. i'd test a larger file that cant be 100% held in memory cache i usually use a like 10GB movie file.

 

[videobruce]

Ok, but how does that explain the difference between which machine initiates the transfer?

 

[Robert17]

How much RAM does each have? HDD cache/page filing? I'm wondering if memory is playing a role.

 

[wagex]

Ok, but how does that explain the difference between which machine initiates the transfer?

network file transfers that small are always weird especially when cached information is taken into account.

 

[videobruce]

8GB in the tower, 2GB in the Laptop.
The tower has a SSD, no page file, the Laptop has a conventional HDD with a 500MB page file.

Where does memory or a page file come into play, doesn't the file just gets transfered?

 

[wagex]

8GB in the tower, 2GB in the Laptop.
The tower has a SSD, no page file, the Laptop has a conventional HDD with a 500MB page file.

Where does memory or a page file come into play, doesn't the file just gets transfered?

the computer reads it from the hard drive loads it into memory then transfers the data over the nic until that memory has been rewritten or dumped that file is still sitting in the memory and next time you copy / move it doesnt need to be read from disk so that will make the variation. it never goes straight from disk to nic to disk always goes through the memory as everything that happens on a pc does. plus theres the hard drive cache which is usually 64 or 128mb lots of variables.

 

[the_darkness]

I would agree about memory being a factor. Plus, regardless of the same file, same disk location, etc - you have an SSD in your tower and a HDD in your laptop and you have way more memory in your tower too. Not only is this not "apples to apples", this is inherently going to slow things down on the laptop end. As others have stated, caching, write speed, read speed, OS, A/V, controllers..... these are all factors. If you do alot of transferring between the two, swap out your hard drive in your laptop with an SSD or a 10000rpm+ HDD as there are still alot of laptops floating around with 5400RPM drives. Otherwise, just know that you're not using a very good config for what you're looking to test.

 

[videobruce]

I didn't know that any file transfer went thru memory. I though that was were active services, processes & programs reside.
Believe me, I know the Laptop is older with a 'weak' processor, one of two reasons I have left XP on it. It's also used to interface with a couple of pieces of older test equipment that won't work with XP .

 

[the_darkness]

The file transfer itself doesn't go through memory. However, where the file is and what to do with it - these are instructions the processor will need in order to do what you're asking it to. I can't speak for OSX (although I think it's the same), but in Windows, those instructions will come from memory.

 

[videobruce]

Then memory is not especially a issue.

 

[wagex]

The file transfer itself doesn't go through memory. However, where the file is and what to do with it - these are instructions the processor will need in order to do what you're asking it to. I can't speak for OSX (although I think it's the same), but in Windows, those instructions will come from memory.

if that is the case then why is this file transfer filling up my ram?



look at cached, standby and modified. also look what happens when i cancel the transfer bam its all gone.
EVERYTHING goes through the memory at some point it cant just go straight from the disk to the nic.

p.s. that is a file transfer from a network drive


also. that file is so small idk how you are getting an accurate reading i mean any hard disk is going to read a 100MB file in less than a second and it should be instant over 1gbs. mine doesnt even show a transfer graph with something that small. unless you are watching your nic traffic in task manager. in that case it parses every couple miliseconds or even a full second... in that second it could have easily peaked the same through all tests it just was getting read by task manager at the wrong time. you really need to be sending multi GB at a time to test network speeds.

 

[the_darkness]

I guess I stand corrected. So you're saying that if you looked inside the memory, you'd find an exact copy of the file? Also, in the poster's case, should his RAM only increase by 100MB if he's transferring a 100MB file?

 

[wagex]

I guess I stand corrected. So you're saying that if you looked inside the memory, you'd find an exact copy of the file? Also, in the poster's case, should his RAM only increase by 100MB if he's transferring a 100MB file?

yes if you were able to unscramble it from all the memory addresses and reassembled it i guess. yes his ram should only increase by 100MB, i tested it just before this with a 10MB mp3 file and i seen standby usage jump just about 10MB.

theres so much going on between cached files, 100mbs lan monitoring utilities theres no way to get a good test with a file that small by the time the transfer is done the computer is still running formulas to figure out how fast its going lol.

 

[the_darkness]

Good info - thank you. Now, I shall bow down to all those stars and banners you have.....

 

[Alaric]

Doesn't W7 run transfers through MSE (if used)?